├── LICENSE ├── README.md ├── configs ├── config_CD19-CD20_all_TCGA.ini ├── config_CD19-CD20_selection.ini ├── config_CD3_all_TCGA.ini ├── config_CD3_selection.ini ├── config_MKI67_all_TCGA.ini ├── config_MKI67_selection.ini ├── config_all_genes.ini ├── config_epithelium_all_TCGA.ini └── config_epithelium_selection.ini ├── constant.py ├── data └── MSI_labels │ ├── msi_COAD.csv │ ├── msi_COAD_KR.csv │ ├── msi_READ.csv │ ├── msi_READ_KR.csv │ └── msi_STAD.csv ├── extract_tile_features.py ├── extract_tile_features_from_slides.py ├── gdc_manifests ├── gdc_manifest.2018-03-13_alltranscriptome.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-ACC.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-BLCA.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-BRCA.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-CESC.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-CHOL.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-COAD.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-DLBC.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-ESCA.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-GBM.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-HNSC.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-KICH.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-KIRC.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-KIRP.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-LGG.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-LIHC.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-LUAD.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-LUSC.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-MESO.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-OV.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-PAAD.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-PCPG.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-PRAD.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-READ.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-SARC.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-SKCM.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-STAD.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-TGCT.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-THCA.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-THYM.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-UCEC.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-UCS.txt ├── gdc_manifest.2018-06-26_diagnostic_TCGA-UVM.txt └── gdc_manifest.CRC_frozen_slides.txt ├── main.py ├── metadata └── samples_description.csv ├── model.py ├── msi_prediction.py ├── patient_splits.pkl ├── requirements.txt ├── spatialization.py ├── supertile_preprocessing.py ├── tile_coordinates.gz ├── transcriptome_data.py ├── utils.py └── wsi_data.py /README.md: -------------------------------------------------------------------------------- 1 | # Gene expression prediction 2 | 3 | Predict gene expression from WSIs taken from TCGA with HE2RNA [1]. The model takes as inputs arrays of size n_tiles * 2048, where n_tiles = 100 when super-tile preprocessing is used, and n_tiles = 8,000 when all tiles are treated separately. The model is implemented as a succession of 1D convolution (equivalent to an MLP shared among all tiles). 4 | Additionally, Model interpretability can be explored at: https://owkin.com/he2rna-result-visualization/. 5 | 6 | ## Installation 7 | 8 | Create a virtual environment and install the required packages (the variable CUDA_TOOLKIT_ROOT_DIR is needed to install libKMcuda): 9 | ```bash 10 | python3 -m venv .env 11 | source .env/bin/activate 12 | 13 | export CUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda 14 | pip install -r requirements.txt 15 | ``` 16 | NOTE: code was run with python 3.7.4 17 | 18 | ## Data collection and preprocessing 19 | 20 | To ensure reproducibility of the results, coordinates of the tiles used in the paper (necessary to extract tile images and features from whole-slide images) are provided in the archive tile_coordinates.gz. 21 | 22 | EDIT: due to an issue related to data quota, file tile_coordinates.gz should be downloaded instead from https://drive.google.com/file/d/1PJsUv1SQieJs7hqtWOqW68v1K9c-mIF6/view?usp=sharing. 23 | 24 | To uncompress it, run 25 | ```bash 26 | tar -xzvf tile_coordinates.gz 27 | ``` 28 | Splits used in the paper are also provided in patient_splits.pkl. 29 | 30 | ### TCGA 31 | 32 | We originally downloaded the whole-slide images from the TCGA data portal https://portal.gdc.cancer.gov/ via the gdc-client tool. To access all of TCGA data used in this work, follow the steps described below. 33 | First, create a folder to store data. 34 | ```bash 35 | mkdir data 36 | ``` 37 | Paths to folders containing slides, tile features and RNAseq data should be consistent with the contant of file constant.py. If data is saved in a different location, constant.py has to be modified accordingly, as well as the example config files. 38 | 39 | #### Download TCGA slides 40 | Go to the dedicated folder to store files (all FFPE slides from TCGA is approx. 10To) 41 | ```bash 42 | cd data 43 | mkdir TCGA_slides/ 44 | cd TCGA_slides/ 45 | ``` 46 | For each project, create a subfolder, e.g. 47 | ```bash 48 | mkdir TCGA_LIHC/ 49 | cd TCGA_LIHC/ 50 | ``` 51 | Download images using the corresponding manifest: 52 | ```bash 53 | gdc-client download -m gdc_manifests/gdc_manifest.2018-06-26_TCGA-LIHC.txt 54 | ``` 55 | Frozen slides from COAD and READ have been grouped together in CRC. 56 | ```bash 57 | mkdir TCGA_CRC_frozen/ 58 | cd TCGA_CRC_frozen/ 59 | gdc-client download -m gdc_manifests/gdc_manifest.CRC_frozen_slides.txt 60 | ``` 61 | 62 | #### Tile feature extraction 63 | The code in extract_tile_features_from_slides.py is designed to extract resnet features of tile images directly from whole-slide images, using the coordinates of the tiles in Openslide format. To extract tile features from WSIs from a given TCGA project, e.g. LIHC, run: 64 | ```bash 65 | mkdir TCGA_tiles/ 66 | 67 | python extract_tile_features_from_slides.py --path_to_tiles /TCGA_slides/TCGA_LIHC --tile_coordinates tile_coordinates/tile_coordinates_TCGA_LIHC.pkl --path_to_save_features TCGA_tiles/TCGA_LIHC 68 | ``` 69 | 70 | #### Download and preprocess RNAseq data 71 | Create a folder to store rnaseq data and download transcriptomes: 72 | ```bash 73 | cd data 74 | mkdir TCGA_transcriptome 75 | cd TCGA_transcriptome 76 | gdc-client download -m gdc_manifests/gdc_manifest.2018-03-13_alltranscriptome.txt 77 | ``` 78 | At this stage, there should be one folder per sample, containing a .gz archive. Extract the archives, using for instance gunzip 79 | ```bash 80 | gunzip */*.txt.gz 81 | ``` 82 | To make things more convenient, we already save a file containing transcriptomes matched to whole-slide images, using 83 | ```bash 84 | python transcriptome_data.py 85 | ``` 86 | 87 | #### Supertile preprocessing 88 | Finally, once all previous steps have been performed, supertile preprocessing can be performed using the following command (the csv file containing transcriptome is used here to ensure consistency between preprocessed image samples and RNAseq data), 89 | ```bash 90 | python supertile_preprocessing.py --path_to_slides data/TCGA_slides --path_to_transcriptome data/TCGA_transcriptome/all_transcriptomes.csv --path_to_save_processed_data data/TCGA_100_supertiles.h5 --n_tiles 100 91 | ``` 92 | 93 | ### 100,000 histological images of human colorectal cancer and healthy tissue 94 | The dataset '100,000 histological images of human colorectal cancer and healthy tissue' [2] is available from https://zenodo.org/record/1214456#.XpgF4m46--w. The file we use here is NCT-CRC-HE-100K-NONORM.zip. Download this file and unzip it. You should have a folder (e.g. data/NCT-CRC-HE-100K-NONORM) containing one subfolder per class (ADI, LYM, etc...). 95 | 96 | The code in extract_tile_features.py is designed to extract resnet features from those tile images 97 | 98 | ```bash 99 | python extract_tile_features.py --path_to_tiles data/NCT-CRC-HE-100K-NONORM --path_to_save_features data/NCT-CRC-HE-100K-NONORM_tiles 100 | ``` 101 | 102 | ### PESO 103 | The Prostate Epithelium Segmentation dataset (PESO) [3] (whole-slide images and segmentation masks) are available from https://zenodo.org/record/1485967#.Xusr2PI6--x (peso_training_wsi_x.zip and peso_training_masks.zip). Download and unzip those files in a folder (e.g. data/PESO) so that this folder contains subfolders named peso_training_wsi_x/ 104 | 105 | he code in extract_tile_features_from_slides.py can be used to extract features from the PESO dataset, using tile_coordinates_PESO.pkl 106 | 107 | ```bash 108 | python extract_tile_features_from_slides.py --path_to_slides data/PESO --tile_coordinates tile_coordinates/tile_coordinates_PESO.pkl --path_to_save_features data/PESO_tiles 109 | ``` 110 | 111 | ## Gene expression prediction experiment 112 | 113 | To run an experiment, write first a config file or use one of the examples available in folder condigs. 114 | 115 | * config_all_genes.ini: simultaneous prediction of all genes on all TCGA data, using super-tile-preprocessed data. 116 | * config_CD3_all_TCGA.ini: prediction of CD3 genes on all TCGA data, using super-tile-preprocessed data. 117 | * config_CD3_selection.ini: prediction of CD3 genes on a subset of cancers (COAD/LIHC/PRAD/LUAD/LUSC/BRCA), using all available tiles (8,000) per slide, and starting training from checkpoint previously saved. 118 | Similarly for CD19/CD20 genes, epithelium genes (TP63, KRT8 and KRT18) and MKI67. 119 | 120 | Launch experiment with a single train-test split: 121 | ```bash 122 | python main.py --config --run single_run --logdir ./exp 123 | ``` 124 | Launch cross-validation: 125 | ```bash 126 | python main.py --config --run cross_validation --n_folds 5 --logdir ./exp 127 | ``` 128 | Launch TensorboardX for visualizing training curves 129 | ```bash 130 | tensorboard --logdir=./exp --port=6006 131 | ``` 132 | 133 | Results will be saved in the specified path as follows: 134 | * for a single train/valid/test split, the model will be saved as model.pt and the correlation per gene and cancer type will be saved as results_single_split.csv 135 | * for a cross-validation, each model will be saved in a dedicated folder model_i/model.pt, the correlation per gene, cancer type and fold will be saved as results_per_fold.csv. 136 | 137 | ### Config file options 138 | 139 | * [main] 140 | * path: Path to the directory where model's weights will be saved. 141 | * use_saved_model (optional): Path to previous experiment to reload saved models 142 | * splits (optional): Path to Pickle file containing saved patient splits for cross-validation, useful in particular when finetuning a model on a subset of the data, to ensure consistency of the train and test set with those used for pretraining. 143 | * single_split (optional): Path to Pickle file containing saved patient split for single run 144 | 145 | * [data] 146 | * genes (optional): List of coma-separated Ensembl IDs, or path to a pickle file containing such a list. If None, all available genes with nonzero median expression are used. 147 | * path_to_transcriptome (optional): If None, build targets from projectname and list of genes. Otherwise, load transcriptome data from a saved csv file. 148 | * path_to_data (optional): Path to the data, saved either in a pickle file (for aggregated data) or in an hdf5 file. If None, build the dataset from .npy files. 149 | 150 | * [architecture] 151 | * layers: Integers defining the number of feature maps of the model's 1D convolutional layers 152 | * dropout: Float between 0 and 1. 153 | * ks: List of ks to sample from 154 | * nonlin: 'relu', 'sigmoid' or 'tanh'. 155 | * device: 'cpu' or 'cuda'. 156 | 157 | * [training] 158 | * max_epochs: Integer, defaults to 200. 159 | * patience: Integer, defaults to 20. 160 | * batch_size: Integer, defaults to 16. 161 | * num_workers: number of workers used for loading batches, defaults to 0 (value should be 0 when working with hdf5-stored data) 162 | 163 | * [optimization] 164 | * algo: 'sgd' or 'adam'. 165 | * lr: Float. 166 | * momentum: Float, optional 167 | 168 | ## Spatialization of gene expression 169 | 170 | ### Spatialization of lymphocyte genes in colorectal cancer 171 | 172 | Once a model has been trained to predict the expression of genes specifically expressed by lymphocytes (for instance CD3), the following script can be used to compute the AUCs for distinguishing tiles labelled with lymphocytes (LYM) from other categories 173 | ```bash 174 | python spatialization.py --experiment CRC --path_to_model CD3_selection --path_to_tiles data/NCT-CRC-HE-100K-NONORM_tiles 175 | ``` 176 | 177 | ### Spatialization of epithelium genes in prostate adenocarcinoma 178 | 179 | Once a model has been trained to predict the expression of genes specifically expressed by the epithelium in prostate, 180 | the following script can be used to compare the average expression predicted by the model for those genes and the ground truth segmentation of epithelium 181 | ```bash 182 | python spatialization.py --experiment PESO --path_to_model epithelium_selection --path_to_tiles data/PESO_tiles --path_to_masks data/PESO/peso_training_masks --corr pearson 183 | ``` 184 | 185 | ## MSI prediction 186 | 187 | This part is relatively independant. All that is needed here is: 188 | * preprocessed tiles from a dataset with MSI status: COAD(FFPE or frozen), READ (FFPE or frozen) or STAD (FFPE) 189 | * rnaseq data from this dataset 190 | ```bash 191 | python msi_prediction.py --cancer_types COAD READ --type_of_slides FFPE --msi_l 0 --Nsplit 50 --Ncval_all 10 --Ncval 10 --n_internsplit_A 3 --n_internsplit_B 3 --n_epoch 50 192 | ``` 193 | Note: for this part, tile features from CRC frozen slides are expected to be located in PATH_TO_TILES/TCGA_CRC_frozen. 194 | 195 | 196 | ## References 197 | 198 | [1] Schmauch, B., Romagnoni, A., Pronier, E., Saillard, C., Maillé, P., Calderaro, J., ... & Courtiol, P. (2019). Transcriptomic learning for digital pathology. bioRxiv, 760173. 199 | 200 | [2] Kather, J. N et al. 100,000 histological images of human colorectal cancer and healthy tissue (Version v0.1). Zenodo. http://doi.org/10.5281/zenodo.1214456 (2018). 201 | 202 | [3] Bulten, W., et al. PESO: Prostate Epithelium Segmentation on H&E-stained prostatectomy whole slide images (Version 1). Zenodo. http://doi.org/10.5281/zenodo.1485967 (2018). 203 | 204 | # License 205 | 206 | GPL v3.0 207 | -------------------------------------------------------------------------------- /configs/config_CD19-CD20_all_TCGA.ini: -------------------------------------------------------------------------------- 1 | [main] 2 | path: CD19-CD20_pancancer 3 | splits: patient_splits.pkl 4 | 5 | [data] 6 | path_to_transcriptome: data/TCGA_transcriptome/all_transcriptomes.csv 7 | genes: ENSG00000156738.16,ENSG00000177455.10 8 | path_to_data: data/TCGA_100_supertiles.h5 9 | 10 | [architecture] 11 | layers: 256,256 12 | ks: 1,2,5,10,20,50,100 13 | dropout: 0.25 14 | nonlin: relu 15 | device: cuda 16 | 17 | [training] 18 | max_epochs: 200 19 | patience: 50 20 | batch_size: 16 21 | num_workers: 0 22 | 23 | [optimization] 24 | optimizer: adam 25 | lr: 3e-4 -------------------------------------------------------------------------------- /configs/config_CD19-CD20_selection.ini: -------------------------------------------------------------------------------- 1 | [main] 2 | path: CD19-CD20_selection 3 | splits: patient_splits.pkl 4 | use_saved_model: CD19-CD20_pancancer 5 | 6 | [data] 7 | path_to_transcriptome: data/TCGA_transcriptome/all_transcriptomes.csv 8 | genes: ENSG00000156738.16,ENSG00000177455.10 9 | projectname: TCGA_COAD,TCGA_LIHC,TCGA_PRAD,TCGA_LUAD,TCGA_LUSC,TCGA_BRCA 10 | 11 | [architecture] 12 | layers: 256,256 13 | ks: 10,20,50,100,200,500,1000,2000,5000 14 | dropout: 0.25 15 | nonlin: relu 16 | device: cuda 17 | 18 | [training] 19 | max_epochs: 100 20 | patience: 30 21 | batch_size: 4 22 | num_workers: 16 23 | 24 | [optimization] 25 | optimizer: adam 26 | lr: 3e-4 -------------------------------------------------------------------------------- /configs/config_CD3_all_TCGA.ini: -------------------------------------------------------------------------------- 1 | [main] 2 | path: CD3_pancancer 3 | splits: patient_splits.pkl 4 | 5 | [data] 6 | path_to_transcriptome: data/TCGA_transcriptome/all_transcriptomes.csv 7 | genes: ENSG00000167286.8,ENSG00000198821.9,ENSG00000198851.8,ENSG00000160654.8 8 | path_to_data: data/TCGA_100_supertiles.h5 9 | 10 | [architecture] 11 | layers: 256,256 12 | ks: 1,2,5,10,20,50,100 13 | dropout: 0.25 14 | nonlin: relu 15 | device: cuda 16 | 17 | [training] 18 | max_epochs: 200 19 | patience: 50 20 | batch_size: 16 21 | num_workers: 0 22 | 23 | [optimization] 24 | optimizer: adam 25 | lr: 3e-4 -------------------------------------------------------------------------------- /configs/config_CD3_selection.ini: -------------------------------------------------------------------------------- 1 | [main] 2 | path: CD3_selection 3 | splits: patient_splits.pkl 4 | use_saved_model: CD3_pancancer 5 | 6 | [data] 7 | path_to_transcriptome: data/TCGA_transcriptome/all_transcriptomes.csv 8 | genes: ENSG00000167286.8,ENSG00000198821.9,ENSG00000198851.8,ENSG00000160654.8 9 | projectname: TCGA_COAD,TCGA_LIHC,TCGA_PRAD,TCGA_LUAD,TCGA_LUSC,TCGA_BRCA 10 | 11 | [architecture] 12 | layers: 256,256 13 | ks: 10,20,50,100,200,500,1000,2000,5000 14 | dropout: 0.25 15 | nonlin: relu 16 | device: cuda 17 | 18 | [training] 19 | max_epochs: 100 20 | patience: 30 21 | batch_size: 4 22 | num_workers: 16 23 | 24 | [optimization] 25 | optimizer: adam 26 | lr: 3e-4 -------------------------------------------------------------------------------- /configs/config_MKI67_all_TCGA.ini: -------------------------------------------------------------------------------- 1 | [main] 2 | path: MKI67_pancancer 3 | splits: patient_splits.pkl 4 | 5 | [data] 6 | path_to_transcriptome: data/TCGA_transcriptome/all_transcriptomes.csv 7 | genes: ENSG00000148773.11 8 | path_to_data: data/TCGA_100_supertiles.h5 9 | 10 | [architecture] 11 | layers: 256,256 12 | ks: 1,2,5,10,20,50,100 13 | dropout: 0.25 14 | nonlin: relu 15 | device: cuda 16 | 17 | [training] 18 | max_epochs: 200 19 | patience: 50 20 | batch_size: 16 21 | num_workers: 0 22 | 23 | [optimization] 24 | optimizer: adam 25 | lr: 3e-4 -------------------------------------------------------------------------------- /configs/config_MKI67_selection.ini: -------------------------------------------------------------------------------- 1 | [main] 2 | path: MKI67_selection 3 | splits: patient_splits.pkl 4 | use_saved_model: MKI67_pancancer 5 | 6 | [data] 7 | path_to_transcriptome: data/TCGA_transcriptome/all_transcriptomes.csv 8 | genes: ENSG00000148773.11 9 | projectname: TCGA_COAD,TCGA_LIHC,TCGA_PRAD,TCGA_LUAD,TCGA_LUSC,TCGA_BRCA 10 | 11 | [architecture] 12 | layers: 256,256 13 | ks: 10,20,50,100,200,500,1000,2000,5000 14 | dropout: 0.25 15 | nonlin: relu 16 | device: cuda 17 | 18 | [training] 19 | max_epochs: 100 20 | patience: 30 21 | batch_size: 4 22 | num_workers: 16 23 | 24 | [optimization] 25 | optimizer: adam 26 | lr: 3e-4 -------------------------------------------------------------------------------- /configs/config_all_genes.ini: -------------------------------------------------------------------------------- 1 | [main] 2 | path: all_genes 3 | # The following line aims at reproducing the exact same cross-validation as in the paper 4 | splits: patient_splits.pkl 5 | 6 | [data] 7 | path_to_transcriptome: data/TCGA_transcriptome/all_transcriptomes.csv 8 | path_to_data: data/TCGA_100_supertiles.h5 9 | 10 | [architecture] 11 | layers: 1024,1024 12 | ks: 1,2,5,10,20,50,100 13 | dropout: 0.25 14 | nonlin: relu 15 | device: cuda 16 | 17 | [training] 18 | max_epochs: 200 19 | patience: 50 20 | batch_size: 16 21 | num_workers: 0 22 | 23 | [optimization] 24 | optimizer: adam 25 | lr: 3e-4 -------------------------------------------------------------------------------- /configs/config_epithelium_all_TCGA.ini: -------------------------------------------------------------------------------- 1 | [main] 2 | path: epithelium_pancancer 3 | splits: patient_splits.pkl 4 | 5 | [data] 6 | path_to_transcriptome: data/TCGA_transcriptome/all_transcriptomes.csv 7 | genes: ENSG00000073282.11,ENSG00000111057.9,ENSG00000170421.10 8 | path_to_data: data/TCGA_100_supertiles.h5 9 | 10 | [architecture] 11 | layers: 256,256 12 | ks: 1,2,5,10,20,50,100 13 | dropout: 0.25 14 | nonlin: relu 15 | device: cuda 16 | 17 | [training] 18 | max_epochs: 200 19 | patience: 50 20 | batch_size: 16 21 | num_workers: 0 22 | 23 | [optimization] 24 | optimizer: adam 25 | lr: 3e-4 -------------------------------------------------------------------------------- /configs/config_epithelium_selection.ini: -------------------------------------------------------------------------------- 1 | [main] 2 | path: epithelium_selection 3 | splits: patient_splits.pkl 4 | use_saved_model: epithelium_pancancer 5 | 6 | [data] 7 | path_to_transcriptome: data/TCGA_transcriptome/all_transcriptomes.csv 8 | genes: ENSG00000073282.11,ENSG00000111057.9,ENSG00000170421.10 9 | projectname: TCGA_COAD,TCGA_LIHC,TCGA_PRAD,TCGA_LUAD,TCGA_LUSC,TCGA_BRCA 10 | 11 | [architecture] 12 | layers: 256,256 13 | ks: 10,20,50,100,200,500,1000,2000,5000 14 | dropout: 0.25 15 | nonlin: relu 16 | device: cuda 17 | 18 | [training] 19 | max_epochs: 100 20 | patience: 30 21 | batch_size: 4 22 | num_workers: 16 23 | 24 | [optimization] 25 | optimizer: adam 26 | lr: 3e-4 -------------------------------------------------------------------------------- /constant.py: -------------------------------------------------------------------------------- 1 | PATH_TO_SLIDE = 'data/TCGA_slides' 2 | PATH_TO_TILES = 'data/TCGA_tiles' 3 | PATH_TO_TRANSCRIPTOME = 'data/TCGA_transcriptome' 4 | PATH_TO_MSI_LABELS = 'data/MSI_labels' -------------------------------------------------------------------------------- /data/MSI_labels/msi_COAD.csv: -------------------------------------------------------------------------------- 1 | ,0,1 2 | 0,TCGA-3L-AA1B,MSS 3 | 1,TCGA-4N-A93T,MSS 4 | 2,TCGA-4T-AA8H,Indeterminate 5 | 3,TCGA-5M-AAT4,MSS 6 | 4,TCGA-5M-AAT5,MSI-L 7 | 5,TCGA-5M-AAT6,MSI-H 8 | 6,TCGA-5M-AATE,MSS 9 | 7,TCGA-A6-2671,MSS 10 | 8,TCGA-A6-2672,MSI-H 11 | 9,TCGA-A6-2674,MSS 12 | 10,TCGA-A6-2675,MSS 13 | 11,TCGA-A6-2676,MSI-H 14 | 12,TCGA-A6-2678,MSS 15 | 13,TCGA-A6-2679,MSS 16 | 14,TCGA-A6-2682,MSS 17 | 15,TCGA-A6-2685,MSS 18 | 16,TCGA-A6-2686,MSI-H 19 | 17,TCGA-A6-3807,MSS 20 | 18,TCGA-A6-3808,MSI-L 21 | 19,TCGA-A6-4105,MSS 22 | 20,TCGA-A6-4107,MSS 23 | 21,TCGA-A6-5657,MSS 24 | 22,TCGA-A6-5660,MSS 25 | 23,TCGA-A6-5661,MSI-H 26 | 24,TCGA-A6-5662,MSS 27 | 25,TCGA-A6-5664,MSS 28 | 26,TCGA-A6-5665,MSI-H 29 | 27,TCGA-A6-5666,MSI-L 30 | 28,TCGA-A6-5667,MSS 31 | 29,TCGA-A6-6137,MSS 32 | 30,TCGA-A6-6138,MSS 33 | 31,TCGA-A6-6140,MSS 34 | 32,TCGA-A6-6142,MSS 35 | 33,TCGA-A6-6648,MSS 36 | 34,TCGA-A6-6649,MSS 37 | 35,TCGA-A6-6651,MSS 38 | 36,TCGA-A6-6652,MSS 39 | 37,TCGA-A6-6653,MSI-H 40 | 38,TCGA-A6-6654,MSS 41 | 39,TCGA-A6-A565,MSI-L 42 | 40,TCGA-A6-A566,MSI-L 43 | 41,TCGA-A6-A567,MSS 44 | 42,TCGA-A6-A56B,MSS 45 | 43,TCGA-A6-A5ZU,MSS 46 | 44,TCGA-AA-3488,MSS 47 | 45,TCGA-AA-3489,MSS 48 | 46,TCGA-AA-3492,MSI-H 49 | 47,TCGA-AA-3494,MSS 50 | 48,TCGA-AA-3495,MSS 51 | 49,TCGA-AA-3496,MSI-L 52 | 50,TCGA-AA-3506,MSS 53 | 51,TCGA-AA-3509,MSS 54 | 52,TCGA-AA-3514,MSS 55 | 53,TCGA-AA-3517,MSI-L 56 | 54,TCGA-AA-3518,MSI-H 57 | 55,TCGA-AA-3519,MSS 58 | 56,TCGA-AA-3520,MSI-L 59 | 57,TCGA-AA-3521,MSS 60 | 58,TCGA-AA-3522,MSS 61 | 59,TCGA-AA-3524,MSS 62 | 60,TCGA-AA-3525,MSI-H 63 | 61,TCGA-AA-3526,MSI-L 64 | 62,TCGA-AA-3527,MSS 65 | 63,TCGA-AA-3529,MSI-L 66 | 64,TCGA-AA-3530,MSS 67 | 65,TCGA-AA-3531,MSI-L 68 | 66,TCGA-AA-3532,MSS 69 | 67,TCGA-AA-3534,MSS 70 | 68,TCGA-AA-3538,MSS 71 | 69,TCGA-AA-3542,MSS 72 | 70,TCGA-AA-3543,MSI-H 73 | 71,TCGA-AA-3544,MSS 74 | 72,TCGA-AA-3548,MSS 75 | 73,TCGA-AA-3549,MSS 76 | 74,TCGA-AA-3552,MSS 77 | 75,TCGA-AA-3553,MSI-L 78 | 76,TCGA-AA-3554,MSI-H 79 | 77,TCGA-AA-3556,MSS 80 | 78,TCGA-AA-3560,MSS 81 | 79,TCGA-AA-3561,MSS 82 | 80,TCGA-AA-3562,MSS 83 | 81,TCGA-AA-3655,MSS 84 | 82,TCGA-AA-3660,MSS 85 | 83,TCGA-AA-3662,MSS 86 | 84,TCGA-AA-3663,MSI-H 87 | 85,TCGA-AA-3664,MSS 88 | 86,TCGA-AA-3667,MSI-L 89 | 87,TCGA-AA-3672,MSI-H 90 | 88,TCGA-AA-3673,MSS 91 | 89,TCGA-AA-3675,MSS 92 | 90,TCGA-AA-3678,MSS 93 | 91,TCGA-AA-3679,MSS 94 | 92,TCGA-AA-3680,MSI-L 95 | 93,TCGA-AA-3681,MSS 96 | 94,TCGA-AA-3684,MSS 97 | 95,TCGA-AA-3685,MSS 98 | 96,TCGA-AA-3688,MSI-L 99 | 97,TCGA-AA-3692,MSI-L 100 | 98,TCGA-AA-3693,MSS 101 | 99,TCGA-AA-3696,MSS 102 | 100,TCGA-AA-3697,MSI-L 103 | 101,TCGA-AA-3710,MSI-H 104 | 102,TCGA-AA-3712,MSS 105 | 103,TCGA-AA-3713,MSI-H 106 | 104,TCGA-AA-3715,MSI-H 107 | 105,TCGA-AA-3811,MSI-H 108 | 106,TCGA-AA-3812,MSS 109 | 107,TCGA-AA-3814,MSS 110 | 108,TCGA-AA-3815,MSI-H 111 | 109,TCGA-AA-3818,MSS 112 | 110,TCGA-AA-3819,MSI-L 113 | 111,TCGA-AA-3821,MSI-H 114 | 112,TCGA-AA-3831,MSS 115 | 113,TCGA-AA-3833,MSI-H 116 | 114,TCGA-AA-3837,MSS 117 | 115,TCGA-AA-3841,MSS 118 | 116,TCGA-AA-3842,MSS 119 | 117,TCGA-AA-3844,MSS 120 | 118,TCGA-AA-3845,MSI-H 121 | 119,TCGA-AA-3846,MSS 122 | 120,TCGA-AA-3848,MSS 123 | 121,TCGA-AA-3850,MSS 124 | 122,TCGA-AA-3851,MSS 125 | 123,TCGA-AA-3852,MSI-L 126 | 124,TCGA-AA-3854,MSI-L 127 | 125,TCGA-AA-3855,MSI-L 128 | 126,TCGA-AA-3856,MSS 129 | 127,TCGA-AA-3858,MSS 130 | 128,TCGA-AA-3860,MSS 131 | 129,TCGA-AA-3861,MSI-L 132 | 130,TCGA-AA-3862,MSS 133 | 131,TCGA-AA-3864,MSI-H 134 | 132,TCGA-AA-3866,MSI-L 135 | 133,TCGA-AA-3867,MSS 136 | 134,TCGA-AA-3869,MSS 137 | 135,TCGA-AA-3870,MSS 138 | 136,TCGA-AA-3872,MSS 139 | 137,TCGA-AA-3875,MSS 140 | 138,TCGA-AA-3877,MSI-H 141 | 139,TCGA-AA-3930,MSI-L 142 | 140,TCGA-AA-3939,MSS 143 | 141,TCGA-AA-3941,MSI-L 144 | 142,TCGA-AA-3947,MSI-H 145 | 143,TCGA-AA-3949,MSI-H 146 | 144,TCGA-AA-3950,MSI-H 147 | 145,TCGA-AA-3952,MSS 148 | 146,TCGA-AA-3955,MSS 149 | 147,TCGA-AA-3966,MSI-H 150 | 148,TCGA-AA-3968,MSS 151 | 149,TCGA-AA-3970,MSS 152 | 150,TCGA-AA-3971,MSS 153 | 151,TCGA-AA-3972,MSI-L 154 | 152,TCGA-AA-3973,MSI-L 155 | 153,TCGA-AA-3975,MSS 156 | 154,TCGA-AA-3976,MSS 157 | 155,TCGA-AA-3977,MSS 158 | 156,TCGA-AA-3979,MSS 159 | 157,TCGA-AA-3980,MSS 160 | 158,TCGA-AA-3982,MSI-L 161 | 159,TCGA-AA-3984,MSS 162 | 160,TCGA-AA-3986,MSS 163 | 161,TCGA-AA-3989,MSS 164 | 162,TCGA-AA-3994,MSS 165 | 163,TCGA-AA-A004,MSI-L 166 | 164,TCGA-AA-A00A,MSI-H 167 | 165,TCGA-AA-A00D,MSS 168 | 166,TCGA-AA-A00E,MSI-H 169 | 167,TCGA-AA-A00F,MSS 170 | 168,TCGA-AA-A00J,MSI-H 171 | 169,TCGA-AA-A00K,MSI-L 172 | 170,TCGA-AA-A00L,MSS 173 | 171,TCGA-AA-A00N,MSI-L 174 | 172,TCGA-AA-A00O,MSI-L 175 | 173,TCGA-AA-A00Q,MSS 176 | 174,TCGA-AA-A00R,MSI-H 177 | 175,TCGA-AA-A00U,MSS 178 | 176,TCGA-AA-A00W,MSS 179 | 177,TCGA-AA-A00Z,MSS 180 | 178,TCGA-AA-A010,MSI-L 181 | 179,TCGA-AA-A017,MSS 182 | 180,TCGA-AA-A01C,MSS 183 | 181,TCGA-AA-A01D,MSS 184 | 182,TCGA-AA-A01F,MSS 185 | 183,TCGA-AA-A01G,MSI-L 186 | 184,TCGA-AA-A01I,MSS 187 | 185,TCGA-AA-A01K,MSS 188 | 186,TCGA-AA-A01P,MSI-H 189 | 187,TCGA-AA-A01Q,MSI-H 190 | 188,TCGA-AA-A01V,MSS 191 | 189,TCGA-AA-A01X,MSS 192 | 190,TCGA-AA-A01Z,MSS 193 | 191,TCGA-AA-A022,MSI-H 194 | 192,TCGA-AA-A024,MSI-L 195 | 193,TCGA-AA-A029,MSI-L 196 | 194,TCGA-AA-A02E,MSI-L 197 | 195,TCGA-AA-A02F,MSS 198 | 196,TCGA-AA-A02H,MSS 199 | 197,TCGA-AA-A02J,MSS 200 | 198,TCGA-AA-A02K,MSS 201 | 199,TCGA-AA-A02R,MSI-H 202 | 200,TCGA-AA-A02W,MSI-L 203 | 201,TCGA-AA-A03J,MSS 204 | 202,TCGA-AD-5900,MSI-H 205 | 203,TCGA-AD-6548,MSI-L 206 | 204,TCGA-AD-6888,MSS 207 | 205,TCGA-AD-6889,MSI-H 208 | 206,TCGA-AD-6890,MSS 209 | 207,TCGA-AD-6895,MSI-H 210 | 208,TCGA-AD-6899,MSS 211 | 209,TCGA-AD-6901,MSI-L 212 | 210,TCGA-AD-6963,MSS 213 | 211,TCGA-AD-6964,MSI-H 214 | 212,TCGA-AD-6965,MSS 215 | 213,TCGA-AD-A5EJ,MSI-H 216 | 