├── .gitignore ├── .travis.yml ├── LICENSE-BSD.md ├── LICENSE-CC0.md ├── README.md ├── config_files ├── CONFIG.md ├── README.md ├── pubtator_central_config.json ├── pubtator_config.json └── tests_config.json ├── data ├── .gitattributes ├── example │ ├── 1-sample-annotations.txt │ ├── 2-sample-docs.xml │ ├── 3-sample-tags.tsv │ ├── 4-hetnet-tags.tsv │ ├── 5-sample-pmids-to-pmcids.tsv │ ├── 6-sample-full-text.xml │ ├── 7-sample-full-text-tags.tsv │ ├── 8-hetnet-full-text-tags.tsv │ ├── README.md │ └── ncbi_pmid_to_pmcid_map.tsv.xz └── temp │ ├── batch_0.xml │ ├── batch_1.xml │ └── batch_log.tsv ├── download └── bioconcepts2pubtator_offsets.gz.log ├── execute.py ├── mapper ├── drugbank_mapper.tsv └── map_to_drugbank.py ├── requirements.txt ├── scripts ├── __init__.py ├── download_full_text.py ├── extract_tags.py ├── hetnet_id_extractor.py ├── map_ids.py ├── pubtator_to_xml.py └── utilities.py └── tests.sh /.gitignore: -------------------------------------------------------------------------------- 1 | # Python 2 | __pycache__/ 3 | *.pyc 4 | 5 | # Jupyter Notebook 6 | .ipynb_checkpoints 7 | -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- 1 | language: generic 2 | before_install: 3 | - sudo apt-get update --quiet --quiet 4 | - wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh --output-document miniconda.sh 5 | - bash miniconda.sh -b -p $HOME/miniconda 6 | - export PATH="$HOME/miniconda/bin:$PATH" 7 | - hash -r 8 | - conda config --set always_yes yes --set changeps1 no 9 | - conda update --quiet conda 10 | - conda info --all 11 | install: 12 | - conda create --name pubtator python=3.8 13 | - source activate pubtator 14 | - pip install -r requirements.txt 15 | script: 16 | - sh tests.sh 17 | -------------------------------------------------------------------------------- /LICENSE-BSD.md: -------------------------------------------------------------------------------- 1 | # BSD 3-Clause License 2 | 3 | _Copyright © 2017, The Greene Lab at the University of Pennsylvania_ 4 |
5 | _All rights reserved._ 6 | 7 | Redistribution and use in source and binary forms, with or without 8 | modification, are permitted provided that the following conditions are met: 9 | 10 | 1. Redistributions of source code must retain the above copyright notice, this 11 | list of conditions and the following disclaimer. 12 | 13 | 2. Redistributions in binary form must reproduce the above copyright notice, 14 | this list of conditions and the following disclaimer in the documentation 15 | and/or other materials provided with the distribution. 16 | 17 | 3. Neither the name of the copyright holder nor the names of its contributors 18 | may be used to endorse or promote products derived from this software without 19 | specific prior written permission. 20 | 21 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND 22 | ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED 23 | WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE 24 | DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE 25 | FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 26 | DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR 27 | SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 28 | CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, 29 | OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 30 | OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 31 | -------------------------------------------------------------------------------- /LICENSE-CC0.md: -------------------------------------------------------------------------------- 1 | # CC0 1.0 Universal 2 | 3 | ``` 4 | CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED HEREUNDER. 5 | ``` 6 | 7 | ### Statement of Purpose 8 | 9 | The laws of most jurisdictions throughout the world automatically confer exclusive Copyright and Related Rights (defined below) upon the creator and subsequent owner(s) (each and all, an "owner") of an original work of authorship and/or a database (each, a "Work"). 10 | 11 | Certain owners wish to permanently relinquish those rights to a Work for the purpose of contributing to a commons of creative, cultural and scientific works ("Commons") that the public can reliably and without fear of later claims of infringement build upon, modify, incorporate in other works, reuse and redistribute as freely as possible in any form whatsoever and for any purposes, including without limitation commercial purposes. These owners may contribute to the Commons to promote the ideal of a free culture and the further production of creative, cultural and scientific works, or to gain reputation or greater distribution for their Work in part through the use and efforts of others. 