├── Example
    ├── toy_GE.csv
    └── toy_me.csv
├── MOMA
    └── MOMA_toy_example.ipynb
├── README.md
├── Supplementary_Material
    ├── MOMA Supplementary Material.z01
    ├── MOMA Supplementary Material.z02
    └── MOMA Supplementary Material.zip
└── requirements.txt


/README.md:
--------------------------------------------------------------------------------
 1 | # MOMA: A Multi-task Attention Learning Algorithm for Multi-omics Data Interpretation and Classification
 2 | 
 3 | MOMA is a **multi-task attention learning model** that provides a general classification framework for **multi-data**. <br/>
 4 | MOMA can capture **important biological processes for high diagnostic performance** and **interpretability**.<br/>
 5 | The model vectorizes features and modules using a geometric approach, and focuses on important modules in multi-omics data via an attention mechanism.
 6 | 
 7 | * * *
 8 | 
 9 | ###  We found that there was a download error related to the supplementary material, so we uploaded the file. 
10 | 
11 | * * *
12 | ⭐⭐⭐<br/>
13 | **The appropriate hyperparameters are different according to various multi-modal data and tasks.<br/>**
14 |  **The following is an empirical priority order, and it is recommended to put it on the tuning list at a minimum.<br/>**
15 |  **Number of module = 16, 32, 64, 128, ... <br/>**
16 |  **LearningRate = 5e-7, 5e-6, 5e-5, 5e-4, ... (with ADAM on PyTorch) <br/>**
17 |  
18 | * * *
19 | ## MOMA workflow
20 | <img src="https://user-images.githubusercontent.com/37695581/108037054-62285c80-707c-11eb-9048-380fac6e58d8.jpg" width="90%" height="90%"> 
21 | <br/>
22 | <img src="https://user-images.githubusercontent.com/37695581/108036374-7d469c80-707b-11eb-9392-1498bd00be32.png" width="90%" height="90%">
23 | 
24 | ## Example
25 | Check dependencies in requirements.txt, and necessarily run
26 | ```
27 | pip install -r requirements.txt
28 | ```
29 | Example codes that employ MOMA to build classifiers of simulation data are included in the /[Example/](https://https://github.com/DMCB-GIST/MOMA/tree/main/Example)   folder and /[MOMA/MOMA_toy_example.ipynb](https://https://https://github.com/DMCB-GIST/MOMA/blob/main/MOMA/MOMA_toy_example.ipynb).<br/>
30 | 


--------------------------------------------------------------------------------
/Supplementary_Material/MOMA Supplementary Material.z01:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/DMCB-GIST/MOMA/e9e027df1afddc7abf5a7c8ee7bec7b3542c3e6e/Supplementary_Material/MOMA Supplementary Material.z01


--------------------------------------------------------------------------------
/Supplementary_Material/MOMA Supplementary Material.z02:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/DMCB-GIST/MOMA/e9e027df1afddc7abf5a7c8ee7bec7b3542c3e6e/Supplementary_Material/MOMA Supplementary Material.z02


--------------------------------------------------------------------------------
/Supplementary_Material/MOMA Supplementary Material.zip:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/DMCB-GIST/MOMA/e9e027df1afddc7abf5a7c8ee7bec7b3542c3e6e/Supplementary_Material/MOMA Supplementary Material.zip


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | python==3.7.9
2 | numpy==1.19.2
3 | matplotlib==3.3.2
4 | sklearn==0.23.2
5 | pandas==1.1.3
6 | torch==1.4.0
7 | scipy==1.5.3
8 | seaborn==0.11.0


--------------------------------------------------------------------------------