214,TCGA-AD-A5EK,MSS 217 | 215,TCGA-AM-5820,MSS 218 | 216,TCGA-AM-5821,MSI-H 219 | 217,TCGA-AU-3779,MSS 220 | 218,TCGA-AU-6004,MSI-H 221 | 219,TCGA-AY-4070,MSS 222 | 220,TCGA-AY-4071,MSS 223 | 221,TCGA-AY-5543,MSS 224 | 222,TCGA-AY-6196,MSI-L 225 | 223,TCGA-AY-6197,MSI-H 226 | 224,TCGA-AY-6386,MSS 227 | 225,TCGA-AY-A54L,MSI-L 228 | 226,TCGA-AY-A69D,MSI-L 229 | 227,TCGA-AY-A71X,MSS 230 | 228,TCGA-AY-A8YK,MSS 231 | 229,TCGA-AZ-4308,MSS 232 | 230,TCGA-AZ-4313,MSI-H 233 | 231,TCGA-AZ-4315,MSS 234 | 232,TCGA-AZ-4614,MSI-L 235 | 233,TCGA-AZ-4615,MSI-H 236 | 234,TCGA-AZ-4616,MSI-L 237 | 235,TCGA-AZ-4682,MSS 238 | 236,TCGA-AZ-4684,MSI-L 239 | 237,TCGA-AZ-5403,MSS 240 | 238,TCGA-AZ-5407,MSS 241 | 239,TCGA-AZ-6598,MSI-H 242 | 240,TCGA-AZ-6599,MSS 243 | 241,TCGA-AZ-6600,MSS 244 | 242,TCGA-AZ-6601,MSI-H 245 | 243,TCGA-AZ-6603,MSS 246 | 244,TCGA-AZ-6605,MSS 247 | 245,TCGA-AZ-6606,MSS 248 | 246,TCGA-AZ-6607,MSS 249 | 247,TCGA-AZ-6608,MSI-L 250 | 248,TCGA-CA-5254,MSI-L 251 | 249,TCGA-CA-5255,MSS 252 | 250,TCGA-CA-5256,MSS 253 | 251,TCGA-CA-5796,MSS 254 | 252,TCGA-CA-5797,MSS 255 | 253,TCGA-CA-6715,MSS 256 | 254,TCGA-CA-6716,MSS 257 | 255,TCGA-CA-6717,MSS 258 | 256,TCGA-CA-6719,MSI-L 259 | 257,TCGA-CK-4947,MSS 260 | 258,TCGA-CK-4948,MSI-L 261 | 259,TCGA-CK-4950,MSS 262 | 260,TCGA-CK-4951,MSI-H 263 | 261,TCGA-CK-4952,MSS 264 | 262,TCGA-CK-5912,MSS 265 | 263,TCGA-CK-5913,MSI-H 266 | 264,TCGA-CK-5914,MSS 267 | 265,TCGA-CK-5915,MSS 268 | 266,TCGA-CK-5916,MSI-H 269 | 267,TCGA-CK-6746,MSI-H 270 | 268,TCGA-CK-6747,MSI-H 271 | 269,TCGA-CK-6748,MSS 272 | 270,TCGA-CK-6751,MSS 273 | 271,TCGA-CM-4743,MSI-H 274 | 272,TCGA-CM-4744,MSS 275 | 273,TCGA-CM-4746,MSI-H 276 | 274,TCGA-CM-4747,MSI-L 277 | 275,TCGA-CM-4748,MSS 278 | 276,TCGA-CM-4750,MSI-L 279 | 277,TCGA-CM-4751,MSS 280 | 278,TCGA-CM-4752,MSS 281 | 279,TCGA-CM-5341,MSS 282 | 280,TCGA-CM-5344,MSS 283 | 281,TCGA-CM-5348,MSS 284 | 282,TCGA-CM-5349,MSS 285 | 283,TCGA-CM-5860,MSS 286 | 284,TCGA-CM-5861,MSI-H 287 | 285,TCGA-CM-5862,MSS 288 | 286,TCGA-CM-5863,MSS 289 | 287,TCGA-CM-5864,MSS 290 | 288,TCGA-CM-5868,MSS 291 | 289,TCGA-CM-6161,MSI-L 292 | 290,TCGA-CM-6162,MSI-H 293 | 291,TCGA-CM-6163,MSS 294 | 292,TCGA-CM-6164,MSS 295 | 293,TCGA-CM-6165,MSS 296 | 294,TCGA-CM-6166,MSS 297 | 295,TCGA-CM-6167,MSS 298 | 296,TCGA-CM-6168,MSI-L 299 | 297,TCGA-CM-6169,MSS 300 | 298,TCGA-CM-6170,MSS 301 | 299,TCGA-CM-6171,MSI-H 302 | 300,TCGA-CM-6172,MSS 303 | 301,TCGA-CM-6674,MSI-H 304 | 302,TCGA-CM-6675,MSS 305 | 303,TCGA-CM-6676,MSI-L 306 | 304,TCGA-CM-6677,MSS 307 | 305,TCGA-CM-6678,MSS 308 | 306,TCGA-CM-6679,MSS 309 | 307,TCGA-CM-6680,MSS 310 | 308,TCGA-D5-5537,MSS 311 | 309,TCGA-D5-5538,MSS 312 | 310,TCGA-D5-5539,MSS 313 | 311,TCGA-D5-5540,MSI-L 314 | 312,TCGA-D5-5541,MSS 315 | 313,TCGA-D5-6529,MSI-L 316 | 314,TCGA-D5-6530,MSI-H 317 | 315,TCGA-D5-6531,MSS 318 | 316,TCGA-D5-6532,MSI-L 319 | 317,TCGA-D5-6533,MSS 320 | 318,TCGA-D5-6534,MSS 321 | 319,TCGA-D5-6535,MSS 322 | 320,TCGA-D5-6536,MSS 323 | 321,TCGA-D5-6537,MSS 324 | 322,TCGA-D5-6538,MSI-L 325 | 323,TCGA-D5-6539,MSS 326 | 324,TCGA-D5-6541,MSS 327 | 325,TCGA-D5-6898,MSS 328 | 326,TCGA-D5-6920,MSS 329 | 327,TCGA-D5-6922,MSS 330 | 328,TCGA-D5-6923,MSS 331 | 329,TCGA-D5-6924,MSS 332 | 330,TCGA-D5-6926,MSS 333 | 331,TCGA-D5-6927,MSI-H 334 | 332,TCGA-D5-6928,MSI-H 335 | 333,TCGA-D5-6929,MSI-L 336 | 334,TCGA-D5-6930,MSI-H 337 | 335,TCGA-D5-6931,MSS 338 | 336,TCGA-D5-6932,MSS 339 | 337,TCGA-D5-7000,MSS 340 | 338,TCGA-DM-A0X9,MSS 341 | 339,TCGA-DM-A0XD,MSI-L 342 | 340,TCGA-DM-A0XF,MSI-L 343 | 341,TCGA-DM-A1D0,MSS 344 | 342,TCGA-DM-A1D4,MSI-L 345 | 343,TCGA-DM-A1D6,MSS 346 | 344,TCGA-DM-A1D7,MSS 347 | 345,TCGA-DM-A1D8,MSS 348 | 346,TCGA-DM-A1D9,MSS 349 | 347,TCGA-DM-A1DA,MSI-L 350 | 348,TCGA-DM-A1DB,MSS 351 | 349,TCGA-DM-A1HA,MSS 352 | 350,TCGA-DM-A280,MSS 353 | 351,TCGA-DM-A282,MSS 354 | 352,TCGA-DM-A285,MSS 355 | 353,TCGA-DM-A288,MSS 356 | 354,TCGA-DM-A28A,MSS 357 | 355,TCGA-DM-A28E,MSS 358 | 356,TCGA-DM-A28F,MSS 359 | 357,TCGA-DM-A28G,MSS 360 | 358,TCGA-DM-A28H,MSI-L 361 | 359,TCGA-DM-A28K,MSS 362 | 360,TCGA-DM-A28M,MSS 363 | 361,TCGA-F4-6459,MSS 364 | 362,TCGA-F4-6460,MSS 365 | 363,TCGA-F4-6461,MSS 366 | 364,TCGA-F4-6463,MSS 367 | 365,TCGA-F4-6569,MSS 368 | 366,TCGA-F4-6570,MSI-H 369 | 367,TCGA-F4-6703,MSI-H 370 | 368,TCGA-F4-6704,MSS 371 | 369,TCGA-F4-6805,MSS 372 | 370,TCGA-F4-6806,MSS 373 | 371,TCGA-F4-6807,MSS 374 | 372,TCGA-F4-6808,MSS 375 | 373,TCGA-F4-6809,MSS 376 | 374,TCGA-F4-6854,MSS 377 | 375,TCGA-F4-6855,MSI-L 378 | 376,TCGA-F4-6856,MSI-H 379 | 377,TCGA-G4-6293,MSI-L 380 | 378,TCGA-G4-6294,MSS 381 | 379,TCGA-G4-6295,MSI-L 382 | 380,TCGA-G4-6297,MSS 383 | 381,TCGA-G4-6298,MSI-L 384 | 382,TCGA-G4-6299,MSS 385 | 383,TCGA-G4-6302,MSI-H 386 | 384,TCGA-G4-6303,MSI-L 387 | 385,TCGA-G4-6304,MSI-H 388 | 386,TCGA-G4-6306,MSS 389 | 387,TCGA-G4-6307,MSS 390 | 388,TCGA-G4-6309,MSI-H 391 | 389,TCGA-G4-6310,MSS 392 | 390,TCGA-G4-6311,MSS 393 | 391,TCGA-G4-6314,MSS 394 | 392,TCGA-G4-6315,MSS 395 | 393,TCGA-G4-6317,MSI-L 396 | 394,TCGA-G4-6320,MSI-H 397 | 395,TCGA-G4-6321,MSI-L 398 | 396,TCGA-G4-6322,MSI-L 399 | 397,TCGA-G4-6323,MSS 400 | 398,TCGA-G4-6586,MSI-H 401 | 399,TCGA-G4-6588,MSI-H 402 | 400,TCGA-G4-6625,MSS 403 | 401,TCGA-G4-6626,MSS 404 | 402,TCGA-G4-6627,MSI-L 405 | 403,TCGA-G4-6628,MSI-H 406 | 404,TCGA-NH-A50T,MSS 407 | 405,TCGA-NH-A50U,MSS 408 | 406,TCGA-NH-A50V,MSI-L 409 | 407,TCGA-NH-A5IV,MSI-H 410 | 408,TCGA-NH-A6GA,MSS 411 | 409,TCGA-NH-A6GB,MSS 412 | 410,TCGA-NH-A6GC,MSS 413 | 411,TCGA-NH-A8F7,Indeterminate 414 | 412,TCGA-NH-A8F8,MSS 415 | 413,TCGA-QG-A5YV,MSS 416 | 414,TCGA-QG-A5YW,MSI-L 417 | 415,TCGA-QG-A5YX,MSI-L 418 | 416,TCGA-QG-A5Z1,MSI-L 419 | 417,TCGA-QG-A5Z2,MSI-H 420 | 418,TCGA-QL-A97D,MSS 421 | 419,TCGA-SS-A7HO,MSS 422 | 420,TCGA-T9-A92H,MSS 423 | 421,TCGA-WS-AB45,MSI-H 424 | -------------------------------------------------------------------------------- /data/MSI_labels/msi_COAD_KR.csv: -------------------------------------------------------------------------------- 1 | ,0,1 2 | 0,TCGA-3L-AA1B,MSS 3 | 1,TCGA-4N-A93T,MSS 4 | 2,TCGA-4T-AA8H,Indeterminate 5 | 3,TCGA-5M-AAT4,MSS 6 | 4,TCGA-5M-AAT5,MSI-L 7 | 5,TCGA-5M-AAT6,MSI-H 8 | 6,TCGA-5M-AATA,MSS 9 | 7,TCGA-5M-AATE,MSS 10 | 8,TCGA-A6-2671,MSS 11 | 9,TCGA-A6-2672,MSI-H 12 | 10,TCGA-A6-2674,MSS 13 | 11,TCGA-A6-2675,MSS 14 | 12,TCGA-A6-2676,MSI-H 15 | 13,TCGA-A6-2678,MSS 16 | 14,TCGA-A6-2679,MSS 17 | 15,TCGA-A6-2682,MSS 18 | 16,TCGA-A6-2685,MSS 19 | 17,TCGA-A6-2686,MSI-H 20 | 18,TCGA-A6-3807,MSS 21 | 19,TCGA-A6-3808,MSI-L 22 | 20,TCGA-A6-4105,MSS 23 | 21,TCGA-A6-4107,MSS 24 | 22,TCGA-A6-5657,MSS 25 | 23,TCGA-A6-5660,MSS 26 | 24,TCGA-A6-5661,MSI-H 27 | 25,TCGA-A6-5662,MSS 28 | 26,TCGA-A6-5664,MSS 29 | 27,TCGA-A6-5665,MSI-H 30 | 28,TCGA-A6-5666,MSI-L 31 | 29,TCGA-A6-5667,MSS 32 | 30,TCGA-A6-6137,MSS 33 | 31,TCGA-A6-6138,MSS 34 | 32,TCGA-A6-6140,MSS 35 | 33,TCGA-A6-6142,MSS 36 | 34,TCGA-A6-6648,MSS 37 | 35,TCGA-A6-6649,MSS 38 | 36,TCGA-A6-6651,MSS 39 | 37,TCGA-A6-6652,MSS 40 | 38,TCGA-A6-6653,MSI-H 41 | 39,TCGA-A6-6654,MSS 42 | 40,TCGA-A6-6781,MSI-H 43 | 41,TCGA-A6-6782,MSS 44 | 42,TCGA-A6-A565,MSI-L 45 | 43,TCGA-A6-A566,MSI-L 46 | 44,TCGA-A6-A567,MSS 47 | 45,TCGA-A6-A56B,MSS 48 | 46,TCGA-A6-A5ZU,MSS 49 | 47,TCGA-AA-3488,MSS 50 | 48,TCGA-AA-3489,MSS 51 | 49,TCGA-AA-3492,MSI-H 52 | 50,TCGA-AA-3494,MSS 53 | 51,TCGA-AA-3495,MSS 54 | 52,TCGA-AA-3496,MSI-L 55 | 53,TCGA-AA-3502,MSI-L 56 | 54,TCGA-AA-3506,MSS 57 | 55,TCGA-AA-3509,MSS 58 | 56,TCGA-AA-3510,MSS 59 | 57,TCGA-AA-3511,MSS 60 | 58,TCGA-AA-3514,MSS 61 | 59,TCGA-AA-3517,MSI-L 62 | 60,TCGA-AA-3518,MSI-H 63 | 61,TCGA-AA-3519,MSS 64 | 62,TCGA-AA-3520,MSI-L 65 | 63,TCGA-AA-3521,MSS 66 | 64,TCGA-AA-3522,MSS 67 | 65,TCGA-AA-3524,MSS 68 | 66,TCGA-AA-3525,MSI-H 69 | 67,TCGA-AA-3526,MSI-L 70 | 68,TCGA-AA-3527,MSS 71 | 69,TCGA-AA-3529,MSI-L 72 | 70,TCGA-AA-3530,MSS 73 | 71,TCGA-AA-3531,MSI-L 74 | 72,TCGA-AA-3532,MSS 75 | 73,TCGA-AA-3534,MSS 76 | 74,TCGA-AA-3538,MSS 77 | 75,TCGA-AA-3542,MSS 78 | 76,TCGA-AA-3543,MSI-H 79 | 77,TCGA-AA-3544,MSS 80 | 78,TCGA-AA-3548,MSS 81 | 79,TCGA-AA-3549,MSS 82 | 80,TCGA-AA-3552,MSS 83 | 81,TCGA-AA-3553,MSI-L 84 | 82,TCGA-AA-3554,MSI-H 85 | 83,TCGA-AA-3556,MSS 86 | 84,TCGA-AA-3560,MSS 87 | 85,TCGA-AA-3561,MSS 88 | 86,TCGA-AA-3562,MSS 89 | 87,TCGA-AA-3655,MSS 90 | 88,TCGA-AA-3660,MSS 91 | 89,TCGA-AA-3662,MSS 92 | 90,TCGA-AA-3663,MSI-H 93 | 91,TCGA-AA-3664,MSS 94 | 92,TCGA-AA-3667,MSI-L 95 | 93,TCGA-AA-3672,MSI-H 96 | 94,TCGA-AA-3673,MSS 97 | 95,TCGA-AA-3675,MSS 98 | 96,TCGA-AA-3678,MSS 99 | 97,TCGA-AA-3679,MSS 100 | 98,TCGA-AA-3680,MSI-L 101 | 99,TCGA-AA-3681,MSS 102 | 100,TCGA-AA-3684,MSS 103 | 101,TCGA-AA-3685,MSS 104 | 102,TCGA-AA-3688,MSI-L 105 | 103,TCGA-AA-3692,MSI-L 106 | 104,TCGA-AA-3693,MSS 107 | 105,TCGA-AA-3696,MSS 108 | 106,TCGA-AA-3697,MSI-L 109 | 107,TCGA-AA-3710,MSI-H 110 | 108,TCGA-AA-3712,MSS 111 | 109,TCGA-AA-3713,MSI-H 112 | 110,TCGA-AA-3715,MSI-H 113 | 111,TCGA-AA-3811,MSI-H 114 | 112,TCGA-AA-3812,MSS 115 | 113,TCGA-AA-3814,MSS 116 | 114,TCGA-AA-3815,MSI-H 117 | 115,TCGA-AA-3818,MSS 118 | 116,TCGA-AA-3819,MSI-L 119 | 117,TCGA-AA-3821,MSI-H 120 | 118,TCGA-AA-3831,MSS 121 | 119,TCGA-AA-3833,MSI-H 122 | 120,TCGA-AA-3837,MSS 123 | 121,TCGA-AA-3841,MSS 124 | 122,TCGA-AA-3842,MSS 125 | 123,TCGA-AA-3844,MSS 126 | 124,TCGA-AA-3845,MSI-H 127 | 125,TCGA-AA-3846,MSS 128 | 126,TCGA-AA-3848,MSS 129 | 127,TCGA-AA-3850,MSS 130 | 128,TCGA-AA-3851,MSS 131 | 129,TCGA-AA-3852,MSI-L 132 | 130,TCGA-AA-3854,MSI-L 133 | 131,TCGA-AA-3855,MSI-L 134 | 132,TCGA-AA-3856,MSS 135 | 133,TCGA-AA-3858,MSS 136 | 134,TCGA-AA-3860,MSS 137 | 135,TCGA-AA-3861,MSI-L 138 | 136,TCGA-AA-3862,MSS 139 | 137,TCGA-AA-3864,MSI-H 140 | 138,TCGA-AA-3866,MSI-L 141 | 139,TCGA-AA-3867,MSS 142 | 140,TCGA-AA-3869,MSS 143 | 141,TCGA-AA-3870,MSS 144 | 142,TCGA-AA-3872,MSS 145 | 143,TCGA-AA-3875,MSS 146 | 144,TCGA-AA-3877,MSI-H 147 | 145,TCGA-AA-3930,MSI-L 148 | 146,TCGA-AA-3939,MSS 149 | 147,TCGA-AA-3941,MSI-L 150 | 148,TCGA-AA-3947,MSI-H 151 | 149,TCGA-AA-3949,MSI-H 152 | 150,TCGA-AA-3950,MSI-H 153 | 151,TCGA-AA-3952,MSS 154 | 152,TCGA-AA-3955,MSS 155 | 153,TCGA-AA-3966,MSI-H 156 | 154,TCGA-AA-3968,MSS 157 | 155,TCGA-AA-3970,MSS 158 | 156,TCGA-AA-3971,MSS 159 | 157,TCGA-AA-3972,MSI-L 160 | 158,TCGA-AA-3973,MSI-L 161 | 159,TCGA-AA-3975,MSS 162 | 160,TCGA-AA-3976,MSS 163 | 161,TCGA-AA-3977,MSS 164 | 162,TCGA-AA-3979,MSS 165 | 163,TCGA-AA-3980,MSS 166 | 164,TCGA-AA-3982,MSI-L 167 | 165,TCGA-AA-3984,MSS 168 | 166,TCGA-AA-3986,MSS 169 | 167,TCGA-AA-3989,MSS 170 | 168,TCGA-AA-3994,MSS 171 | 169,TCGA-AA-A004,MSI-L 172 | 170,TCGA-AA-A00A,MSI-H 173 | 171,TCGA-AA-A00D,MSS 174 | 172,TCGA-AA-A00E,MSI-H 175 | 173,TCGA-AA-A00F,MSS 176 | 174,TCGA-AA-A00J,MSI-H 177 | 175,TCGA-AA-A00K,MSI-L 178 | 176,TCGA-AA-A00L,MSS 179 | 177,TCGA-AA-A00N,MSI-L 180 | 178,TCGA-AA-A00O,MSI-L 181 | 179,TCGA-AA-A00Q,MSS 182 | 180,TCGA-AA-A00R,MSI-H 183 | 181,TCGA-AA-A00U,MSS 184 | 182,TCGA-AA-A00W,MSS 185 | 183,TCGA-AA-A00Z,MSS 186 | 184,TCGA-AA-A010,MSI-L 187 | 185,TCGA-AA-A017,MSS 188 | 186,TCGA-AA-A01C,MSS 189 | 187,TCGA-AA-A01D,MSS 190 | 188,TCGA-AA-A01F,MSS 191 | 189,TCGA-AA-A01G,MSI-L 192 | 190,TCGA-AA-A01I,MSS 193 | 191,TCGA-AA-A01K,MSS 194 | 192,TCGA-AA-A01P,MSI-H 195 | 193,TCGA-AA-A01Q,MSI-H 196 | 194,TCGA-AA-A01V,MSS 197 | 195,TCGA-AA-A01X,MSS 198 | 196,TCGA-AA-A01Z,MSS 199 | 197,TCGA-AA-A022,MSI-H 200 | 198,TCGA-AA-A024,MSI-L 201 | 199,TCGA-AA-A029,MSI-L 202 | 200,TCGA-AA-A02E,MSI-L 203 | 201,TCGA-AA-A02F,MSS 204 | 202,TCGA-AA-A02H,MSS 205 | 203,TCGA-AA-A02J,MSS 206 | 204,TCGA-AA-A02K,MSS 207 | 205,TCGA-AA-A02R,MSI-H 208 | 206,TCGA-AA-A02W,MSI-L 209 | 207,TCGA-AA-A03J,MSS 210 | 208,TCGA-AD-5900,MSI-H 211 | 209,TCGA-AD-6548,MSI-L 212 | 210,TCGA-AD-6888,MSS 213 | 211,TCGA-AD-6889,MSI-H 214 | 212,TCGA-AD-6890,MSS 215 | 213,TCGA-AD-6895,MSI-H 216 | 214,TCGA-AD-6899,MSS 217 | 215,TCGA-AD-6901,MSI-L 218 | 216,TCGA-AD-6963,MSS 219 | 217,TCGA-AD-6964,MSI-H 220 | 218,TCGA-AD-6965,MSS 221 | 219,TCGA-AD-A5EJ,MSI-H 222 | 220,TCGA-AD-A5EK,MSS 223 | 221,TCGA-AM-5820,MSS 224 | 222,TCGA-AM-5821,MSI-H 225 | 223,TCGA-AU-3779,MSS 226 | 224,TCGA-AU-6004,MSI-H 227 | 225,TCGA-AY-4070,MSS 228 | 226,TCGA-AY-4071,MSS 229 | 227,TCGA-AY-5543,MSS 230 | 228,TCGA-AY-6196,MSI-L 231 | 229,TCGA-AY-6197,MSI-H 232 | 230,TCGA-AY-6386,MSS 233 | 231,TCGA-AY-A54L,MSI-L 234 | 232,TCGA-AY-A69D,MSI-L 235 | 233,TCGA-AY-A71X,MSS 236 | 234,TCGA-AY-A8YK,MSS 237 | 235,TCGA-AZ-4308,MSS 238 | 236,TCGA-AZ-4313,MSI-H 239 | 237,TCGA-AZ-4315,MSS 240 | 238,TCGA-AZ-4323,MSI-L 241 | 239,TCGA-AZ-4614,MSI-L 242 | 240,TCGA-AZ-4615,MSI-H 243 | 241,TCGA-AZ-4616,MSI-L 244 | 242,TCGA-AZ-4682,MSS 245 | 243,TCGA-AZ-4684,MSI-L 246 | 244,TCGA-AZ-6598,MSI-H 247 | 245,TCGA-AZ-6599,MSS 248 | 246,TCGA-AZ-6600,MSS 249 | 247,TCGA-AZ-6601,MSI-H 250 | 248,TCGA-AZ-6603,MSS 251 | 249,TCGA-AZ-6605,MSS 252 | 250,TCGA-AZ-6606,MSS 253 | 251,TCGA-AZ-6607,MSS 254 | 252,TCGA-AZ-6608,MSI-L 255 | 253,TCGA-CA-5254,MSI-L 256 | 254,TCGA-CA-5255,MSS 257 | 255,TCGA-CA-5256,MSS 258 | 256,TCGA-CA-5796,MSS 259 | 257,TCGA-CA-5797,MSS 260 | 258,TCGA-CA-6715,MSS 261 | 259,TCGA-CA-6716,MSS 262 | 260,TCGA-CA-6717,MSS 263 | 261,TCGA-CA-6719,MSI-L 264 | 262,TCGA-CK-4947,MSS 265 | 263,TCGA-CK-4948,MSI-L 266 | 264,TCGA-CK-4950,MSS 267 | 265,TCGA-CK-4951,MSI-H 268 | 266,TCGA-CK-4952,MSS 269 | 267,TCGA-CK-5912,MSS 270 | 268,TCGA-CK-5913,MSI-H 271 | 269,TCGA-CK-5914,MSS 272 | 270,TCGA-CK-5915,MSS 273 | 271,TCGA-CK-5916,MSI-H 274 | 272,TCGA-CK-6746,MSI-H 275 | 273,TCGA-CK-6747,MSI-H 276 | 274,TCGA-CK-6748,MSS 277 | 275,TCGA-CK-6751,MSS 278 | 276,TCGA-CM-4743,MSI-H 279 | 277,TCGA-CM-4744,MSS 280 | 278,TCGA-CM-4746,MSI-H 281 | 279,TCGA-CM-4747,MSI-L 282 | 280,TCGA-CM-4748,MSS 283 | 281,TCGA-CM-4750,MSI-L 284 | 282,TCGA-CM-4751,MSS 285 | 283,TCGA-CM-4752,MSS 286 | 284,TCGA-CM-5341,MSS 287 | 285,TCGA-CM-5344,MSS 288 | 286,TCGA-CM-5348,MSS 289 | 287,TCGA-CM-5349,MSS 290 | 288,TCGA-CM-5860,MSS 291 | 289,TCGA-CM-5861,MSI-H 292 | 290,TCGA-CM-5862,MSS 293 | 291,TCGA-CM-5863,MSS 294 | 292,TCGA-CM-5864,MSS 295 | 293,TCGA-CM-5868,MSS 296 | 294,TCGA-CM-6161,MSI-L 297 | 295,TCGA-CM-6162,MSI-H 298 | 296,TCGA-CM-6163,MSS 299 | 297,TCGA-CM-6164,MSS 300 | 298,TCGA-CM-6165,MSS 301 | 299,TCGA-CM-6166,MSS 302 | 300,TCGA-CM-6167,MSS 303 | 301,TCGA-CM-6168,MSI-L 304 | 302,TCGA-CM-6169,MSS 305 | 303,TCGA-CM-6170,MSS 306 | 304,TCGA-CM-6171,MSI-H 307 | 305,TCGA-CM-6172,MSS 308 | 306,TCGA-CM-6674,MSI-H 309 | 307,TCGA-CM-6675,MSS 310 | 308,TCGA-CM-6676,MSI-L 311 | 309,TCGA-CM-6677,MSS 312 | 310,TCGA-CM-6678,MSS 313 | 311,TCGA-CM-6679,MSS 314 | 312,TCGA-CM-6680,MSS 315 | 313,TCGA-D5-5537,MSS 316 | 314,TCGA-D5-5538,MSS 317 | 315,TCGA-D5-5539,MSS 318 | 316,TCGA-D5-5540,MSI-L 319 | 317,TCGA-D5-5541,MSS 320 | 318,TCGA-D5-6529,MSI-L 321 | 319,TCGA-D5-6530,MSI-H 322 | 320,TCGA-D5-6531,MSS 323 | 321,TCGA-D5-6532,MSI-L 324 | 322,TCGA-D5-6533,MSS 325 | 323,TCGA-D5-6534,MSS 326 | 324,TCGA-D5-6535,MSS 327 | 325,TCGA-D5-6536,MSS 328 | 326,TCGA-D5-6537,MSS 329 | 327,TCGA-D5-6538,MSI-L 330 | 328,TCGA-D5-6539,MSS 331 | 329,TCGA-D5-6541,MSS 332 | 330,TCGA-D5-6898,MSS 333 | 331,TCGA-D5-6920,MSS 334 | 332,TCGA-D5-6922,MSS 335 | 333,TCGA-D5-6923,MSS 336 | 334,TCGA-D5-6924,MSS 337 | 335,TCGA-D5-6926,MSS 338 | 336,TCGA-D5-6927,MSI-H 339 | 337,TCGA-D5-6928,MSI-H 340 | 338,TCGA-D5-6929,MSI-L 341 | 339,TCGA-D5-6930,MSI-H 342 | 340,TCGA-D5-6931,MSS 343 | 341,TCGA-D5-6932,MSS 344 | 342,TCGA-D5-7000,MSS 345 | 343,TCGA-DM-A0X9,MSS 346 | 344,TCGA-DM-A0XD,MSI-L 347 | 345,TCGA-DM-A0XF,MSI-L 348 | 346,TCGA-DM-A1D0,MSS 349 | 347,TCGA-DM-A1D4,MSI-L 350 | 348,TCGA-DM-A1D6,MSS 351 | 349,TCGA-DM-A1D7,MSS 352 | 350,TCGA-DM-A1D8,MSS 353 | 351,TCGA-DM-A1D9,MSS 354 | 352,TCGA-DM-A1DA,MSI-L 355 | 353,TCGA-DM-A1DB,MSS 356 | 354,TCGA-DM-A1HA,MSS 357 | 355,TCGA-DM-A1HB,MSI-H 358 | 356,TCGA-DM-A280,MSS 359 | 357,TCGA-DM-A282,MSS 360 | 358,TCGA-DM-A285,MSS 361 | 359,TCGA-DM-A288,MSS 362 | 360,TCGA-DM-A28A,MSS 363 | 361,TCGA-DM-A28C,MSS 364 | 362,TCGA-DM-A28E,MSS 365 | 363,TCGA-DM-A28F,MSS 366 | 364,TCGA-DM-A28G,MSS 367 | 365,TCGA-DM-A28H,MSI-L 368 | 366,TCGA-DM-A28K,MSS 369 | 367,TCGA-DM-A28M,MSS 370 | 368,TCGA-F4-6459,MSS 371 | 369,TCGA-F4-6460,MSS 372 | 370,TCGA-F4-6461,MSS 373 | 371,TCGA-F4-6463,MSS 374 | 372,TCGA-F4-6569,MSS 375 | 373,TCGA-F4-6570,MSI-H 376 | 374,TCGA-F4-6703,MSI-H 377 | 375,TCGA-F4-6704,MSS 378 | 376,TCGA-F4-6805,MSS 379 | 377,TCGA-F4-6806,MSS 380 | 378,TCGA-F4-6807,MSS 381 | 379,TCGA-F4-6808,MSS 382 | 380,TCGA-F4-6809,MSS 383 | 381,TCGA-F4-6854,MSS 384 | 382,TCGA-F4-6855,MSI-L 385 | 383,TCGA-F4-6856,MSI-H 386 | 384,TCGA-G4-6293,MSI-L 387 | 385,TCGA-G4-6294,MSS 388 | 386,TCGA-G4-6295,MSI-L 389 | 387,TCGA-G4-6297,MSS 390 | 388,TCGA-G4-6298,MSI-L 391 | 389,TCGA-G4-6299,MSS 392 | 390,TCGA-G4-6302,MSI-H 393 | 391,TCGA-G4-6303,MSI-L 394 | 392,TCGA-G4-6304,MSI-H 395 | 393,TCGA-G4-6306,MSS 396 | 394,TCGA-G4-6307,MSS 397 | 395,TCGA-G4-6309,MSI-H 398 | 396,TCGA-G4-6310,MSS 399 | 397,TCGA-G4-6311,MSS 400 | 398,TCGA-G4-6314,MSS 401 | 399,TCGA-G4-6315,MSS 402 | 400,TCGA-G4-6317,MSI-L 403 | 401,TCGA-G4-6320,MSI-H 404 | 402,TCGA-G4-6321,MSI-L 405 | 403,TCGA-G4-6322,MSI-L 406 | 404,TCGA-G4-6323,MSS 407 | 405,TCGA-G4-6586,MSI-H 408 | 406,TCGA-G4-6588,MSI-H 409 | 407,TCGA-G4-6625,MSS 410 | 408,TCGA-G4-6626,MSS 411 | 409,TCGA-G4-6627,MSI-L 412 | 410,TCGA-G4-6628,MSI-H 413 | 411,TCGA-NH-A50T,MSS 414 | 412,TCGA-NH-A50U,MSS 415 | 413,TCGA-NH-A50V,MSI-L 416 | 414,TCGA-NH-A5IV,MSI-H 417 | 415,TCGA-NH-A6GA,MSS 418 | 416,TCGA-NH-A6GB,MSS 419 | 417,TCGA-NH-A6GC,MSS 420 | 418,TCGA-NH-A8F7,Indeterminate 421 | 419,TCGA-NH-A8F8,MSS 422 | 420,TCGA-QG-A5YV,MSS 423 | 421,TCGA-QG-A5YW,MSI-L 424 | 422,TCGA-QG-A5YX,MSI-L 425 | 423,TCGA-QG-A5Z1,MSI-L 426 | 424,TCGA-QG-A5Z2,MSI-H 427 | 425,TCGA-QL-A97D,MSS 428 | 426,TCGA-RU-A8FL,MSS 429 | 427,TCGA-SS-A7HO,MSS 430 | 428,TCGA-T9-A92H,MSS 431 | 429,TCGA-WS-AB45,MSI-H 432 | -------------------------------------------------------------------------------- /data/MSI_labels/msi_READ.csv: -------------------------------------------------------------------------------- 1 | ,0,1 2 | 0,TCGA-AF-2687,MSS 3 | 1,TCGA-AF-2690,MSS 4 | 2,TCGA-AF-2692,MSS 5 | 3,TCGA-AF-2693,MSS 6 | 4,TCGA-AF-3400,MSS 7 | 5,TCGA-AF-3911,MSI-L 8 | 6,TCGA-AF-3913,MSS 9 | 7,TCGA-AF-4110,MSS 10 | 8,TCGA-AF-5654,MSS 11 | 9,TCGA-AF-6136,MSS 12 | 10,TCGA-AF-6655,MSS 13 | 11,TCGA-AF-6672,MSS 14 | 12,TCGA-AF-A56K,MSS 15 | 13,TCGA-AF-A56L,MSS 16 | 14,TCGA-AF-A56N,MSS 17 | 15,TCGA-AG-3575,MSS 18 | 16,TCGA-AG-3578,MSS 19 | 17,TCGA-AG-3580,MSS 20 | 18,TCGA-AG-3581,MSS 21 | 19,TCGA-AG-3583,MSI-L 22 | 20,TCGA-AG-3584,MSS 23 | 21,TCGA-AG-3586,MSS 24 | 22,TCGA-AG-3587,MSS 25 | 23,TCGA-AG-3592,MSI-L 26 | 24,TCGA-AG-3593,MSS 27 | 25,TCGA-AG-3594,MSS 28 | 26,TCGA-AG-3598,MSS 29 | 27,TCGA-AG-3599,MSS 30 | 28,TCGA-AG-3600,MSS 31 | 29,TCGA-AG-3601,MSI-L 32 | 30,TCGA-AG-3602,MSS 33 | 31,TCGA-AG-3605,MSS 34 | 32,TCGA-AG-3608,Indeterminate 35 | 33,TCGA-AG-3609,MSS 36 | 34,TCGA-AG-3611,MSS 37 | 35,TCGA-AG-3612,MSS 38 | 36,TCGA-AG-3725,MSS 39 | 37,TCGA-AG-3726,MSS 40 | 38,TCGA-AG-3727,MSS 41 | 39,TCGA-AG-3728,MSS 42 | 40,TCGA-AG-3731,MSI-L 43 | 41,TCGA-AG-3732,MSS 44 | 42,TCGA-AG-3742,MSS 45 | 43,TCGA-AG-3878,MSS 46 | 44,TCGA-AG-3881,MSS 47 | 45,TCGA-AG-3882,MSS 48 | 46,TCGA-AG-3883,MSS 49 | 47,TCGA-AG-3887,MSS 50 | 48,TCGA-AG-3890,MSS 51 | 49,TCGA-AG-3892,MSS 52 | 50,TCGA-AG-3893,MSS 53 | 51,TCGA-AG-3894,MSS 54 | 52,TCGA-AG-3898,MSS 55 | 53,TCGA-AG-3902,MSS 56 | 54,TCGA-AG-3909,MSS 57 | 55,TCGA-AG-3999,MSS 58 | 56,TCGA-AG-4001,MSI-L 59 | 57,TCGA-AG-4005,MSS 60 | 58,TCGA-AG-4007,MSI-L 61 | 59,TCGA-AG-4008,MSS 62 | 60,TCGA-AG-4021,MSS 63 | 61,TCGA-AG-4022,MSS 64 | 62,TCGA-AG-A002,MSS 65 | 63,TCGA-AG-A008,MSS 66 | 64,TCGA-AG-A00C,MSS 67 | 65,TCGA-AG-A00H,MSS 68 | 66,TCGA-AG-A00Y,MSS 69 | 67,TCGA-AG-A011,MSS 70 | 68,TCGA-AG-A014,MSS 71 | 69,TCGA-AG-A015,MSS 72 | 70,TCGA-AG-A016,MSS 73 | 71,TCGA-AG-A01J,MSS 74 | 72,TCGA-AG-A01L,MSS 75 | 73,TCGA-AG-A01N,MSS 76 | 74,TCGA-AG-A01W,MSS 77 | 75,TCGA-AG-A01Y,MSS 78 | 76,TCGA-AG-A020,MSS 79 | 77,TCGA-AG-A023,MSS 80 | 78,TCGA-AG-A025,MSS 81 | 79,TCGA-AG-A026,MSS 82 | 80,TCGA-AG-A02G,MSS 83 | 81,TCGA-AG-A02N,MSI-H 84 | 82,TCGA-AG-A02X,MSS 85 | 83,TCGA-AG-A036,MSS 86 | 84,TCGA-AH-6544,MSS 87 | 85,TCGA-AH-6547,MSS 88 | 86,TCGA-AH-6549,MSI-L 89 | 87,TCGA-AH-6643,MSS 90 | 88,TCGA-AH-6644,MSI-L 91 | 89,TCGA-AH-6897,MSI-L 92 | 90,TCGA-AH-6903,MSS 93 | 91,TCGA-BM-6198,MSS 94 | 92,TCGA-CI-6622,MSS 95 | 93,TCGA-CI-6624,MSS 96 | 94,TCGA-CL-4957,MSS 97 | 95,TCGA-CL-5917,MSS 98 | 96,TCGA-CL-5918,MSS 99 | 97,TCGA-DC-4745,MSS 100 | 98,TCGA-DC-4749,MSS 101 | 99,TCGA-DC-5337,MSS 102 | 100,TCGA-DC-5869,MSS 103 | 101,TCGA-DC-6154,MSI-H 104 | 102,TCGA-DC-6155,MSS 105 | 103,TCGA-DC-6156,MSS 106 | 104,TCGA-DC-6157,MSS 107 | 105,TCGA-DC-6158,MSS 108 | 106,TCGA-DC-6160,MSS 109 | 107,TCGA-DC-6681,MSS 110 | 108,TCGA-DC-6682,MSS 111 | 109,TCGA-DC-6683,MSS 112 | 110,TCGA-DT-5265,MSS 113 | 111,TCGA-DY-A0XA,MSS 114 | 112,TCGA-DY-A1DC,MSS 115 | 113,TCGA-DY-A1DD,MSI-L 116 | 114,TCGA-DY-A1DE,MSS 117 | 115,TCGA-DY-A1DF,MSI-L 118 | 116,TCGA-DY-A1DG,MSS 119 | 117,TCGA-EF-5830,MSS 120 | 118,TCGA-EI-6506,MSS 121 | 119,TCGA-EI-6507,MSI-H 122 | 120,TCGA-EI-6508,MSS 123 | 121,TCGA-EI-6509,MSS 124 | 122,TCGA-EI-6510,MSI-L 125 | 123,TCGA-EI-6511,MSS 126 | 124,TCGA-EI-6512,MSS 127 | 125,TCGA-EI-6513,MSS 128 | 126,TCGA-EI-6514,MSS 129 | 127,TCGA-EI-6881,MSS 130 | 128,TCGA-EI-6882,MSI-H 131 | 129,TCGA-EI-6883,MSS 132 | 130,TCGA-EI-6884,MSS 133 | 131,TCGA-EI-6885,MSS 134 | 132,TCGA-EI-6917,MSS 135 | 133,TCGA-EI-7002,MSI-L 136 | 134,TCGA-EI-7004,MSS 137 | 135,TCGA-F5-6464,MSS 138 | 136,TCGA-F5-6465,MSS 139 | 137,TCGA-F5-6571,MSI-L 140 | 138,TCGA-F5-6702,MSS 141 | 139,TCGA-F5-6810,MSS 142 | 140,TCGA-F5-6811,MSI-L 143 | 141,TCGA-F5-6812,MSS 144 | 142,TCGA-F5-6813,MSS 145 | 143,TCGA-F5-6861,MSS 146 | 144,TCGA-F5-6863,MSI-L 147 | 145,TCGA-F5-6864,MSI-L 148 | 146,TCGA-G5-6233,MSI-L 149 | 147,TCGA-G5-6235,MSS 150 | 148,TCGA-G5-6572,MSS 151 | 149,TCGA-G5-6641,MSS 152 | -------------------------------------------------------------------------------- /data/MSI_labels/msi_READ_KR.csv: -------------------------------------------------------------------------------- 1 | ,0,1 2 | 0,TCGA-AF-2687,MSS 3 | 1,TCGA-AF-2690,MSS 4 | 2,TCGA-AF-2692,MSS 5 | 3,TCGA-AF-2693,MSS 6 | 4,TCGA-AF-3400,MSS 7 | 5,TCGA-AF-3911,MSI-L 8 | 6,TCGA-AF-3913,MSS 9 | 7,TCGA-AF-4110,MSS 10 | 8,TCGA-AF-5654,MSS 11 | 9,TCGA-AF-6136,MSS 12 | 10,TCGA-AF-6655,MSS 13 | 11,TCGA-AF-6672,MSS 14 | 12,TCGA-AF-A56K,MSS 15 | 13,TCGA-AF-A56L,MSS 16 | 14,TCGA-AF-A56N,MSS 17 | 15,TCGA-AG-3575,MSS 18 | 16,TCGA-AG-3578,MSS 19 | 17,TCGA-AG-3580,MSS 20 | 18,TCGA-AG-3581,MSS 21 | 19,TCGA-AG-3583,MSI-L 22 | 20,TCGA-AG-3584,MSS 23 | 21,TCGA-AG-3586,MSS 24 | 22,TCGA-AG-3587,MSS 25 | 23,TCGA-AG-3591,MSS 26 | 24,TCGA-AG-3592,MSI-L 27 | 25,TCGA-AG-3593,MSS 28 | 26,TCGA-AG-3594,MSS 29 | 27,TCGA-AG-3598,MSS 30 | 28,TCGA-AG-3599,MSS 31 | 29,TCGA-AG-3600,MSS 32 | 30,TCGA-AG-3601,MSI-L 33 | 31,TCGA-AG-3602,MSS 34 | 32,TCGA-AG-3605,MSS 35 | 33,TCGA-AG-3608,Indeterminate 36 | 34,TCGA-AG-3609,MSS 37 | 35,TCGA-AG-3611,MSS 38 | 36,TCGA-AG-3612,MSS 39 | 37,TCGA-AG-3725,MSS 40 | 38,TCGA-AG-3726,MSS 41 | 39,TCGA-AG-3727,MSS 42 | 40,TCGA-AG-3728,MSS 43 | 41,TCGA-AG-3731,MSI-L 44 | 42,TCGA-AG-3732,MSS 45 | 43,TCGA-AG-3742,MSS 46 | 44,TCGA-AG-3878,MSS 47 | 45,TCGA-AG-3881,MSS 48 | 46,TCGA-AG-3882,MSS 49 | 47,TCGA-AG-3883,MSS 50 | 48,TCGA-AG-3887,MSS 51 | 49,TCGA-AG-3890,MSS 52 | 50,TCGA-AG-3892,MSS 53 | 51,TCGA-AG-3893,MSS 54 | 52,TCGA-AG-3894,MSS 55 | 53,TCGA-AG-3898,MSS 56 | 54,TCGA-AG-3902,MSS 57 | 55,TCGA-AG-3909,MSS 58 | 56,TCGA-AG-3999,MSS 59 | 57,TCGA-AG-4001,MSI-L 60 | 58,TCGA-AG-4005,MSS 61 | 59,TCGA-AG-4007,MSI-L 62 | 60,TCGA-AG-4008,MSS 63 | 61,TCGA-AG-4021,MSS 64 | 62,TCGA-AG-4022,MSS 65 | 63,TCGA-AG-A002,MSS 66 | 64,TCGA-AG-A008,MSS 67 | 65,TCGA-AG-A00C,MSS 68 | 66,TCGA-AG-A00H,MSS 69 | 67,TCGA-AG-A00Y,MSS 70 | 68,TCGA-AG-A011,MSS 71 | 69,TCGA-AG-A014,MSS 72 | 70,TCGA-AG-A015,MSS 73 | 71,TCGA-AG-A016,MSS 74 | 72,TCGA-AG-A01J,MSS 75 | 73,TCGA-AG-A01L,MSS 76 | 74,TCGA-AG-A01N,MSS 77 | 75,TCGA-AG-A01W,MSS 78 | 76,TCGA-AG-A01Y,MSS 79 | 77,TCGA-AG-A020,MSS 80 | 78,TCGA-AG-A023,MSS 81 | 79,TCGA-AG-A025,MSS 82 | 80,TCGA-AG-A026,MSS 83 | 81,TCGA-AG-A02G,MSS 84 | 82,TCGA-AG-A02N,MSI-H 85 | 83,TCGA-AG-A02X,MSS 86 | 84,TCGA-AG-A036,MSS 87 | 85,TCGA-AH-6544,MSS 88 | 86,TCGA-AH-6547,MSS 89 | 87,TCGA-AH-6549,MSI-L 90 | 88,TCGA-AH-6643,MSS 91 | 89,TCGA-AH-6644,MSI-L 92 | 90,TCGA-AH-6897,MSI-L 93 | 91,TCGA-AH-6903,MSS 94 | 92,TCGA-BM-6198,MSS 95 | 93,TCGA-CI-6619,MSS 96 | 94,TCGA-CI-6620,MSS 97 | 95,TCGA-CI-6621,MSS 98 | 96,TCGA-CI-6622,MSS 99 | 97,TCGA-CI-6623,MSS 100 | 98,TCGA-CI-6624,MSS 101 | 99,TCGA-CL-4957,MSS 102 | 100,TCGA-CL-5917,MSS 103 | 101,TCGA-CL-5918,MSS 104 | 102,TCGA-DC-4745,MSS 105 | 103,TCGA-DC-4749,MSS 106 | 104,TCGA-DC-5337,MSS 107 | 105,TCGA-DC-5869,MSS 108 | 106,TCGA-DC-6154,MSI-H 109 | 107,TCGA-DC-6155,MSS 110 | 108,TCGA-DC-6156,MSS 111 | 109,TCGA-DC-6157,MSS 112 | 110,TCGA-DC-6158,MSS 113 | 111,TCGA-DC-6160,MSS 114 | 112,TCGA-DC-6681,MSS 115 | 113,TCGA-DC-6682,MSS 116 | 114,TCGA-DC-6683,MSS 117 | 115,TCGA-DT-5265,MSS 118 | 116,TCGA-DY-A0XA,MSS 119 | 117,TCGA-DY-A1DC,MSS 120 | 118,TCGA-DY-A1DD,MSI-L 121 | 119,TCGA-DY-A1DE,MSS 122 | 120,TCGA-DY-A1DF,MSI-L 123 | 121,TCGA-DY-A1DG,MSS 124 | 122,TCGA-DY-A1H8,MSS 125 | 123,TCGA-EF-5830,MSS 126 | 124,TCGA-EF-5831,MSS 127 | 125,TCGA-EI-6506,MSS 128 | 126,TCGA-EI-6507,MSI-H 129 | 127,TCGA-EI-6508,MSS 130 | 128,TCGA-EI-6509,MSS 131 | 129,TCGA-EI-6510,MSI-L 132 | 130,TCGA-EI-6511,MSS 133 | 131,TCGA-EI-6512,MSS 134 | 132,TCGA-EI-6513,MSS 135 | 133,TCGA-EI-6514,MSS 136 | 134,TCGA-EI-6881,MSS 137 | 135,TCGA-EI-6882,MSI-H 138 | 136,TCGA-EI-6883,MSS 139 | 137,TCGA-EI-6884,MSS 140 | 138,TCGA-EI-6885,MSS 141 | 139,TCGA-EI-6917,MSS 142 | 140,TCGA-EI-7002,MSI-L 143 | 141,TCGA-EI-7004,MSS 144 | 142,TCGA-F5-6464,MSS 145 | 143,TCGA-F5-6465,MSS 146 | 144,TCGA-F5-6571,MSI-L 147 | 145,TCGA-F5-6702,MSS 148 | 146,TCGA-F5-6810,MSS 149 | 147,TCGA-F5-6811,MSI-L 150 | 148,TCGA-F5-6812,MSS 151 | 149,TCGA-F5-6813,MSS 152 | 150,TCGA-F5-6861,MSS 153 | 151,TCGA-F5-6863,MSI-L 154 | 152,TCGA-F5-6864,MSI-L 155 | 153,TCGA-G5-6233,MSI-L 156 | 154,TCGA-G5-6235,MSS 157 | 155,TCGA-G5-6572,MSS 158 | 156,TCGA-G5-6641,MSS 159 | -------------------------------------------------------------------------------- /data/MSI_labels/msi_STAD.csv: -------------------------------------------------------------------------------- 1 | ,0,1 2 | 0,TCGA-3M-AB46,MSS 3 | 1,TCGA-3M-AB47,MSI-L 4 | 2,TCGA-BR-4187,MSS 5 | 3,TCGA-BR-4191,MSS 6 | 4,TCGA-BR-4201,MSI-H 7 | 5,TCGA-BR-4253,MSS 8 | 6,TCGA-BR-4256,MSI-H 9 | 7,TCGA-BR-4257,MSI-H 10 | 8,TCGA-BR-4267,MSS 11 | 9,TCGA-BR-4279,MSS 12 | 10,TCGA-BR-4294,MSI-L 13 | 11,TCGA-BR-4357,MSS 14 | 12,TCGA-BR-4361,MSI-H 15 | 13,TCGA-BR-4363,MSI-H 16 | 14,TCGA-BR-4366,MSS 17 | 15,TCGA-BR-4367,MSS 18 | 16,TCGA-BR-4368,MSI-H 19 | 17,TCGA-BR-4369,MSS 20 | 18,TCGA-BR-4370,MSI-H 21 | 19,TCGA-BR-4371,MSS 22 | 20,TCGA-BR-6452,MSI-H 23 | 21,TCGA-BR-6453,MSS 24 | 22,TCGA-BR-6454,MSS 25 | 23,TCGA-BR-6455,MSS 26 | 24,TCGA-BR-6456,MSS 27 | 25,TCGA-BR-6457,MSS 28 | 26,TCGA-BR-6458,MSI-L 29 | 27,TCGA-BR-6563,MSS 30 | 28,TCGA-BR-6564,MSS 31 | 29,TCGA-BR-6565,MSS 32 | 30,TCGA-BR-6566,MSI-H 33 | 31,TCGA-BR-6705,MSI-L 34 | 32,TCGA-BR-6707,MSS 35 | 33,TCGA-BR-6709,MSS 36 | 34,TCGA-BR-6710,MSS 37 | 35,TCGA-BR-6801,MSI-L 38 | 36,TCGA-BR-6802,MSI-H 39 | 37,TCGA-BR-6803,MSS 40 | 38,TCGA-BR-6852,MSI-H 41 | 39,TCGA-BR-7196,MSS 42 | 40,TCGA-BR-7197,MSS 43 | 41,TCGA-BR-7704,MSS 44 | 42,TCGA-BR-7707,MSI-H 45 | 43,TCGA-BR-7715,MSS 46 | 44,TCGA-BR-7716,MSS 47 | 45,TCGA-BR-7717,MSS 48 | 46,TCGA-BR-7722,MSS 49 | 47,TCGA-BR-7723,MSI-L 50 | 48,TCGA-BR-7851,MSI-H 51 | 49,TCGA-BR-7901,MSS 52 | 50,TCGA-BR-7957,MSS 53 | 51,TCGA-BR-7958,MSS 54 | 52,TCGA-BR-7959,MSI-L 55 | 53,TCGA-BR-8059,MSI-H 56 | 54,TCGA-BR-8060,MSS 57 | 55,TCGA-BR-8077,MSS 58 | 56,TCGA-BR-8080,MSS 59 | 57,TCGA-BR-8081,MSI-H 60 | 58,TCGA-BR-8284,MSI-H 61 | 59,TCGA-BR-8286,MSI-L 62 | 60,TCGA-BR-8289,MSS 63 | 61,TCGA-BR-8291,MSS 64 | 62,TCGA-BR-8295,MSI-L 65 | 63,TCGA-BR-8296,MSS 66 | 64,TCGA-BR-8297,MSS 