12 | 13 | For these and/or other purposes and motivations, and without any expectation of additional consideration or compensation, the person associating CC0 with a Work (the "Affirmer"), to the extent that he or she is an owner of Copyright and Related Rights in the Work, voluntarily elects to apply CC0 to the Work and publicly distribute the Work under its terms, with knowledge of his or her Copyright and Related Rights in the Work and the meaning and intended legal effect of CC0 on those rights. 14 | 15 | 1. __Copyright and Related Rights.__ A Work made available under CC0 may be protected by copyright and related or neighboring rights ("Copyright and Related Rights"). Copyright and Related Rights include, but are not limited to, the following: 16 | 17 | i. the right to reproduce, adapt, distribute, perform, display, communicate, and translate a Work; 18 | 19 | ii. moral rights retained by the original author(s) and/or performer(s); 20 | 21 | iii. publicity and privacy rights pertaining to a person's image or likeness depicted in a Work; 22 | 23 | iv. rights protecting against unfair competition in regards to a Work, subject to the limitations in paragraph 4(a), below; 24 | 25 | v. rights protecting the extraction, dissemination, use and reuse of data in a Work; 26 | 27 | vi. database rights (such as those arising under Directive 96/9/EC of the European Parliament and of the Council of 11 March 1996 on the legal protection of databases, and under any national implementation thereof, including any amended or successor version of such directive); and 28 | 29 | vii. other similar, equivalent or corresponding rights throughout the world based on applicable law or treaty, and any national implementations thereof. 30 | 31 | 2. __Waiver.__ To the greatest extent permitted by, but not in contravention of, applicable law, Affirmer hereby overtly, fully, permanently, irrevocably and unconditionally waives, abandons, and surrenders all of Affirmer's Copyright and Related Rights and associated claims and causes of action, whether now known or unknown (including existing as well as future claims and causes of action), in the Work (i) in all territories worldwide, (ii) for the maximum duration provided by applicable law or treaty (including future time extensions), (iii) in any current or future medium and for any number of copies, and (iv) for any purpose whatsoever, including without limitation commercial, advertising or promotional purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each member of the public at large and to the detriment of Affirmer's heirs and successors, fully intending that such Waiver shall not be subject to revocation, rescission, cancellation, termination, or any other legal or equitable action to disrupt the quiet enjoyment of the Work by the public as contemplated by Affirmer's express Statement of Purpose. 32 | 33 | 3. __Public License Fallback.__ Should any part of the Waiver for any reason be judged legally invalid or ineffective under applicable law, then the Waiver shall be preserved to the maximum extent permitted taking into account Affirmer's express Statement of Purpose. In addition, to the extent the Waiver is so judged Affirmer hereby grants to each affected person a royalty-free, non transferable, non sublicensable, non exclusive, irrevocable and unconditional license to exercise Affirmer's Copyright and Related Rights in the Work (i) in all territories worldwide, (ii) for the maximum duration provided by applicable law or treaty (including future time extensions), (iii) in any current or future medium and for any number of copies, and (iv) for any purpose whatsoever, including without limitation commercial, advertising or promotional purposes (the "License"). The License shall be deemed effective as of the date CC0 was applied by Affirmer to the Work. Should any part of the License for any reason be judged legally invalid or ineffective under applicable law, such partial invalidity or ineffectiveness shall not invalidate the remainder of the License, and in such case Affirmer hereby affirms that he or she will not (i) exercise any of his or her remaining Copyright and Related Rights in the Work or (ii) assert any associated claims and causes of action with respect to the Work, in either case contrary to Affirmer's express Statement of Purpose. 