67 | 65,TCGA-BR-8361,MSI-H 68 | 66,TCGA-BR-8364,MSS 69 | 67,TCGA-BR-8365,MSS 70 | 68,TCGA-BR-8366,MSS 71 | 69,TCGA-BR-8367,MSS 72 | 70,TCGA-BR-8368,MSI-H 73 | 71,TCGA-BR-8369,MSS 74 | 72,TCGA-BR-8371,MSS 75 | 73,TCGA-BR-8372,MSI-H 76 | 74,TCGA-BR-8373,MSI-L 77 | 75,TCGA-BR-8380,MSI-L 78 | 76,TCGA-BR-8381,MSS 79 | 77,TCGA-BR-8382,MSI-H 80 | 78,TCGA-BR-8384,MSS 81 | 79,TCGA-BR-8484,MSS 82 | 80,TCGA-BR-8485,MSS 83 | 81,TCGA-BR-8487,MSI-H 84 | 82,TCGA-BR-8588,MSS 85 | 83,TCGA-BR-8589,MSS 86 | 84,TCGA-BR-8590,MSS 87 | 85,TCGA-BR-8591,MSI-H 88 | 86,TCGA-BR-8592,MSS 89 | 87,TCGA-BR-8676,MSS 90 | 88,TCGA-BR-8677,MSS 91 | 89,TCGA-BR-8678,MSS 92 | 90,TCGA-BR-8679,MSI-L 93 | 91,TCGA-BR-8680,MSS 94 | 92,TCGA-BR-8682,MSS 95 | 93,TCGA-BR-8683,MSI-L 96 | 94,TCGA-BR-8686,MSS 97 | 95,TCGA-BR-8687,MSS 98 | 96,TCGA-BR-8690,MSI-L 99 | 97,TCGA-BR-A44T,MSS 100 | 98,TCGA-BR-A44U,MSS 101 | 99,TCGA-BR-A4CR,MSS 102 | 100,TCGA-BR-A4CS,MSS 103 | 101,TCGA-BR-A4IV,MSS 104 | 102,TCGA-BR-A4J4,MSI-L 105 | 103,TCGA-BR-A4J5,MSS 106 | 104,TCGA-BR-A4J6,MSS 107 | 105,TCGA-BR-A4J7,MSS 108 | 106,TCGA-BR-A4J8,MSS 109 | 107,TCGA-BR-A4J9,MSS 110 | 108,TCGA-BR-A4PF,MSS 111 | 109,TCGA-BR-A4QL,MSI-H 112 | 110,TCGA-CD-5798,MSS 113 | 111,TCGA-CD-5799,MSS 114 | 112,TCGA-CD-5800,MSS 115 | 113,TCGA-CD-5801,MSS 116 | 114,TCGA-CD-5803,MSS 117 | 115,TCGA-CD-5804,MSS 118 | 116,TCGA-CD-5813,MSS 119 | 117,TCGA-CD-8524,MSI-L 120 | 118,TCGA-CD-8525,MSS 121 | 119,TCGA-CD-8526,MSS 122 | 120,TCGA-CD-8527,MSI-L 123 | 121,TCGA-CD-8528,MSI-L 124 | 122,TCGA-CD-8529,MSS 125 | 123,TCGA-CD-8530,MSS 126 | 124,TCGA-CD-8531,MSS 127 | 125,TCGA-CD-8532,MSS 128 | 126,TCGA-CD-8533,MSI-L 129 | 127,TCGA-CD-8534,MSS 130 | 128,TCGA-CD-8535,MSS 131 | 129,TCGA-CD-A486,MSS 132 | 130,TCGA-CD-A487,MSS 133 | 131,TCGA-CD-A489,MSS 134 | 132,TCGA-CD-A48A,MSI-L 135 | 133,TCGA-CD-A48C,MSS 136 | 134,TCGA-CD-A4MG,MSI-H 137 | 135,TCGA-CD-A4MH,MSS 138 | 136,TCGA-CG-4301,MSS 139 | 137,TCGA-CG-4304,MSS 140 | 138,TCGA-CG-4305,MSI-H 141 | 139,TCGA-CG-4306,MSI-H 142 | 140,TCGA-CG-4436,MSI-L 143 | 141,TCGA-CG-4437,MSI-L 144 | 142,TCGA-CG-4438,MSS 145 | 143,TCGA-CG-4440,MSI-L 146 | 144,TCGA-CG-4441,MSS 147 | 145,TCGA-CG-4442,MSI-H 148 | 146,TCGA-CG-4443,MSS 149 | 147,TCGA-CG-4444,MSS 150 | 148,TCGA-CG-4460,MSI-H 151 | 149,TCGA-CG-4462,MSS 152 | 150,TCGA-CG-4465,MSI-H 153 | 151,TCGA-CG-4466,MSI-L 154 | 152,TCGA-CG-4469,MSI-L 155 | 153,TCGA-CG-4475,MSS 156 | 154,TCGA-CG-4476,MSS 157 | 155,TCGA-CG-4477,MSS 158 | 156,TCGA-CG-5716,MSS 159 | 157,TCGA-CG-5718,MSS 160 | 158,TCGA-CG-5719,MSS 161 | 159,TCGA-CG-5720,MSI-L 162 | 160,TCGA-CG-5721,MSI-H 163 | 161,TCGA-CG-5722,MSS 164 | 162,TCGA-CG-5723,MSI-H 165 | 163,TCGA-CG-5724,MSI-L 166 | 164,TCGA-CG-5725,MSS 167 | 165,TCGA-CG-5726,MSI-H 168 | 166,TCGA-CG-5732,MSS 169 | 167,TCGA-CG-5734,MSI-L 170 | 168,TCGA-D7-5577,MSS 171 | 169,TCGA-D7-5578,MSI-L 172 | 170,TCGA-D7-6519,MSS 173 | 171,TCGA-D7-6520,MSS 174 | 172,TCGA-D7-6521,MSI-L 175 | 173,TCGA-D7-6522,MSS 176 | 174,TCGA-D7-6524,MSS 177 | 175,TCGA-D7-6525,MSI-L 178 | 176,TCGA-D7-6526,MSS 179 | 177,TCGA-D7-6527,MSI-L 180 | 178,TCGA-D7-6528,MSI-L 181 | 179,TCGA-D7-6815,MSS 182 | 180,TCGA-D7-6818,MSS 183 | 181,TCGA-D7-6822,MSS 184 | 182,TCGA-D7-8570,MSS 185 | 183,TCGA-D7-8572,MSS 186 | 184,TCGA-D7-8573,MSI-L 187 | 185,TCGA-D7-8574,MSS 188 | 186,TCGA-D7-8575,MSS 189 | 187,TCGA-D7-8576,MSS 190 | 188,TCGA-D7-8578,MSS 191 | 189,TCGA-D7-8579,MSS 192 | 190,TCGA-D7-A4YU,MSS 193 | 191,TCGA-D7-A4YX,MSS 194 | 192,TCGA-D7-A4Z0,MSS 195 | 193,TCGA-D7-A6EV,MSI-L 196 | 194,TCGA-D7-A6EX,MSS 197 | 195,TCGA-D7-A6EY,MSI-H 198 | 196,TCGA-D7-A6EZ,MSS 199 | 197,TCGA-D7-A6F0,MSS 200 | 198,TCGA-D7-A6F2,MSS 201 | 199,TCGA-D7-A747,MSS 202 | 200,TCGA-D7-A748,MSS 203 | 201,TCGA-D7-A74A,MSS 204 | 202,TCGA-F1-6177,MSI-H 205 | 203,TCGA-F1-6874,MSI-H 206 | 204,TCGA-F1-6875,MSS 207 | 205,TCGA-F1-A448,MSI-H 208 | 206,TCGA-F1-A72C,MSS 209 | 207,TCGA-FP-7735,MSS 210 | 208,TCGA-FP-7829,MSS 211 | 209,TCGA-FP-7916,MSS 212 | 210,TCGA-FP-7998,MSS 213 | 211,TCGA-FP-8099,MSS 214 | 212,TCGA-FP-8209,MSS 215 | 213,TCGA-FP-8210,MSS 216 | 214,TCGA-FP-8211,MSS 217 | 215,TCGA-FP-8631,MSS 218 | 216,TCGA-FP-A4BF,MSS 219 | 217,TCGA-FP-A8CX,MSS 220 | 218,TCGA-FP-A9TM,MSS 221 | 219,TCGA-HF-7131,MSS 222 | 220,TCGA-HF-7132,MSI-H 223 | 221,TCGA-HF-7133,MSS 224 | 222,TCGA-HF-7134,MSI-L 225 | 223,TCGA-HF-A5NB,MSI-H 226 | 224,TCGA-HJ-7597,MSI-H 227 | 225,TCGA-HU-8238,MSS 228 | 226,TCGA-HU-8244,MSI-L 229 | 227,TCGA-HU-8249,MSS 230 | 228,TCGA-HU-8604,MSS 231 | 229,TCGA-HU-8608,MSS 232 | 230,TCGA-HU-8610,MSS 233 | 231,TCGA-HU-A4G2,MSS 234 | 232,TCGA-HU-A4G3,MSS 235 | 233,TCGA-HU-A4G8,MSI-H 236 | 234,TCGA-HU-A4G9,MSI-H 237 | 235,TCGA-HU-A4GC,MSI-L 238 | 236,TCGA-HU-A4GD,MSS 239 | 237,TCGA-HU-A4GF,MSS 240 | 238,TCGA-HU-A4GH,MSS 241 | 239,TCGA-HU-A4GJ,MSS 242 | 240,TCGA-HU-A4GP,MSI-L 243 | 241,TCGA-HU-A4GQ,MSI-H 244 | 242,TCGA-HU-A4GT,MSI-H 245 | 243,TCGA-HU-A4GU,MSI-H 246 | 244,TCGA-HU-A4GX,MSI-H 247 | 245,TCGA-HU-A4GY,MSS 248 | 246,TCGA-HU-A4H0,MSS 249 | 247,TCGA-HU-A4H5,MSS 250 | 248,TCGA-HU-A4H6,MSS 251 | 249,TCGA-HU-A4H8,MSI-H 252 | 250,TCGA-HU-A4HB,MSS 253 | 251,TCGA-HU-A4HD,MSI-L 254 | 252,TCGA-IN-7806,MSS 255 | 253,TCGA-IN-7808,MSS 256 | 254,TCGA-IN-8663,MSI-L 257 | 255,TCGA-IP-7968,MSS 258 | 256,TCGA-KB-A6F7,MSS 259 | 257,TCGA-KB-A93G,MSS 260 | 258,TCGA-KB-A93H,MSS 261 | 259,TCGA-KB-A93J,MSS 262 | 260,TCGA-MX-A5UG,MSS 263 | 261,TCGA-MX-A5UJ,MSI-H 264 | 262,TCGA-MX-A663,MSS 265 | 263,TCGA-MX-A666,MSS 266 | 264,TCGA-R5-A7O7,MSS 267 | 265,TCGA-R5-A7ZE,MSS 268 | 266,TCGA-R5-A7ZF,MSS 269 | 267,TCGA-R5-A7ZI,MSI-H 270 | 268,TCGA-R5-A7ZR,MSS 271 | 269,TCGA-R5-A805,MSI-L 272 | 270,TCGA-RD-A7BS,MSS 273 | 271,TCGA-RD-A7BT,MSI-L 274 | 272,TCGA-RD-A7BW,MSS 275 | 273,TCGA-RD-A7C1,MSS 276 | 274,TCGA-RD-A8MV,MSS 277 | 275,TCGA-RD-A8MW,MSS 278 | 276,TCGA-RD-A8N0,MSS 279 | 277,TCGA-RD-A8N1,MSS 280 | 278,TCGA-RD-A8N2,MSS 281 | 279,TCGA-RD-A8N4,MSS 282 | 280,TCGA-RD-A8N5,MSS 283 | 281,TCGA-RD-A8N6,MSS 284 | 282,TCGA-RD-A8N9,MSS 285 | 283,TCGA-RD-A8NB,MSI-H 286 | 284,TCGA-SW-A7EA,MSI-H 287 | 285,TCGA-SW-A7EB,MSS 288 | 286,TCGA-VQ-A8DT,MSS 289 | 287,TCGA-VQ-A8DU,MSS 290 | 288,TCGA-VQ-A8DV,MSS 291 | 289,TCGA-VQ-A8DZ,MSS 292 | 290,TCGA-VQ-A8E0,MSS 293 | 291,TCGA-VQ-A8E2,MSS 294 | 292,TCGA-VQ-A8E3,MSI-H 295 | 293,TCGA-VQ-A8E7,MSS 296 | 294,TCGA-VQ-A8P2,MSI-H 297 | 295,TCGA-VQ-A8P3,MSS 298 | 296,TCGA-VQ-A8P5,MSI-L 299 | 297,TCGA-VQ-A8P8,MSS 300 | 298,TCGA-VQ-A8PB,MSI-H 301 | 299,TCGA-VQ-A8PC,MSS 302 | 300,TCGA-VQ-A8PD,MSS 303 | 301,TCGA-VQ-A8PE,MSS 304 | 302,TCGA-VQ-A8PF,MSS 305 | 303,TCGA-VQ-A8PH,MSS 306 | 304,TCGA-VQ-A8PJ,MSS 307 | 305,TCGA-VQ-A8PK,MSS 308 | 306,TCGA-VQ-A8PM,MSS 309 | 307,TCGA-VQ-A8PO,MSI-H 310 | 308,TCGA-VQ-A8PP,MSI-H 311 | 309,TCGA-VQ-A8PQ,MSS 312 | 310,TCGA-VQ-A8PU,MSS 313 | 311,TCGA-VQ-A8PX,MSI-H 314 | 312,TCGA-VQ-A91A,MSS 315 | 313,TCGA-VQ-A91D,MSI-H 316 | 314,TCGA-VQ-A91E,MSI-H 317 | 315,TCGA-VQ-A91K,MSI-H 318 | 316,TCGA-VQ-A91N,MSS 319 | 317,TCGA-VQ-A91Q,MSS 320 | 318,TCGA-VQ-A91S,MSS 321 | 319,TCGA-VQ-A91U,MSS 322 | 320,TCGA-VQ-A91V,MSS 323 | 321,TCGA-VQ-A91X,MSI-L 324 | 322,TCGA-VQ-A91Y,MSS 325 | 323,TCGA-VQ-A91Z,MSS 326 | 324,TCGA-VQ-A922,MSI-L 327 | 325,TCGA-VQ-A923,MSS 328 | 326,TCGA-VQ-A924,MSI-H 329 | 327,TCGA-VQ-A925,MSS 330 | 328,TCGA-VQ-A927,MSS 331 | 329,TCGA-VQ-A928,MSS 332 | 330,TCGA-VQ-A92D,MSI-L 333 | 331,TCGA-VQ-A94O,MSS 334 | 332,TCGA-VQ-A94P,MSS 335 | 333,TCGA-VQ-A94R,MSI-L 336 | 334,TCGA-VQ-A94T,MSI-L 337 | 335,TCGA-VQ-A94U,MSS 338 | 336,TCGA-VQ-AA64,MSS 339 | 337,TCGA-VQ-AA68,MSS 340 | 338,TCGA-VQ-AA69,MSS 341 | 339,TCGA-VQ-AA6A,MSS 342 | 340,TCGA-VQ-AA6D,MSI-H 343 | 341,TCGA-VQ-AA6F,MSS 344 | 342,TCGA-VQ-AA6G,MSS 345 | 343,TCGA-VQ-AA6J,MSS 346 | 344,TCGA-VQ-AA6K,MSS 347 | 345,TCGA-ZA-A8F6,MSS 348 | 346,TCGA-ZQ-A9CR,MSI-L 349 | -------------------------------------------------------------------------------- /extract_tile_features.py: -------------------------------------------------------------------------------- 1 | """ 2 | HE2RNA: Extract ResNet features from tile images 3 | Copyright (C) 2020 Owkin Inc. 4 | 5 | This program is free software: you can redistribute it and/or modify 6 | it under the terms of the GNU General Public License as published by 7 | the Free Software Foundation, either version 3 of the License, or 8 | (at your option) any later version. 9 | 10 | This program is distributed in the hope that it will be useful, 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 | GNU General Public License for more details. 14 | 15 | You should have received a copy of the GNU General Public License 16 | along with this program. If not, see . 17 | """ 18 | 19 | import tensorflow as tf 20 | from keras.backend.tensorflow_backend import set_session 21 | 22 | config = tf.ConfigProto() 23 | config.gpu_options.per_process_gpu_memory_fraction = 0.4 # To use 40% of memory 24 | set_session(tf.Session(config=config)) 25 | 26 | import os 27 | import numpy as np 28 | import argparse 29 | from colorcorrect.util import from_pil, to_pil 30 | from colorcorrect import algorithm as cca 31 | from tqdm import tqdm 32 | from keras.applications.resnet50 import ResNet50 33 | from keras.models import Model 34 | from keras.applications.resnet50 import preprocess_input 35 | from PIL import Image 36 | 37 | 38 | def extract_and_save_features(path_to_tiles, 39 | path_to_save_features): 40 | """Extract ResNet features from tile images. 41 | """ 42 | model = ResNet50(weights='imagenet', include_top=True) 43 | model = Model(inputs=model.inputs, outputs=model.get_layer('avg_pool').output) 44 | 45 | if not os.path.exists(path_to_save_features): 46 | os.mkdir(path_to_save_features) 47 | for cat in ['ADI', 'MUC', 'BACK', 'LYM', 'NORM', 'DEB', 'MUS', 'STR', 'TUM']: 48 | X = [] 49 | for filename in tqdm(os.listdir(os.path.join(path_to_tiles, cat))): 50 | try: 51 | tile = Image.open(os.path.join(path_to_tiles, cat, filename)) 52 | tile = to_pil(cca.stretch(from_pil(tile))) 53 | tile = np.array(tile) 54 | features = model.predict(preprocess_input(tile[np.newaxis]), batch_size=1) 55 | X.append(features) 56 | except ZeroDivisionError: 57 | pass 58 | np.save(os.path.join(path_to_save_features, f'{cat}.npy'), np.array(X)) 59 | 60 | def main(): 61 | parser = argparse.ArgumentParser() 62 | parser.add_argument("--path_to_tiles", help="path to folder containing tile images", 63 | default='data/NCT-CRC-HE-100K-NONORM/') 64 | parser.add_argument("--path_to_save_features", help="path to save features as npy files", 65 | default='data/NCT-CRC-HE-100K-NONORM_tiles/') 66 | args = parser.parse_args() 67 | extract_and_save_features( 68 | path_to_tiles=args.path_to_tiles, 69 | path_to_save_features=args.path_to_save_features 70 | ) 71 | 72 | if __name__ == '__main__': 73 | main() 74 | -------------------------------------------------------------------------------- /extract_tile_features_from_slides.py: -------------------------------------------------------------------------------- 1 | """ 2 | HE2RNA: Divide whole-slide images in tiles and extract ResNet features 3 | Copyright (C) 2020 Owkin Inc. 4 | 5 | This program is free software: you can redistribute it and/or modify 6 | it under the terms of the GNU General Public License as published by 7 | the Free Software Foundation, either version 3 of the License, or 8 | (at your option) any later version. 9 | 10 | This program is distributed in the hope that it will be useful, 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 | GNU General Public License for more details. 14 | 15 | You should have received a copy of the GNU General Public License 16 | along with this program. If not, see . 17 | """ 18 | 19 | import tensorflow as tf 20 | from keras.backend.tensorflow_backend import set_session 21 | 22 | config = tf.ConfigProto() 23 | config.gpu_options.per_process_gpu_memory_fraction = 0.50 # To use 50% of memory 24 | set_session(tf.Session(config=config)) 25 | 26 | import os 27 | import numpy as np 28 | import pickle as pkl 29 | import argparse 30 | import openslide 31 | import openslide.deepzoom 32 | import colorcorrect 33 | from joblib import Parallel, delayed 34 | from PIL import Image 35 | from colorcorrect.util import from_pil, to_pil 36 | from colorcorrect import algorithm as cca 37 | from tqdm import tqdm 38 | from keras.applications.resnet50 import ResNet50 39 | from keras.models import Model 40 | from keras.applications.resnet50 import preprocess_input 41 | 42 | def extract_tile_features(level, coord, zoom): 43 | tile = np.array(zoom.get_tile(level, (coord[1], coord[2]))) 44 | tile = Image.fromarray(tile) 45 | tile = to_pil(cca.stretch(from_pil(tile))) 46 | tile = np.array(tile) 47 | return tile 48 | 49 | def save_numpy_features(path2slides, folder, slidename, coords, path): 50 | model = ResNet50(weights='imagenet', include_top=True) 51 | model = Model(inputs=model.inputs, outputs=model.get_layer('avg_pool').output) 52 | 53 | slide = openslide.OpenSlide(os.path.join(path2slides, folder, slidename)) 54 | zoom = openslide.deepzoom.DeepZoomGenerator(slide, tile_size=224, overlap=0) 55 | level = int(coords[0, 0]) 56 | tiles = np.array([extract_tile_features(level, coord, zoom) for coord in tqdm(coords)]) 57 | tiles = preprocess_input(tiles) 58 | X = model.predict(tiles, batch_size=32) 59 | X = np.concatenate([coords, X], axis=1) 60 | np.save(os.path.join(path, '0.50_mpp', slidename.split('.')[0] + '.npy'), X) 61 | 62 | def process_all_slides(path2slides, tile_coords, path): 63 | 64 | subfolder = {} 65 | slide_dirs = [d for d in os.listdir(path2slides) if os.path.isdir(os.path.join(path2slides, d))] 66 | 67 | slidenames = [] 68 | subfolders = [] 69 | 70 | for d in slide_dirs: 71 | for f in os.listdir(os.path.join(path2slides, d)): 72 | if f.endswith('.svs') or f.endswith('.tif') and 'mask' not in f: 73 | slidenames.append(f) 74 | subfolders.append(d) 75 | 76 | if not os.path.exists(path): 77 | os.mkdir(path) 78 | if not os.path.exists(os.path.join(path, '0.50_mpp')): 79 | os.mkdir(os.path.join(path, '0.50_mpp')) 80 | 81 | for folder, slidename in zip(subfolders, slidenames): 82 | if slidename in tile_coords.keys(): 83 | save_numpy_features(path2slides, folder, slidename, tile_coords[slidename], path) 84 | else: 85 | print(f'Warning: tile coordinates not found for file {slidename}, skipping it') 86 | 87 | def main(): 88 | parser = argparse.ArgumentParser() 89 | parser.add_argument("--path_to_slides", help="path to folder containing subfolders with whole-slide images", 90 | default='data/PESO/') 91 | parser.add_argument("--path_to_save_features", help="path to save features as npy files", 92 | default='data/PESO_tiles') 93 | parser.add_argument("--tile_coordinates", help="path to pkl file containing tile coordinates", 94 | default='tile_coordinates/tile_coordinates_PESO.pkl') 95 | args = parser.parse_args() 96 | path2slides = args.path_to_slides 97 | path = args.path_to_save_features 98 | tile_coords = args.tile_coordinates 99 | process_all_slides(path2slides, pkl.load(open(tile_coords, 'rb')), path) 100 | 101 | if __name__ == '__main__': 102 | 103 | main() -------------------------------------------------------------------------------- /gdc_manifests/gdc_manifest.2018-06-26_diagnostic_TCGA-CHOL.txt: -------------------------------------------------------------------------------- 1 | id filename md5 size state 2 | 489 dcd9384e-332a-43cb-b98a-aa87efe543d0 TCGA-W6-AA0T-01Z-00-DX1.7B6C4BED-EFFE-46A3-9C37-1267E05C4DE8.svs 42f5b6b17883e3485df5b11761473e13 4886012293 live 3 | 1008 7633972e-778e-4918-8079-e95a97dbe0ea TCGA-W5-AA2G-01Z-00-DX1.DA30CC19-6DDF-4A23-8FC6-D800155FAAC5.svs a8d3557979adbced7dfc1666f6d0fe33 1248103020 live 4 | 1009 7b39721d-d747-488e-8278-239c3ca9aef1 TCGA-3X-AAVB-01Z-00-DX1.E3ACE310-E861-488D-A1BC-8BF59AE1778E.svs 4243f7deac67198691c180d6aaab7f5b 2253075679 live 5 | 1010 0d6d8d8f-302e-41a3-960d-028381f1c4dd TCGA-WD-A7RX-01Z-00-DX1.9489CBFD-8D05-46C9-B6A3-55684E29862A.svs a697b8473ed70f5d6155f90fd1b12d47 2101372398 live 6 | 1011 9de217b7-6836-41b3-9b6b-b6caa9c2e217 TCGA-4G-AAZT-01Z-00-DX1.2E91D9BC-6C6A-4357-83F8-E27E28C958D0.svs baa07b389bbd810e7a744053527bd3f5 660886963 live 7 | 1012 ae80bfe1-6643-45d7-92fd-368b676c52ee TCGA-3X-AAV9-01Z-00-DX1.308BB261-7A52-434F-94E6-F07379F43A1B.svs bde9a3e195bd36c9c35413fedde83965 1847967389 live 8 | 1013 f3726112-31af-4f3d-8121-4a2701e4348c TCGA-W6-AA0S-01Z-00-DX1.B8B9641D-CF45-42D1-A08C-898DCE0BEE09.svs 513fb10f9571b2e818c66e0354c7a56a 3681051671 live 9 | 1014 5520ef95-97e7-4d70-9eb8-bf9ba90c219c TCGA-W5-AA36-01Z-00-DX1.3BA86FC3-7B7F-462B-A220-D23F295A2E95.svs 3b0c21a9c197839f631c809c75bebf64 1541576206 live 10 | 1015 e1bdc342-8750-4f4d-8714-8801827a7261 TCGA-ZH-A8Y4-01Z-00-DX1.80DEF07F-1DDD-4998-82FC-C5CC68904D32.svs 2d3a2878fa6dffce4c412d8e4ac01236 1870258210 live 11 | 4896 b4552b11-1831-4bf2-a266-866897618c5c TCGA-ZH-A8Y3-01Z-00-DX1.D4110867-EC54-4455-A335-3CB51AF67908.svs fcc88ec36b92e14081272b5930cfd345 2253106492 live 12 | 5106 6d9d156f-c314-494f-bbf3-0ffc2672ddaa TCGA-ZD-A8I3-01Z-00-DX1.ECD6891B-38C1-4A52-97C1-ABAD5BB43D6A.svs 457045438af6e579cb2b2589687a77f7 747598463 live 13 | 5107 723344ad-d31b-463d-be69-117fc946aa49 TCGA-W5-AA2U-01Z-00-DX1.156F2419-5D8B-410C-B1CA-20F60602A5BA.svs f52e55876e77c81e3a00664d98002a78 1858535947 live 14 | 5108 30ba3693-75d2-4c6e-ac28-6c4ac3a8496e TCGA-W5-AA31-01Z-00-DX1.59C6CCA7-943F-4058-81C0-2123C6F96B0A.svs 4617dd68547798c67db9a789a6427c90 1640449134 live 15 | 5109 cb611e38-f501-479a-9a99-18a7eef651f1 TCGA-4G-AAZO-01Z-00-DX1.B3E01FF4-2D88-49D5-8D09-582B68B2EA12.svs ea150901c1d5cc495f4cc78492cc5a45 521278197 live 16 | 5110 4cf9e5c7-663d-4418-ab7c-10c127de931d TCGA-ZH-A8Y1-01Z-00-DX1.2FE51BA7-9B4D-48B3-AB81-9C744DBA13A4.svs e7cd88cdd33e4d08111f1c65ae0e308f 2131924850 live 17 | 6513 5abc0db4-c2e5-429d-9a01-27ae82e4639b TCGA-ZH-A8Y6-01Z-00-DX1.9FDB5467-91A4-43D4-BB49-AA2017E9DBA1.svs a1bb4ea78580b593f1086670f5705565 1153316450 live 18 | 6514 baf4e24b-0ccd-41fd-98c3-9a406a2c9cb9 TCGA-3X-AAVE-01Z-00-DX1.26FC1984-B066-4BE4-9A5A-DFEC74D4C582.svs f3d657738a147b66ea78f49a0473b6de 2287867995 live 19 | 6515 2287b0b1-5150-42ab-a7dd-f0b1b9bb75f9 TCGA-W5-AA2X-01Z-00-DX1.B584C604-4CB3-43E4-9845-C94B199B64B3.svs 60ea3e75142b0fd6ba8ba369e4196d64 1556204538 live 20 | 6516 4a02d0ba-d90b-4640-b022-361c29c2f7f0 TCGA-W5-AA2R-01Z-00-DX1.B24FCBB2-795C-4545-9B6F-AF5D2AC3FB4C.svs 07314467f6862ff84e8e683722f691a4 1132086424 live 21 | 6517 bba17e6b-a9d3-4fe3-8790-5e74f7ee2b48 TCGA-W5-AA2Q-01Z-00-DX1.6548C6C8-A24B-426B-A01C-F6E067CC8381.svs 04f27c6a833245c47f77d37fda24ac4b 2686149224 live 22 | 6518 9c8b360c-360f-49b6-ac1a-5ba368de10d6 TCGA-3X-AAVC-01Z-00-DX1.4E5A22D6-108E-48E1-B7F3-A99B52A0DB18.svs 8ffda36523cbb807ecef77ecfe918883 1786338121 live 23 | 6519 10bc368f-bcdd-40c6-acff-02405f6bb603 TCGA-W5-AA2I-01Z-00-DX1.7A0ED531-4BC7-4CF8-AD01-C57D9070B2EB.svs 63bdab772c51c325c1a20f651918b8fc 1608384010 live 24 | 6520 b9b5783d-f343-4797-9db5-3801199d3f2c TCGA-W5-AA2W-01Z-00-DX1.8EF8CC01-E6E2-4197-BDE7-6184D327A161.svs f1a4f9afe203ed35e39b6b6a8ff9167b 2579540637 live 25 | 7552 10c93838-32bf-4230-a5d9-32729fce30da TCGA-W5-AA39-01Z-00-DX1.319835AC-855E-4D24-8DDF-DDE5A72DAE63.svs cef1f01f293404eba0847dee344e8c00 1480754868 live 26 | 7553 6e12584d-1ca5-41e9-87f9-69873d2539a1 TCGA-ZU-A8S4-01Z-00-DX1.90E3AC43-66E2-41E6-8253-487B95B4D7C9.svs b0d67bffa3c7558a00ab7fb5f0ad4bd8 1637599061 live 27 | 7554 b05ecfe8-ef04-4704-9a33-7fa472bd2abf TCGA-W5-AA38-01Z-00-DX1.84893B97-DE21-449D-83C4-9233D461A11F.svs ba0bfa54aaab32a2b5b2d76d617ac09a 1917665198 live 28 | 7555 aa80abac-4d10-4386-a8ba-fca5ccfe835d TCGA-ZH-A8Y8-01Z-00-DX1.174309BD-9629-4567-9646-A18CD9D54FDE.svs a5a919d5fffad72e5677005256abeb1b 2304587262 live 29 | 7556 5205ff58-1ca0-438b-a0b3-348f55dce0e1 TCGA-W5-AA2Z-01Z-00-DX1.49AB7E33-EE0C-42DE-9EDE-91E01290BE45.svs 76d480652db224dec97c3245e09717ea 2388080802 live 30 | 7557 d31e2562-5199-41d4-a799-4d5ab4b36156 TCGA-W5-AA33-01Z-00-DX1.4A6B21B2-0EE4-4433-B67C-3C97E29A335F.svs f179b7517fb18a04415e3413e53504ec 3570938382 live 31 | 7558 679bb76e-bffe-4669-a2df-3ecb84caf81f TCGA-W5-AA2H-01Z-00-DX1.55FD7D7E-F9AE-4102-A85A-9D45202DFA1C.svs b58e31970df820db6b66a2a93c87c6bf 1451019859 live 32 | 7559 1717ab42-985e-4601-8106-d90646324b2d TCGA-W5-AA30-01Z-00-DX1.1B63C128-3C86-4ED2-9A26-15BB5E47D66A.svs c9558ed693fd8836c7487307ab07a46e 2464012974 live 33 | 8826 fc7934b2-e7ae-47e5-a102-b4170bba43bc TCGA-ZH-A8Y5-01Z-00-DX1.A7172CB3-474B-455E-8F62-DDE31CAA6783.svs 7c89bac0451c1a196e43ef270357d42e 2349129544 live 34 | 8827 0dccea3c-d76a-4a00-9a22-1000dfd1f48d TCGA-W5-AA2T-01Z-00-DX1.0DC8411E-9AAA-4DA0-AF3D-E1E2A59AF229.svs 46388942b5f18bc9a5db136abb1d78b5 2044246342 live 35 | 8828 73b016f8-d32d-499e-a331-08bd20b88fe1 TCGA-W5-AA2O-01Z-00-DX1.2A089837-4C85-492B-8EB3-F7C51B8ADF55.svs 510986633c87625e8df237d42809d676 2877380958 live 36 | 8829 90ea4d0a-851b-4b49-b9da-368a5c323fb5 TCGA-ZH-A8Y2-01Z-00-DX1.AF4DA602-F161-4461-9371-B2A3D9E745D0.svs 41493d3342c12f66045a938b68055df4 1734912114 live 37 | 8830 09074f6d-932b-43db-b086-601533ba40a0 TCGA-3X-AAVA-01Z-00-DX1.A04F5D5B-5D2B-478E-90BE-572DC5E3FAE6.svs f936ddde911411c6613bbb09b49f7d3c 1749548453 live 38 | 8831 7379b796-8ec2-4a2b-b1ba-8a76ce0d5e61 TCGA-W5-AA34-01Z-00-DX1.FC4DD81F-FF94-4110-9A2C-9C885E8CACAE.svs ba19f484b75d7f76fcf4b65db3ca5100 1692435578 live 39 | 8832 def2a950-228a-4a81-aec6-acb200f34756 TCGA-YR-A95A-01Z-00-DX1.7197CB70-9FF4-4C82-9FF4-548F1969E40E.svs 61edac0ad7071ed60ac2a2046fc5d077 2131515993 live 40 | 11863 24770761-378b-440d-9c60-05864bd379e8 TCGA-ZH-A8Y7-01Z-00-DX1.781FF59A-8A68-4A27-AB42-560F4BBAA1CF.svs f6db73be45ac0fe0514b1131c072e638 1639532620 live 41 | -------------------------------------------------------------------------------- /gdc_manifests/gdc_manifest.2018-06-26_diagnostic_TCGA-DLBC.txt: -------------------------------------------------------------------------------- 1 | id filename md5 size state 2 | 1066 f431289a-9184-42e2-9ef1-525dea316977 TCGA-FM-8000-01Z-00-DX1.c8307f0d-6f7f-4f4c-bd71-4c4a3da528d4.svs a1fd2d40f161f1d987d108253dc7a3fa 101026281 live 3 | 1067 f13c7592-9fa1-4b82-b631-da025ccdb479 TCGA-G8-6324-01Z-00-DX1.30727896-3e02-44c8-a7b2-745f70c441ed.svs edb552993cdc4db8456a7838d4dee67f 711700673 live 4 | 1068 36958fae-abca-4c97-bbdf-071ecf143e70 TCGA-G8-6907-01Z-00-DX1.71ada905-9b5b-4757-8dfd-584a79d56ccc.svs 29d5049912ed307a372abb9d509da5de 642203197 live 5 | 1098 5b3cd70e-7256-4565-80df-d747e46d832e TCGA-GS-A9TZ-01Z-00-DX1.75FFC0BE-5C16-4AFC-BC7D-42D047636DBC.svs 67444443411f5fbd2a305a817341229d 1389587015 live 6 | 1486 1682dfa4-572f-49f0-b3a5-bab57442b566 TCGA-FA-A7Q1-01Z-00-DX1.99220CAA-6160-48FA-AA65-94705EA46773.svs 0250743fb0d5d3ba2ad153bdc0ac88ee 174631217 live 7 | 1487 519a3047-2960-42b7-b162-5bb07e01bb96 TCGA-GS-A9TV-01Z-00-DX1.FD6E85B5-1F95-47DA-84CE-C7B888D29D26.svs 6b0163218561b9259d4056c632c035c4 475116067 live 8 | 1488 9997ba50-fa9a-4ef5-8a51-b7d5d78925ba TCGA-VB-A8QN-01Z-00-DX1.7A114AF2-E4D0-4761-A22A-64D62F5C89CB.svs 52cbecc98d9c35d69126fff69c46d863 1751725209 live 9 | 1489 8ba5fb75-728a-4da3-9384-1f0bd4a2db39 TCGA-GS-A9TT-01Z-00-DX1.630224CC-8145-496E-8F9B-C6805C774FCB.svs 55a7c2de0a53b89da2ba1b455082cdb1 1451130351 live 10 | 1619 d3b5789f-17be-423a-b37f-603699cf282d TCGA-FA-8693-01Z-00-DX1.7bef9346-e85d-44c2-aa85-1f5faca9f97e.svs 109fb715745d3d4b35648850e48d9caa 935538577 live 11 | 2302 2594e921-253e-4c68-ac64-fe41259c3b0c TCGA-GS-A9TW-01Z-00-DX1.D38BD003-8DF1-4740-B83D-3426B00EF686.svs 31ea968b79cd35a568ea803d5dbc4a90 1370021319 live 12 | 2450 4cd95092-93d5-4fea-b147-5c31f9803669 TCGA-FA-A6HN-01Z-00-DX1.2406492D-4D38-436A-8896-A2A7F44F87AD.svs e7de059916129ecce28af11c8cb514c2 313360179 live 13 | 2451 4ce3aa5d-e18c-496e-852c-a19229aa511a TCGA-GR-A4D5-01Z-00-DX1.D80C72B3-C80D-47E4-AF4B-44AB5F1AD8C5.svs 95faec4f9465cfc961795294defa83f1 491714792 live 14 | 2748 fabe1c73-ec6c-4eab-bef8-fee875294331 TCGA-FA-A4BB-01Z-00-DX1.2BF28C5E-B2BE-4C0A-A369-BDE825EF32AD.svs ed358de6b00c02bbaf22fc0fa3cd8768 1089784861 live 15 | 2749 24969364-e6d5-46a2-886a-edbd46035a67 TCGA-GR-A4D4-01Z-00-DX1.CE57E44B-E1BB-4269-9B81-5BFA55248883.svs 37d917c979428f9c69ebb99c2c550c79 258160154 live 16 | 2750 cb362e89-3d84-453c-8483-b4040850ea7d TCGA-RQ-A6JB-01Z-00-DX1.13EB389B-B463-4722-A074-5E9002B327C1.svs 56c230a211637109b8408b1d794f6e77 1779726073 live 17 | 4240 79a1504f-1fd7-4fde-acfe-ca0c0c878fe1 TCGA-FA-A4XK-01Z-00-DX1.650FD75C-6486-4593-812A-B3CB2B5316C0.svs 1ed92e06fb7d5f1a1de5394dd61ef4ec 2183158605 live 18 | 4380 c2afc927-575f-4e23-8df7-24b75f754937 TCGA-GR-A4D6-01Z-00-DX1.5C79ED21-5689-45C5-8E08-2EF67056F7CA.svs 84a69092e9d0d8b097bb115479791b31 577999254 live 19 | 5151 8c3a56d9-6ccf-4be3-bec4-6260b9c72006 TCGA-FF-8047-01Z-00-DX1.75aa745c-bbe3-4869-a37b-c18ee50c14d5.svs 8399fc10a313c7f687a22378f865197d 291477431 live 20 | 5176 f57399ab-9461-4a6f-b91a-982fa3a04e11 TCGA-RQ-AAAT-01Z-00-DX1.E6B3D983-E4A3-4E5F-B571-376C18A36F45.svs d10ac9c12048042078fb137c5227f0eb 517485219 live 21 | 6397 63646425-ee04-4d8e-98a5-bd926c9a0d38 TCGA-FA-A6HO-01Z-00-DX1.9E6256E7-5C4A-4D57-9810-8F52D3826BC7.svs 325b1d2660f56aef94b5bef453b80969 334895495 live 22 | 6398 a3ba6414-a432-40c6-9a0c-8877abbe7549 TCGA-RQ-A68N-01Z-00-DX1.5F93A566-8CDF-44E1-B402-45350674992B.svs 94fa1c1533f59ec1f0a20759060aa9b6 660737545 live 23 | 6557 8bf1d441-429f-4ecc-adb3-078b719be271 TCGA-G8-6909-01Z-00-DX1.f38a05fd-179e-40ae-9fa2-337e09235691.svs b5187fd7baeddcf3204d2516fb031a1b 271454999 live 24 | 6558 4d011d94-b1a6-4f32-8058-4f66d0a1f5c7 TCGA-FF-8061-01Z-00-DX1.c48e8418-275d-403d-b645-71eac3fb5c2d.svs 68affb9f8c614a00e08f3f44d4eb69eb 950175587 live 25 | 6559 5a61e474-5c07-4bf9-8047-067379ca209c TCGA-FF-8042-01Z-00-DX1.bf80d981-9209-4933-8f80-e9e689971999.svs 6a1664099e6381edba9ed1873d65f6db 531954549 live 26 | 6560 a54ae089-1d7a-482d-8d95-9f50916c2b67 TCGA-FF-8062-01Z-00-DX1.834a90d5-cf7b-471a-95f1-9a02477bed7e.svs 95801cd217d9d3cea1775c5153c8e6b0 113418289 live 27 | 6561 14519642-9ba5-4022-b515-158867f9d3d5 TCGA-FF-8041-01Z-00-DX1.b9ba3fca-9adc-43d2-8439-7231a5be67a9.svs 822247a83b3aefe45fd0facfdd8fe93c 220207211 live 28 | 6562 147c945f-f869-4906-bd3d-c285fc5d5a2f TCGA-GR-7351-01Z-00-DX1.8e04901a-4f59-449e-a992-dc2966906035.svs 413e709241e0e98df690a312cfe01e6c 255136650 live 29 | 7222 1fcdcacb-3b8f-4310-83a6-856cfb3c4f66 TCGA-FA-A86F-01Z-00-DX1.EE36DC3F-7539-41E8-ADF6-6BA0FB0F47C4.svs 430d9f89acb7ec983313bee339d8a97a 753663393 live 30 | 7225 7fbf36fe-7888-4002-a42b-be88c378e2ec TCGA-GS-A9TX-01Z-00-DX1.5A1B7A1F-76EE-4E63-92C1-44AD0523F37B.svs c6688be17dfe1af9aa32e44b8f29fc65 1547190635 live 31 | 7361 50ed8a83-0d5d-4ab4-a393-3918d53532a6 TCGA-GS-A9TQ-01Z-00-DX1.AC86A0E2-8FBA-4A3D-A1C8-BB403D9C93E8.svs 821f0fca2469725dc608666a453c2b08 1061993409 live 32 | 7363 3197aa1c-8747-4f42-adfe-d014fbe4b9e0 TCGA-FA-A7DS-01Z-00-DX1.62649098-BD0B-40F6-9629-3A53C507811A.svs 76fd7b41af68f8baf5c02432f4ba6180 1394785989 live 33 | 7364 576c759f-94b3-4f77-844a-e695e7a2993d TCGA-GS-A9TU-01Z-00-DX1.F10984B9-F06A-4729-B668-A5C184EE6D28.svs 13639641f1ade222570d447d1a30b381 632981733 live 34 | 7608 4621083f-f498-4a40-b649-7efd0b634a9f TCGA-G8-6906-01Z-00-DX1.61bfad6c-4e24-414f-9bcf-18ce30d6a75e.svs 36d12161caecfec55d4e3f770ac81ec0 1030688017 live 35 | 7609 c535f224-a3f9-4759-ba72-1342792883ee TCGA-G8-6326-01Z-00-DX1.0cbf64a5-7322-4ce4-b8e6-545e5ef1e3cc.svs fd44f40677197b9c0f9c04a338cce51d 783860851 live 36 | 7610 7cf01283-46b5-4ef1-9d6f-6ba3731ae32d TCGA-FF-8043-01Z-00-DX1.f3a8c298-f59e-469a-93f0-3221101771ce.svs 614e2078ca21dcaa174ec92830370803 508886817 live 37 | 7625 774bff97-ec47-4720-a456-385a4b67467e TCGA-GS-A9U3-01Z-00-DX1.2A338F39-0486-45EF-B829-19360F2E2FC9.svs 25c25c9521c9042f645efd83269ae164 980484625 live 38 | 7626 b59c6a5e-624b-4912-8bd6-bf48f4d2475e TCGA-GS-A9TY-01Z-00-DX1.A04FA83C-736C-4C55-91F2-B1CD892178A6.svs 04bb625c9c6985f786aad35c8af5b3cb 1528973641 live 39 | 7836 2ee1d234-e69f-471c-b333-98591ea9188f TCGA-GR-A4D9-01Z-00-DX1.443D848D-2F3A-461D-8990-2C823D783B0A.svs f3f7b3fc08d9d219568cbbf9c3fcfee5 325792520 live 40 | 8879 99b351af-0fd8-47ab-abbc-1bea979253cd TCGA-FF-8046-01Z-00-DX1.074ee1a6-9809-450d-bf4e-42230ce9ef70.svs 98376350203756e54566249027354327 347890501 live 41 | 8880 5140f035-01b3-4d34-98c5-28f69380fb8b TCGA-G8-6914-01Z-00-DX1.910a33a3-3c27-4368-a223-d15a5e024c5a.svs b692301e5dbd4beef8df7838831ff493 920306275 live 42 | 8881 62dac3ae-812f-434d-9930-fbdc44808dd6 TCGA-G8-6325-01Z-00-DX1.973b0dd6-d701-4224-9395-eab9603488ce.svs e368645a416cae7fe3cff6df04768866 902950541 live 43 | 8882 7b6ac473-64fe-404f-8810-677953c7a873 TCGA-GR-7353-01Z-00-DX1.98554629-7e97-41ea-9fef-13e7b88f4ecc.svs 42c7c20def19c2382f4de6b805edf7f9 157891802 live 44 | 8905 f3133e4b-1498-40f5-b26d-258c445131e3 TCGA-GS-A9U4-01Z-00-DX1.E8F03678-760A-4956-A829-708C6F6B968B.svs e1a4c8e0d69a30c48f863ab30a4e5b35 897185589 live 45 | 11676 20eaadb0-9573-454a-8e64-e61b64827e7a TCGA-FA-A82F-01Z-00-DX1.6D1B9A0A-FAA1-4E4D-9280-3D87F9929972.svs 4ed0caa6b9d566af0aeacf6cc8d20788 1483129033 live 46 | -------------------------------------------------------------------------------- /gdc_manifests/gdc_manifest.2018-06-26_diagnostic_TCGA-KICH.txt: -------------------------------------------------------------------------------- 1 | id filename md5 size state 2 | 0 47cb8fa7-bca5-41f7-a009-e11ef50b7f70 TCGA-UW-A7GP-11Z-00-DX1.C89DD837-4B77-4CB5-8FAB-DF9315892B9B.svs 5a22b920e8f8d84ee55dfdd683b5ab76 1337351668 live 3 | 1 c86b6bc8-fa9a-4a51-b547-7d270ee3ca50 TCGA-KM-A7QD-01Z-00-DX1.E1FCB533-0017-4A90-9835-6CD26FEA30CA.svs 545ff517a94aa16cddb11f3f7471c3fc 1162699927 live 4 | 2 6427fcf1-f481-4d83-8c58-6bd0690603af TCGA-UW-A7GY-01Z-00-DX1.CD2CCA5D-C92B-409C-B5D6-1EB7C8A0B4CD.svs c87900710701a20cadf2c627ecfc89ce 1905957156 live 5 | 5 c1c5c019-93e0-4fbf-a60c-b7e6d0b883fa TCGA-UW-A7GG-01Z-00-DX1.83625891-206C-4060-924A-166BE9E893A7.svs 3fc977cf96526fd522b61416faa73733 1639266820 live 6 | 6 73591ea5-c0b8-42c7-8dd5-44fca3969577 TCGA-UW-A7GN-11Z-00-DX1.ABAA5DC6-D63C-4BBF-AB0C-213B95C79720.svs d53eb2dbac9721ae2313058a8d621ffc 1009491360 live 7 | 7 3080b0d0-174e-4247-b4df-ecb5b282770b TCGA-KM-A7QC-01Z-00-DX1.4B44EEAA-FA1C-47F9-852F-68EE45E09D5E.svs b3de6258a7eda6b726c36181a8aa49b2 1580370105 live 8 | 8 185b5356-e97d-495e-beb3-832a5c1015f1 TCGA-KM-A7QK-01Z-00-DX1.8D69EA34-F28A-4267-8A82-159FB2B7008B.svs b0e82bd4ea82fdb4a67d2f2348c9765e 1095633437 live 9 | 11 245b2509-5093-4d3f-b005-ca2d210643ec TCGA-UW-A7GK-11Z-00-DX1.123382DA-3237-4467-ADDD-21A1617DF4E8.svs c75494ea83e324fcb38978b76ebbdb93 1176001414 live 10 | 12 6fa4ab82-9c88-4117-ab7a-6f4b85967749 TCGA-UW-A7GG-11Z-00-DX1.35E063D3-7E85-4BEB-9807-26F96CE31364.svs 9c86d040d5182ee5608e5e65390743da 1164726682 live 11 | 13 6983cd7b-f67e-4ae2-bb45-7baf6632562f TCGA-UW-A7GU-01Z-00-DX1.30C1C11C-4113-4F8D-8372-5EE3DD33564D.svs d4d37cc3564ce3a702c5a5adf1e1fbdd 720365928 live 12 | 18 263b2fde-6a10-418b-af92-e0e599ebff8a TCGA-KM-A7QL-01Z-00-DX1.2447532C-3635-4F36-952E-F5A5A566A7DB.svs 9e946cef6f0b83d5c953aa20414b1447 1203480689 live 13 | 19 1e8c0ba6-a63b-4d09-a54a-e6455a028333 TCGA-UW-A7GJ-11Z-00-DX1.97F9F149-FA58-4535-AE9B-237B8F87DEC7.svs 038d0c4ce5f16f450be488354db42c96 1253194132 live 14 | 22 f012eb21-dd05-4e7e-aa6e-ca49c9847ce5 TCGA-UW-A7GR-01Z-00-DX1.094D510F-5348-4543-9F18-73815250F824.svs 6c2220de9d6a40250e80e8707e998ae9 1478967802 live 15 | 24 ba03cdf4-81ed-4374-affb-a91dcce5d354 TCGA-UW-A7GC-01Z-00-DX1.D2D6FCC6-719A-4C03-A496-E23D18655538.svs 6daf1b87a43214b528de454a4cf68d83 728488842 live 16 | 26 ea82a79f-30d3-456c-8433-992b317ff27d TCGA-UW-A7GX-01Z-00-DX1.C99CCFC7-C714-4F0D-AC12-D88F6DFAEFB6.svs aad15ca9e7b3cedd94d627d2c47535eb 1074179686 live 17 | 29 5baf8b15-c5d4-48ad-9769-4001453f8d33 TCGA-KM-A7QA-01Z-00-DX1.971BE7D3-6E83-44C9-AFC4-50FE85E9C982.svs 5068f5d7d0397dee874a2edd2cde5c3c 781444727 live 18 | 32 ad8b89db-5e44-4266-8fa1-41caa39fb2ed TCGA-KM-A7QB-01Z-00-DX1.CC441A0F-8A5C-4406-8A8D-86CB62E7B114.svs ce27e23452c367c09bcbca7d56f2a227 1125133081 live 19 | 33 278a7bfd-428b-4b75-964a-7a2027165b08 TCGA-UW-A7GY-11Z-00-DX1.7410A3EA-BFFD-4744-8DB2-66A409C0BFA9.svs 337883fb8957f931485cfcd971c1f0c2 430526190 live 20 | 213 91df97d2-d170-4d2f-9f2f-faca0a0a1c80 TCGA-KO-8408-01Z-00-DX1.4D45F809-E93A-4221-832A-97C3A4B4E30C.svs fc1540266a493812f387fb6f448d63d1 1268096819 live 21 | 214 1f6f6944-1c24-42cf-8b78-8eb39657e222 TCGA-KL-8328-01Z-00-DX1.497ddcb5-0436-4c76-a633-4744e24e6efe.svs f7e0565cc53bba2ae823dbc552375387 1406379264 live 22 | 215 3d1c4865-c3fc-49d3-8d0e-a97eddf17018 TCGA-KL-8336-01Z-00-DX1.bfba9373-efa8-4573-8ee6-8ac961f0b65a.svs 95e97d430db6bc89a44a9a05ebe851e4 1245812512 live 23 | 216 e68e301d-5b12-4c73-a837-b1c4858163e6 TCGA-KN-8423-01Z-00-DX1.EE5F8790-38EB-437F-9C5A-BC6FB58F6ACD.svs 96d9669428ab74188dae07f10946d22e 1588073099 live 24 | 217 6396db9f-91d2-4ff1-b539-c9eab1a3edab TCGA-KN-8422-01Z-00-DX1.26F9BF86-6D2C-4C99-BFEB-A3708AD48734.svs a15c29967660760594f02803a04dcde3 2227897183 live 25 | 323 7e76dfa7-91c6-4c1d-b23d-0bcb5216b90f TCGA-KO-8406-01Z-00-DX1.F9FDAB2C-9EEC-41D0-A29C-530107B96AC2.svs f2daccf0b3a24f6f5e0540d945e81097 1173741371 live 26 | 351 8a9b6298-1d78-4d97-b714-443bd39d5119 TCGA-KM-8438-01Z-00-DX1.1106521B-3563-43AA-8971-18560BAC51C4.svs b52f392d835f7ba009aaefae4121fa8a 1007291297 live 27 | 352 9e719292-72b4-482d-a93c-98cb760966ee TCGA-KM-8440-01Z-00-DX1.528E053C-E8A4-464F-BE47-412836B1C31B.svs b08d2c9f065780cb8e541c39523748a5 1889681701 live 28 | 353 f4313ab9-9de6-4464-a5c7-f06ddfd0dec9 TCGA-KL-8338-01Z-00-DX1.c3febc9e-8adc-49e0-9ce1-9d2dcc79c09c.svs 51293042d4fbd0722bc46094b25b68be 1356107726 live 29 | 377 76385cf1-ae15-4882-8241-aa3a07a4d04f TCGA-KN-8425-01Z-00-DX1.1D2AB7D2-6AC3-4785-9FBC-40AEED5DE558.svs c48307da46094ef3eeca422b7f39797a 935473777 live 30 | 378 d376a22b-0e0f-46e2-ad06-bdc2ba3f0d39 TCGA-KM-8476-01Z-00-DX1.BDC7C35E-1B36-4CF6-9CF0-B63C68724EF2.svs b8fc903fe19fd777f429380c2a500d96 713807597 live 31 | 379 f508e715-976f-4bdf-976f-77fa655d3798 TCGA-KL-8345-01Z-00-DX1.e6265e77-7c45-4e54-a703-6d2013aba525.svs 06c70dae53c15df62427d6aa75ee8732 1653079376 live 32 | 722 0096d378-26ed-4fbc-85e6-6b5903673784 TCGA-KN-8419-01Z-00-DX1.15311E57-CCC5-4D15-88DC-0ED9FD2CF2D0.svs f420c7f105d12fe0b2aab52391a55525 1982785195 live 33 | 723 1d761563-33c9-4272-9201-4b35b424445c TCGA-KN-8424-01Z-00-DX1.4EC063E2-A058-4610-9B47-FCE2172955B6.svs 2acafc098387077ceafa6ba23d072e5e 1950857407 live 34 | 724 b26956f6-5462-4442-b956-602f34855ec7 TCGA-KL-8346-01Z-00-DX1.af2fc9c2-98b7-471f-9777-08c7cc8c734e.svs 70950f3039a36c1b3482432852cfeceb 1177329982 live 35 | 725 de96f01c-1ec5-47a7-8704-20ac8711ba84 TCGA-KO-8415-01Z-00-DX1.CB5F5330-C4E6-4ABB-B9A5-92F94EF23837.svs 50b9eb60d7a1ebd56230c70bc562b62d 1078800083 live 36 | 726 08730d9e-4ff3-4e00-8f1f-cda038dd258a TCGA-KN-8433-01Z-00-DX1.4AE64138-3E04-46AC-B905-52CB71261230.svs fb8d07d783bab0d963b07545c2494025 364251607 live 37 | 727 674f6ef4-cb0c-47d5-9d9c-6731e897a3ce TCGA-KL-8332-01Z-00-DX1.3a375f5f-38e4-4022-8b36-5d8547870417.svs 40185195de563560283c216d079b9c91 2178187898 live 38 | 728 33e21f72-eb8d-4409-996a-fac1f2c67564 TCGA-KN-8430-01Z-00-DX1.8192F868-A504-44E0-929B-7527EB37ECAB.svs a60abb459b90bfce76c871e842ed7151 2212101927 live 39 | 729 f9ce0f4c-84f2-4497-ba97-5c0578344eb2 TCGA-KL-8331-01Z-00-DX1.3c39f9b9-b639-4bca-a415-bf7427ea2ba5.svs 01d9ac147d647bfc6aa61b4d4584686b 1269280738 live 40 | 1452 be50607b-e554-4eb6-944c-dab92f66d09a TCGA-NP-A5B3-01Z-00-DX1.6DE4C2C4-E135-4117-864D-2A477D6FDB86.svs 5542e9302beea978c56c720a3f25d2c7 134144490 live 41 | 1453 2ec24aee-c0e9-480b-b0d3-a7a50cfd51c9 TCGA-NP-A5GY-01Z-00-DX1.F405475A-B246-42FB-8380-8953B328193E.svs b8bd1cf87ef118f937f1bdf8469b0d33 222112566 live 42 | 1454 b346f490-2a4b-4d41-af8d-66044209758e TCGA-UW-A72H-01Z-00-DX1.25A52BAA-4000-4AC7-9B93-9D9790C8834A.svs 8dc065559b3c1693555cc11b1b7388b9 1288946082 live 43 | 1455 94716644-b920-4dfb-93a3-c7840ab7a676 TCGA-NP-A5H6-01Z-00-DX1.49B2A361-7BCD-4321-8372-8BAB636E812F.svs 737c38aa1beee5117f222868af5beb39 198959314 live 44 | 1456 90d36e04-a44c-4746-8fbf-b73a7c75f953 TCGA-UW-A72O-01Z-00-DX1.755C4693-A9CE-48E7-A76B-DAECEE850D35.svs 14dd0e9905f6727d052d955a0fcda0f4 1072874874 live 45 | 1457 ad80118d-09f8-427d-9570-8e57cae82bca TCGA-UW-A72S-01Z-00-DX1.EA180EA6-ADD1-4ECC-89D8-082B185AC2B4.svs 1000cb7fadfd91b0e41e62a648be3ff1 2374520108 live 46 | 1860 6c19cfa0-02ac-4640-82d4-dd4e83a1e2c5 TCGA-UW-A72T-01Z-00-DX1.1F6EC843-0D4C-4231-99D2-82174C9FF94D.svs e591d95f1cd0d34f00d818acbd7e6cce 1010481802 live 47 | 1861 3a36f2c7-fc92-4707-beb8-8adcfa19f2bd TCGA-UW-A72K-01Z-00-DX1.F1E38D60-26AA-4D0E-8738-7711611D10D6.svs be10aae8a5ec6b486a46d88e987e5eed 1184832260 live 48 | 1862 0293ea6e-dd9a-4e8c-8122-159a57cc8807 TCGA-UW-A72Q-01Z-00-DX1.6EEF0E01-E576-4DCA-B613-451D0079EB13.svs 57f4fa48a9a94e2608c4b5e848dce148 495213450 live 49 | 1863 aec4419d-5e37-4033-a260-e0f732fb251a TCGA-UW-A72M-01Z-00-DX1.D2F473F4-24A1-4F02-B02E-C5A0390F0C8F.svs 83f8e66250571b8e4904f9930ae92662 2063858880 live 50 | 2396 9ab77c29-01db-484f-aa0e-eb91e68948a6 TCGA-KL-8337-01Z-00-DX1.78306056-304b-44c3-87cd-46d3785b7204.svs 90db4b63aeb924dd025337faccbd231c 829531386 live 51 | 3946 ca1b59cc-4d11-4618-8a87-0fb53daae22a TCGA-KO-8416-01Z-00-DX1.AA58FA3E-02A6-4696-A4F6-2B11C5B0C0E8.svs 364b74c7e066d1d9f6ebe21ccb9e9f51 1436766025 live 52 | 3947 92470c64-a48d-497f-9a78-484b98ccdd6c TCGA-KL-8333-01Z-00-DX1.830e3f78-ba43-4b42-b2b5-f3be10d2b781.svs 02c3f08f131e492d8deffdcf4f669f01 1866348416 live 53 | 3948 4244f201-60c9-44bc-9cf0-095039437692 TCGA-KO-8407-01Z-00-DX1.4EB39EA8-2A33-48E1-88A6-EE3B544249AB.svs a5c6691909192008a6f17f3659c4a751 1080428391 live 54 | 3949 86a0433e-a385-4a15-8b78-5a9e8b655193 TCGA-KL-8323-01Z-00-DX1.01d72f6a-cc87-4082-8af4-738250ec4d9c.svs 2163a438fbcbdf2996d635d3b21f3d5e 1435204404 live 55 | 3950 c8ee8bcb-440a-4c21-85b2-4f311eb8500c TCGA-KO-8413-01Z-00-DX1.592BC1BB-35B9-4CE1-ACD2-76DD4C4FE7A4.svs 409302800c0abc99cbde7aa21fcf76bf 1167128585 live 56 | 3951 19e81b78-5e55-4939-a01d-79b02e4e9122 TCGA-KO-8417-01Z-00-DX1.E145D87F-24DC-4336-98BD-2D142079D73D.svs c9cf9af2b58b19dfe023393d475fe8fb 1761458151 live 57 | 3952 6d8a9e94-033a-4111-becb-30905f0b0db3 TCGA-KN-8431-01Z-00-DX1.BAEA4392-5CD8-4B28-8A47-E9DCE88F5820.svs e0dfdb37d88448d1475e56fc2dd61e6f 999950315 live 58 | 3953 886b4074-bf1d-4e23-bdc9-a6306a1a5acd TCGA-KL-8340-01Z-00-DX1.85fe33f4-87d5-4e36-9389-d093cde30f80.svs 3a559e1c51ee350c130c4b1fe95f5b8a 1155978714 live 59 | 3954 da5a7122-00ee-4f37-8fce-95dac52f1528 TCGA-KL-8325-01Z-00-DX1.330bdb6c-86ee-4577-9846-298080b4c2ad.svs f58177ac0c2e300df97b407e969e9820 1494850390 live 60 | 3955 9b081e41-e0e5-4f27-9a59-3746f901edff TCGA-KN-8437-01Z-00-DX1.573F2559-097F-4A87-9AB6-55BF2FEB724F.svs ed7259f1274087243e0ba8bee1ea2055 998308461 live 61 | 3956 7327bae2-ec9f-443e-a69c-2bffa5b61856 TCGA-KM-8477-01Z-00-DX1.5419F74B-EE1C-47C3-A5A7-B22768E613A8.svs 61e0f943f627198650b01a38a88430b0 1974190975 live 62 | 3957 8793823d-818f-4928-86bf-70611f756a44 TCGA-KO-8411-01Z-00-DX1.57A47A81-003C-4F34-B8FA-D1313114892F.svs e8d1f4a61ffa749aa153d49733966119 843237399 live 63 | 3958 f509b691-99b1-407f-b84f-3b4da3c07627 TCGA-KO-8404-01Z-00-DX1.0285FDDF-1C75-4DF3-BD59-285870B73B88.svs c6ccd59c695c3a4c38f75a28313ed86c 1130006161 live 64 | 3959 3abaa491-da97-4687-aff0-74a400239eeb TCGA-KL-8343-01Z-00-DX1.e5aeff79-6d98-4c53-923e-a8fe204fbb43.svs 1515dec6771d333a1b4e53274fd9c2af 1754386304 live 65 | 3960 da3d80ee-1fd9-48ee-bfd3-04ae0762729b TCGA-KN-8434-01Z-00-DX1.EC2C42B5-DB0D-44A3-8224-E982201AE337.svs fce54bd70846adc3a51f6676c56fb0e9 402241321 live 66 | 3961 89fe5b36-1700-42f6-911a-c3676f8be8e6 TCGA-KL-8339-01Z-00-DX1.5826ea77-f0a1-4b47-acd7-62a6ba878dec.svs e269495e7fbb43e2add964a3794579ce 2139228024 live 67 | 3962 a062450e-8aa6-46a8-a4d9-96b1b89164c0 TCGA-KM-8442-01Z-00-DX1.46835CE2-819D-4887-9633-422BC9F5E366.svs 6bc9f72d3d8bacc39fd200d8b74d6d66 2247620823 live 68 | 3963 526bb7f4-bd3a-44cb-a08f-dfd5d03bbc4a TCGA-KL-8330-01Z-00-DX1.30a61e5b-9379-498a-9aa4-60fd7a3a2f32.svs 612aef25c48499a4e8bb3a5493825fc6 1542727132 live 69 | 3964 f5e7cd3e-61c5-4539-aed6-c6749cd60a6e TCGA-KL-8329-01Z-00-DX1.6c9000ef-34ff-4e44-84b3-755a868f6a4e.svs 0b18430e089c98d200f276820a426216 1319639226 live 70 | 3965 ce03a633-f783-4940-85d1-db557f02879b TCGA-KN-8418-01Z-00-DX1.376DD52D-EF98-4564-B8E3-FE4D219A5C88.svs 818f699141dcc9e44042c550383b0a33 2319195871 live 71 | 3966 ee792b1a-0101-4d19-a305-0f6aad17670d TCGA-KN-8421-01Z-00-DX1.A90EB3F7-DE68-4078-BB5B-B35561F96071.svs e7df2739223cf9dcfc784e9b07e54f11 456063677 live 72 | 3967 feb524f5-4f8d-4fee-8900-c8217d0ebefc TCGA-KL-8344-01Z-00-DX1.fdcc3157-799f-42ed-99dc-b13d381d9230.svs 4e65ca7a066667be21bedf1a3b724d53 1447151882 live 73 | 5941 83a582eb-98cd-4c91-a89f-9c9e55d274a8 TCGA-NP-A5H7-01Z-00-DX1.3AEF89FD-4E13-433C-85D8-C8F9F9EA9EF3.svs a00926e1dc44f46048f9927687ef7905 183138192 live 74 | 5942 d7426d2a-ab4b-407e-b76a-5a1eec5baf79 TCGA-NP-A5GZ-01Z-00-DX1.07B19B85-A1CE-4AF2-B3E2-C86D11FAC907.svs 31b6d0f3789bca838829da2db34456ee 135265752 live 75 | 5943 c725091a-95fb-4bc4-8a60-b7fbe87c994d TCGA-UW-A72N-01Z-00-DX1.458F977B-AA32-4073-BDC6-FCAD44C6B83D.svs 73dfc8816c66ab7d9ced8ea8b102251b 1114395572 live 76 | 6973 6808b0e3-9231-4d09-bb91-1c75ad00ab7d TCGA-UW-A72R-01Z-00-DX1.0D9559B0-80C4-42BA-9461-F92792F0FC0F.svs b5e580242f2967f8a1ec5f4ea1298e8a 2579284394 live 77 | 6974 fa1f0224-2a8b-49c7-963d-9b2601da4731 TCGA-NP-A5H5-01Z-00-DX1.E6434A29-9182-4476-9E89-62B9C8EABC5B.svs 64b38950e8123163ff18f604b3e2671d 192790998 live 78 | 6975 9163b49a-90f6-486e-8f1c-5ff6d344e1b4 TCGA-NP-A5H1-01Z-00-DX1.ABF28359-B224-4C36-9217-C6DB90692848.svs d399273648f183917c3ad649910cd677 196539072 live 79 | 6976 8d9bf0e7-9ede-4f67-b2c8-344c659e00c9 TCGA-UW-A72P-01Z-00-DX1.B16A8F4B-6E8E-4642-AEEF-EBD0613C372D.svs 4a5d80289d99ed47a4407882a796382d 2450154000 live 80 | 7706 ca61be6f-2664-4384-8729-a9c1e79d8f6a TCGA-KM-8639-01Z-00-DX1.13E1C61C-16F6-4FC5-B1D2-DDBF7DE16639.svs cebb4a3554b4eb4f2537a5459df6e4e3 2100421383 live 81 | 8568 d30a03a3-2a1f-4aeb-b595-db97d40216fa TCGA-UW-A72I-01Z-00-DX1.EAA44029-3390-4AEF-8B86-E4A1F64E486C.svs 75b83796d49bfcf42b616af453875908 863630794 live 82 | 8569 064869ad-7f86-4590-870b-7d2156a41945 TCGA-UW-A72L-01Z-00-DX1.0A459BE8-D799-441D-85C0-B02AF6EDC806.svs f21daa9c3db9fd8355836c940f9b629b 985328290 live 83 | 8570 55f40a51-3deb-4e19-a5b0-62dc65301965 TCGA-UW-A72J-01Z-00-DX1.B62772BA-DC29-40C9-B5C8-AC47AFA0437D.svs f0885f231ceeb83024bb4980dca13dc0 1493249266 live 84 | 10727 3f8a25c4-f294-4c5c-a69d-4d17d0e88e72 TCGA-UW-A7GU-11Z-00-DX1.BC340CDF-7F82-4314-86BA-E003AE43389D.svs fe81fbe95ffb8615a08521b355de7bd6 40098742 live 85 | 10730 7e16e8ae-3fba-4646-8da8-1697239db8f9 TCGA-UW-A7GR-11Z-00-DX1.33EC231A-1C19-48A5-B37E-14C79191DDD6.svs 9068314e4916714791ca470cc38310bd 1980565872 live 86 | 10731 aa7fc7b8-4a07-4395-a785-8df880b91c79 TCGA-UW-A7GC-11Z-00-DX1.ADAF7B0F-8EDC-4022-A873-3A5EBA4A46C3.svs 75ba020e62864cc238452c11dc269fbc 520129390 live 87 | 10732 a6f0869d-c4b0-488d-abc1-4cad601fb2aa TCGA-UW-A7GJ-01Z-00-DX1.5CA0FD93-E237-4AEC-84D6-0199A62105DE.svs 7bcf95a676bb15038bcba0b7d9668a99 1509483110 live 88 | 10737 86ab071f-9343-4118-ae56-139b128d857c TCGA-UW-A7GL-11Z-00-DX1.3508B4AD-C189-4416-848A-CA6771F2EE46.svs c7b82fe57226121889002115aba5f661 1754801950 live 89 | 10739 8b5a21ea-ab9f-4df7-9c99-a1836b64572d TCGA-UW-A7GL-01Z-00-DX1.BE2C0D9F-3F84-4363-9B79-01883E8F0306.svs 7924fdd88692e374acb95f8c0ea68df1 1963274202 live 90 | 10810 a191aa30-1068-41c2-bd76-8b66b49d32d3 TCGA-UW-A7GI-11Z-00-DX1.3D506541-C999-4897-B21B-2211ADB364AE.svs abbdb7041522ba9c658cb9061880f562 1088932490 live 91 | 10811 bb1519f8-88d9-4cd2-b252-059734fd6938 TCGA-KM-A7QI-01Z-00-DX1.D5284A3E-891C-4750-BE93-C09C7F23C95C.svs ad4ebe44023c2acc02bbccc151169191 1042206607 live 92 | 10813 8efd36d5-8545-4b26-a63f-85cfb2731eb1 TCGA-KM-A7QE-01Z-00-DX1.82CBD529-FBB8-4969-A6E0-B563F0C9D73B.svs e3918fbdb4838dd4ef2a710cb2ce717d 1212313199 live 93 | 10815 77280cfa-9fdd-4778-b016-c0fdbd458022 TCGA-KM-A7QG-01Z-00-DX1.7275EEF1-1D4E-4471-89C3-5B99EC03515E.svs 17744eddf18d91a60790129e90ec7dd1 1317800365 live 94 | 10821 d74894c7-6efa-4934-bf94-49f45e273a92 TCGA-KM-A7QH-01Z-00-DX1.8CBB8760-A00D-4289-AD09-959FEC2EC03C.svs bca31aa8aa7ba96d13e8d64d9d06c5b0 629158787 live 95 | 10823 8db4d172-6676-4652-b807-ff26d87d7941 TCGA-UW-A7GN-01Z-00-DX1.0DCDED5B-B0D4-4B0F-81DB-1534E331ED3C.svs f1e36d70ca916caf07888d19586d3318 1370320186 live 96 | 10825 7e42eb36-52d0-446c-8f4c-904ace660e93 TCGA-UW-A7GX-11Z-00-DX1.57C4FD28-5463-40C5-9E87-484F3326B395.svs 84126d2ed06d3d41a580f0031678d1f9 1145731400 live 97 | 10826 c29d08ed-a146-4779-bec0-5a7d57869065 TCGA-UW-A7GI-01Z-00-DX1.4A1709FC-F8F3-4509-A011-10CBF1B53DA9.svs 435a66f65a186eceaa4dd06f3a7d6bfd 1463222614 live 98 | 10896 38019e48-1d8f-4c72-95fe-4305c6258a64 TCGA-KM-8441-01Z-00-DX1.D2CA0ADE-7EDF-49A6-989C-2761F1CFE340.svs 98df1090de439e8f83fea9379817677a 1887076183 live 99 | 10897 f82e1de7-4384-45be-9890-621460da4cad TCGA-KN-8427-01Z-00-DX1.8B2A5B0B-977E-4ED9-A9D2-23FFFBA43B7C.svs 71657f6ec98f92099eb0cba788ef024f 1588769539 live 100 | 10898 9cbc3a9f-37f7-4d4b-9019-a8a7358a997c TCGA-KN-8429-01Z-00-DX1.473181A7-5F6A-4B68-B6E0-44EF34F67DA0.svs a6a83e99cae49a7cc296e6a2e7a0201b 2050278313 live 101 | 10899 8ad3e763-69cd-435e-9f28-eb1e874a558b TCGA-KO-8409-01Z-00-DX1.C73F6879-81C2-4D2D-9673-4989AADB568D.svs 9ec267201310a5768d62553e349b8751 1241793801 live 102 | 10900 8a19f9cb-c117-4a0a-9dc2-bca9f864159a TCGA-KL-8341-01Z-00-DX1.eb0da21c-75f5-4de5-a753-12666eff0030.svs b849dda6e9452e7d7e5cc90f3d8fd88b 1241477650 live 103 | 10901 42f86f6c-e615-4a5d-8ccd-413b4a897f14 TCGA-KL-8327-01Z-00-DX1.f3009cdc-baf7-45ba-95a6-1b6311799cc8.svs 0cb5e93e98a3567e9b31713d36d55c7e 1384391182 live 104 | 10902 312cc77f-06e9-4cf1-9255-bb4dc2a6aa4d TCGA-KL-8324-01Z-00-DX1.d99a7299-8f9b-4881-8324-50ed2d63358c.svs e6f54fa5a2cfbb012129d2707e1bb1ca 1053306684 live 105 | 10903 f7b61690-9b16-4b52-a49a-eefd05a14eaf TCGA-KN-8432-01Z-00-DX1.D4136A31-C2DC-432C-96FB-FD5EE47ECC0D.svs af34ebb835a922777431052a658bd986 323888457 live 106 | 10904 d7b9052d-805f-4386-ae1a-8624e962b750 TCGA-KN-8435-01Z-00-DX1.99219621-93BA-448B-8AFE-AEECA888BDA4.svs a12fca1b9df772da2d2ddc8a168fa30f 1057655053 live 107 | 11149 df08a244-870c-488b-8fc2-400211e07a39 TCGA-UW-A7GK-01Z-00-DX1.B074DEBE-1697-443B-B426-BD57553E1108.svs 273f1500f826e643d4a1e10abeb18ca3 1505071092 live 108 | 11387 e5379f26-3b38-4005-b20c-922f48f55c00 TCGA-KO-8405-01Z-00-DX1.DB2F9FFE-B562-4D52-A4DF-E939DE99B5F7.svs 88cd7d1f66d8f037457954d53eecd0cb 1677920747 live 109 | 11388 094bf3a4-966c-43a4-84c2-47df8e0f818a TCGA-KO-8414-01Z-00-DX1.F827AA8C-3A50-4697-9788-98A3D87BCE52.svs 713e06ac7016e624fa21f3e3d8ce8772 1299492325 live 110 | 11389 4c777c75-0101-46bb-b5a8-ef99c2b0ae76 TCGA-KN-8436-01Z-00-DX1.0CCCF11D-ED0E-4575-8F25-813415391524.svs 6823a035c559ce2f095541e37e7f6070 1780252143 live 111 | 11390 e6bce15f-5a9a-4213-9d4b-1a1b2cc27b14 TCGA-KL-8326-01Z-00-DX1.0fe86143-728f-4447-98a5-4a6d87ef398b.svs 437e2c4838b186f7b7db829270d5071d 888359022 live 112 | 11391 37d2dd09-a360-48b7-9e20-5f3fc55650f7 TCGA-KL-8335-01Z-00-DX1.3F291515-CD98-4D8F-A255-A10A69139242.svs a5e8dfb731679b3bad0debbad40d1394 590490040 live 113 | 11392 84fe97ea-e198-4182-a88c-0678a353129e TCGA-KO-8410-01Z-00-DX1.95A5FA25-6C01-478E-8CAB-20DF56E8D01C.svs 3ee7659d9d7dca25913578b2581a4734 1331986235 live 114 | 11393 7e416d60-7c54-4146-bdf3-4984dabed55b TCGA-KL-8334-01Z-00-DX1.bc0857e2-938f-497a-ab63-38bc87e1af30.svs 4f3d0cbba657e1bbc46cd57904b189b5 1373004210 live 115 | 11394 6708f647-5590-4542-b409-a27125c0bf9c TCGA-KM-8443-01Z-00-DX1.A97D876A-6453-4335-B805-C54529D3915F.svs 8c2c98c259ff412c54d3585523b21436 1790237405 live 116 | 11395 dfc4d48f-5fe2-488e-b9e9-bc42cbd99861 TCGA-KN-8428-01Z-00-DX1.CA71B178-286E-4EDF-9B37-1D2CEE07F9F4.svs cd2ff1dba1a8e512c67f40c1f733709b 1864527755 live 117 | 11396 2f6eab65-409c-4669-9f2d-52629ce33872 TCGA-KM-8439-01Z-00-DX1.F99904A8-21AB-476A-BFE5-B8FAB44FEB4D.svs 31c6b002dc39e5378f9072d19d32dc3f 966695683 live 118 | 11397 cd295eea-be63-4de2-afc0-9672b2435769 TCGA-KN-8426-01Z-00-DX1.FA31AC9B-A378-467E-97CB-7EFA06B804A1.svs f241111dcf393e008065a22835e716a8 711457525 live 119 | 11398 b862f72a-c919-4973-bee4-a635ccc90479 TCGA-KL-8342-01Z-00-DX1.a0dac779-03d7-4041-9e56-b33e548d5567.svs 0c04822230d122b132ec2b14b3d14ead 1389700774 live 120 | 11399 2ff5a232-8c9b-4693-8c82-17544524e1c5 TCGA-KO-8403-01Z-00-DX1.47C5A937-3397-4313-BE8B-0C6E4B12C301.svs 18fad355840ea6bea43797f4011b90a8 1297028219 live 121 | 11846 ef342640-d7f1-408a-9ba7-d87b57ffb343 TCGA-KM-A7QJ-01Z-00-DX1.5011C41F-4385-4AB2-8AFE-5409125EDC31.svs 5e97de4b9011be009e13a4e8db8f2316 1206253383 live 122 | 11850 59d108ea-8482-4f93-bf52-92b9225277f0 TCGA-UW-A7GP-01Z-00-DX1.C997CBA5-AF20-4CB3-9CB3-82AA65146EF5.svs 53bba8e4b2e8d549fa912dd4ca100708 1601448324 live 123 | -------------------------------------------------------------------------------- /gdc_manifests/gdc_manifest.2018-06-26_diagnostic_TCGA-MESO.txt: -------------------------------------------------------------------------------- 1 | id filename md5 size state 2 | 1155 0cc2af56-07b1-4571-9948-654430123d6d TCGA-LK-A4NW-01Z-00-DX1.0A16E20B-1CFA-43B4-9C95-43BCFA6EC6A4.svs b27d0692a7df5105fb4c01c491f34d11 2835401429 live 3 | 1156 5703278d-2b10-4de5-84ac-f257dad48e06 TCGA-SC-A6LM-01Z-00-DX1.FE4FD258-4B18-4A9C-84DC-A9940CBCF0B9.svs 7e70a256950563ed9981d631d98126ce 328240798 live 4 | 1157 e84dc62d-48b9-40bb-8cbd-3db3174b7133 TCGA-TS-A7PB-01Z-00-DX1.1A1BCC79-0CE1-4CFB-B362-FDB766885FEE.svs b6e71286f6dbe70276af2dddba768930 825898371 live 5 | 1414 f44e7146-40fd-4b6f-b937-04d16d075663 TCGA-TS-A8AS-01Z-00-DX1.4278D910-79C3-44AB-A2A0-5B7CE54D64CB.svs 00fa4982a9b74b052de84a6541dba528 423836257 live 6 | 1415 9db25854-c155-4d54-9707-f5303a360786 TCGA-UD-AAC7-01Z-00-DX1.A72102D3-0FEC-4F9B-AE49-5D6A5262A35F.svs 3c4732ee28ad51cb12682ce570b32622 1366373084 live 7 | 1416 670312c9-eb7a-40e0-b443-9014ea83b0eb TCGA-3H-AB3S-01Z-00-DX3.BC2DBEEA-1C7C-41AD-97D4-92FBF0483200.svs bb0c3a3f8879121677182c80e3aca627 1043508396 live 8 | 1417 6352c88a-d75f-4f1e-a0b1-72f70b279b2b TCGA-TS-A8AI-01Z-00-DX1.68C1CAA9-FCF0-42C5-8C6A-A382CD2252BF.svs 1bc9c14b67c25f04e55ee6f8a08f6ca6 604151579 live 9 | 1418 5c405ba7-eebf-44fa-bd14-a633b8e44faa TCGA-UD-AAC1-01Z-00-DX1.787A89D0-C918-43CF-9D1B-80DB1686BA21.svs 804186474a36547fbba92ff8f79b6446 3353361992 live 10 | 1419 10c9866f-c50e-450a-b5b4-e9ac0cd01a40 TCGA-3H-AB3S-01Z-00-DX2.473241AA-3BD7-4EA0-827B-EFE5FA2C7E67.svs d60224643f6b8f9a4bd265878f9cf51c 328211790 live 11 | 1420 884c0638-8446-402f-a099-4d5d0f7849ca TCGA-UD-AABY-01Z-00-DX1.17CE3A58-EF84-424F-8BD0-7E0C2B93B901.svs 75fd5ea4352ea08e4370361128eaa9c6 425600632 live 12 | 1421 20237d24-470b-4f10-80b4-a74115f9f4a8 TCGA-UT-A88D-01Z-00-DX2.AE0B6725-767E-4E45-A34D-3BC8F1CBE923.svs 73e8234ca22dc1aa993b39cc79f3494d 314689817 live 13 | 1422 6dda3477-c25f-4ecf-8a53-ef3f60dcad33 TCGA-SC-AA5Z-01Z-00-DX1.78B57359-29FE-418E-B5AB-750CF6687579.svs 02f0b242d86357b9b78fe80ce4416e4a 1292215907 live 14 | 1423 d7b03dc7-63d5-4dba-a1fd-f7015683af92 TCGA-3H-AB3S-01Z-00-DX1.B3743D6A-2DCC-46D5-9058-619F85B84138.svs 84d7ea0d40916932a0db2a1ca33eaad8 1354814358 live 15 | 1424 10aab73e-dbfd-43d0-87b2-f88e1afc0adc TCGA-3U-A98E-01Z-00-DX1.9A2C6D9A-9753-411E-8E05-22D381312CED.svs f4fdf5b9b3560ae811eb612d79f2cc12 582247344 live 16 | 1425 6bfd8331-6152-42b7-a125-afaf82ade180 TCGA-UT-A88G-01Z-00-DX2.3EA01D0E-2A35-4284-8C43-7E1710C3A297.svs 0b77ead8b511cb2ba55e3acb04b14c30 568123579 live 17 | 1426 bd15ad9e-95cf-427c-88c2-fb116954ca82 TCGA-SH-A9CT-01Z-00-DX1.B89F48C7-DB0F-4D4F-8731-A59AC2511F7A.svs 21f3b5ad06904e8f33ec73c07854e9d9 1438813875 live 18 | 1427 68ddd4f9-d535-4a8f-a958-f6a06666f91b TCGA-ZN-A9VO-01Z-00-DX1.6CE41901-D74E-404F-89D3-7DDB97378854.svs d633355ce63bea1b2456517d0f97e079 1457519651 live 19 | 1428 f6f94fbc-47ba-479d-babb-461ba7e6969e TCGA-3H-AB3S-01Z-00-DX2.943D90C4-82AC-4ECE-982A-E4DFF72B03BB.svs c62f708cdbc19a641e2720a3c84adf15 1226707362 live 20 | 1828 58817240-cc92-401d-a9f3-a7ebfd36648c TCGA-UT-A88C-01Z-00-DX3.A761E40B-50C2-4157-BE06-52095FD4FAF6.svs 422386da94e0815f9439acdf63b04cb5 639700683 live 21 | 1829 cd5651cb-a4cc-4b9d-ba56-34fd760f66b3 TCGA-3H-AB3S-01Z-00-DX3.16176098-1380-4FB8-91BE-A9162E627B96.svs 3c86626094dcb9ea996f8950f7bf8798 316009856 live 22 | 1830 bf80c353-c71c-43ce-9526-54960976ad40 TCGA-3H-AB3U-01Z-00-DX2.FA1C562C-39DA-4EE5-8DC3-DF5672720DE9.svs b8f1642688339a198132679b03929194 329038514 live 23 | 1831 39e54f9f-23ae-4838-b066-6ffbca81eb97 TCGA-TS-A8AF-01Z-00-DX1.B3F310A9-EA42-4B82-BC54-80839B324008.svs 22621479415aab136fc89bb5509dd785 567017321 live 24 | 1832 9e17c0cc-d91c-4205-af47-b8aa4094adfa TCGA-3H-AB3S-01Z-00-DX1.06B58072-6CE2-4898-B194-4878F57C57B0.svs 1060cab79d1c8cc9312f601ccc2dd18b 415050348 live 25 | 1833 cda010a7-1944-4482-99e3-418dfcc5849e TCGA-UT-A88E-01Z-00-DX2.CC3E0AEE-61DE-46E0-B5B5-3387EC9A757C.svs 1cfafd4b12bfc8c0c723e2d827743356 329103263 live 26 | 1984 fc365cf1-6f05-48e7-a8e4-5b2628aa102e TCGA-MQ-A6BL-01Z-00-DX1.739C3B7A-6A6F-4EDA-9DC4-47ABD8634EAA.svs 1d0648d28e0dc5b041713c0c0d28e711 558924885 live 27 | 1985 008ab1ae-9668-4a1e-93a6-1a528df1b331 TCGA-TS-A7OY-01Z-00-DX1.55585B4A-A419-42EF-80CF-ADD1A51854F1.svs ec6679bb969f5e92bf65859b814f5b2f 1037415179 live 28 | 1986 f6fd2e2c-30d4-4089-abe0-b6549023f89d TCGA-LK-A4O7-01Z-00-DX1.C097DA83-39E4-468C-98CB-8F7D8802E7D5.svs 48e79b625101e73ab9a969688cd9bed4 849978851 live 29 | 1987 4733539c-f8e7-45c4-ba77-878d8ab665b5 TCGA-SH-A7BC-01Z-00-DX1.FFC2EAE3-6C71-4702-9CC1-1C2471149E9A.svs 0a09e003916953594bcc06250d221086 1004157995 live 30 | 1988 19ecb6ac-a52a-489f-b0db-9acc086090a3 TCGA-MQ-A6BR-01Z-00-DX1.89F49746-16A3-4862-BAFE-2933608202DB.svs d6a36e49506e4eb54fac3bc9981117ec 351857925 live 31 | 1989 8bb4c624-3b6d-4a2e-92dc-caddf8f1c5d7 TCGA-NQ-A57I-01Z-00-DX1.274B053D-5E9D-4D31-8C1E-C036EB56BBC7.svs af93fb0a336c8e997181a749d0eef355 73286208 live 32 | 5909 911c4adc-679b-4ee8-bb16-b157c06e8afa TCGA-UT-A88D-01Z-00-DX3.11C557F2-220F-4200-8003-90CAFCD5E1FC.svs d788695d69c3b9ee6761e9c6ab97f39d 416898343 live 33 | 5910 c1a284b9-4c5b-4a37-b054-ac640f339f27 TCGA-UT-A88E-01Z-00-DX1.D4C533DB-FC2C-4E07-BC29-2C262E70FF96.svs 359eb119f1f8708c954d124d0b1f4b8b 557700625 live 34 | 5911 c28b2aa2-a2c0-4b9c-bd2b-8b59a5a91e23 TCGA-TS-A8AV-01Z-00-DX1.39EFD486-8628-4C10-8D28-4AABE6BB661A.svs ad9ef59ff911ba26a5f92a9edf3bebef 371920353 live 35 | 5912 44fae205-f7d4-45fa-a4a1-04450ff1ba31 TCGA-UT-A88C-01Z-00-DX2.941278A1-EB79-4363-937F-6DB9B702510F.svs ebb28f861c97c0b2c48cbcd2e716d7cc 2034242597 live 36 | 5913 51d34682-3fbc-4593-9a7f-48fc236b55ad TCGA-UT-A88C-01Z-00-DX1.A3206848-4B03-49CB-AF3C-720272E97AEE.svs c805c6e030843b69e6080396811eca4f 1002581429 live 37 | 5914 b82b0d50-7db4-4c39-b0a7-70ceb968c189 TCGA-ZN-A9VU-01Z-00-DX1.05957B52-B0F0-45BC-AE2E-821F257E1BD5.svs ccfa63793c2d64c27857ca6aa8e05a0c 1460405613 live 38 | 5915 dff977f0-5d5e-4fd3-a71a-87f617a400c3 TCGA-UD-AAC5-01Z-00-DX1.753D74E9-45EF-48F6-9F34-F4D8A3DE8AC6.svs d95e893d3df1ab4c5ff362f44e20086a 1029169280 live 39 | 5916 697ef7e2-cc3a-4d59-9dc1-759470dc7169 TCGA-3H-AB3U-01Z-00-DX2.E66C5B39-8F58-44E0-BC1B-5688CF0B03A0.svs 8e965b77dc701ebd0883e5fd37f150fd 1337211016 live 40 | 5917 9da40fd5-ae3e-4859-9591-050e0df0ced8 TCGA-3H-AB3X-01Z-00-DX1.FCF648D1-1067-4CBE-8D78-22A93591B335.svs 3de75d81ab38f450eb342e046fb6e980 235573262 live 41 | 5918 b78f0063-2586-4e26-ac21-5e3fe9004ed2 TCGA-TS-A7P7-01Z-00-DX1.0EDCAFAC-38E5-4521-A0E3-25DD79FDBF26.svs 19b2e63d32992f79df9dd6a706f542b4 1498808167 live 42 | 5919 e042723e-90dd-410d-9fb1-f35f02ddf70c TCGA-3H-AB3O-01Z-00-DX1.1458D00A-B6D7-4154-B149-9F16AE5CFFC0.svs 905ab109b5521fd2f597c49d50f7b246 2538274540 live 43 | 5920 ee486c45-8ac9-4359-b3e7-654040dd4d4b TCGA-UT-A97Y-01Z-00-DX1.19376AE8-F20F-49A8-BD6C-3998FD71628E.svs 894d535cf93d4460a026d024ef43912b 1517272333 live 44 | 5921 4cd2b0f9-7c6e-4f56-9aac-97e490fe4e70 TCGA-3H-AB3O-01Z-00-DX1.83AB41D0-0ACE-4FEF-A8B3-DA6BE97EDB60.svs 7b92c6508a02ccd07008a92045ed5415 636798762 live 45 | 5922 05fdada6-a798-45e3-b330-ae80e5356cc6 TCGA-3H-AB3M-01Z-00-DX1.9CD8A3B1-0F0F-418C-B54F-CBA22BB19469.svs 69ad523eaa27ddf59f3b7d4bd6b10f4f 219395010 live 46 | 5923 69e03c76-1e92-499b-b9ed-dc1e825dbf33 