34 | 35 | 4. __Limitations and Disclaimers.__ 36 | 37 | a. No trademark or patent rights held by Affirmer are waived, abandoned, surrendered, licensed or otherwise affected by this document. 38 | 39 | b. Affirmer offers the Work as-is and makes no representations or warranties of any kind concerning the Work, express, implied, statutory or otherwise, including without limitation warranties of title, merchantability, fitness for a particular purpose, non infringement, or the absence of latent or other defects, accuracy, or the present or absence of errors, whether or not discoverable, all to the greatest extent permissible under applicable law. 40 | 41 | c. Affirmer disclaims responsibility for clearing rights of other persons that may apply to the Work or any use thereof, including without limitation any person's Copyright and Related Rights in the Work. Further, Affirmer disclaims responsibility for obtaining any necessary consents, permissions or other rights required for any use of the Work. 42 | 43 | d. Affirmer understands and acknowledges that Creative Commons is not a party to this document and has no duty or obligation with respect to this CC0 or use of the Work. 44 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # PubTator: tagged PubMed abstracts for literature mining 2 | 3 | [![Build Status](https://travis-ci.org/greenelab/pubtator.svg?branch=master)](https://travis-ci.org/greenelab/pubtator) 4 | 5 | [PubTator](https://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/PubTator/) and its 2.0 version ([PubTator Central](https://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/PubTatorCentral/)) uses text mining to tag PubMed abstracts/artciles with standardized concepts. This repository retrieves and processes PubTator annotations for use in [`greenelab/snorkeling`](https://github.com/greenelab/snorkeling) and elsewhere. 6 | 7 | # Get Started 8 | 9 | ## **Depreciation Notice** 10 | 11 | If you have arrived at this page in order to convert Pubtator into BioCXML format, you no longer need to. 12 | Pubtator Central now provides their own BioCXML files which can be found [here](https://ftp.ncbi.nlm.nih.gov/pub/lu/PubTatorCentral/PubTatorCentral_BioCXML/). 13 | 14 | ## Set-up Environment 15 | 16 | ### Conda 17 | 18 | 1. Install the [conda](https://conda.io) environment. 19 | 2. Create the pubtator environmenmt by running: 20 | 21 | ```sh 22 | conda create --name pubtator python=3.8 23 | ``` 24 | 3. Install packages via pip by running the following: 25 | 26 | ```sh 27 | pip install -r requirements.txt 28 | ``` 29 | 30 | 4. Activate with `conda activate pubtator`. 31 | 32 | ### Pip 33 | 34 | 1. Make sure you have python version **3.8** installed. 35 | 2. Install packages by running the following: 36 | 37 | ```sh 38 | pip install -r requirements.txt 39 | ``` 40 | 41 | 42 | ## Execution 43 | 44 | To start processing Pubtator/Pubtator Central run the following command: 45 | 46 | ```sh 47 | python execute.py --config config_files/pubtator_central_config.json 48 | ``` 49 | 50 | If the original Pubtator is desired replace `pubtator_central_config.json` with `pubtator_config.json`. The json file contains all the necessary parameters needed to run. More information for the json file can be found [here](config_files). 51 | 52 | ## License 53 | 54 | This repository is dual licensed as [BSD 3-Clause](LICENSE-BSD.md) and [CC0 1.0](LICENSE-CC0.md), meaning any repository content can be used under either license. This licensing arrangement ensures source code is available under an [OSI-approved License](https://opensource.org/licenses/alphabetical), while non-code content — such as figures, data, and documentation — is maximally reusable under a public domain dedication. 55 | -------------------------------------------------------------------------------- /config_files/CONFIG.md: -------------------------------------------------------------------------------- 1 | # Configuration Files Explained 2 | 3 | This file explains the pipeline steps and parameters needed for each step. 4 | **Note: any added parameter or step will be ignored unless `execute.py` is manually changed.** 5 | 6 | ## Repository Download 7 | 8 | This is the first step of the Pubtator pipeline. 9 | Basically this step downloads Pubtator Central's annotation file from their ftp server. 