TCGA-UT-A88G-01Z-00-DX1.AF4DD793-5603-4E9E-94D3-D8E30FAE4281.svs c8a3afb64e5d3071553c91101554df13 344849905 live 47 | 6941 986769dc-ce95-4859-81e7-8b0ffbca66e6 TCGA-ZN-A9VQ-01Z-00-DX1.EB537816-420D-4DE6-990D-22A55226FBD5.svs 8172083b12b47bea2c38a9afff408d0a 1103167933 live 48 | 6942 373488ac-2244-4600-8c1f-62c7d8b85113 TCGA-XT-AASU-01Z-00-DX1.FC2B9466-98D6-4AF8-89AB-F7409BEF789B.svs 1e9134b943edf2483475b5f886ac3c96 176866187 live 49 | 6943 a0c009fe-494b-4b4a-9e99-be6f891681df TCGA-3H-AB3X-01Z-00-DX1.1EF5CB2E-61DF-4BB3-903C-D5F6488DE985.svs 3a08101ace19fb5772c04e7811a862e8 745706884 live 50 | 6944 7eaaae6a-6977-4929-9b59-81888e586ff7 TCGA-3H-AB3L-01Z-00-DX1.AED33A7B-EEED-468B-8892-2B7F338C5471.svs 5404a315dd79e2bfb7805c4579617095 470462988 live 51 | 6945 bb78c752-6a9a-46f0-a07f-9f20f54621bb TCGA-3U-A98F-01Z-00-DX1.4D2C4E75-7D1A-40C3-AD67-BB5789EC9FB2.svs 5f7072504109305754a94574f9deb5b5 529467814 live 52 | 6946 30f82cee-c511-4a38-8530-cc636d9e421b TCGA-YS-A95C-01Z-00-DX1.FCAE7A66-7E0C-4406-BBF3-E938EB196875.svs 7845d989703d0429680b7d60a212dd37 1182827921 live 53 | 6947 144ccdbb-ccb4-4599-8153-23c7187e2244 TCGA-3U-A98H-01Z-00-DX1.CE8066E4-A543-445D-84D9-819C8C0922CB.svs b22a4e0d89d0f7cd2bc19a5069d8f346 799989758 live 54 | 6948 ff82e283-9eb2-42fe-8b35-6b63384d41d5 TCGA-UD-AAC4-01Z-00-DX1.3485484D-1085-4FD5-B60E-FB3927BA0853.svs f25f8b2076ddd669fd15c301b8df15b6 2750937072 live 55 | 6949 254eef2f-8c60-4a53-b89f-98d39240e2f3 TCGA-UT-A88C-01Z-00-DX4.70BC2CAA-E576-4D03-B996-B67F6ABDA950.svs 6820ec5d7d4736ea01d98b9a8c400d75 1264906239 live 56 | 6950 0bc5fc24-b2be-46d2-89df-d0c6da8425c5 TCGA-UT-A88D-01Z-00-DX1.45ED3296-2618-4CC3-BE69-78B0B097162C.svs da6582d6cea952e826a40b9e005b210a 490717347 live 57 | 6951 a5bb7ecf-2b3f-46e6-8095-e69a442c3741 TCGA-ZN-A9VV-01Z-00-DX1.EA8BD141-90F1-47C9-B97E-65EEDF7613BE.svs 7e13183e9024c8bb1ed07514e8e24396 1522479521 live 58 | 6952 6de9409e-910f-43b7-a89a-2c8317dfcf32 TCGA-3U-A98I-01Z-00-DX1.982F29A4-ED58-44EE-8438-323BBDF2A788.svs 483aa3c9d4691727de75600f0ce653ce 911119902 live 59 | 6953 7c99edf8-45b3-4cb9-9a4a-74185ebadb78 TCGA-3U-A98J-01Z-00-DX1.4594931A-DC81-4CD1-852C-DD9A5730111A.svs e8151b6c7d5afe60a5ce6d104ca52579 1358804850 live 60 | 6954 028442b1-19d7-4d4d-b4d6-7e3dc37422c1 TCGA-UT-A88E-01Z-00-DX3.B727FAE0-4562-4976-A896-6DAB791045AE.svs 01db0c275255e9a5a11123ff7a4c2402 749999963 live 61 | 6955 af72d1a2-af76-4e00-a8ef-ef15ad25dbb3 TCGA-TS-A7P1-01Z-00-DX1.7820F2FA-E75B-47D5-A2FF-1246A234FB1D.svs 17125391d1d6d17198e9f6fa44896a91 788972611 live 62 | 6956 f7152dd4-9f19-499c-9e3f-32fe369bed0d TCGA-3U-A98D-01Z-00-DX1.3CADC856-EEB0-410E-9881-B8188B91110D.svs 7f80aec56db6ef6b41df57ab8ccb248e 1951583986 live 63 | 6957 f8dd3dfe-3bb4-4756-8967-d7fd50f1bdd3 TCGA-UD-AAC6-01Z-00-DX1.56D04FBC-2F26-4679-A597-C036E9CEDB37.svs f84a88464f16a9ebf9ff08d8c41a1c58 2076384684 live 64 | 7279 9d9a2723-5f20-4efc-bdfe-9e70d14334ab TCGA-TS-A7P6-01Z-00-DX1.0C2B22D5-27C7-4A7E-80B3-F2E7CC26CA01.svs 2a18150378c3697b7695f7d888ec43eb 652177355 live 65 | 7280 33ef6084-5709-41b1-b0ff-bf6bc29ab1e3 TCGA-LK-A4NY-01Z-00-DX1.4967FC6B-411E-4447-B114-A64F164B0E04.svs bdd3c8cf2ab88fdfdf1b9c59292f2beb 1731260633 live 66 | 7281 4a57b36f-679b-4b29-8589-02c32a7e9044 TCGA-LK-A4NZ-01Z-00-DX1.8A842571-2333-4957-A88F-EFBBA763830C.svs ddcdaa0eae67b8d8e7b40ce8316833c7 1144808677 live 67 | 7282 005432b4-1eb5-433b-846a-fad531634a08 TCGA-LK-A4O5-01Z-00-DX1.826C5B0C-5F02-494E-8CB3-02E5DEAACCBC.svs 1f73295ac2e2c78b3f2b75a0a196fecf 762200837 live 68 | 7283 e0a7ac61-e661-4f25-8af8-2be69698eec8 TCGA-TS-A7P3-01Z-00-DX1.BE9B8EB9-9680-4F07-8248-5BE552C6AC9A.svs cce03565c8b009028cc5f284105729ff 1254588283 live 69 | 7284 ede619a1-74bc-4223-8909-38ef61d17176 TCGA-TS-A7P0-01Z-00-DX1.6CC0800C-C45C-4F50-B201-3975EBFD7970.svs 5704c86eb30400a09db4ea6090ce20b3 623559285 live 70 | 7285 a0df4a65-6b8d-4da7-bec1-3efe23d37ef0 TCGA-MQ-A6BN-01Z-00-DX1.6DA0AD03-A9F5-4F77-B9F6-C5CD4904975B.svs c70026fd491e89c5543b8e3ab3c05190 66808827 live 71 | 7286 37c47c05-4455-4d5f-8238-ce6da80d9fc5 TCGA-LK-A4O2-01Z-00-DX1.3CE365F3-3A3C-44A6-AEB9-ED8027459770.svs 3758958fecc14f270407cc7cb266012c 1814456863 live 72 | 7287 1f71f2c5-d597-428d-a4ad-21e5e4c3dec0 TCGA-SC-A6LP-01Z-00-DX1.F0FFC261-1A10-4B09-84BD-6C056C9B9262.svs de65ab2c74711531abf39d57808e228d 716911340 live 73 | 8200 768b842e-709b-47df-9d08-be4a587dccf1 TCGA-UD-AABZ-01Z-00-DX1.1F9761D0-1133-403D-B113-B04A0FFD4527.svs 5cf0a4b5cdfb1564b3adcea1a7602ed1 632166058 live 74 | 8201 3f04eadc-4101-446b-a539-c62f3e8cb498 TCGA-3U-A98G-01Z-00-DX1.5315FC96-F850-44EA-8480-04EDD64B1BAF.svs b2c61830941f684f291461d85a6a443d 745039152 live 75 | 8202 8d2fd004-0e08-43e0-b646-e424bed120f6 TCGA-3H-AB3U-01Z-00-DX1.FCEF64AF-9EC9-4595-8478-F7440E346415.svs 9db906702584d0be41fbe822a9a5ff1c 356283966 live 76 | 8203 d28f608f-c5ba-41a1-8bae-519743ff3d88 TCGA-YS-AA4M-01Z-00-DX1.01220286-CBBD-410C-839C-83BFAF957A44.svs 4c1b3b38e2c8c3f01710d26cddc3c222 783679633 live 77 | 8204 b1672e07-f2d1-4dea-8e58-db71926de227 TCGA-3H-AB3U-01Z-00-DX1.D051FA12-C938-47C8-B540-89DA42D9610A.svs 51d6ba2d36c1322cc8caafd659d40965 1712937550 live 78 | 8205 37f1891d-6a76-4563-b397-f0d059e7082d TCGA-TS-A7OZ-01Z-00-DX1.F295DAAC-AD14-4B71-AFCE-4756D179811E.svs 57663cc51af9a440493d2953926e7beb 2107401229 live 79 | 8206 9842dc58-6033-4f11-af24-1c381f520790 TCGA-TS-A7OU-01Z-00-DX1.5761F431-1E4C-4093-8FBA-EF79925D1B4C.svs cf61cc99b61230fd2996baf799050766 1360578059 live 80 | 8207 507dc774-0e5b-491c-853b-6203aa327a4b TCGA-YS-A95B-01Z-00-DX1.95D754B0-A70F-478E-AE2B-5663A4DD0CF2.svs 06b1ca720bdf77545a43d5f018fa5373 467290371 live 81 | 8208 c5b8b6af-d64d-4992-869c-e93949ebdc4f TCGA-TS-A8AY-01Z-00-DX1.EC2F69B8-D46B-45FA-8CE2-D6512EF19E02.svs 0cae55e218a0fb0c373301bfd2c927f5 1194977255 live 82 | 8209 c615a7c1-c80f-4cbf-9d50-c6a59647cf68 TCGA-SH-A9CU-01Z-00-DX1.CFB41962-652B-424B-83F9-5430F2BCE895.svs ae492b06b68cffb6318663c0e6dcc9cb 1453313267 live 83 | 8210 a37d45fb-72cc-47c1-a746-403adb98545f TCGA-3H-AB3M-01Z-00-DX1.F4BC3549-A177-4CAC-A779-C221D0A72097.svs 23f3107150bf003df365f4ad32aaa33e 47816886 live 84 | 8520 a70ee278-8a0a-4b6e-9536-706dea7dd5a1 TCGA-SC-A6LQ-01Z-00-DX1.7DDA24D0-B0C9-4CAB-9991-092DBD33DC5B.svs 02c45a34feea562863a9d1a1c05b34c5 427847634 live 85 | 8521 af81023b-6cf1-4f39-af39-188f7e868cb8 TCGA-SH-A7BD-01Z-00-DX1.9411F2E8-F569-46B2-86AC-EE4FCC459738.svs 0a7f5c3fad68c5eb0874d4dbd47d8424 731253585 live 86 | 8522 a6859c2b-437a-482b-9576-5e6b04454b58 TCGA-SH-A7BH-01Z-00-DX1.5341A643-1358-4D60-9CB7-8252B5D7E2AC.svs 1c1ac1ac7e8ad3ab5e6aff78bd482f52 770094505 live 87 | 8523 ca6a5394-3bc3-402d-b4d6-356836ad5fc8 TCGA-MQ-A6BS-01Z-00-DX1.B70332BE-BF97-45E5-B835-5158983ED6B5.svs d62dfea93d464e86f9f8b2280eae3a1e 895307019 live 88 | 8524 2c9f283b-ca07-406e-b4db-b640ef91cf23 TCGA-LK-A4O4-01Z-00-DX1.A4452851-1EB2-4F3D-AC95-8A532DF87B5D.svs 6f031e856e295074372126dead550f9c 1914270347 live 89 | 8525 f43f72fd-bf2e-4713-a0c1-dbf6d86746be TCGA-SC-A6LM-01Z-00-DX2.C1D6F813-9E5B-4AF2-B579-2DF46384C098.svs 3c1e67e5f780db1831b273fd38d902c4 303674408 live 90 | 11735 d97c3e3c-f48b-4058-a224-bb4878c2af4e TCGA-LK-A4O6-01Z-00-DX1.A6158ECE-9C14-43DD-BF04-EA36CD68C57B.svs e36bfd3ebf55aa76c601ef80ec5982fb 1169370991 live 91 | 11736 e0f421eb-c8c9-4c55-863a-bf3072cda670 TCGA-TS-A7P8-01Z-00-DX1.25E9AFA9-6C12-4F18-BE79-2F4F19887ECD.svs 0c6226fa6a87c7c9229e44ed6e68908f 910468555 live 92 | 11737 1b503262-e3e5-4d1c-9f97-ceeac394a5e3 TCGA-SC-A6LR-01Z-00-DX1.39A8C601-6445-4D04-B939-D5B860E558DD.svs adc926a3a6eba1d000b42cfa46983bb8 441482450 live 93 | 11738 d07bf6f4-9d8d-442f-a216-12959717f734 TCGA-MQ-A6BQ-01Z-00-DX1.72BF21E4-17D6-436B-AAD9-7960342894F4.svs 4149e2a455a0d7ce0feb81388d61dbe1 570770191 live 94 | 11739 d57811ec-9086-4ffc-94e3-59ffdd1946bc TCGA-NQ-A638-01Z-00-DX1.BBE8E433-E9CF-4D03-81AF-66D4EE33D51F.svs cd40e6f1ba7de071c15870a6bef6e035 210615244 live 95 | 11740 fca70d45-4970-4aff-8b8e-6d6629f534b6 TCGA-SC-A6LN-01Z-00-DX1.379BF588-5A65-4BF8-84CF-5136085D8A47.svs fe53202c7e80596088ec417ec171aead 695269236 live 96 | 11741 0459038a-3f4a-4800-a05c-7e309b79b800 TCGA-LK-A4O0-01Z-00-DX1.C174E1A1-0EB8-418A-91E3-A5282D6358D6.svs c3a75e9b42e905faaaba5851a81768d4 1903697597 live 97 | -------------------------------------------------------------------------------- /gdc_manifests/gdc_manifest.2018-06-26_diagnostic_TCGA-OV.txt: -------------------------------------------------------------------------------- 1 | id filename md5 size state 2 | 170 b5325b4c-cd49-4652-ab42-34841b9dd6e6 TCGA-23-2077-01Z-00-DX1.9EB664FA-CC13-4A49-89BA-8A4573CE48F1.svs c00264d1e503ac3d608fcfb8a6c83c84 1531744381 live 3 | 199 152a6196-b317-4ae3-b8b4-3abb62bf7c5d TCGA-23-1114-01Z-00-DX1.26CCA42E-4947-4318-A983-D3B31603482E.svs cbcd9e0e0a89ce10e0d247661a266173 2334571527 live 4 | 300 52f9fc19-b571-49ea-bb1a-3f85312e83b7 TCGA-5X-AA5U-01Z-00-DX1.1A03C105-4086-4AAB-B821-A9E8156FA704.svs 4bb051cfde35590c5c19dbde1aee6300 1056363595 live 5 | 526 2d857297-5ac3-48b2-a1c5-109368beb813 TCGA-23-2081-01Z-00-DX1.4105A382-4C2B-4C62-AC93-CB21CC360254.svs 70696ab1a2bde7b5e761db67dcf3272a 1407335385 live 6 | 717 a2a5d590-c2f1-4266-bc07-249387ec0ca2 TCGA-OY-A56Q-01Z-00-DX1.F1556F26-8845-4962-9004-70F9747B46B7.svs b09fd2206efe9d0c28fb81a0d3308397 912585610 live 7 | 718 a90fe66e-3054-466a-ac1c-3fb60313b752 TCGA-3P-A9WA-01Z-00-DX1.A5FDC436-7F0D-4DD2-8644-CEF1BFF9C614.svs 7d1f5c86933f7e8d476d1628c16f399c 2047208537 live 8 | 950 9754ea54-209b-4848-a450-3e24137b46cb TCGA-25-2042-01Z-00-DX1.79198B62-0E0B-46C4-8D35-FE20582B8035.svs 1eec6fbca1494e99f94ec89d7530a407 3144896714 live 9 | 951 e9354ab7-5ab7-416d-851a-415ffd8ac55b TCGA-25-2408-01Z-00-DX1.760F6B8D-A61E-4C87-B90D-82E1AF56C204.svs 705997fb0a41bcc8b06ca00f776ee264 2656842596 live 10 | 952 8af97848-f142-4e18-acdc-46371ac6dc68 TCGA-25-2401-01Z-00-DX1.AEA99982-DB6B-4178-BEDC-6E1F605B8D7C.svs a99fa49d0c8770d6fc056ee3971013bc 2229177980 live 11 | 953 98d927d2-4eac-4cfe-a372-683cc5556afb TCGA-25-2392-01Z-00-DX1.C37932E5-973F-444D-8CEB-1BED4279165E.svs 40ac078e14f61be15316693aa14fb5d7 2195886372 live 12 | 1223 1cea1dd0-eb1d-49cb-a01d-72c9df9db485 TCGA-23-1024-01Z-00-DX1.B9194D3F-C6F4-4FC8-B0CA-6E347FF4F885.svs d99776bbd50e349da8a3b22fe5a40c5a 1864302957 live 13 | 1224 10a98b4b-ab0a-4056-9146-2e778d0632e2 TCGA-23-1023-01Z-00-DX1.0C96E118-A4D9-4A9A-B95E-C0AA114D2483.svs a307419ff3a7d285248beade6198d60b 1753648025 live 14 | 1641 547322e5-62ed-48da-9bbf-a018b0aeee8b TCGA-23-2649-01Z-00-DX1.C94C3B32-D5F5-4A85-9F35-50B377FF9E75.svs 7102f5a08312bd099162fa0a94d015a8 1158200527 live 15 | 1642 6a5aa9b9-03c5-45b5-af81-cde9e724311f TCGA-23-2647-01Z-00-DX1.21E5D0D8-6BA8-4D49-BA70-EC228CF10387.svs 790513207efdde2cca1fc08906f272f7 1932863803 live 16 | 2097 f19898c5-864f-442c-942a-8a77a0e51e8b TCGA-23-1031-01Z-00-DX1.12B1996D-E5BB-424C-B59E-4BE7E1ED6BA1.svs 4c75c5906b6fe7598599d3bb5e097de2 1327235219 live 17 | 2098 3f6c2755-9348-4ff2-bd9d-db7371593f09 TCGA-23-1026-01Z-00-DX1.2875B4F7-D6B2-4C72-8A68-4E7C92D04BF0.svs 02dfd516dd5e1c7207ce8bd82f3303b1 1776522739 live 18 | 2099 c5326c10-c217-4280-81b2-12f1a0dcd06b TCGA-23-1120-01Z-00-DX1.59367B12-17F1-41AA-A6FB-8D940365176A.svs a2852c5485c193a6da6aeb196802c88c 1682446983 live 19 | 2100 4d4aed44-ae23-4ce0-ae7d-a26dd89c2645 TCGA-23-1116-01Z-00-DX1.FC5FC1E1-56DD-498C-AA9F-4434C6E733A8.svs 23f574991f9331f8b6deccfaa6610143 2009665469 live 20 | 2101 0674a0d3-2026-4b46-80a3-a0ddf1c21e8e TCGA-23-1107-01Z-00-DX1.5B9C1283-62B5-4329-873D-009FA939CA69.svs e2859adee723d3107787a2042d99dcde 2264299355 live 21 | 2147 3f250157-d310-48a9-8fc9-af5c58d57146 TCGA-23-2645-01Z-00-DX1.72C0AB89-9A64-4656-B03E-A5D65BA03188.svs a0e65f1ab334740b53c780956e835371 1802508275 live 22 | 2148 de829cf5-ce1a-45d3-afd7-c7935ce4fab1 TCGA-42-2593-01Z-00-DX1.9d506f1d-a5b3-4643-bd12-91c33fae4286.svs a77f2f39d657b24a681792f8edbeacda 109931477 live 23 | 2216 1c55697f-6d71-4b8d-97f1-fce8e5f1d4f3 TCGA-25-1627-01Z-00-DX1.7596F7F5-D705-46B4-B3A6-833D31482D28.svs da9b50c8509438a10000b29107501ee8 1928378328 live 24 | 2279 095d9654-fd29-40e1-bca7-185ad9e19744 TCGA-42-2587-01Z-00-DX1.7a887a16-a8bc-403b-ab71-a8b43e5613fc.svs 881341c9fd9ad8716820e93ecd9e8623 138457713 live 25 | 2280 fb863fa4-7ffd-43c8-a97a-7bc9b6f86ab1 TCGA-42-2590-01Z-00-DX1.83ff5df9-0f36-4884-a93e-f2928ff3c719.svs be83b8a4345e879f2db8e04db68f7866 483499597 live 26 | 2656 3154605f-6da2-4968-8e65-4c1ef1454593 TCGA-23-1029-01Z-00-DX1.0044B39A-51B3-4F76-90A9-00CDF851DE2A.svs 8ca431c3f1b0f1d0eb6ce278c8bd7582 1498211461 live 27 | 2978 0bc96ac2-c780-4e0a-a97c-727183fa4a50 TCGA-25-1323-01Z-00-DX1.1B82D1C9-2310-4AAB-B531-45C1191E5FF8.svs 77f999fbd2ece44119a14a6c881d6a24 3180539114 live 28 | 2980 639f99d4-20ab-4a62-a9ea-9d70bf75ae21 TCGA-25-1321-01Z-00-DX1.56C898D8-14CE-4C2D-B5C9-AC33FF91FE68.svs 8b0b97386b902e130b5d49c9a340ed60 2920456238 live 29 | 2982 c4b8006e-b782-48c7-a7c2-f2ffd89bdcb0 TCGA-25-1314-01Z-00-DX1.E01C2237-E2D6-4D84-9FB4-624734F30375.svs fba28748debc6913d114f2501c2d34b5 2993836380 live 30 | 2984 8f2c7702-dc87-4246-87ba-e43e54f09da4 TCGA-25-1319-01Z-00-DX1.71EFB946-ACAF-4BA6-8855-D336268D87F0.svs dd2c1d48b35306c41cc3b78c72722c08 2522265752 live 31 | 2986 5c927205-f828-47ef-bdfe-971999838af0 TCGA-25-1325-01Z-00-DX1.FA0DD977-D2F2-4319-B614-3EB20E966D97.svs 5e8c5c5039edfc95b4db5b90c9f0fbaa 3408033806 live 32 | 2988 f606492b-b412-47ba-b826-23d11a2c6357 TCGA-25-1312-01Z-00-DX1.733EC7A7-0FC8-4DDC-B366-DF5A45D6BB4E.svs c71be59dda7274616bf67b1596b1a2ac 2547376292 live 33 | 2990 c93c270e-2668-4107-8f41-9797d93a5c0e TCGA-25-1324-01Z-00-DX1.37D77658-1D25-49B2-8CDE-FC092EAA4CDF.svs f816d05095c37de174dfecc00555c7aa 2753444494 live 34 | 3275 82a73a8d-f89b-4cf7-af26-4a6d8b5904be TCGA-25-1871-01Z-00-DX1.1BF3077E-910F-4992-AD46-B6869A136E98.svs 6a211fa809db3f26c26d7659f84a3ff7 3383269768 live 35 | 3395 51a3a22c-9097-4e9c-9972-4cc0df308633 TCGA-25-1316-01Z-00-DX1.A9B7F47C-5BDC-4B7D-BC9F-C4C9DBA663C8.svs 4e3e44888b14edc60b70c3d7b04f7c4e 3883353140 live 36 | 3438 4d0e76f6-0c09-4ffe-9ec1-ea07f3cff988 TCGA-25-1870-01Z-00-DX1.780BB62D-71C1-4B21-A2F4-61AC4B0234EE.svs d7ad66655f7094a6b099a061bbc2ae03 2120321276 live 37 | 3578 dc4f35d9-0e42-430a-b17e-4543e814da57 TCGA-57-1993-01Z-00-DX1.464F641B-AA9F-49A7-A224-88D9847159DF.svs bf8bdf883603d44bad122d3bf24f5c35 152037448 live 38 | 3660 44c334a4-2279-4904-9656-96bd5ef2a03c TCGA-57-1994-01Z-00-DX1.A0798185-30C5-4C32-B1A8-B440D4F4ED95.svs cedd220ef9e4f9ab5a73fe5ff3afff68 93340338 live 39 | 3943 839811b3-2964-4b85-99a3-edf1199a6300 TCGA-VG-A8LO-01A-02-DX2.9B58474C-DAC0-4D45-B13C-0A1EA9E1BC32.svs 3efd05550f90ce2d60ee66ab68f63a5b 225422354 live 40 | 3944 95a8a665-e8bd-4943-9af7-c1789207b6e9 TCGA-59-A5PD-01Z-00-DX1.0A4D38A2-7B15-4550-B00C-4276485A9613.svs 10c1026d95c7eeb089d20f5198ff164b 1598181501 live 41 | 3945 a21cffe2-318c-4112-8226-8c263ef38717 TCGA-13-A5FT-01Z-00-DX1.2B292DC8-7336-4CD9-AB1A-F6F482E6151A.svs bf3a1e701b605b7316b80f755b84de08 691602559 live 42 | 4371 0ef91b7b-c1e5-4528-8a51-8a0d5c6e46d8 TCGA-23-1111-01Z-00-DX1.A99421E1-C73E-42AE-990F-E5E6D26EDDBE.svs 8496a9472b5757abe5bbc3011f867b74 1016117227 live 43 | 4597 d6d8d9ad-95a8-4532-a394-274d18d61161 TCGA-23-2079-01Z-00-DX1.01383205-B7A7-4529-9207-880687650A50.svs 601c2103f1178eeb8761df43c4ab92db 1586922623 live 44 | 4929 7ac12b5d-e213-47da-ad27-06f161b73cb7 TCGA-23-2078-01Z-00-DX1.E31A9C1E-00EF-4B0D-A15D-6A5C2D00E986.svs d6e4e468dec5e4bb0aabfd44816cdcd3 1032145867 live 45 | 4931 6a9be68e-4865-442f-bd75-193847962afa TCGA-23-2084-01Z-00-DX1.94780F2B-9A88-47ED-982B-0048081309C9.svs cf0cbd1277958bcafd0936dd2baf9794 1055561075 live 46 | 5348 91ab3015-f3cb-4a33-aa47-05a049c55b3b TCGA-25-2399-01Z-00-DX1.B9A34CB0-9EBB-4435-8EDE-E4B9078565B1.svs f8e606a76a93a2c0b963f314efde28f6 3652997604 live 47 | 5349 7e34d209-3d11-4bb4-a8a9-f234b4d10cac TCGA-25-2391-01Z-00-DX1.3930615C-785B-48D4-BD69-FD87932A518A.svs a8eea2d1c9797b2b7b2c3f929694a85b 2179256044 live 48 | 5350 fdba3de3-1aa1-4bf4-b43b-5ebdbbcf1552 TCGA-25-2390-01Z-00-DX1.BC83304E-747C-47EC-BD80-BA0B322C8630.svs 3c0d734ddc3a8bf94e6be314321121f3 2482532976 live 49 | 5705 837d80ab-2afa-44b5-ba5f-b800953aa76f TCGA-25-1329-01Z-00-DX1.6DD994F3-E426-4749-8ECA-9A0B87FF04DC.svs a22622606eea36d2aa6f3a6bac52a17a 3950703384 live 50 | 5706 1bca2242-62e9-48c6-bb05-82c0462f5fb2 TCGA-25-1313-01Z-00-DX1.5A2732D5-01D6-4285-9283-1839E1703C27.svs da8e4b680d6d6664987a1b567292cbba 3630426186 live 51 | 5707 e4f3736d-7142-4f50-97df-9144fcac1692 TCGA-25-1315-01Z-00-DX1.BC434CCE-7E21-479F-8A5D-1FC7F601C8C5.svs 8e471d0bac20a42236e5a88efb381254 2516060062 live 52 | 6437 ed2bda7c-3a1f-4c81-8534-6ec151e9108b TCGA-25-2400-01Z-00-DX1.AAD20514-6FF7-47A5-89DB-8AA15DCC101B.svs bb059e462517e418509a57039be0dc07 2987536558 live 53 | 6438 d1d4afcc-d157-489a-8f9d-9294de75a5dc TCGA-25-2393-01Z-00-DX1.A311D005-D661-4851-A54F-EE3310C9CD8A.svs 012f7f84ed507990ea48c1694d774bed 2621017280 live 54 | 6977 9f0369e7-461d-416d-8b0d-b01d56466279 TCGA-42-2582-01Z-00-DX1.891d6182-c96b-4709-abeb-314d6874856a.svs a33e7a06b62e2dd3fe21aec535a355fb 194853649 live 55 | 7054 b7c357ee-535b-4bb0-a6be-ab1eda30d4aa TCGA-57-1583-01Z-00-DX1.88ACB045-1DBD-4F0B-A6D0-53B6C208805C.svs 8a5a4982bf2a7e61da00da7cb67c9f5f 475885874 live 56 | 7055 f7f9ece7-51fa-4322-880b-899b0efb4554 TCGA-25-1633-01Z-00-DX1.B3F91D16-A9AA-479F-8326-DD3E280C8759.svs 888ca361b7f3b1b3fa1c5f038abf9efa 2061487010 live 57 | 7151 ae8012e7-35ad-4c72-8fe9-db9f4604989d TCGA-23-1121-01Z-00-DX1.E2F25441-32C3-46BF-A845-CB4FA787E8CB.svs 2ff42a9c8f457a3305bcac9b5c78dbbc 2008119069 live 58 | 7152 0e8f401f-4224-4b7b-bbab-ef885a3992e0 TCGA-23-1122-01Z-00-DX1.991C230C-E3B4-4DAC-9DCC-69E9FA7DF772.svs cfd1216a8dda30eb20b3dda47e512894 2368635901 live 59 | 7153 6c47e661-9457-4b6a-b617-3cd47e6a67e4 TCGA-23-1117-01Z-00-DX1.783914B6-B079-4828-B77B-4C6306FAE4C1.svs 15e6f189efcec0b61123b3ad2b47490f 2214439179 live 60 | 7486 f45621f0-c5a8-4390-8a20-39eeced6a6f9 TCGA-25-2397-01Z-00-DX1.B6FDE9A3-6A51-4A79-82CB-51ED37945A54.svs 297020065977d0fa2abf0211837f2d80 2358953486 live 61 | 7487 aa5c4207-7a53-4bc4-8e49-4467c73668fa TCGA-25-2404-01Z-00-DX1.7193B185-31C3-41D0-9194-86DEDF15F096.svs 34e16de61e3ed1e29bd39a8d9730d1df 1999509800 live 62 | 7731 57ab308b-0825-480c-a216-5149c02f8be3 TCGA-25-1878-01Z-00-DX1.618F8128-41C4-411B-9B26-B490E066B30D.svs 6d7c2e20b06e07b09c3969a5b45f266f 2919939438 live 63 | 8677 f2d75fb8-fc74-46ff-b20c-adfbc1694a58 TCGA-25-1317-01Z-00-DX1.2E7A7AF9-4D04-4EBD-8C79-7117F76511D5.svs 20adb062b3ec444953b85213c2423024 3787847486 live 64 | 9029 a443dd1f-ecbe-4e63-a21d-026f22c86e6e TCGA-25-1877-01Z-00-DX1.ECD98484-514C-4E9A-913B-F7EC55D6A8FE.svs c36635e924d3c80c191bdb0be6bcb149 4221998982 live 65 | 9031 1314b103-5c5a-46b8-b560-14e01713f278 TCGA-57-1992-01Z-00-DX1.1022B1ED-3DC1-4F71-8635-0F8B28138B8C.svs 5bba44e935694a8601ff717d66e3b481 900700524 live 66 | 9423 757231ed-bd9e-4359-a46d-89986ef0c308 TCGA-25-1318-01Z-00-DX1.742CB28E-DB0A-4BE1-8047-5265FE80F861.svs adc329385695c0b5fc377b043c94542e 3433000966 live 67 | 9424 d9890613-f76c-4e67-af48-e146e2ccceed TCGA-25-1322-01Z-00-DX1.20DA1932-908F-44E5-B2F2-43E41E06165B.svs 79b496e0ef31ec569b0f845792eae3c0 3846321624 live 68 | 9493 49aadcb6-5cb3-411c-be4d-da8b60eaafcc TCGA-25-2396-01Z-00-DX1.3E755B49-EFC5-49B8-A381-0B06DAE56961.svs c1fd621e5ccc6d953a50d78470de159d 2928582606 live 69 | 9494 ac9d0e1a-fc0c-45b7-87de-1a215a429bea TCGA-25-2398-01Z-00-DX1.3F0E9A15-DBC8-43A0-8C94-20B02757CD10.svs 2af000091a885970cf9eba5eba9ec17e 1951490878 live 70 | 9495 69b1beb9-e85e-4221-91c0-6b75db3b0227 TCGA-25-2409-01Z-00-DX1.34FFD6A9-4919-4DF5-8415-215CC833F12D.svs 9ec46c6937b09ea04602fa6b3197ab93 3432072424 live 71 | 9561 acdebd36-6cca-4309-a991-1417775a4b6e TCGA-25-1328-01Z-00-DX1.A0145C96-19A9-4F2D-8570-ECF039F99405.svs 05e4e242dea3e53c75f42acd59037a61 1788544134 live 72 | 9563 a8b40915-6004-4458-8793-516b3b8b8180 TCGA-25-1320-01Z-00-DX1.30C154CE-C75B-4815-BF05-7D011B761993.svs cc002ac800519b0d591ca20530416dca 4056272902 live 73 | 9565 2a2f2e23-3f95-4afd-8726-5d8be0e173ce TCGA-25-1326-01Z-00-DX1.686E3548-8891-42ED-ABBA-BE3DA6D4CAAB.svs ba0b497b7410d3d89577df96f21e43ab 1643178148 live 74 | 10008 59f22b0f-f946-4232-8f07-78fb65271362 TCGA-25-1634-01Z-00-DX1.6E449C67-922B-409A-84B4-581B9B468682.svs 84edaf3cf3439f4ac1c5455e37378d4a 3364086764 live 75 | 10009 c3ee4e94-ca68-4d42-bd6c-329186e31913 TCGA-57-1582-01Z-00-DX1.BDF02DAA-E520-46BD-A479-58CAA4354B1A.svs 1e840f32525bba922a241cc27f9bc6c8 90025528 live 76 | 10010 72800757-c563-40f9-939d-a2800603c997 TCGA-57-1585-01Z-00-DX1.934E0F30-F804-4CFA-92D5-41576DA6C367.svs 5e94cce98ceeb88b88f970a36b75f4e6 234287190 live 77 | 10069 5c2e8d06-a94c-43cd-a5c8-847763e5cef3 TCGA-23-1028-01Z-00-DX1.117B4B7B-F796-4D33-A645-CD80E5C43E6D.svs acdf22cfc7da4e0de133fa86ab7f1a3d 894793941 live 78 | 10070 ceb122d0-4980-4127-a32f-decf8bd6d338 TCGA-23-1123-01Z-00-DX1.764A8E5C-F2E7-441D-B9FB-23ECF7183740.svs 8ce280278933c73a9c67c68cf44d61ba 2092687325 live 79 | 10071 042aaf5c-e836-4aed-98ab-3605c420b25c TCGA-23-1118-01Z-00-DX1.D69E130E-33C7-4F8A-99AF-400B81378578.svs f4c73a8f7a15f420caeb8bceb9e8c68c 1437585949 live 80 | 10072 ce4695cc-f342-482b-b6e8-41fcc23f602c TCGA-23-1021-01Z-00-DX1.F07C221B-D401-47A5-9519-10DE59CA1E9D.svs fd32243cd7dbe5ec7cc9ee85839e8480 1555934033 live 81 | 10073 31aade1c-2d2d-4df2-8786-1d28087d5a08 TCGA-23-1110-01Z-00-DX1.61C2DBB8-7F5C-4878-BEDC-6AE061A2D7D4.svs f89a1ab32f0b4d45f12f17cce8522cdc 1992524927 live 82 | 10074 dc5c431d-8d46-4da0-8e8c-d8f5d4048cb2 TCGA-23-1027-01Z-00-DX1.53F9DFF4-6811-4184-B2FD-1F6706B948FD.svs 1e6631b009fecdedb4e41761e687ebe4 1642502065 live 83 | 10124 7462fc21-e62c-4c30-8229-438a1a60c65a TCGA-42-2589-01Z-00-DX1.c3abd56a-7d75-4972-982f-3d86da96ad1b.svs 41d5b040a2dc1977f75324a3ae5fa7bc 180705935 live 84 | 10125 fbdfd212-617d-461a-886f-660e01c4d109 TCGA-42-2588-01Z-00-DX1.e0bd9f78-2078-4bc3-867b-136d117f7b13.svs c6f5734281d5ffd49b25386025a97184 252398217 live 85 | 10213 f5e45a42-7996-4125-a2f1-62e5edf4f66a TCGA-25-1626-01Z-00-DX1.2C6EA1FE-8063-40AC-B81A-CC0A630FCFCC.svs 5fd95d9d4d09e00faa8a8a4190b44121 2692887216 live 86 | 10214 6823ec0c-9595-41c0-a2bf-78b69d1cb3ce TCGA-25-1635-01Z-00-DX1.D21D2855-43F0-4766-934A-3CE1E3A099B9.svs 8dac7d66a4a5c2d61aadc4e992cfed0e 3257709758 live 87 | 10215 d45eae85-34b9-43fd-98b3-7971c42e6b4e TCGA-25-1631-01Z-00-DX1.7CA82CFB-E5F6-4148-8B5E-088B7FE6331F.svs 7e495c332695a3074957367e4936bcd3 4150552750 live 88 | 10216 2cbc33bc-f40a-4be9-b91a-8618b48f2a2d TCGA-25-1628-01Z-00-DX1.8275623E-8A30-4ABB-8846-34DAEE43523E.svs beda06aaf986423b5f2a040d9f286aac 2597671096 live 89 | 10217 1766d897-3b92-4852-98db-a4e23bad35a0 TCGA-25-1623-01Z-00-DX1.28D89405-5F27-47CF-ABC7-01AB494C28D2.svs 6dc8f11e33901053a77c0efa059ff4da 3626573712 live 90 | 10231 94c7d8fd-7e4c-4ce6-bba3-00b753ce21c1 TCGA-23-1119-01Z-00-DX1.44D3D70A-A421-4962-8385-2A3CF8E9880A.svs e286642e25c43a5a53bb1cb44eb8bbe8 2679787667 live 91 | 10232 f1c88deb-5f10-4c26-85a2-d8c9e6cf5c28 TCGA-23-1113-01Z-00-DX1.D72B1587-444A-4DEC-8D92-703699822BE2.svs 614c9505117433a2a540639077415545 988224639 live 92 | 10233 88a625ab-0933-4429-9995-cb29d3df4b21 TCGA-23-1030-01Z-00-DX1.FC93147F-FB55-4C62-B187-337A5C107096.svs f737ce4e96ad3382fba992f6efb43ea4 1666318223 live 93 | 10234 119de60d-8e8a-480e-8e89-dfe21ccaa858 TCGA-23-1109-01Z-00-DX1.FB0886B9-8108-4A74-8A29-FEA4381AD69C.svs ac4d61be92757f920ffc392443b88dfe 2129352197 live 94 | 10235 c8dd50c8-fba1-4fab-9569-30e9fbc1b490 TCGA-23-1032-01Z-00-DX1.0C1074AE-D59C-4C74-B929-593AE89E5DC1.svs 4b6ae18ce8bf1441fdee0167d58d867b 1380794393 live 95 | 10236 488a49e7-e1d5-4a35-a4f3-8ebda947755e TCGA-23-1022-01Z-00-DX1.AF9E523E-CB0F-4AB5-AD43-C96731BF9141.svs 43245d29464c071d28e9584d22f8a004 1368851883 live 96 | 10573 a5e01b52-8211-441b-985a-cdd23036de3b TCGA-23-2641-01Z-00-DX1.DB792236-39EC-4090-9938-B0915C3378A0.svs 8766a62993e0d5830d270363ff2e63f1 2347494343 live 97 | 10574 7c934491-c7b7-4625-a8bd-35f76d84ae1e TCGA-42-2591-01Z-00-DX1.ea85e14f-5f0a-4ed0-9afe-025bb95fca40.svs 9fca1b9081347cc14571a66be479fef3 415765713 live 98 | 10575 96a9524e-a40b-4b51-ac70-3319f01ca57d TCGA-23-2643-01Z-00-DX1.E60DF03D-326E-4182-84DA-77263C4C52B3.svs f79fd2a3a39d64bf0c8622b6840024b9 875878857 live 99 | 10790 ba37d875-e72d-4b84-b359-9903d2d6b945 TCGA-25-1632-01Z-00-DX1.B911E6FF-D6A9-4AC7-873C-58B2059DE7E6.svs 6ec8b4c81cbc8984aef8cb746b1ff25d 2805842892 live 100 | 10791 94b6c769-5d5d-4554-a458-94797c13d002 TCGA-25-1630-01Z-00-DX1.75C53351-1511-4CCE-97AC-1650010AC568.svs d729d0017eeb66a9a4231b68f1d01757 2630508006 live 101 | 10792 61e9b8b3-480f-4ec4-bd48-0107c1d517af TCGA-25-1625-01Z-00-DX1.64A0B073-8EC8-4BE1-BECA-B956A6A96FCC.svs e303d4f3d6af8a664a005b4bd0af381a 2433855706 live 102 | 10822 0a0bb4c4-b5dd-48e6-a1ce-e0a4872a4766 TCGA-VG-A8LO-01A-01-DX1.B39A4D64-82A1-4A04-8AB6-918F3058B83B.svs df63e73a3f179ad2de48f2225d202e39 133282492 live 103 | 10894 23bdd35f-7740-474c-80f7-27f3cfa03c81 TCGA-OY-A56P-01Z-00-DX1.59CA76B0-5613-48CB-ACE7-6F808B8A9423.svs bd07938d5a23b07bd66ab379ac5ca924 1003142300 live 104 | 10895 276ba090-db09-4c1e-bb34-0e92b2750594 TCGA-13-A5FU-01Z-00-DX1.9AD9E4B9-3F87-4879-BC0F-148B12C09036.svs 338ba8b797984df4b6e027d8d19997e2 544302707 live 105 | 11319 5e552c8f-1087-4d4b-bfa9-30c0c50b2ba4 TCGA-23-2072-01Z-00-DX1.478243FF-BFF0-48A4-ADEA-DE789331A50E.svs f7ad5c8f2974e617674c30f537a863b6 1953258999 live 106 | 11384 11a6dba8-50a6-4437-bd7b-9c60c91d78a1 TCGA-57-1586-01Z-00-DX1.5C85A9B1-9ACC-4D62-BA09-91F8BDB2A058.svs dc43991121ff0095d12a69a7d391378c 228797480 live 107 | 11385 7e2e0932-a3fd-428b-80d6-87256a87b1e1 TCGA-23-1809-01Z-00-DX1.A8767DEC-EB1A-4EDC-906E-C0560A30455F.svs bbba95f91807549ec1b8a814842867dd 1744362619 live 108 | 11386 8db7935c-3adc-418f-ba35-824c8de2e60d TCGA-WR-A838-01Z-00-DX1.5FE22DE4-CEFB-45F6-9299-505023A8F3BA.svs 8e398993f4dfac7d4fb56808fe1e8408 997188345 live 109 | -------------------------------------------------------------------------------- /gdc_manifests/gdc_manifest.2018-06-26_diagnostic_TCGA-UCS.txt: -------------------------------------------------------------------------------- 1 | id filename md5 size state 2 | 2541 3ab4d371-38b2-4dac-9bb6-4edce9de7b57 TCGA-ND-A4W6-01Z-00-DX2.6C2B0FF1-4DC6-425C-844F-6BDD4C658451.svs a9bade7dc80d20eeabb4593a73c815cb 2035318891 live 3 | 2542 17d57157-792c-45c9-ba82-bbefee32e391 TCGA-NA-A4QX-01Z-00-DX3.E47A2B5D-8280-44CC-9354-0F662529EC89.svs 10b9026132338d71e7d53051703951ec 2339325701 live 4 | 2543 ed361452-1132-48fd-990f-507e57ffecba TCGA-N8-A4PL-01Z-00-DX1.34181D81-E843-4543-AEB3-31D893282134.svs 1018cb5fa1b476760c2411133793f855 1424972130 live 5 | 2544 235c22fc-8d4f-43ae-a1a0-6dee5f009d02 TCGA-N7-A4Y8-01Z-00-DX5.8024FD57-2A1A-4579-A008-DB0CDDB83A58.svs 012ca994e6cd3faa75d0f897ace33dc2 1856358895 live 6 | 2545 89878c79-853a-4945-a874-adf375310e84 TCGA-NA-A5I1-01Z-00-DX2.C1292DF7-FB78-4869-B4CA-AF5C1D65628A.svs 50c3e2d9b44a19f50cd5070365bfec6e 1651429823 live 7 | 2546 2281f84f-a416-49aa-be2c-e4ebad53ec33 TCGA-ND-A4W6-01Z-00-DX3.0A25A619-FC83-4116-8143-81D77D3798D5.svs cd5aabe45411f4d1caee91cd9b029837 2299453429 live 8 | 2547 ca3c2029-7aa1-4085-bac1-510c1ba533ef TCGA-N5-A4RF-01Z-00-DX1.E91A00EF-9CD5-41D6-8EF6-D8C147E080D8.svs a8a8297a93f65a8da482ad8b9abfc52c 1503299471 live 9 | 2548 c242be69-45f7-4471-9790-72627e39627f TCGA-N9-A4Q4-01Z-00-DX1.16E8D41B-34B2-4382-BA3E-2601FF91839C.svs e55f617853ca3c39dbe91fdf92c4c5ef 653839093 live 10 | 2549 99f43cfd-8351-4260-98d8-02c4d238d4c1 TCGA-N8-A4PI-01Z-00-DX1.3D04E506-3B74-4B73-B287-2402ADDBA0F5.svs 7c43373ebbba068b386b68b9a929cdde 528378776 live 11 | 2550 209ab9ba-c75f-4798-b36c-cc8dc1018117 TCGA-N8-A4PQ-01Z-00-DX1.ADA7FB4A-BE7D-4638-8C67-6078B3B6E431.svs feb66f4a583a21c8b2fbec48e544fc39 870629990 live 12 | 2551 ca203b73-df41-48c2-a7c1-d6a3d189440c TCGA-N6-A4VC-01Z-00-DX1.18468117-C130-4E03-84DA-774F4BEB7DFC.svs 6f2a636f6b9bd314048c071bc4393a0a 1828218289 live 13 | 2552 6f3f1d9f-dc43-49a1-b9b9-32c96cc69b5a TCGA-ND-A4W6-01Z-00-DX4.5F16BF71-71E6-46D2-BE61-300268E4B710.svs d90f5772479347d96b1ab0093171bc85 885796259 live 14 | 2553 e42b77df-bc06-4c77-af2c-113bd291e95e TCGA-N9-A4Q3-01Z-00-DX2.584DDA2B-B267-4484-AC8C-B1853E7C6DF0.svs 7dd13f2edba5dff9cbc3c382ae41d71c 634841002 live 15 | 2554 40ddcd7a-13dd-4c85-a577-df9104d36c37 TCGA-N5-A4RJ-01Z-00-DX1.4E355249-9DF9-41F3-A94E-5C04B6425337.svs 781d32b4aece91f1a62e122580ae234e 1582854957 live 16 | 2555 f5de8c22-73ea-42f8-a9bb-6504eec1da47 TCGA-N5-A4RD-01Z-00-DX1.2844A70E-7C13-4FA0-910A-08BB1942F375.svs 764279ee49b9d7b984d956c25e8511fa 1995550241 live 17 | 2556 e8f6396b-1485-4e53-96e7-149da3615a08 TCGA-ND-A4WF-01Z-00-DX2.871259CF-886F-4EBA-B1D2-F8A654D3FA4A.svs a36a4353d711cd1078e392b542d14e8a 2212364783 live 18 | 2557 7ffb37b8-e6aa-4e57-8221-68bf7fb57fef TCGA-N5-A4RM-01Z-00-DX1.8FB1D437-C61C-46A3-8EF8-247B4261B718.svs 9b2d0d147f55f772dd6f7b74e3fd827b 1712579911 live 19 | 2558 5c29e065-db36-4f3a-a517-d47b5d77c8c6 TCGA-N8-A56S-01Z-00-DX1.BC1241E1-777A-4FFC-A09D-E8F0E066BCFD.svs 1f90eb01abbf27d50d12a147c065627f 2662825349 live 20 | 2559 870dce11-eaa0-4162-9f0e-d780fb01b555 TCGA-ND-A4W6-01Z-00-DX1.05AE2CC4-CCB7-4C26-8031-23018FC4919E.svs e0a1f07774a9ecea4a27031a47fac4a1 1760742121 live 21 | 2560 6e3b1d57-da84-465e-aad4-3362a2f77927 TCGA-N6-A4VF-01Z-00-DX1.D78EF5C0-E015-42DB-8D41-FE41FAB0E26D.svs e4f37e94c7c3e7f318142b3b7ee4bb4c 1465712675 live 22 | 4248 96af071c-01f0-48ab-a527-c711d95ab7a3 TCGA-N8-A4PO-01Z-00-DX1.D73029FC-ADE9-4FA3-BE96-514C8A77DD33.svs b14178e1307fbc73dd3587e2b3498d9a 1567650278 live 23 | 4249 804ce807-406d-4b8f-a4ff-a79fed9b0247 TCGA-QN-A5NN-01Z-00-DX3.15BBBDB5-B81A-46C8-934B-FF1AD2CF0A4F.svs fe97dc326e8ed5a7c6404cf6df4806f1 321914543 live 24 | 4250 4c38c80a-3c54-464c-9b1b-f322f8524190 TCGA-ND-A4WA-01Z-00-DX3.A4F9ADC0-021F-4579-8CF7-7EFFA49CCA4C.svs a527690a8bec514feeb1ede7a45e286c 1892068669 live 25 | 4251 57c3489e-f99d-4a08-8c77-6b733566ee30 TCGA-N5-A4RT-01Z-00-DX1.D8442398-1D66-4439-8F24-A5833EB46F72.svs a2392760d15fcf8439d8d9b441ff4788 2102927731 live 26 | 4252 0614d1ff-82fd-4469-834d-50aedbbb9c51 TCGA-N7-A4Y5-01Z-00-DX2.BCCAC6B0-7FAF-4C70-A446-7905FFE4F4BA.svs 3eae46fb3733f5d0b82bd53124583b54 1783724255 live 27 | 4253 df586308-a2cc-4c18-98b0-6cf25fa1802a TCGA-ND-A4WA-01Z-00-DX2.071A8B48-72E2-4872-AB73-47B5F5F76440.svs 76f19b268177d1daca2cbab63dffaf16 1946169573 live 28 | 4254 816acfcd-9d96-42f3-92d2-ad2d49083868 TCGA-N9-A4Q7-01Z-00-DX1.1CFC484F-0B47-4767-9F38-17B174B022AC.svs cedffcec10bf61a201f9cb5f853b1c2f 1055542745 live 29 | 4255 0edd8b26-2306-4801-8d1f-e0ab05d21aa2 TCGA-NG-A4VW-01Z-00-DX2.F21D5CCC-A5FE-4972-AAFC-32966AB658DC.svs 3d47ee0f97cc973b9bfda85e9e0a6515 3163712899 live 30 | 4256 fb5378a9-8b8c-4297-b814-214214a48b08 TCGA-N5-A4RU-01Z-00-DX1.BEDD8FC8-AA33-42A5-A8BB-3B2E078D74B4.svs b57f3f1a01d6145796944b06b446f518 1331444777 live 31 | 4257 74081259-a703-45c5-9ddd-dbe6791bb8c8 TCGA-N6-A4VE-01Z-00-DX1.52BCF1BC-C8A0-48D6-8348-7AD873581D59.svs d9c4419596731e963c2fcd64f7917ad2 495070755 live 32 | 4258 c81cf07b-d40e-404b-848a-d3293e584a81 TCGA-N9-A4Q8-01Z-00-DX1.6D35B9F6-B56C-4CEF-A897-1B68928C7362.svs 4c412ef450bbdcaf3bb9c2194efefe85 809587973 live 33 | 4259 2dd89cc9-749e-4a60-bdd9-23f6bbeb209d TCGA-NA-A4QW-01Z-00-DX1.37801BA0-624E-47FB-99ED-219D4F22E36C.svs 0308b7ffa0e99facb3405424787e329e 1863346941 live 34 | 4260 c91f1f6c-44f0-4a5c-a059-0dcaabf32aa1 TCGA-ND-A4WF-01Z-00-DX1.A82E5E1F-9D99-4A2F-9BF8-D2AC3ECB9A00.svs 30d1e4b3620856453e055bd305465363 2314071283 live 35 | 4261 5797d334-a32d-4859-84ea-0d85b7734463 TCGA-N5-A4RA-01Z-00-DX1.663D082C-3844-468F-9D5D-260F7655D0B6.svs 2ab4b5260d9b4b750ddb2b7d21e82dd5 2738228961 live 36 | 4262 d29911ee-74fd-426a-87b3-3d3737c510b5 TCGA-NA-A4R0-01Z-00-DX1.76E2E632-B869-4F1B-A03B-BE00E303B6FE.svs ee3d6e6a1cf620e9919fe3f2cb1019b6 2452761621 live 37 | 4263 193325c7-9644-421c-9db8-063b83475889 TCGA-QN-A5NN-01Z-00-DX2.0FE8A3DA-ABAD-4517-9D4E-E64E927C50F4.svs c1a0fd02a846518f5cbb28746d0723fe 1477683125 live 38 | 4676 39a8b6f4-80ca-4ad8-a696-0f61f47c0836 TCGA-N7-A4Y5-01Z-00-DX1.D62099BE-7AD6-4350-BBC3-95901B839BC4.svs 058fdd1d84fb8c06eef32be9c32a2693 1663471439 live 39 | 4677 cf7c3f68-6075-4428-95b3-f1df7bf59ad2 TCGA-NA-A4QY-01Z-00-DX1.E6D30574-886A-4E01-B4C1-D10C0EE23AEE.svs b6d18ae1cd3c363682bf6167c8bd29cf 2112665773 live 40 | 4678 fe01c9ac-fdbd-4942-93ac-550576fb97df TCGA-N5-A4RS-01Z-00-DX1.0BE07A3E-C1FB-417C-ADEB-C7CF9DED65CD.svs 1db6656fe321570ed81912ff119c471a 1658347719 live 41 | 4679 4bc70715-30e9-46a1-b162-359c011cde37 TCGA-QM-A5NM-01Z-00-DX1.B4B9A4C5-AB04-4302-9C17-A7A88CEED873.svs f6af907da0609f9dfc8f738454cfea17 790346160 live 42 | 4680 4b53c8de-a9de-495d-b891-32eea51153cb TCGA-ND-A4WA-01Z-00-DX1.747FD9FF-B6FF-4108-8EFC-BC8898E4FAA5.svs 6125d90a664568c1857be732c9a61b34 2051429495 live 43 | 4681 b0912839-a71a-4268-b436-74182bc9efad TCGA-N8-A4PP-01Z-00-DX1.C7EDA950-0E71-4380-BD0F-A77F037AB444.svs 24dda78227e0f504471ab1efe6515a95 2023998386 live 44 | 4682 be2504c8-3ef0-4984-a2ee-8f37cec8c8cc TCGA-NA-A4R1-01Z-00-DX3.EE4A6E57-9190-48B8-975A-532DDCFFE369.svs 90aa4b58e83cc34b4276865ffbb0f467 1992829659 live 45 | 4683 c28b8b40-1023-4970-8b70-6e5a9c3123fe TCGA-NA-A5I1-01Z-00-DX1.1B9A17E8-9BCB-4C81-94F8-B4592615664D.svs c09ce54d8b591b8e4dda428228a30117 1592598437 live 46 | 4684 6dde8368-66d7-4b0f-a41b-8c0a89097075 TCGA-NG-A4VU-01Z-00-DX1.1EA57488-7E0C-4FE2-84D3-28A46DF84F94.svs 675122240771b414cc1e215587b8a0a6 2164098165 live 47 | 4685 a1ea89a1-5ff6-4201-91f2-371414414d7a TCGA-QN-A5NN-01Z-00-DX4.AB57D943-2A7C-46E8-AD24-94E36B9A836A.svs b1a953ca0b89ee065f78d66dd72c08e9 1999093775 live 48 | 4686 8632723b-a70c-4baf-a0da-41155b90747f TCGA-N5-A4RO-01Z-00-DX2.C833DA0E-2C7C-438C-8878-2C5656E50228.svs a90e9ab832b275bfbe0b4dff23e0def3 1661285009 live 49 | 4687 fa686c50-a093-4315-aaf3-22e1dc8a7177 TCGA-ND-A4WC-01Z-00-DX1.A81AB325-119A-4946-8F26-40D9444A6427.svs 085509646a75e8c772618a344a20d511 2014009197 live 50 | 4688 8403cb89-4a8a-4abe-bc0b-c1ed54584cb9 TCGA-N7-A59B-01Z-00-DX1.D8BE1C60-BBB1-4A6C-8EB3-1453D29EAC42.svs 9bb1f5fadc1105519ace3799fb4135f1 1138628329 live 51 | 4689 6749c97e-118c-4be8-8a8c-24585ca9d403 TCGA-NG-A4VU-01Z-00-DX2.5A4EB668-1F2D-4B8B-B223-81B77C35CF13.svs 3542d4c2ce36b46778cd0c865a8f7990 2966512775 live 52 | 4690 6bbe3ce8-c5b8-4502-9d43-7a3ab7c331d7 TCGA-ND-A4WC-01Z-00-DX3.C9E15FCA-65BA-4F46-B9FF-320C021FE76C.svs c7dfdc9624cb77d98a40da3dbeade9ce 1679098909 live 53 | 4691 b37eb169-6ca0-4962-b275-7ea4a152d5bd TCGA-NA-A4QX-01Z-00-DX2.21B263F6-984A-4F28-9414-63AE29DDB5B6.svs 77d962ecf9bdd556e9da5af3d9c39582 2159719845 live 54 | 5975 ccdb9fec-2542-4370-8e3b-cfa1a8001c5b TCGA-N8-A4PN-01Z-00-DX2.5E54DCF8-7D21-4A35-B8DF-2AFA88424478.svs a3126407cfe05f75f3df01f0390b1c48 1493657119 live 55 | 5976 064530fa-a00e-49bc-9ec6-ae01159d4ed4 TCGA-N5-A59F-01Z-00-DX2.DE0D67D3-439E-401D-81CA-8D25FA8A3466.svs f44ed8f0f618a02b57f54fad8cb9f47b 2575048525 live 56 | 5977 068cf24c-c588-4e80-a068-776cc944aef5 TCGA-N8-A4PN-01Z-00-DX1.92336FBA-79D1-49F9-BC2A-7C7BF4147E07.svs 0698a4c23d265f59051d227116524100 2457840258 live 57 | 5978 809f72a2-34b9-410a-8a53-5316fa297e5d TCGA-N6-A4VD-01Z-00-DX1.2BFBD228-8B03-40FA-9BC8-DAFA34142A7A.svs 0313c032dc781cbeb3f5a2d2654022dd 1202063207 live 58 | 5979 1de00299-f585-47ee-945c-91ebede2ad24 TCGA-N9-A4Q3-01Z-00-DX3.69E43341-B4D7-4B99-A280-01CEE9C51DAC.svs 227ce73599574d89563e122b295cbfa1 855071884 live 59 | 5980 b0becf69-a7df-4974-bde5-40ba2afe4bd1 TCGA-ND-A4W6-01Z-00-DX5.7A91D15A-1DCB-4B22-96FD-740F0F3332B4.svs 09ce0e2ff78c0e1a584bff4a5c09a647 2084602841 live 60 | 5981 edb43cb1-7c1c-4555-b911-4d68cdd3860b TCGA-N7-A4Y8-01Z-00-DX2.1C1909D1-FDB6-4C5B-B393-F8F04E970210.svs 754c2db23f9defc87cf1930b52cf9990 1197773581 live 61 | 5982 6ff2c4f0-0b93-4197-a1d0-106e8cef69ac TCGA-NF-A4WU-01Z-00-DX1.C50C3F98-470B-41E5-AC20-644EA8B42E22.svs 39ce31051c2164b33e070c1f1e93af04 952761416 live 62 | 5983 40c73591-c139-46f6-982f-4eef3b0a4312 TCGA-N8-A4PN-01Z-00-DX3.910926E1-09EF-47F0-99CA-C5EEEFB18866.svs f0238e29f965da013d593213cab881c3 1435214791 live 63 | 5984 64662ff2-3e62-4418-abb0-850c40e008df TCGA-NF-A4WX-01Z-00-DX1.C7DF8EF9-75C5-4D45-86B5-E2A679062B76.svs 91ab4730b6867b8f3f9e87a5eef58293 501995222 live 64 | 5985 8afb6db8-ce89-4264-a493-77aef824eb38 TCGA-N6-A4VG-01Z-00-DX1.7DC1C1DB-95F7-47DA-8111-DF1A5E479193.svs 313cb9778578872958897b6c31f62b39 1549284403 live 65 | 5986 07be8a7d-b7bf-4ac0-8f71-41b4e40c01a8 TCGA-N7-A4Y8-01Z-00-DX3.A444534B-CC40-400C-92C2-B3003BA2D8B8.svs 76099bd622ef364bfea1665c779594c5 2046135379 live 66 | 5987 4cb8542a-762f-42b4-87f8-688f22291db6 TCGA-N5-A59F-01Z-00-DX1.9DA5BE76-078C-44F9-B562-0CF5BF8AEB9D.svs e48cfd68b70e732a3a348178e1e32c4a 2306268331 live 67 | 5988 9daba973-3443-4943-9cee-10331b6ddb7d TCGA-NG-A4VW-01Z-00-DX1.93289E3C-F0AE-4192-A8C7-6AFDCE9E8ADB.svs cf81dba25497465600fcb1f1c5a21e13 2608134009 live 68 | 5989 684d6f62-c307-4169-9a8f-be675706a068 TCGA-N5-A4RO-01Z-00-DX1.F244C2C1-8C30-4F93-9F13-6C25F2008186.svs ca7b6e4c4cbb1037718171fce10acd3f 1802123101 live 69 | 5990 970c87c6-d074-426c-9641-f83520db3f3e TCGA-NA-A4R1-01Z-00-DX2.362E9E9F-0225-4189-8E45-B96BE2340415.svs 4c26c477381546bca284de07baf5c7d5 1994223675 live 70 | 5991 25d7e5a5-f83b-423f-8ccd-d9f98de1482a TCGA-NA-A4QV-01Z-00-DX1.F4B25213-F920-46F6-8263-48DBF15C0527.svs 349d97bc0711bb93bb08fa1efefe8f61 1787868525 live 71 | 5992 d36a9be7-b739-4eae-ad2c-bb44cac7ce84 TCGA-N5-A4RT-01Z-00-DX2.48015BD4-1202-443B-96C8-934A9C77309D.svs 39f6f137c869a270f053771239d6b99c 1099350115 live 72 | 6646 8fd7ef90-f699-48d8-9e0c-a7d037968ea8 TCGA-QM-A5NM-01Z-00-DX2.7FB04E1D-1F1D-4217-8D3B-261B0E949038.svs cd117fe3e401c6925794632bf094e5bd 1074314584 live 73 | 6647 cb7f5e12-c722-47f1-8c74-00eaf63fb811 TCGA-N6-A4V9-01Z-00-DX1.5E294AB9-44B9-4207-B8D5-41D8C5BF3326.svs e350c89aadd3b6ac5883fb37300dbd72 2194481567 live 74 | 6648 d3844a20-d5d5-417e-9376-0f62374cd866 TCGA-N5-A4R8-01Z-00-DX1.1E2F2A7A-9807-404D-B563-5E9BF8530E1E.svs c4c75791519cccb64aeb149e493f4a8f 1489712603 live 75 | 6649 d11c222d-ab2d-4b44-8a0a-c08f03b71263 TCGA-N9-A4PZ-01Z-00-DX1.279251BB-086C-419F-87D6-032F1EA34102.svs 9df5db0f838e76f90e201111f9434ea6 439788191 live 76 | 6650 fa213f0a-ea17-4b70-a565-e840cb85e946 TCGA-N7-A4Y8-01Z-00-DX1.97A6AB74-559F-4DE4-8D7D-C3A2CE6E2231.svs 178560ad850adfad994a2d4a9d3adcc6 1725319369 live 77 | 6651 77fdcdbe-249e-41df-b07e-553bc6c93e5d TCGA-N7-A4Y8-01Z-00-DX4.94589553-78C5-414A-92C9-78EAE3375F37.svs 505a276c56f9c58594947f89c690196c 2261418417 live 78 | 6652 b32ac718-f0da-4d1a-a29a-441eca500e0b TCGA-NA-A4QX-01Z-00-DX1.3B96FAE9-A546-4157-9DE6-E6E8C4CEC941.svs 0cc30d9cbdf46b0b3e2cf7f3221d8d56 1509907549 live 79 | 6653 f7020b9b-138c-4043-84e2-174eb01db034 TCGA-N5-A4RV-01Z-00-DX1.96D6BADC-B0A0-473C-9D7A-8458789C16B8.svs 90edad9ba5aac3ab7b7f7d96d3989ddb 1702553531 live 80 | 6654 d6ff89c5-35ac-4ca0-ba37-78606ce25cf0 TCGA-ND-A4WC-01Z-00-DX2.4677B271-CD27-44A3-9BC0-C604FDF2B779.svs c52929ef257daad1b883abe7e4290538 1311921239 live 81 | 6655 8db33f00-026f-4d84-9cb3-4296bed97dc3 TCGA-QN-A5NN-01Z-00-DX1.FA7E8A3C-CA46-4F3B-843D-43E231A57E54.svs 062afb978c436608086086584f33f752 427508717 live 82 | 6656 a82337ea-79ec-4648-9441-469030a61a5c TCGA-NA-A4R1-01Z-00-DX1.FFF6520E-AB1C-4F3A-92C9-3C776D779231.svs c78e8d7a4e7ce05460dcc86d2ce10e7e 2578103619 live 83 | 6657 4307b66b-11bd-4c5d-a6fb-9f8da1da8762 TCGA-N7-A4Y0-01Z-00-DX1.A771FBB2-AAB1-434B-B28E-C0587DF9F07C.svs 2a268eea055b0d08d56bf176fb43e657 1578868191 live 84 | 6658 a64d2951-c068-479e-afc3-371cee9c30b6 TCGA-N5-A59E-01Z-00-DX1.D8A42938-3B45-46AF-981A-53C618A6EC74.svs d97ae18a38c61409009e5c6c8ee82125 1775369719 live 85 | 6659 1ab690c6-8f94-44a0-9a98-071862c19613 TCGA-N8-A4PM-01Z-00-DX1.9C154E50-6D39-4BC9-9CB0-A347E71969C2.svs c848f60f1f910e4e79f6868badebfef3 1616092290 live 86 | 6660 afbb6e68-67eb-4804-a1b0-e1082bfde0f9 TCGA-NF-A5CP-01Z-00-DX1.FA60B2E0-880E-41FB-92B9-0F61C76A8CF2.svs 8225a42e7891e7af65e7cf7d09b8c4b1 457304574 live 87 | 6661 e7fca259-a9fa-4511-bdf3-d8f27c7a7c31 TCGA-N5-A4RN-01Z-00-DX1.3C7D1446-F9CF-470B-B5ED-A4A7DF564D18.svs 95b2c78735992082b5252f7a0d6ce698 1201418137 live 88 | 6662 f1590a88-64ba-4e8f-a238-a8bf11dbedc4 TCGA-NF-A4X2-01Z-00-DX1.B09588B4-FBD3-4CED-9E88-6D018F0B5098.svs f88ae5d9cdab0d3f1e78cc7647effd1d 1811480290 live 89 | 6663 85b8e29f-9387-4454-96ce-ec97c0b416cb TCGA-N9-A4Q3-01Z-00-DX1.B9E5BC01-25DD-4725-9B10-811A636E2402.svs 8338bed4148a48d2b7b573ada22d93df 738185529 live 90 | 6664 cd55e8ab-5d43-4278-a201-e3c8519a6c1f TCGA-ND-A4WA-01Z-00-DX4.CDED0DCF-D49E-472E-AE55-9467013B3CFF.svs f661fe9a701530979ba684aa584af6cc 1967846985 live 91 | 6665 560126f1-2612-4562-bb4f-d06631b56694 TCGA-N8-A4PN-01Z-00-DX4.4E5C6562-85D0-45E3-AD6A-3C129A18B3E8.svs d3287cda8c4d592bb2f00ea782bb2892 1465746991 live 92 | 6666 0bbd3cdd-45f9-47e9-90c7-08c28b1e7621 TCGA-N9-A4Q1-01Z-00-DX1.7B37F0FE-8EB9-464D-8645-417BF8470967.svs ac163d2e0a6bf5b6ad877d5c0a95ddeb 381320537 live 93 | -------------------------------------------------------------------------------- /gdc_manifests/gdc_manifest.2018-06-26_diagnostic_TCGA-UVM.txt: -------------------------------------------------------------------------------- 1 | id filename md5 size state 2 | 23 8f0b3ffc-322c-4692-aa8c-344bb8175540 TCGA-VD-A8KN-01Z-00-DX1.0AFBBD8D-DAB9-424D-BFE1-632C283B24A7.svs f950424d0ae410def0e8606e7fc83ffd 380585458 live 3 | 25 351d0fcd-bc0b-4d3b-8042-a1dcc51e63a8 TCGA-VD-A8KM-01Z-00-DX1.1D881A73-FE65-4CC3-AA03-4F4BC168205A.svs 5d922af1e33a6b5e4dc4c585adebcbb9 504861262 live 4 | 1525 2a2db394-8e44-4ad4-9a6a-9992e8992452 TCGA-V4-A9ES-01Z-00-DX1.40F620B4-1AB0-4501-A370-6FBD90A2D12D.svs cd35929019b373c9d48257e82556662e 857115039 live 5 | 1526 5df505e4-9187-4f17-8af3-a6873df7a875 TCGA-VD-A8KH-01Z-00-DX1.E63BFFDC-0572-4DF4-928A-3E84350433E8.svs 6e321346c9890036fc69c58f0248d47e 597857202 live 6 | 1527 e2fe9063-d13e-4925-b0ee-bc51fb2a701a TCGA-VD-A8KJ-01Z-00-DX1.31C09AA6-FB01-4FFD-841D-81BE24532CFC.svs 96c9563d4d7b4072e73fc0a8b9eac9fa 621864796 live 7 | 1528 84d80c59-99a4-467f-9b0a-53ab81d1520d TCGA-VD-A8KI-01Z-00-DX1.E82FC46C-138C-4115-B81C-6A991FB753A2.svs d75d0636b2c9cb6e0d7ac654ca6f8690 442888322 live 8 | 1529 85ec1fa9-cb81-4562-9ab5-5a532cc8b0cb TCGA-YZ-A980-01Z-00-DX1.70AB0D30-D42F-41CC-B68E-99BB35CD363B.svs 04cf58a90d2b13825fd86c92a1117884 620779576 live 9 | 1530 4c106f57-d587-44f1-ac7e-3405729330e8 TCGA-V4-A9EM-01Z-00-DX1.E74E99E2-CB99-4C01-99FA-6F79371F0792.svs 44b91a8f0b1aed127f69977a4f0dd8b8 2265325995 live 10 | 1531 a022253a-4ca2-44ee-af78-1a33e0a5c9d3 TCGA-VD-AA8N-01Z-00-DX1.5888B8F4-9292-4403-A71B-BC744AE7670F.svs 2ab5666469f646a2d2d30d7ae0b15ebd 682684822 live 11 | 1532 7032a626-38b4-477b-9113-f2d87a5d2382 TCGA-VD-A8KG-01Z-00-DX1.65E318B8-C0FF-41D0-B78E-B8328AFE4E63.svs a0a6c17d788f33fa44d3471ffe2fc701 408086976 live 12 | 1533 1360e6a6-1b66-4ead-9e50-7c0c9a03e15c TCGA-V4-A9F4-01Z-00-DX1.1AC1A857-BF91-4872-91B7-CCFCFBF3AA11.svs c74375c8ea542278ca146a30663d4bd9 1024461143 live 13 | 1534 2dc19729-fbcd-495c-b611-870c95195773 TCGA-VD-A8KK-01Z-00-DX1.81AFEEA7-4171-495A-AD24-7603DD4194D2.svs 1a6dfcf4a1d25fc43b802e91a4b5345a 558090880 live 14 | 1535 6e69539f-d82b-40ee-a1fb-a2b6c9515e86 TCGA-V4-A9EL-01Z-00-DX1.D805EC59-74E4-482F-981D-BDDFD92FD3CB.svs f8a89d5198b43e2e597ef2bd9a69f409 1081035631 live 15 | 1536 c1288e7e-b071-4345-bcec-af334a2b4c2e TCGA-V4-A9EA-01Z-00-DX1.DB8360B6-2BF1-4538-AF2C-29EB7186946E.svs a3b96121fb4be6cce61d48c3bfe1dbcc 1865302441 live 16 | 1537 9866d9c2-935a-489f-a7ee-e297baed87c1 TCGA-V4-A9ED-01Z-00-DX1.D424FFFA-D661-4E93-9F25-9CC621926298.svs e0770d79acb323938c80b507987db5c5 1467290881 live 17 | 1538 91d1983c-7791-46f3-bec7-968ebb121cbc TCGA-YZ-A982-01Z-00-DX1.9D8A15CA-E938-48D6-955B-0A0621D42F06.svs 9d82a46efa716edd4a4ec0a010518242 1619202090 live 18 | 1539 eafeabc2-63a8-4c91-a5e9-7ec21b4ebd65 TCGA-WC-AA9A-01Z-00-DX1.623129B9-6420-4844-8E29-0D2C788CDC88.svs e2ab12611c46d3f5c51eaafcb824b765 998302187 live 19 | 1540 2477be45-426f-476b-b1bb-8fea3ece7f10 TCGA-V4-A9EH-01Z-00-DX1.53450D2F-449A-4F7A-96D3-C2F9B8EB05B6.svs a0ba1ef8e34dc83c444156727e111e4b 1596961027 live 20 | 1541 a4c2fa57-685b-40bc-b21d-cedf1d2ae0ae TCGA-V4-A9EY-01Z-00-DX1.685E5631-DF28-479B-AB4A-20B2BF07E97D.svs 9f1f0aefeab1c6d6cc2e8b91952067d9 787087847 live 21 | 1542 277e68eb-8098-4d81-983f-6913e8b5c244 TCGA-V4-A9F8-01Z-00-DX1.310A7148-C6B5-4BAC-A341-00F915961CD0.svs 3042c71da5006fa555f5ba6b28a83b74 1105680169 live 22 | 3224 235e4b08-d9d5-4da1-8b82-f38b3b3dd7ca TCGA-V4-A9EI-01Z-00-DX1.2D27A195-FB57-4CD0-9B86-032A0EDFEEC0.svs 13b9e25f15d9bcf225d0430c5302046c 943598539 live 23 | 3225 27efce87-8ff0-4b13-bca3-78e8f7d91f44 TCGA-V4-A9E9-01Z-00-DX1.3B6A6FBE-41DE-40A2-BDD2-E895DAE4127D.svs c532fb1cf94f12354d0bcc80e2a7c627 2708066061 live 24 | 3226 959a741e-a43d-47b7-93ac-b5c4674f998e TCGA-V4-A9F0-01Z-00-DX1.C3909E27-4255-4F4F-BE02-791E097D2843.svs 3e21d9db280ab09743c3745a29194885 770810671 live 25 | 3227 d9291d63-c3ce-4c69-a442-c2b8a35ce664 TCGA-VD-AA8O-01Z-00-DX1.A7A42183-8D3E-43B6-A54F-461FB955296B.svs 8e92b7a8a3e63e1ab845473614650e39 546521810 live 26 | 3228 58d0b13b-e077-4c00-90d1-25de18f3006e TCGA-V4-A9EX-01Z-00-DX1.34B99C00-621F-49DF-88B3-20E70EB53637.svs 536c386327d876741d8fecc9a9ca455c 1101697467 live 27 | 3229 91cb88a6-4a6b-4520-8f65-0730f0dfcb0b TCGA-WC-A883-01Z-00-DX1.51BC7B12-45FF-403E-B347-E590B2374EC9.svs 6c25171d4fd95d496d7b58eabdfd1771 746330017 live 28 | 3230 b34c17f3-af9b-4798-a943-51f7809f3c01 TCGA-V4-A9E5-01Z-00-DX1.97279EE1-33FD-46C7-95B3-0E4065DF3069.svs d1783cb4b7f1d2b6a19a847ad0b97e98 1783681533 live 29 | 3231 57e5b0cf-aad2-48ce-ad2b-a743b7d6fffc TCGA-VD-A8KA-01Z-00-DX1.BAC376F9-7038-423B-8D37-7751B5514092.svs f63737eebdfbf922ea7cce135277c079 212116160 live 30 | 3232 f251b9c2-d44f-4e4e-9c2e-8e65a0c9b06b TCGA-V4-A9F3-01Z-00-DX1.39FC86CA-2833-4361-93A0-C8534EBFD255.svs 2fe16572b7620b3f93ac1201e8a60dba 1285854583 live 31 | 3233 ecac9f14-b0ce-49f1-84ff-c5be609b600f TCGA-V4-A9EO-01Z-00-DX1.F918F843-0A2E-4ECF-953F-D61269F077E7.svs 512cfc372489007be5753aa7cad30cd4 2345468857 live 32 | 3234 0d13374c-96ee-4be9-b0bb-fb7b8218f7c5 TCGA-WC-A881-01Z-00-DX1.E3827A53-8E60-4018-AA54-37A8596C7040.svs d261cd03a9a147ca512974d6ac3c1d73 1036220927 live 33 | 3235 dcafe8d1-0c08-4181-b4e1-99932a2058ce TCGA-WC-A884-01Z-00-DX1.D7134947-7DA5-4921-AD57-65C5E7B613A4.svs 26392963995383b1b3d4fac774b41686 1330728489 live 34 | 6195 43bea75c-bd79-458e-9e9e-53e699ff9a47 TCGA-V4-A9EE-01Z-00-DX1.46C2BBBC-16B6-48B0-8350-F25A367F6A09.svs 11617de024cd3a922db8cb0c2d3fd715 2066853721 live 35 | 6196 f6cd1856-de6e-423b-89a6-5eefee854541 TCGA-VD-AA8M-01Z-00-DX1.AA194E33-B494-44E3-9C7C-29AA6A68393F.svs 91bca804ec5caa3ee44ca4430d4bf5b4 422874208 live 36 | 6197 c1a2f7e9-670a-4c55-84d7-9fb64c58ab50 TCGA-V4-A9EV-01Z-00-DX1.164C1623-BF78-43BC-8222-8AD6B103B449.svs 713691ccc5a6734e745f528ccf9ae55b 778518895 live 37 | 6198 38291d2e-ae22-46b9-ab87-ec06fc073cc6 TCGA-V4-A9EQ-01Z-00-DX1.BE3D1D29-CF65-4166-871D-9719207BE4B1.svs d91e734f45e3f8e443867488871ebf19 1194707087 live 38 | 6199 416aa0a5-ae06-4c3a-a6ca-3053652ae3a9 TCGA-V4-A9EW-01Z-00-DX1.4C6703D3-2310-4C6C-8E54-327082184585.svs fcb8699326c349727089e085df965151 1212496451 live 39 | 6212 42530e90-5876-4f4e-a144-3d28c0c062a0 TCGA-VD-A8KD-01Z-00-DX1.D9D20501-0089-4B70-826A-3CBC8EF6A9D5.svs 0bcdd5ed1748f2fde662c503db7dd980 633338244 live 40 | 6213 4ca6ed3d-4112-4c89-95bb-a7ca2c8c8fdf TCGA-WC-A885-01Z-00-DX1.E38A80BB-5313-4ED5-8818-C5CC21365E16.svs 17adead712ce5b7c3123b04cfc39bfb4 618417319 live 41 | 6214 cfe50537-9bb7-4612-bd6a-a6247eddb010 TCGA-VD-AA8P-01Z-00-DX1.5F8231B1-9302-47B5-8915-450A22AFDE7D.svs f4356b2842135aa7c1429d3b948f4bc5 319058958 live 42 | 6215 c91e2a66-af03-4b42-bb97-88056bb4df54 TCGA-V4-A9EJ-01Z-00-DX1.B78B6AEC-DE0F-4E45-ABCE-5ED7FDB2D75C.svs ac14c6702dc5b972891ffa08ebcaf93d 1766244825 live 43 | 6216 5792b009-04d0-4721-a372-15198832a4e8 TCGA-WC-A87T-01Z-00-DX1.9A9FD724-37D1-4660-A88D-3D4286EC781E.svs d2424c288b54b7faca6e8251029ae694 1046232759 live 44 | 6217 e3acb67e-fa00-4cfb-8c3e-fbd01d18008a TCGA-V4-A9EK-01Z-00-DX1.3AD38873-F6F5-45E1-87EC-3C1B6C5D9967.svs ff275a03a879ec054bd74ebc2cadce2f 2200602301 live 45 | 6218 0764713c-fee3-4787-92ce-169658a26fd3 TCGA-V3-A9ZX-01Z-00-DX1.B4A9BC5E-3AFA-4765-BB79-25F3B0497B09.svs d04e60f4a2166c9488761341bbc034fa 558279008 live 46 | 6219 16c14965-cec2-4235-8d7e-cade704b119a TCGA-VD-A8KL-01Z-00-DX1.8285E272-DF38-41A5-B8FD-BE4D3273C45F.svs d7c77a3f4e0f9a2fc0fd8792fa1286cc 484246078 live 47 | 6220 d250d9d9-dd2c-4580-923a-ac9fa3182d52 TCGA-WC-A882-01Z-00-DX1.69320618-1047-4A9A-A0E0-F5D5D798EABF.svs 63e4b45256e6fb3578c883abe9990dc0 1053031451 live 48 | 6221 77d9ab93-5f32-45af-8c8d-ee7621729584 TCGA-VD-AA8S-01Z-00-DX1.4472340D-E9D2-48D1-96B7-5C0D1DC7C846.svs 23febf8dfa57ad7bb90dba7d00b09fba 368315828 live 49 | 8386 1fbef5e0-13d3-4442-85e0-9c897df43875 TCGA-V4-A9F7-01Z-00-DX1.EDC25B84-ADFA-4216-8640-12A15E2AC08A.svs ed5d11a93b8f44065b98aed926741d49 823243365 live 50 | 8387 e9102451-0f50-4be7-ad49-76d4c8115021 TCGA-V4-A9EZ-01Z-00-DX1.90136571-87FB-4B1B-9C4B-052773C65FAE.svs 03a0687169b9b8ba4ec7d7cc96d008e8 1310785279 live 51 | 8388 39e4c2db-9c76-4cf8-98be-97d36aeea4e8 TCGA-VD-AA8Q-01Z-00-DX1.DA856B64-9633-4798-8B53-3ECFA8DA3064.svs b487a9b41353b5f9f8192fc80f645a30 455140130 live 52 | 8389 56d1ca31-96d1-4049-ab8b-d7d2c7691bde TCGA-V4-A9F1-01Z-00-DX1.6CCFEBB7-1589-45CC-A60C-7068DD25EB27.svs 37fd48b6b0bcc5f0b6e3eaa2790bd821 759159405 live 53 | 8390 0ff44385-bbad-41ee-8718-d4571a180360 TCGA-VD-AA8T-01Z-00-DX1.AC226DDF-7ED7-4BC1-B1BE-C697AE3C2F21.svs e4c53f01ebf0d4d157bc3264478b6e4a 464001246 live 54 | 8391 24538266-96a3-4d93-860e-f2c12b3e318c TCGA-V4-A9E7-01Z-00-DX1.465EFC95-3B6C-4836-A8BC-0A4F0BBFA601.svs 721b208da4bba48615afbb0a0c14bcda 2303203685 live 55 | 8392 9fba4b43-dfb8-4ad1-93f1-5342f43ce852 TCGA-WC-A888-01Z-00-DX1.61DC04F2-C7D1-4B96-9D39-A348323CF468.svs 4e2f2d4694ba62ca75d07477b3fed6a5 1512591875 live 56 | 8393 a6ff8ea5-4f69-49af-95b5-41d7aa09d272 TCGA-V4-A9F5-01Z-00-DX1.D02E1BC5-7BBC-4931-8E24-72FA101FA24B.svs dd4d3eb598178e53068eb14b7ebbba91 1209746895 live 57 | 8394 a6d06d04-7952-4235-9a5c-dc0c002b95bb TCGA-WC-A87Y-01Z-00-DX1.7B4CB33C-5D8F-4477-90F5-80F7402A6D7C.svs 3b03fd423d62538a81fe4c5a4a31623f 1150336151 live 58 | 8395 731b3aaf-9213-4b9b-9728-491c3dbd3c05 TCGA-VD-A8KO-01Z-00-DX1.E35420FA-00A5-4954-8DE2-861359A01667.svs 226e06440f90931fa38bb8d2441b2de1 549136944 live 59 | 8396 7867d4ce-b245-4e5f-9672-d08ffd9e95b8 TCGA-WC-AA9E-01Z-00-DX1.356F1D8F-8FE4-436A-A0D6-2CDF5AE097BE.svs e0d3dd6a5f74fab10833de0ad838299c 1203644769 live 60 | 8397 3dba57d6-9da5-4809-a8bb-89b942f4366e TCGA-V4-A9F2-01Z-00-DX1.59FA5015-785F-4715-9CA6-C2C7C1299CC6.svs 84a71a0a2ee9ace82aefeabe5177d976 913496207 live 61 | 9357 8d700716-a15c-42e0-9070-4f16feb95405 TCGA-YZ-A983-01Z-00-DX1.63D28F02-8496-467E-9A00-A16431335342.svs 685f13f52993ee1d7d5bf5784e76609c 1331362568 live 62 | 9358 6196d9dd-f2de-4c55-8604-7ac93f5c6986 TCGA-YZ-A984-01Z-00-DX1.3355DCC6-95E4-4B92-AA9D-732D363F2543.svs 0b4fa43b5f4e995404c8ba49fa464c00 1540409238 live 63 | 9359 6ce93c10-91c0-45da-b493-a25f836452c0 TCGA-V3-A9ZY-01Z-00-DX1.4A7D770A-0F63-453C-A7F9-966F8EE9D64F.svs 932fc022bcd0c38a58e58d165f23f9a9 305240966 live 64 | 9360 c1dc8aa8-7f8c-4d8a-a967-44e21e29d106 TCGA-V4-A9ET-01Z-00-DX1.D9386E86-5C0A-4C0B-BF30-CA87A2BE9AB3.svs 9afe76d77c9a5cf7d64d396c06788345 1204890363 live 65 | 9361 78d3d05e-e8f8-4f5a-8c3b-cb38d82f5f65 TCGA-V4-A9E8-01Z-00-DX1.425016C7-FDCA-4AC5-AEE3-7ACB3B4CBD61.svs b923a4273e27cf8345363637d0c38ec8 1445169799 live 66 | 9362 f6ee2383-c960-4d75-a64f-8589608299f3 TCGA-V4-A9EF-01Z-00-DX1.3084FABF-8AC4-403A-ADD7-64CFB34CCB95.svs 1383cf5e40d8c7befda1787f99b7c4ec 1733207091 live 67 | 9363 565e9f6b-811e-4b81-b035-80ba5c93f827 TCGA-WC-A880-01Z-00-DX1.23412607-4382-4D0D-9CD6-8A2C4BE4FA2E.svs 7527245c6705151f16520ef9b6cfef4f 1262645005 live 68 | 9364 bbcdf959-653d-472c-8bb1-2b04a4caa406 TCGA-V4-A9EC-01Z-00-DX1.5730E636-95F2-4665-BC43-0746B2C05595.svs 5d95d0465b8519cec5e8298a598a1908 1607512745 live 69 | 9365 3c1f6767-3db7-4abf-a7e0-91e932f8d60c TCGA-WC-A87W-01Z-00-DX1.F1119669-4C30-4FAE-8BF2-432E8037268B.svs cde2b6073a127dffd524f552a09e8116 993515137 live 70 | 9366 843a35a5-a2ee-4ef4-8c14-dd8ec26b5ce0 TCGA-WC-A87U-01Z-00-DX1.C172A901-BFAB-4455-9367-D599B1C1EFCD.svs 83dfecae603b549ac1a3375c31184248 1123481355 live 71 | 9367 c0e806bc-09cc-49e3-bc25-b181598f1c12 TCGA-RZ-AB0B-01Z-00-DX1.0DF1A3A6-3030-4988-AC2C-CAA0F2EBAEB2.svs b96f37150ec5f103d442b8f5db0b90e7 1196105461 live 72 | 9368 c9c10748-3244-4140-9a3e-090341dc397a TCGA-VD-A8KF-01Z-00-DX1.1A4B266E-463A-4E66-A6B2-DE78441972A8.svs 0001b06485d4295998c70540d7704e9f 345133368 live 73 | 9369 3effd086-ec54-4405-9de1-c2a2d64d960a TCGA-YZ-A985-01Z-00-DX1.CA3BB3E0-1C23-4312-87EA-3EE2F3F33770.svs b68e84197206b11f6375e412a41e20b6 742090676 live 74 | 9370 6214addb-efa3-447f-b436-09d5020189f4 TCGA-WC-A88A-01Z-00-DX1.6010AB59-DE5A-4119-8A9E-D582BD63D02B.svs 924d9d59309efa1d58380ece2e83c6c6 1293972019 live 75 | 9371 b27105c9-d44b-49ed-990a-7e4c5f6ac5cf TCGA-V4-A9EU-01Z-00-DX1.4BFDB2BE-471D-4151-8854-03462D335F94.svs 0782e5cc30419a162258e0aacf688c5d 908240843 live 76 | 10738 0d111251-c559-4a76-ab85-3eae5606627a TCGA-VD-A8K7-01Z-00-DX1.67A55BCD-F1B3-4D33-875A-082BBC055EE3.svs a8e3286eaaa924748157c0d31a995e6d 541177836 live 77 | 10814 80a79a32-11d4-4437-8175-57bb937219fb TCGA-VD-A8K9-01Z-00-DX1.2694845F-57E3-41BE-AEA4-FB2152432823.svs e22667648bb20a8b4c920c2f84f0ddd7 387033338 live 78 | 10817 1fc80dba-274d-49db-83a7-fd8cb62c2a92 TCGA-VD-A8KE-01Z-00-DX1.E1611C2F-76E9-48E3-BADF-FA5FAA613746.svs 7f91052ddae4280fab42fc6ceaa355e5 410702530 live 79 | 10819 bb505a94-f294-4130-8d58-f0b6205a0ae8 TCGA-VD-A8KB-01Z-00-DX1.F581FF22-C343-4DFF-8328-8F17927C72AA.svs d34a64f8a2a6e717f5d47c1275eb0913 233681848 live 80 | 10824 512ca6bc-790b-4ca2-8d2d-87aae93d7bfe TCGA-VD-AA8R-01Z-00-DX1.B2072EA5-0AF2-433C-B5F2-81125ACE37C2.svs e42aee6ebe93f34891bb87f0654e21b9 399046620 live 81 | 11845 3c7cce9a-eccc-44d7-b324-9da38db3baa5 TCGA-VD-A8K8-01Z-00-DX1.31C5F45C-FC14-4823-978B-9D81E3D4FB7C.svs e7ed75586ca40c1ecb34b7d201c97c57 667849718 live 82 | -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- 1 | """ 2 | HE2RNA: Train a model to predict gene expression on TCGA slides, either on a single train/valid/test split or in cross-validation 3 | Copyright (C) 2020 Owkin Inc. 4 | 5 | This program is free software: you can redistribute it and/or modify 6 | it under the terms of the GNU General Public License as published by 7 | the Free Software Foundation, either version 3 of the License, or 8 | (at your option) any later version. 9 | 10 | This program is distributed in the hope that it will be useful, 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 | GNU General Public License for more details. 14 | 15 | You should have received a copy of the GNU General Public License 16 | along with this program. If not, see . 17 | """ 18 | 19 | import os 20 | import configparser 21 | import argparse 22 | import pickle as pkl 23 | import pandas as pd 24 | import numpy as np 25 | import copy as cp 26 | import torch 27 | from torch import nn 28 | from torch.utils.data import Subset, DataLoader 29 | from torch import optim 30 | from sklearn.metrics import roc_auc_score 31 | from transcriptome_data import TranscriptomeDataset 32 | from wsi_data import load_labels, AggregatedDataset, TCGAFolder, \ 33 | H5Dataset, patient_split, match_patient_split, \ 34 | patient_kfold, match_patient_kfold 35 | from model import HE2RNA, fit, predict 36 | from utils import compute_metrics 37 | 38 | 39 | class Experiment(object): 40 | """An class that uses a config file to setup and run a gene expression 41 | prediction experiment. 42 | 43 | Args: 44 | configfile (str): Path to the configuration file. 45 | """ 46 | 47 | def __init__(self, 48 | configfile='config.ini'): 49 | 50 | # Read configuration file 51 | self.config = configparser.ConfigParser() 52 | self.config.read(configfile) 53 | 54 | assert 'main' in self.config.sections(), \ 55 | "No 'main' section in config file" 56 | 57 | if 'path' in self.config['main'].keys(): 58 | self.savedir = self.config['main']['path'] 59 | if not os.path.exists(self.savedir): 60 | os.mkdir(self.savedir) 61 | else: 62 | self.savedir = '.' 63 | 64 | if 'use_saved_model' in self.config['main'].keys(): 65 | self.use_saved_model = self.config['main']['use_saved_model'] 66 | else: 67 | self.use_saved_model = False 68 | 69 | if 'single_split' in self.config['main'].keys(): 70 | self.split = pkl.load(open(self.config['main']['single_split'], 'rb')) 71 | else: 72 | self.split = None 73 | if 'splits' in self.config['main'].keys(): 74 | self.splits = pkl.load(open(self.config['main']['splits'], 'rb')) 75 | else: 76 | self.splits = None 77 | 78 | if 'subsample' in self.config['main'].keys(): 79 | self.subsample = float(self.config['main']['subsample']) 80 | else: 81 | self.subsample = None 82 | 83 | if 'p_value' in self.config['main'].keys(): 84 | self.p_value = self.config['main']['p_value'] 85 | else: 86 | self.p_value = 't_test' 87 | assert self.p_value in ['empirical', 't_test'], \ 88 | "Unrecognized test, should be 'empirical' or 't_test'" 89 | 90 | def _read_architecture(self): 91 | model_params = {} 92 | if 'architecture' in self.config.sections(): 93 | dic = self.config['architecture'] 94 | if 'layers' in dic.keys(): 95 | layers = dic['layers'].split(',') 96 | model_params['layers'] = [int(dim) for dim in layers] 97 | if 'dropout' in dic.keys(): 98 | model_params['dropout'] = float(dic['dropout']) 99 | if 'ks' in dic.keys(): 100 | ks = dic['ks'].split(',') 101 | model_params['ks'] = [int(k) for k in ks] 102 | if 'nonlin' in dic.keys(): 103 | if dic['nonlin'] == 'relu': 104 | model_params['nonlin'] = nn.ReLU() 105 | elif dic['nonlin'] == 'tanh': 106 | model_params['nonlin'] = nn.Tanh() 107 | elif dic['nonlin'] == 'sigmoid': 108 | model_params['nonlin'] = nn.Sigmoid() 109 | if 'device' in dic.keys(): 110 | model_params['device'] = dic['device'] 111 | 112 | return model_params 113 | 114 | def _read_training_params(self): 115 | 116 | training_params = {} 117 | if 'training' in self.config.sections(): 118 | dic = self.config['training'] 119 | if 'max_epochs' in dic.keys(): 120 | training_params['max_epochs'] = int(dic['max_epochs']) 121 | if 'patience' in dic.keys(): 122 | training_params['patience'] = int(dic['patience']) 123 | if 'batch_size' in dic.keys(): 124 | training_params['batch_size'] = int(dic['batch_size']) 125 | if 'num_workers' in dic.keys(): 126 | training_params['num_workers'] = int(dic['num_workers']) 127 | 128 | return training_params 129 | 130 | def _setup_optimization(self, model): 131 | 132 | if 'optimization' in self.config.sections(): 133 | dic = self.config['optimization'] 134 | optim_params = {'params': model.parameters(), 135 | 'lr': float(dic['lr'])} 136 | if 'momentum' in self.config['optimization'].keys(): 137 | optim_params['momentum'] = float(dic['momentum']) 138 | optim_params['nesterov'] = True 139 | if 'weight_decay' in self.config['optimization'].keys(): 140 | optim_params['weight_decay'] = float(dic['weight_decay']) 141 | 142 | if dic['optimizer'] == 'sgd': 143 | return optim.SGD(**optim_params) 144 | elif dic['optimizer'] == 'adam': 145 | return optim.Adam(**optim_params) 146 | 147 | else: 148 | return optim.Adam(lr=1e-3) 149 | 150 | def _build_dataset(self): 151 | 152 | assert 'data' in self.config.sections(), \ 153 | "'data' not found in config file" 154 | dic = self.config['data'] 155 | 156 | if 'genes' in dic.keys(): 157 | genes = dic['genes'] 158 | if os.path.exists(genes): 159 | genes = pkl.load( 160 | open(genes, 'rb')) 161 | else: 162 | genes = genes.split(',') 163 | for gene in genes: 164 | assert gene.startswith('ENSG'), "Unknown gene format" 165 | else: 166 | genes = None 167 | 168 | if 'path_to_transcriptome' in dic.keys() and 'projectname' in dic.keys(): 169 | projectname = dic['projectname'].split(',') 170 | transcriptome_data = TranscriptomeDataset.from_saved_file( 171 | dic['path_to_transcriptome'], projectname=projectname, genes=genes) 172 | elif 'path_to_transcriptome' in dic.keys(): 173 | transcriptome_data = TranscriptomeDataset.from_saved_file( 174 | dic['path_to_transcriptome'], genes=genes) 175 | elif 'projectname' in dic.keys(): 176 | projectname = dic['projectname'].split(',') 177 | transcriptome_data = TranscriptomeDataset(projectname, genes) 178 | transcriptome_data.load_transcriptomes() 179 | else: 180 | transcriptome_data = TranscriptomeDataset(None, genes) 181 | transcriptome_data.load_transcriptomes() 182 | 183 | if 'path_to_data' in dic.keys(): 184 | 185 | if dic['path_to_data'].endswith('.pkl'): 186 | X = pkl.load(open(dic['path_to_data'], 'rb')) 187 | y, genes, patients, projects = load_labels(transcriptome_data) 188 | dataset = AggregatedDataset( 189 | genes, patients, projects, 190 | torch.Tensor(X), torch.Tensor(y)) 191 | elif dic['path_to_data'].endswith('.h5'): 192 | y, genes, patients, projects = load_labels(transcriptome_data) 193 | dataset = H5Dataset( 194 | genes, patients, projects, dic['path_to_data'], y) 195 | 196 | else: 197 | dataset = TCGAFolder.match_transcriptome_data( 198 | transcriptome_data) 199 | 200 | return dataset 201 | 202 | def single_run(self, random_state=0, logdir='./exp'): 203 | """Experiment with a single train/test split. 204 | 205 | Args: 206 | random_state (int): Random seed used for splitting the data. 207 | logdir (str): Path for TensoboardX. 208 | 209 | Returns: 210 | pandas DataFrame: The metrics per gene. 211 | """ 212 | 213 | model_params = self._read_architecture() 214 | training_params = self._read_training_params() 215 | dataset = self._build_dataset() 216 | evalset = self._build_dataset() 217 | if dataset.dim == 2051: # Remove tile levels and coordinates 218 | model_params['input_dim'] = dataset.dim - 3 219 | else: 220 | model_params['input_dim'] = dataset.dim 221 | model_params['output_dim'] = len(dataset.genes) 222 | 223 | if self.split is None: 224 | train_idx, valid_idx, test_idx = patient_split(dataset, random_state) 225 | else: 226 | train_idx, valid_idx, test_idx = match_patient_split(dataset, self.split) 227 | 228 | train_set = Subset(dataset, train_idx) 229 | valid_set = Subset(evalset, valid_idx) 230 | test_set = Subset(evalset, test_idx) 231 | 232 | dic = {} 233 | for project in dataset.projects.unique(): 234 | if project in ['TCGA-LUAD', 'TCGA-LUSC', 'TCGA_LUAD', 'TCGA_LUSC']: 235 | dic[project] = 'TCGA-LUNG' 236 | elif project in ['TCGA-KICH', 'TCGA-KIRC', 'TCGA-KIRP', 'TCGA_KICH', 'TCGA_KIRC', 'TCGA_KIRP']: 237 | dic[project] = 'TCGA-KIDN' 238 | elif project in ['TCGA-UCS', 'TCGA-UCEC']: 239 | dic[project] = 'TCGA-UTER' 240 | else: 241 | dic[project] = project 242 | dataset.projects = dataset.projects.map(dic) 243 | 244 | valid_projects = dataset.projects[valid_idx] 245 | valid_projects = valid_projects.astype( 246 | 'category').cat.codes.values.astype('int64') 247 | test_projects = dataset.projects[test_idx].apply( 248 | lambda x: x.replace('_', '-')).values 249 | 250 | if self.use_saved_model: 251 | model = torch.load(os.path.join( 252 | self.use_saved_model, 253 | 'model.pt')) 254 | if 'ks' in model_params.keys(): 255 | model.ks = model_params['ks'] 256 | if 'top_k' in model_params.keys(): 257 | model.top_k = model_params['top_k'] 258 | if 'bottom_ks' in model_params.keys(): 259 | model.bottom_ks = model_params['bottom_ks'] 260 | if 'dropout' in model_params.keys(): 261 | model.do.p = model_params['dropout'] 262 | 263 | else: 264 | # Initialize bias of the last layer with the average target value on the train set 265 | try: 266 | model_params['bias_init'] = torch.nn.Parameter( 267 | torch.Tensor( 268 | np.mean( 269 | [sample[1] for sample in train_set], axis=0) 270 | ).cuda()) 271 | except ValueError: 272 | model_params['bias_init'] = torch.nn.Parameter( 273 | torch.Tensor( 274 | np.mean( 275 | [sample[1].numpy() for sample in train_set], axis=0) 276 | ).cuda()) 277 | model = HE2RNA(**model_params) 278 | optimizer = self._setup_optimization(model) 279 | 280 | preds, labels = fit(model, 281 | train_set, 282 | valid_set, 283 | valid_projects, 284 | test_set=test_set, 285 | params=training_params, 286 | optimizer=optimizer, 287 | logdir=logdir, 288 | path=self.savedir) 289 | 290 | report = {'gene': list(dataset.genes)} 291 | 292 | for project in np.unique(test_projects): 293 | pred = preds[test_projects == project] 294 | label = labels[test_projects == project] 295 | report['correlation_' + project] = compute_metrics( 296 | label, pred) 297 | 298 | report = pd.DataFrame(report) 299 | report.to_csv(os.path.join(self.savedir, 'results_single_split.csv'), index=False) 300 | return report 301 | 302 | def cross_validation(self, n_folds=5, random_state=0, logdir='exp'): 303 | """N-fold cross-validation. 304 | 305 | Args: 306 | n (int): Number of folds 307 | random_state (int): Random seed used for splitting the data. 308 | logdir (str): Path for TensoboardX. 309 | 310 | Returns: 311 | pandas DataFrame: The metrics per gene and per fold. 312 | """ 313 | 314 | model_params = self._read_architecture() 315 | training_params = self._read_training_params() 316 | dataset = self._build_dataset() 317 | evalset = self._build_dataset() 318 | if dataset.dim == 2051: # Remove tile levels and coordinates 319 | model_params['input_dim'] = dataset.dim - 3 320 | else: 321 | model_params['input_dim'] = dataset.dim 322 | model_params['output_dim'] = len(dataset.genes) 323 | 324 | if self.subsample is not None: 325 | np.random.seed(random_state) 326 | ind = np.random.permutation(len(dataset))[:int(self.subsample * len(dataset))] 327 | genes = dataset.genes 328 | patients = dataset.patients[ind] 329 | projects = dataset.projects[ind].reset_index(drop=True) 330 | dataset = Subset(dataset, ind) 331 | dataset.genes = genes 332 | dataset.patients = patients 333 | dataset.projects = projects 334 | 335 | if self.splits is None: 336 | if 'patience' in training_params.keys(): 337 | train_idx, valid_idx, test_idx = patient_kfold( 338 | dataset, n_splits=n_folds, valid_size=0.1, 339 | random_state=random_state) 340 | else: 341 | train_idx, valid_idx, test_idx = patient_kfold( 342 | dataset, n_splits=n_folds, valid_size=0, 343 | random_state=random_state) 344 | else: 345 | train_patients, valid_patients, test_patients = self.splits 346 | splits = zip(train_patients, valid_patients, test_patients) 347 | train_idx, valid_idx, test_idx = match_patient_kfold(dataset, splits) 348 | 349 | dic = {} 350 | for project in dataset.projects.unique(): 351 | if project in ['TCGA-LUAD', 'TCGA-LUSC', 'TCGA_LUAD', 'TCGA_LUSC']: 352 | dic[project] = 'TCGA-LUNG' 353 | elif project in ['TCGA-KICH', 'TCGA-KIRC', 'TCGA-KIRP', 'TCGA_KICH', 'TCGA_KIRC', 'TCGA_KIRP']: 354 | dic[project] = 'TCGA-KIDN' 355 | elif project in ['TCGA-UCS', 'TCGA-UCEC']: 356 | dic[project] = 'TCGA-UTER' 357 | else: 358 | dic[project] = project 359 | dataset.projects = dataset.projects.map(dic) 360 | 361 | report = {'gene': list(dataset.genes)} 362 | if self.p_value == 'empirical': 363 | random = {'gene': list(dataset.genes)} 364 | else: 365 | n_samples = {project: [] for project in dataset.projects} 366 | 367 | for k in range(n_folds): 368 | 369 | train_set = Subset(dataset, train_idx[k]) 370 | test_set = Subset(evalset, test_idx[k]) 371 | if len(valid_idx) > 0: 372 | valid_set = Subset(evalset, valid_idx[k]) 373 | valid_projects = dataset.projects[valid_idx[k]] 374 | valid_projects = valid_projects.astype( 375 | 'category').cat.codes.values.astype('int64') 376 | else: 377 | valid_set = None 378 | valid_projects = None 379 | 380 | test_projects = dataset.projects[test_idx[k]].apply( 381 | lambda x: x.replace('_', '-')).values 382 | 383 | # Initialize the model and define optimizer 384 | if self.use_saved_model: 385 | model = torch.load(os.path.join( 386 | self.use_saved_model, 387 | 'model_' + str(k), 388 | 'model.pt')) 389 | if 'ks' in model_params.keys(): 390 | model.ks = model_params['ks'] 391 | if 'top_k' in model_params.keys(): 392 | model.top_k = model_params['top_k'] 393 | if 'bottom_ks' in model_params.keys(): 394 | model.bottom_ks = model_params['bottom_ks'] 395 | if 'dropout' in model_params.keys(): 396 | model.do.p = model_params['dropout'] 397 | 398 | else: 399 | # Initialize bias of the last layer with the average target value on the train set 400 | try: 401 | model_params['bias_init'] = torch.nn.Parameter( 402 | torch.Tensor( 403 | np.mean( 404 | [sample[1] for sample in train_set], axis=0) 405 | ).cuda()) 406 | except ValueError: 407 | model_params['bias_init'] = torch.nn.Parameter( 408 | torch.Tensor( 409 | np.mean( 410 | [sample[1].numpy() for sample in train_set], axis=0) 411 | ).cuda()) 412 | model = HE2RNA(**model_params) 413 | optimizer = self._setup_optimization(model) 414 | 415 | # Train model 416 | preds, labels = fit(model, 417 | train_set, 418 | valid_set, 419 | valid_projects, 420 | test_set=test_set, 421 | params=training_params, 422 | optimizer=optimizer, 423 | logdir=logdir, 424 | path=os.path.join( 425 | self.savedir, 426 | 'model_' + str(k))) 427 | 428 | # Compute metrics for each fold 429 | for project in np.unique(test_projects): 430 | pred = preds[test_projects == project] 431 | label = labels[test_projects == project] 432 | report['correlation_' + project + '_fold_' + str(k)] = compute_metrics( 433 | label, pred) 434 | 435 | report = pd.DataFrame(report) 436 | report.to_csv(os.path.join(self.savedir, 'results_per_fold.csv'), index=False) 437 | 438 | return report 439 | 440 | 441 | def main(): 442 | parser = argparse.ArgumentParser() 443 | parser.add_argument("--config", help="path to the configuration file") 444 | parser.add_argument( 445 | "--run", help="type of experiment, 'single_run' or 'cross_validation'", 446 | default='single_run') 447 | parser.add_argument( 448 | "--n_folds", help="number of folds for 'cross_validation'", 449 | default=5) 450 | parser.add_argument( 451 | "--logdir", help="path to the directory used by TensoboardX", 452 | default='./exp') 453 | parser.add_argument( 454 | "--rs", help="random state", 455 | default=0) 456 | args = parser.parse_args() 457 | print("Using configuration defined in {}".format(args.config)) 458 | for config in args.config.split(','): 459 | exp = Experiment(config) 460 | 461 | assert args.run in ['single_run', 'cross_validation'], \ 462 | "Unrecognized experiment, must be either 'single_run' or 'cross_validation" 463 | if args.run == 'single_run': 464 | report = exp.single_run(logdir=args.logdir) 465 | elif args.run == 'cross_validation': 466 | report = exp.cross_validation( 467 | n_folds=int(args.n_folds), 468 | random_state=int(args.rs), logdir=args.logdir) 469 | print(report) 470 | 471 | 472 | if __name__ == '__main__': 473 | 474 | main() 475 | -------------------------------------------------------------------------------- /model.py: -------------------------------------------------------------------------------- 1 | """ 2 | HE2RNA: definition of the algorithm to generate a model for gene expression prediction 3 | Copyright (C) 2020 Owkin Inc. 4 | 5 | This program is free software: you can redistribute it and/or modify 6 | it under the terms of the GNU General Public License as published by 7 | the Free Software Foundation, either version 3 of the License, or 8 | (at your option) any later version. 9 | 10 | This program is distributed in the hope that it will be useful, 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 | GNU General Public License for more details. 14 | 15 | You should have received a copy of the GNU General Public License 16 | along with this program. If not, see . 17 | """ 18 | 19 | import numpy as np 20 | import torch 21 | import time 22 | import os 23 | from torch import nn 24 | from torch.utils.data import DataLoader 25 | from tensorboardX import SummaryWriter 26 | from tqdm import tqdm 27 | 28 | 29 | class HE2RNA(nn.Module): 30 | """Model that generates one score per tile and per predicted gene. 31 | 32 | Args 33 | output_dim (int): Output dimension, must match the number of genes to 34 | predict. 35 | layers (list): List of the layers' dimensions 36 | nonlin (torch.nn.modules.activation) 37 | ks (list): list of numbers of highest-scored tiles to keep in each 38 | channel. 39 | dropout (float) 40 | device (str): 'cpu' or 'cuda' 41 | mode (str): 'binary' or 'regression' 42 | """ 43 | def __init__(self, input_dim, output_dim, 44 | layers=[1], nonlin=nn.ReLU(), ks=[10], 45 | dropout=0.5, device='cpu', 46 | bias_init=None, **kwargs): 47 | super(HE2RNA, self).__init__() 48 | 49 | self.input_dim = input_dim 50 | self.output_dim = output_dim 51 | 52 | layers = [input_dim] + layers + [output_dim] 53 | self.layers = [] 54 | for i in range(len(layers) - 1): 55 | layer = nn.Conv1d(in_channels=layers[i], 56 | out_channels=layers[i+1], 57 | kernel_size=1, 58 | stride=1, 59 | bias=True) 60 | setattr(self, 'conv' + str(i), layer) 61 | self.layers.append(layer) 62 | if bias_init is not None: 63 | self.layers[-1].bias = bias_init 64 | self.ks = np.array(ks) 65 | 66 | self.nonlin = nonlin 67 | self.do = nn.Dropout(dropout) 68 | self.device = device 69 | self.to(self.device) 70 | 71 | def forward(self, x): 72 | if self.training: 73 | k = int(np.random.choice(self.ks)) 74 | return self.forward_fixed_k(x, k) 75 | else: 76 | pred = 0 77 | for k in self.ks: 78 | pred += self.forward_fixed_k(x, int(k)) / len(self.ks) 79 | return pred 80 | 81 | def forward_fixed_k(self, x, k): 82 | mask, _ = torch.max(x, dim=1, keepdim=True) 83 | mask = (mask > 0).float() 84 | x = self.conv(x) * mask 85 | t, _ = torch.topk(x, k, dim=2, largest=True, sorted=True) 86 | x = torch.sum(t * mask[:, :, :k], dim=2) / torch.sum(mask[:, :, :k], dim=2) 87 | return x 88 | 89 | def conv(self, x): 90 | x = x[:, x.shape[1] - self.input_dim:] 91 | for i in range(len(self.layers) - 1): 92 | x = self.do(self.nonlin(self.layers[i](x))) 93 | x = self.layers[-1](x) 94 | return x 95 | 96 | 97 | def training_epoch(model, dataloader, optimizer): 98 | """Train model for one epoch. 99 | """ 100 | model.train() 101 | loss_fn = nn.MSELoss() 102 | train_loss = [] 103 | for x, y in tqdm(dataloader): 104 | x = x.float().to(model.device) 105 | y = y.float().to(model.device) 106 | pred = model(x) 107 | loss = loss_fn(pred, y) 108 | train_loss += [loss.detach().cpu().numpy()] 109 | optimizer.zero_grad() 110 | loss.backward() 111 | optimizer.step() 112 | train_loss = np.mean(train_loss) 113 | return train_loss 114 | 115 | def compute_correlations(labels, preds, projects): 116 | metrics = [] 117 | for project in np.unique(projects): 118 | for i in range(labels.shape[1]): 119 | y_true = labels[projects == project, i] 120 | if len(np.unique(y_true)) > 1: 121 | y_prob = preds[projects == project, i] 122 | metrics.append(np.corrcoef(y_true, y_prob)[0, 1]) 123 | metrics = np.asarray(metrics) 124 | return np.mean(metrics) 125 | 126 | 127 | def evaluate(model, dataloader, projects): 128 | """Evaluate the model on the validation set and return loss and metrics. 129 | """ 130 | model.eval() 131 | loss_fn = nn.MSELoss() 132 | valid_loss = [] 133 | preds = [] 134 | labels = [] 135 | for x, y in dataloader: 136 | pred = model(x.float().to(model.device)) 137 | labels += [y] 138 | loss = loss_fn(pred, y.float().to(model.device)) 139 | valid_loss += [loss.detach().cpu().numpy()] 140 | pred = nn.ReLU()(pred) 141 | preds += [pred.detach().cpu().numpy()] 142 | valid_loss = np.mean(valid_loss) 143 | preds = np.concatenate(preds) 144 | labels = np.concatenate(labels) 145 | metrics = compute_correlations(labels, preds, projects) 146 | return valid_loss, metrics 147 | 148 | 149 | def predict(model, dataloader): 150 | """Perform prediction on the test set. 151 | """ 152 | model.eval() 153 | labels = [] 154 | preds = [] 155 | for x, y in dataloader: 156 | pred = model(x.float().to(model.device)) 157 | labels += [y] 158 | pred = nn.ReLU()(pred) 159 | preds += [pred.detach().cpu().numpy()] 160 | preds = np.concatenate(preds) 161 | labels = np.concatenate(labels) 162 | return preds, labels 163 | 164 | 165 | def fit(model, 166 | train_set, 167 | valid_set, 168 | valid_projects, 169 | params={}, 170 | optimizer=None, 171 | test_set=None, 172 | path=None, 173 | logdir='./exp'): 174 | """Fit the model and make prediction on evaluation set. 175 | 176 | Args: 177 | model (nn.Module) 178 | train_set (torch.utils.data.Dataset) 179 | valid_set (torch.utils.data.Dataset) 180 | valid_projects (np.array): list of integers encoding the projects 181 | validation samples belong to. 182 | params (dict): Dictionary for specifying training parameters. 183 | keys are 'max_epochs' (int, default=200), 'patience' (int, 184 | default=20) and 'batch_size' (int, default=16). 185 | optimizer (torch.optim.Optimizer): Optimizer for training the model 186 | test_set (None or torch.utils.data.Dataset): If None, return 187 | predictions on the validation set. 188 | path (str): Path to the folder where th model will be saved. 189 | logdir (str): Path for TensoboardX. 190 | """ 191 | 192 | if path is not None and not os.path.exists(path): 193 | os.mkdir(path) 194 | 195 | default_params = { 196 | 'max_epochs': 200, 197 | 'patience': 20, 198 | 'batch_size': 16, 199 | 'num_workers': 0} 200 | default_params.update(params) 201 | batch_size = default_params['batch_size'] 202 | patience = default_params['patience'] 203 | max_epochs = default_params['max_epochs'] 204 | num_workers = default_params['num_workers'] 205 | 206 | writer = SummaryWriter(log_dir=logdir) 207 | 208 | # SET num_workers TO 0 WHEN WORKING WITH hdf5 FILES 209 | train_loader = DataLoader( 210 | train_set, batch_size=batch_size, shuffle=True, num_workers=num_workers) 211 | 212 | if valid_set is not None: 213 | valid_loader = DataLoader( 214 | valid_set, batch_size=batch_size, shuffle=False, num_workers=num_workers) 215 | 216 | if test_set is not None: 217 | test_loader = DataLoader( 218 | test_set, batch_size=batch_size, shuffle=False, num_workers=num_workers) 219 | 220 | if optimizer is None: 221 | optimizer = torch.optim.Adam(list(model.parameters()), lr=1e-3, 222 | weight_decay=0.) 223 | 224 | metrics = 'correlations' 225 | epoch_since_best = 0 226 | start_time = time.time() 227 | 228 | if valid_set is not None: 229 | valid_loss, best = evaluate( 230 | model, valid_loader, valid_projects) 231 | print('{}: {:.3f}'.format(metrics, best)) 232 | if np.isnan(best): 233 | best = 0 234 | if test_set is not None: 235 | preds, labels = predict(model, test_loader) 236 | else: 237 | preds, labels = predict(model, valid_loader) 238 | 239 | try: 240 | 241 | for e in range(max_epochs): 242 | 243 | epoch_since_best += 1 244 | 245 | train_loss = training_epoch(model, train_loader, optimizer) 246 | dic_loss = {'train_loss': train_loss} 247 | 248 | print('Epoch {}/{} - {:.2f}s'.format( 249 | e + 1, 250 | max_epochs, 251 | time.time() - start_time)) 252 | start_time = time.time() 253 | 254 | if valid_set is not None: 255 | valid_loss, scores = evaluate( 256 | model, valid_loader, valid_projects) 257 | dic_loss['valid_loss'] = valid_loss 258 | score = np.mean(scores) 259 | writer.add_scalars('data/losses', 260 | dic_loss, 261 | e) 262 | writer.add_scalar('data/metrics', score, e) 263 | print('loss: {:.4f}, val loss: {:.4f}'.format( 264 | train_loss, 265 | valid_loss)) 266 | print('{}: {:.3f}'.format(metrics, score)) 267 | else: 268 | writer.add_scalars('data/losses', 269 | dic_loss, 270 | e) 271 | print('loss: {:.4f}'.format(train_loss)) 272 | 273 | if valid_set is not None: 274 | criterion = (score > best) 275 | 276 | if criterion: 277 | epoch_since_best = 0 278 | best = score 279 | if path is not None: 280 | torch.save(model, os.path.join(path, 'model.pt')) 281 | elif test_set is not None: 282 | preds, labels = predict(model, test_loader) 283 | else: 284 | preds, labels = predict(model, valid_loader) 285 | 286 | if epoch_since_best == patience: 287 | print('Early stopping at epoch {}'.format(e + 1)) 288 | break 289 | 290 | except KeyboardInterrupt: 291 | pass 292 | 293 | if path is not None and os.path.exists(os.path.join(path, 'model.pt')): 294 | model = torch.load(os.path.join(path, 'model.pt')) 295 | 296 | elif path is not None: 297 | torch.save(model, os.path.join(path, 'model.pt')) 298 | 299 | if test_set is not None: 300 | preds, labels = predict(model, test_loader) 301 | elif valid_set is not None: 302 | preds, labels = predict(model, valid_loader) 303 | else: 304 | preds = None 305 | labels = None 306 | 307 | writer.close() 308 | 309 | return preds, labels 310 | -------------------------------------------------------------------------------- /patient_splits.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/owkin/HE2RNA_code/d47f481fbcaab41a49635e4a35e810bf30eae0e0/patient_splits.pkl -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | cffi==1.14.0 2 | colorcorrect==0.9 3 | cryptography==2.8 4 | Cython==0.29.14 5 | decorator==4.3.0 6 | -e git+https://github.com/NCI-GDC/gdc-client.git@1c69ed0c2bfa3c6b3784bca1ab6feaed7a81f6cb#egg=gdc_client 7 | h5py==2.9.0 8 | intervaltree==3.0.2 9 | ipykernel==5.0.0 10 | ipython==7.0.1 11 | ipython-genutils==0.2.0 12 | ipywidgets==7.4.2 13 | joblib==0.15.1 14 | jsonschema==2.6.0 15 | jupyter==1.0.0 16 | jupyter-client==5.2.3 17 | jupyter-console==5.2.0 18 | jupyter-contrib-core==0.3.3 19 | jupyter-contrib-nbextensions==0.5.0 20 | jupyter-core==4.4.0 21 | jupyter-highlight-selected-word==0.2.0 22 | jupyter-nbextensions-configurator==0.4.0 23 | Keras==2.2.4 24 | Keras-Applications==1.0.6 25 | Keras-Preprocessing==1.0.5 26 | git+https://github.com/src-d/kmcuda.git#subdirectory=src 27 | lxml==4.4.2 28 | matplotlib==3.1.1 29 | mygene==3.0.0 30 | ndg-httpsclient==0.5.0 31 | numba==0.45.1 32 | numpy==1.17.0 33 | openslide-python==1.1.1 34 | pandas==0.23.4 35 | pathlib==1.0.1 36 | Pillow==6.1.0 37 | progressbar2==3.43.1 38 | pyasn1==0.4.3 39 | pyOpenSSL==18.0.0 40 | PyYAML==3.13 41 | requests==2.22.0 42 | scikit-learn==0.21.2 43 | scipy==1.2.1 44 | seaborn==0.9.0 45 | setuptools==45.3.0 46 | statsmodels==0.9.0 47 | tables==3.5.2 48 | tensorboard==1.14.0 49 | tensorboardX==1.4 50 | tensorflow-estimator==1.14.0 51 | tensorflow-gpu==1.14.0 52 | termcolor==1.1.0 53 | torch==1.4.0 54 | torchvision==0.5.0 55 | tqdm==4.32.2 56 | -------------------------------------------------------------------------------- /spatialization.py: -------------------------------------------------------------------------------- 1 | """ 2 | HE2RNA: Extract prediction of gene expression per tile and compare to ground truth 3 | Copyright (C) 2020 Owkin Inc. 4 | 5 | This program is free software: you can redistribute it and/or modify 6 | it under the terms of the GNU General Public License as published by 7 | the Free Software Foundation, either version 3 of the License, or 8 | (at your option) any later version. 9 | 10 | This program is distributed in the hope that it will be useful, 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 | GNU General Public License for more details. 14 | 15 | You should have received a copy of the GNU General Public License 16 | along with this program. If not, see . 17 | """ 18 | 19 | import os 20 | import argparse 21 | import openslide 22 | import openslide.deepzoom 23 | import pickle as pkl 24 | import pandas as pd 25 | import numpy as np 26 | import matplotlib.pyplot as plt 27 | from matplotlib import gridspec 28 | import torch 29 | from tqdm import tqdm 30 | from torch import nn 31 | from sklearn.metrics import roc_curve, roc_auc_score 32 | from scipy.stats import pearsonr, spearmanr 33 | 34 | 35 | def compute_heatmap(path_to_model, path_to_tile_features): 36 | 37 | X_he = np.load(path_to_tile_features) 38 | coords = X_he[:, :3] 39 | 40 | all_scores = [] 41 | x = torch.Tensor(X_he[np.newaxis].transpose(1, 2, 0)) 42 | clusters = np.arange(X_he.shape[0]) 43 | 44 | # Load all models from cross_validation on TCGA 45 | models = [torch.load(f'{path_to_model}/model_' + 46 | str(k) + '/model.pt', map_location='cpu') for k in range(5)] 47 | 48 | for model in tqdm(models): 49 | all_scores.append(model.conv(x).detach().numpy()) 50 | 51 | # Average over genes and cross-val folds 52 | tile_scores = np.mean(all_scores, axis=(0, 2))[:, 0] 53 | 54 | return coords, tile_scores 55 | 56 | 57 | def display_heatmap(path_to_slide, coords, tile_scores, path=None): 58 | 59 | slide_he = openslide.OpenSlide(path_to_slide) 60 | print(f'Dimensions of the slide: {slide_he.dimensions}') 61 | 62 | fig, (ax1, ax2) = plt.subplots(1, 2, gridspec_kw={'wspace': 0, 'hspace': 0}) 63 | fig.set_size_inches((15, 10)) 64 | zoom_he = openslide.deepzoom.DeepZoomGenerator(slide_he, tile_size=224, overlap=0) 65 | im = np.array(slide_he.get_thumbnail((1000, 1000))) 66 | ax1.imshow(im) 67 | ax1.set_xticks([]) 68 | ax1.set_yticks([]) 69 | 70 | n_tiles = zoom_he.level_tiles[int(coords[0, 0])] 71 | grid = (np.array(im.shape[:2]) / n_tiles[::-1]) 72 | 73 | score = tile_scores 74 | # Clip scores to increase contrast 75 | score = np.clip(score, np.percentile(score, 10), np.percentile(score, 99)) 76 | 77 | mask = np.zeros_like(im[:, :, 0]).astype(float) 78 | for s, coord in zip(score, coords): 79 | x = int((coord[2] + 6)) 80 | y = int((coord[1] + 3)) 81 | mask[int(x * grid[0]): int((x + 1) * grid[0]), 82 | int(y * grid[0]): int((y + 1) * grid[0])] = s 83 | ims = ax2.imshow(mask, cmap='inferno') 84 | ax2.set_xticks([]) 85 | ax2.set_yticks([]) 86 | cbar = plt.colorbar(ims, ax=ax2) 87 | ims.set_clim(np.min(mask[mask > 0]), np.max(mask[mask > 0])) 88 | cbar.ax.tick_params(labelsize=16) 89 | 90 | if path is not None: 91 | plt.savefig(path) 92 | else: 93 | plt.show() 94 | plt.close() 95 | 96 | def compute_aucs_CRC(path_to_model, path_to_tiles): 97 | scores = [] 98 | cats = ['LYM', 'ADI', 'STR', 'NORM', 'TUM', 'DEB', 'MUS', 'MUC', 'BACK'] 99 | for cat in tqdm(cats): 100 | all_scores = [] 101 | X_he = np.load(os.path.join(path_to_tiles, f'{cat}.npy')) 102 | x = torch.Tensor(X_he.transpose(1, 2, 0)) 103 | clusters = np.arange(X_he.shape[0]) 104 | 105 | models = [torch.load(f'{path_to_model}/model_' + str(k) + 106 | '/model.pt', map_location='cpu') for k in range(5)] 107 | 108 | for model in models: 109 | all_scores.append(model.conv(x).detach().numpy()) 110 | 111 | all_scores = np.mean(all_scores, axis=(0, 1, 2)) 112 | scores.append(all_scores) 113 | labels = np.concatenate([np.ones_like(scores[0]), np.zeros_like(np.concatenate(scores[1:]))]) 114 | auc_lym_vs_all = roc_auc_score(labels, np.concatenate(scores)) 115 | print(f'AUC for lymphocytes vs all other classes: {auc_lym_vs_all:.4f}') 116 | dic = {} 117 | for i in range(1, 8): 118 | labels = np.concatenate([np.ones_like(scores[0]), np.zeros_like(scores[i])]) 119 | auc = roc_auc_score(labels, np.concatenate([scores[0], scores[i]])) 120 | print(f'AUC for lymphocytes vs class {cats[i]}: {auc:.4f}') 121 | dic[f'AUC LYM vs {cats[i]}'] = auc 122 | return auc_lym_vs_all, dic 123 | 124 | 125 | def post_processing(seg): 126 | seg = seg[:, :, 0] 127 | seg = (seg > 1).astype(float) 128 | return np.mean(np.clip(seg, 0, 1)) 129 | 130 | 131 | def compute_correlation_PESO(path_to_model, path_to_tiles, path_to_masks, corr='pearson'): 132 | scores = [] 133 | gts = [] 134 | files = os.listdir(path_to_tiles) 135 | ns = np.unique([file.split('_')[1] for file in files]) 136 | models = [torch.load(f'{path_to_model}/model_' + str(k) + 137 | '/model.pt', map_location='cpu') for k in range(5)] 138 | for n in tqdm(ns): 139 | 140 | X_he = np.load(os.path.join(path_to_tiles, '0.50_mpp', f'pds_{n}_HE.npy')) 141 | coords = X_he[:, :3] 142 | mask_ = openslide.OpenSlide(os.path.join(path_to_masks, f'pds_{n}_HE_training_mask.tif')) 143 | 144 | zoom_mask = openslide.deepzoom.DeepZoomGenerator(mask_, tile_size=224, overlap=0) 145 | 146 | tile_scores = [] 147 | x = torch.Tensor(X_he[np.newaxis].transpose(1, 2, 0)) 148 | clusters = np.arange(X_he.shape[0]) 149 | 150 | for model in models: 151 | tile_scores.append(model.conv(x).detach().numpy()) 152 | tile_scores = np.mean(tile_scores, axis=(0, 2, 3)) 153 | scores.append(tile_scores) 154 | 155 | gt = [] 156 | for coord in tqdm(coords): 157 | img_mask = np.array( 158 | zoom_mask.get_tile(int(coord[0]), (int(coord[1]), int(coord[2])))) 159 | ep = post_processing(img_mask) 160 | gt.append(np.mean(ep)) 161 | gt = np.array(gt) 162 | gts.append(gt) 163 | gts = np.concatenate(gts) 164 | scores = np.concatenate(scores) 165 | if corr == 'pearson': 166 | return pearsonr(gts, scores) 167 | elif corr == 'spearman': 168 | return spearmanr(gts, scores) 169 | 170 | 171 | def main(): 172 | parser = argparse.ArgumentParser() 173 | parser.add_argument("--experiment", help="dataset on which to carry spatialization experiment, CRC or PESO") 174 | parser.add_argument("--path_to_model", help="path to the folder containing the models trained by cross-validation", 175 | default='epithelium_selection') 176 | parser.add_argument("--path_to_tiles", help="path to folder containing .npy files of tile features") 177 | parser.add_argument("--path_to_masks", help="path to folder containing training masks from PESO") 178 | parser.add_argument("--corr", help="type of correlation to compute, pearson or spearman", default='pearson') 179 | args = parser.parse_args() 180 | if args.experiment == 'CRC': 181 | compute_aucs_CRC(args.path_to_model, args.path_to_tiles) 182 | elif args.experiment == 'PESO': 183 | compute_correlation_PESO(args.path_to_model, args.path_to_tiles, args.path_to_masks, args.corr) 184 | else: 185 | print("unrecognized experiment") 186 | 187 | if __name__ == '__main__': 188 | 189 | main() -------------------------------------------------------------------------------- /supertile_preprocessing.py: -------------------------------------------------------------------------------- 1 | """ 2 | HE2RNA: Apply super-tile preprocessing to ResNet features of tiles extracted from whole-slide images 3 | Copyright (C) 2020 Owkin Inc. 4 | 5 | This program is free software: you can redistribute it and/or modify 6 | it under the terms of the GNU General Public License as published by 7 | the Free Software Foundation, either version 3 of the License, or 8 | (at your option) any later version. 9 | 10 | This program is distributed in the hope that it will be useful, 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 | GNU General Public License for more details. 14 | 15 | You should have received a copy of the GNU General Public License 16 | along with this program. If not, see . 17 | """ 18 | 19 | import os 20 | import argparse 21 | import numpy as np 22 | import h5py 23 | from torch.utils.data import DataLoader 24 | from tqdm import tqdm 25 | from libKMCUDA import kmeans_cuda 26 | from wsi_data import TCGAFolder, ToTensor 27 | from transcriptome_data import TranscriptomeDataset 28 | 29 | 30 | def cluster_dataset(dataset, n_tiles=100, 31 | path_to_data='data/TCGA_slic_100.h5'): 32 | """Perform KMeans on each tiles to create 'supertiles'. Supertile 33 | features are obtained by averaging resnet features. 34 | 35 | Args 36 | dataset (torch.utils.data.Dataset) 37 | n_tiles (int): number of supertiles to generate 38 | path_to_data (str): path to hdf5 file to save the clustered dataset 39 | """ 40 | 41 | file = h5py.File(path_to_data, 'w') 42 | file.create_dataset('X', (len(dataset), n_tiles, 2051)) 43 | file.create_dataset('cluster_attribution', (len(dataset), 8000)) 44 | 45 | dataloader = DataLoader( 46 | dataset, batch_size=1, shuffle=False, num_workers=16,) 47 | 48 | n = 0 49 | 50 | for x, y in tqdm(dataloader): 51 | x = x[0].numpy().T 52 | # Remove padding 53 | mask = (x[:, 0] > 0) 54 | x = x[mask] 55 | c = x[:, :3] 56 | centroids, clusters = kmeans_cuda(x[:, 1:3].astype('float32'), 57 | min(n_tiles, x.shape[0]), 58 | yinyang_t=0, 59 | verbosity=0) 60 | new_x = [] 61 | new_c = [] 62 | for cl in np.unique(clusters): 63 | if np.sum(clusters == cl) > 0: 64 | new_x.append(np.mean(x[clusters == cl, 3:], axis=0)) 65 | new_c.append(np.mean(c[clusters == cl], axis=0)) 66 | x = np.array(new_x) 67 | c = np.array(new_c) 68 | x = np.concatenate([c, x], axis=1) 69 | if len(x) < n_tiles: 70 | x = np.concatenate([x, np.zeros((n_tiles - len(x), 2051))]) 71 | 72 | file['X'][n] = x 73 | file['cluster_attribution'][n, :len(clusters)] = clusters 74 | 75 | n += 1 76 | file.close() 77 | 78 | def main(): 79 | parser = argparse.ArgumentParser() 80 | parser.add_argument("--path_to_transcriptome", help="path to transcriptome data saved as a csv file", 81 | default='data/TCGA_transcriptome/all_transcriptomes.csv') 82 | parser.add_argument("--path_to_save_processed_data", help="path where supertile-preprocessed data should be saved", 83 | default='data/TCGA_slic_100.h5') 84 | parser.add_argument("--n_tiles", help="number of supertiles", 85 | default=100, type=int) 86 | args = parser.parse_args() 87 | rna_data = TranscriptomeDataset.from_saved_file(args.path_to_transcriptome, genes=[]) 88 | histo_data = TCGAFolder.match_transcriptome_data(rna_data) 89 | histo_data.transform = ToTensor() 90 | cluster_dataset(histo_data, n_tiles=args.n_tiles, path_to_data=args.path_to_save_processed_data) 91 | 92 | 93 | if __name__ == '__main__': 94 | 95 | main() 96 | -------------------------------------------------------------------------------- /tile_coordinates.gz: -------------------------------------------------------------------------------- 1 | version https://git-lfs.github.com/spec/v1 2 | oid sha256:b2e6e6faab43fbfc9d746dc045bccfaddc437b97acb4b46abb236c83c69e93d9 3 | size 313523653 4 | -------------------------------------------------------------------------------- /transcriptome_data.py: -------------------------------------------------------------------------------- 1 | """ 2 | HE2RNA: Match RNAseq data from TCGA with whole-slide images 3 | Copyright (C) 2020 Owkin Inc. 4 | 5 | This program is free software: you can redistribute it and/or modify 6 | it under the terms of the GNU General Public License as published by 7 | the Free Software Foundation, either version 3 of the License, or 8 | (at your option) any later version. 9 | 10 | This program is distributed in the hope that it will be useful, 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 | GNU General Public License for more details. 14 | 15 | You should have received a copy of the GNU General Public License 16 | along with this program. If not, see . 17 | """ 18 | import os 19 | import pandas as pd 20 | from pathlib import Path 21 | from tqdm import tqdm 22 | from constant import PATH_TO_TILES, PATH_TO_TRANSCRIPTOME 23 | 24 | 25 | class TranscriptomeDataset: 26 | """A class for dealing with RNAseq data and matching them with available 27 | slides. 28 | 29 | Args: 30 | projectname (list): If None, all TCGA projects are included. 31 | genes (list or None): list of genes Ensembl IDs. If None, all 32 | available genes are used. 33 | """ 34 | 35 | def __init__(self, projectname=None, genes=None): 36 | 37 | self.projectname = projectname 38 | self.genes = genes 39 | 40 | transcriptome_metadata = pd.read_csv( 41 | os.path.join( 42 | 'metadata', 43 | 'samples_description.csv'), 44 | sep='\t') 45 | 46 | # Select primary tumor samples from the chosen project 47 | if self.projectname is not None: 48 | directories = [ 49 | project.replace('_', '-') for project in self.projectname] 50 | self.transcriptome_metadata = transcriptome_metadata.loc[ 51 | (transcriptome_metadata['Project.ID'].isin(directories)) & 52 | (transcriptome_metadata['Sample.Type'] == 'Primary Tumor')] 53 | else: 54 | self.transcriptome_metadata = transcriptome_metadata.loc[ 55 | transcriptome_metadata['Sample.Type'] == 'Primary Tumor'] 56 | 57 | self.image_metadata = self._get_infos_on_tiles(self.projectname) 58 | self._match_data() 59 | 60 | @classmethod 61 | def from_saved_file(cls, path, projectname=None, genes=None): 62 | """Build TranscriptomeDataset instance from a saved csv file. 63 | """ 64 | if genes is None: 65 | usecols = None 66 | else: 67 | usecols = list(genes) + ['File.ID', 'Sample.ID', 'Case.ID', 'Project.ID'] 68 | transcriptomes = pd.read_csv(path, usecols=usecols) 69 | if projectname is None: 70 | projectname = transcriptomes['Project.ID'].apply( 71 | lambda x: x.replace('-', '_')).unique() 72 | else: 73 | transcriptomes = transcriptomes.loc[transcriptomes['Project.ID'].apply( 74 | lambda x: x.replace('-', '_')).isin(projectname)] 75 | genes = [col for col in transcriptomes.columns if col.startswith('ENSG')] 76 | dataset = cls(projectname, genes) 77 | transcriptomes.sort_values('Sample.ID', inplace=True) 78 | transcriptomes.reset_index(inplace=True, drop=True) 79 | dataset.transcriptomes = transcriptomes 80 | return dataset 81 | 82 | def _get_infos_on_tiles(self, subdirs, zoom='0.50_mpp'): 83 | """Find all slides tiled at a given level of a TCGA project and return a 84 | dataframe with their metadata. 85 | """ 86 | 87 | if subdirs is not None: 88 | df = [] 89 | for subdir in subdirs: 90 | dir_tiles = os.path.join(PATH_TO_TILES, subdir, zoom) 91 | filenames = [f for f in os.listdir(dir_tiles) if f.endswith('.npy') and 'mask' not in f] 92 | case_ids = [f[:12] for f in filenames] 93 | sample_ids = [f[:16] for f in filenames] 94 | full_ids = [f.split('.')[0] for f in filenames] 95 | 96 | df.append(pd.DataFrame( 97 | {'Project.ID': subdir, 'Case.ID': case_ids, 'Sample.ID_image': sample_ids, 98 | 'ID': full_ids, 'Slide.ID': filenames})) 99 | return pd.concat(df) 100 | else: 101 | subdirs = [] 102 | for subdir in os.listdir(PATH_TO_TILES): 103 | if os.path.isdir(os.path.join(PATH_TO_TILES, subdir)) and subdir.startswith('TCGA'): 104 | subdirs.append(subdir) 105 | return self._get_infos_on_tiles(subdirs) 106 | 107 | def _match_data(self): 108 | """Associate transcriptomes with availables slides. 109 | """ 110 | self.transcriptome_metadata['Sample'] = self.transcriptome_metadata['Sample.ID'].apply( 111 | lambda x: x[:-1]) 112 | self.image_metadata['Sample'] = self.image_metadata['Sample.ID_image'].apply( 113 | lambda x: x[:-1]) 114 | self.transcriptome_metadata.drop('Project.ID', axis=1, inplace=True) 115 | self.metadata = self.transcriptome_metadata.merge( 116 | self.image_metadata[['Project.ID', 'Sample', 'Sample.ID_image', 'ID', 'Slide.ID']], 117 | on='Sample') 118 | # If several transcriptomes can be associated with a slide, pick only one. 119 | self.metadata = self.metadata.groupby('Slide.ID').first().reset_index() 120 | self.metadata.sort_values('Sample.ID', inplace=True) 121 | self.metadata.reset_index(inplace=True, drop=True) 122 | 123 | def load_transcriptomes(self): 124 | """Select transcriptomic data of the selected project and genes. 125 | """ 126 | df = pd.read_csv(os.path.join( 127 | PATH_TO_TRANSCRIPTOME, 128 | 'transcriptome_fpkmuq_allsamps.csv'), sep='\t', usecols=self.genes, index_col=0) 129 | 130 | df['File.ID'] = df.index 131 | df = df.merge(self.metadata[['File.ID', 'Sample.ID', 132 | 'Case.ID', 'Project.ID']], 133 | on='File.ID', how='inner') 134 | df.sort_values('Sample.ID', inplace=True) 135 | df.reset_index(inplace=True, drop=True) 136 | self.transcriptomes = df 137 | 138 | 139 | def main(): 140 | df = [] 141 | path = Path(PATH_TO_TRANSCRIPTOME) 142 | for f in tqdm(path.glob('*/*.txt')): 143 | df_ = pd.read_csv(f, sep='\t', header=None, index_col=0) 144 | df_.columns = [str(f).split('/')[-2]] 145 | df.append(df_.T) 146 | df = pd.concat(df) 147 | df.to_csv(path / 'transcriptome_fpkmuq_allsamps.csv', index=True, sep='\t') 148 | dataset = TranscriptomeDataset() 149 | dataset.load_transcriptomes() 150 | dataset.transcriptomes.to_csv(path / 'all_transcriptomes.csv', index=False) 151 | 152 | if __name__ == '__main__': 153 | 154 | main() -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- 1 | """ 2 | HE2RNA: Computation of correlations 3 | Copyright (C) 2020 Owkin Inc. 4 | 5 | This program is free software: you can redistribute it and/or modify 6 | it under the terms of the GNU General Public License as published by 7 | the Free Software Foundation, either version 3 of the License, or 8 | (at your option) any later version. 9 | 10 | This program is distributed in the hope that it will be useful, 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 | GNU General Public License for more details. 14 | 15 | You should have received a copy of the GNU General Public License 16 | along with this program. If not, see . 17 | """ 18 | import numpy as np 19 | import pickle as pkl 20 | from joblib import Parallel, delayed 21 | 22 | def corr(pred, label, i): 23 | return np.corrcoef( 24 | label[:, i], 25 | pred[:, i])[0, 1] 26 | 27 | def compute_metrics(label, pred): 28 | res = Parallel(n_jobs=16)( 29 | delayed(corr)(pred, label, i) for i in range(label.shape[1]) 30 | ) 31 | return res 32 | -------------------------------------------------------------------------------- /wsi_data.py: -------------------------------------------------------------------------------- 1 | """ 2 | HE2RNA: Arrange data and labels into pytorch datasets 3 | Copyright (C) 2020 Owkin Inc. 4 | 5 | This program is free software: you can redistribute it and/or modify 6 | it under the terms of the GNU General Public License as published by 7 | the Free Software Foundation, either version 3 of the License, or 8 | (at your option) any later version. 9 | 10 | This program is distributed in the hope that it will be useful, 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 | GNU General Public License for more details. 14 | 15 | You should have received a copy of the GNU General Public License 16 | along with this program. If not, see . 17 | """ 18 | import os 19 | import numpy as np 20 | import pandas as pd 21 | import h5py 22 | import torch 23 | from torch.utils.data import Dataset, TensorDataset, Subset 24 | from sklearn.model_selection import train_test_split, KFold 25 | from sklearn.metrics import roc_auc_score 26 | from torchvision.transforms import Compose 27 | from tqdm import tqdm 28 | from joblib import Parallel, delayed 29 | from constant import PATH_TO_TILES, PATH_TO_TRANSCRIPTOME 30 | 31 | 32 | def load_labels(transcriptome_dataset): 33 | """Clean up RNAseq data and return labels, genes and patients. 34 | """ 35 | assert hasattr(transcriptome_dataset, 'transcriptomes'), \ 36 | "Transcriptomes have not been loaded for this dataset" 37 | 38 | to_drop = ['Case.ID', 'Sample.ID', 'File.ID', 'Project.ID'] 39 | df = transcriptome_dataset.transcriptomes.copy() 40 | patients = df['Case.ID'].values 41 | projects = df['Project.ID'] 42 | df.drop(to_drop, axis=1, inplace=True) 43 | genes = df.columns 44 | df = np.log10(1 + df) 45 | y = df.values 46 | 47 | return y, genes, patients, projects 48 | 49 | 50 | def load_and_aggregate_file(file, reduce=True): 51 | x = np.load(file) 52 | x = x[:, 3:] 53 | if reduce: 54 | x = np.mean(x, axis=0) 55 | else: 56 | x = np.concatenate((x, np.zeros((8000 - x.shape[0], 2048)))).transpose(1, 0) 57 | return x 58 | 59 | def load_npy_data(file_list, reduce=True): 60 | """Load and aggregate data saved as npy files. 61 | 62 | Args 63 | reduce (bool): If True, perform mean pooling on slide. 64 | Else, pad every slide with zeros. 65 | """ 66 | X = np.array(Parallel(n_jobs=32)(delayed(load_and_aggregate_file)(file) for file in tqdm(file_list))) 67 | return X 68 | 69 | 70 | def make_dataset(dir, file_list, labels): 71 | """Associate file names and labels""" 72 | images = [] 73 | dir = os.path.expanduser(dir) 74 | 75 | for fname, label in zip(file_list, labels): 76 | path = os.path.join(dir, fname) 77 | if os.path.exists(path): 78 | item = (path, label) 79 | images.append(item) 80 | 81 | return images 82 | 83 | 84 | class AggregatedDataset(TensorDataset): 85 | """A subclass of TensorDataset to use for whole-slide analysis 86 | (with aggregated data). 87 | 88 | Args 89 | genes (list): List of Ensembl IDs of genes to be used as targets. 90 | patients (list): list of patient IDs to perform patient split. 91 | """ 92 | def __init__(self, genes, patients, projects, *tensors): 93 | super(AggregatedDataset, self).__init__(*tensors) 94 | self.genes = genes 95 | self.patients = patients 96 | self.projects = projects 97 | self.dim = 2048 98 | 99 | @classmethod 100 | def match_transcriptome_data(cls, transcriptome_dataset): 101 | """Use a TranscriptomeDataset object to read corresponding .npy files 102 | and aggregate tiles. 103 | 104 | Args 105 | transcriptome_dataset (TranscriptomeDataset) 106 | binarize (bool): If True, target gene expressions are binarized with 107 | respect to their median value. 108 | """ 109 | y, cols, patients, projects = load_labels(transcriptome_dataset) 110 | 111 | file_list = [ 112 | os.path.join( 113 | PATH_TO_TILES, project.replace('-', '_'), 114 | '0.50_mpp', filename 115 | ) 116 | for project, filename in transcriptome_dataset.metadata[['Project.ID', 'Slide.ID']].values 117 | ] 118 | X = load_npy_data(file_list) 119 | return cls(cols, patients, projects, torch.Tensor(X), torch.Tensor(y)) 120 | 121 | 122 | class ToTensor(object): 123 | """A simple transformation on numpy array to obtain torch-friendly tensors. 124 | """ 125 | def __init__(self, n_tiles=8000): 126 | self.n_tiles = n_tiles 127 | 128 | def __call__(self, sample): 129 | x = torch.from_numpy(sample).float() 130 | if x.shape[0] > self.n_tiles: 131 | x = x[:self.n_tiles] 132 | elif x.shape[0] < self.n_tiles: 133 | x = torch.cat((x, torch.zeros((self.n_tiles - x.shape[0], 2051)))) 134 | return x.t() 135 | 136 | 137 | class RemoveCoordinates(object): 138 | """Remove tile levels and coordinates.""" 139 | def __call__(self, sample): 140 | return sample[3:] 141 | 142 | 143 | class TCGAFolder(Dataset): 144 | """A class similar to torchvision.FolderDataset for dealing with npy files 145 | of one or several TCGA project(s). 146 | 147 | Args 148 | genes (list): List of Ensembl IDs of genes to be used as targets. 149 | patients (list): list of patient IDs to perform patient split. 150 | projectname (str or None): Project.ID 151 | file_list (list): list of paths to .npy files containing tiled slides. 152 | labels (list or np.array): the associated gene expression values. 153 | transform (callable): Preprocessing of the data. 154 | target_transform (callable): Preprocessing of the targets. 155 | """ 156 | def __init__(self, genes, patients, projects, projectname, file_list, labels, 157 | transform=Compose([ToTensor(), RemoveCoordinates()]), 158 | target_transform=None, masks=None): 159 | root = PATH_TO_TILES 160 | samples = make_dataset(root, file_list, labels) 161 | if len(samples) == 0: 162 | raise(RuntimeError("Found 0 files in subfolders of: " + root + "\n")) 163 | 164 | self.root = root 165 | 166 | self.patients = patients 167 | self.projects = projects 168 | self.samples = samples 169 | 170 | self.transform = transform 171 | self.target_transform = target_transform 172 | 173 | self.genes = genes 174 | self.dim = 2048 175 | self.masks = masks 176 | 177 | @classmethod 178 | def match_transcriptome_data(cls, transcriptome_dataset, binarize=False): 179 | projectname = transcriptome_dataset.projectname 180 | labels, cols, patients, projects = load_labels(transcriptome_dataset) 181 | file_list = [ 182 | os.path.join( 183 | PATH_TO_TILES, project.replace('-', '_'), 184 | '0.50_mpp', filename) 185 | for project, filename in transcriptome_dataset.metadata[['Project.ID', 'Slide.ID']].values] 186 | return cls(cols, patients, projects, projectname, file_list, labels) 187 | 188 | def __getitem__(self, index): 189 | path, target = self.samples[index] 190 | if self.masks is not None: 191 | mask = self.masks[path.split('/')[-1]] 192 | idx = np.argsort(mask[:, 0])[::-1] 193 | sample = np.load(path)[idx] * mask[idx] 194 | else: 195 | sample = np.load(path) 196 | if self.transform is not None: 197 | sample = self.transform(sample) 198 | if self.target_transform is not None: 199 | target = self.target_transform(target) 200 | return sample, target 201 | 202 | def __len__(self): 203 | return len(self.samples) 204 | 205 | 206 | class H5Dataset(Dataset): 207 | """A class for using data saved in an hdf5 file. 208 | 209 | Args 210 | genes (list): List of Ensembl IDs of genes to be used as targets. 211 | patients (list): list of patient IDs to perform patient split. 212 | filename (str): path to the hdf5 file containing the data. 213 | labels (list or np.array): the associated gene expression values. 214 | max_items (int): Maximum number of tiles to use for training. 215 | """ 216 | def __init__(self, genes, patients, projects, filename, labels, max_items=8000): 217 | self.data = h5py.File(filename, 'r') 218 | self.targets = labels 219 | self.max_items = max_items 220 | self.genes = genes 221 | self.patients = patients 222 | self.projects = projects 223 | self.dim = self.data['X'].shape[2] 224 | 225 | def __getitem__(self, index): 226 | 227 | sample = torch.Tensor(self.data['X'][index, :self.max_items, 3:]).float().t() 228 | target = self.targets[index] 229 | 230 | return sample, target 231 | 232 | def __len__(self): 233 | return self.data['X'].shape[0] 234 | 235 | 236 | def patient_split(dataset, random_state=0): 237 | """Perform patient split of any of the previously defined datasets. 238 | """ 239 | patients_unique = np.unique(dataset.patients) 240 | patients_train, patients_valid = train_test_split( 241 | patients_unique, test_size=0.2, random_state=random_state) 242 | patients_valid, patients_test = train_test_split( 243 | patients_valid, test_size=0.5, random_state=random_state) 244 | 245 | indices = np.arange(len(dataset)) 246 | train_idx = indices[np.any(dataset.patients[:, np.newaxis] == 247 | patients_train[np.newaxis], axis=1)] 248 | valid_idx = indices[np.any(dataset.patients[:, np.newaxis] == 249 | patients_valid[np.newaxis], axis=1)] 250 | test_idx = indices[np.any(dataset.patients[:, np.newaxis] == 251 | patients_test[np.newaxis], axis=1)] 252 | 253 | return train_idx, valid_idx, test_idx 254 | 255 | 256 | def match_patient_split(dataset, split): 257 | """Recover previously saved patient split 258 | """ 259 | train_patients, valid_patients, test_patients = split 260 | indices = np.arange(len(dataset)) 261 | train_idx = indices[np.any(dataset.patients[:, np.newaxis] == 262 | train_patients[np.newaxis], axis=1)] 263 | valid_idx = indices[np.any(dataset.patients[:, np.newaxis] == 264 | valid_patients[np.newaxis], axis=1)] 265 | test_idx = indices[np.any(dataset.patients[:, np.newaxis] == 266 | test_patients[np.newaxis], axis=1)] 267 | 268 | return train_idx, valid_idx, test_idx 269 | 270 | 271 | def patient_kfold(dataset, n_splits=5, random_state=0, valid_size=0.1): 272 | """Perform cross-validation with patient split. 273 | """ 274 | indices = np.arange(len(dataset)) 275 | 276 | patients_unique = np.unique(dataset.patients) 277 | 278 | skf = KFold(n_splits, shuffle=True, random_state=random_state) 279 | ind = skf.split(patients_unique) 280 | 281 | train_idx = [] 282 | valid_idx = [] 283 | test_idx = [] 284 | 285 | for k, (ind_train, ind_test) in enumerate(ind): 286 | 287 | patients_train = patients_unique[ind_train] 288 | patients_test = patients_unique[ind_test] 289 | 290 | test_idx.append(indices[np.any(dataset.patients[:, np.newaxis] == 291 | patients_test[np.newaxis], axis=1)]) 292 | 293 | if valid_size > 0: 294 | patients_train, patients_valid = train_test_split( 295 | patients_train, test_size=valid_size, random_state=0) 296 | valid_idx.append(indices[np.any(dataset.patients[:, np.newaxis] == 297 | patients_valid[np.newaxis], axis=1)]) 298 | 299 | train_idx.append(indices[np.any(dataset.patients[:, np.newaxis] == 300 | patients_train[np.newaxis], axis=1)]) 301 | 302 | return train_idx, valid_idx, test_idx 303 | 304 | 305 | def match_patient_kfold(dataset, splits): 306 | """Recover previously saved patient splits for cross-validation. 307 | """ 308 | 309 | indices = np.arange(len(dataset)) 310 | train_idx = [] 311 | valid_idx = [] 312 | test_idx = [] 313 | 314 | for train_patients, valid_patients, test_patients in splits: 315 | 316 | train_idx.append(indices[np.any(dataset.patients[:, np.newaxis] == 317 | train_patients[np.newaxis], axis=1)]) 318 | valid_idx.append(indices[np.any(dataset.patients[:, np.newaxis] == 319 | valid_patients[np.newaxis], axis=1)]) 320 | test_idx.append(indices[np.any(dataset.patients[:, np.newaxis] == 321 | test_patients[np.newaxis], axis=1)]) 322 | 323 | return train_idx, valid_idx, test_idx 324 | --------------------------------------------------------------------------------