10 | 11 | Following Parameters for this section: 12 | | Param | Description | Accepted Values | 13 | | --- | --- | --- | 14 | | url | the url to download the file from | a string with a url path | 15 | | download_folder | the folder to hold the downloaded file | a string name for the folder | 16 | | skip | tell execute.py to ignore this step and contine | true or false | 17 | 18 | ## Pubtator to XML 19 | 20 | This is the second step of the Pubtator pipeline. 21 | This step converts Pubtator/Pubtator Central's annotation file into xml format. 22 | **Note: This step may take awhile to complete** 23 | 24 | Following Parameters for this section: 25 | | Param | Description | Accepted Values | 26 | | --- | --- | --- | 27 | | documents | The file path pointing to the downloaded file from the previous step. | a string for the file path | 28 | | output | The file path to save the xml file. Make sure to keep the xz extension. | a string for the file path | 29 | | skip | Tell execute.py to ignore this step and contine | true or false | 30 | 31 | ## Extract Tags 32 | 33 | This is the second step of the Pubtator pipeline. 34 | This step extracts Pubtator/Pubtator Central's annotations from the xml file. 35 | It outputs a tsv file that contains all extracted annotation. 36 | **Note: This step may take awhile to complete** 37 | 38 | Following Parameters for this section: 39 | | Param | Description | Accepted Values | 40 | | --- | --- | --- | 41 | | input | The file path pointing to the xml file in previouss step. Make sure to keep the xz extension. | a string for the file path | 42 | | output | The file path to save the tsv file. Make sure to keep the xz extension. | a string for the file path | 43 | | skip | Tell execute.py to ignore this step and contine | true or false | 44 | 45 | ## Hetnet ID Extractor 46 | 47 | This is the third step of the Pubtator pipeline. 48 | This step filters out extracted annotations to only include tags within [Hetionet's Database](https://het.io/). 49 | 50 | Following Parameters for this section: 51 | | Param | Description | Accepted Values | 52 | | --- | --- | --- | 53 | | input | The file path pointing to the tsv file in previous step. Make sure to keep the xz extension. | a string for the file path | 54 | | output | The file path to save the tsv file. Make sure to keep the xz extension. | a string for the file path | 55 | | skip | Tell execute.py to ignore this step and contine | true or false | 56 | 57 | ## Map PMIDS to PMCIDS 58 | 59 | This is the forth step of the Pubtator pipeline. 60 | This step querys NCBI's pmid to pmcid mapper in order to grab PMCIDS. 61 | **Note: To download full text you will need to have PMCIDS. PMIDS will not work.** 62 | 63 | Following Parameters for this section: 64 | | Param | Description | Accepted Values | 65 | | --- | --- | --- | 66 | | input | The file path pointing to the tsv file in extract tags step. Make sure to keep the xz extension. | a string for the file path | 67 | | output | The file path to save the tsv file. | a string for the file path | 68 | | debug | This is a flag for debugging purposes. Feel free to ignore and leave as false. | true or false | 69 | | skip | Tell execute.py to ignore this step and contine | true or false | 70 | 71 | ## Download Full Text 72 | 73 | This is the fifth step of the Pubtator pipeline. 74 | This step queries Pubtator Central's api and downloads annotated full text if text is present. 75 | 76 | Following Parameters for this section: 77 | | Param | Description | Accepted Values | 78 | | --- | --- | --- | 79 | | input | The file path pointing to the tsv file in previous step. | a string for the file path | 80 | | output | The file path to save the xml file. | a string for the file path | 81 | | temp_dir | The folder to hold temporary batch files for this step of the pipeline | a string for the folder path | 82 | | log_file | A log file that keeps track of the IDs that have already been queried. It is used to monitor progress in case the process is interrupted. Make sure it has the tsv extension. | a file path for the file | 83 | | skip | Tell execute.py to ignore this step and contine | true or false | 84 | 85 | ## Extract Full Text Tags 86 | 87 | This is the sixth step of the Pubtator pipeline. 88 | This step extracts tags from full text documents. 89 | Please refer to [Extract Tags Section](#extract-tags) for parameter details. 90 | 91 | ## Hetnet ID Extractor Full Text 92 | 93 | This is the last step of the Pubtator pipeline. 94 | This step filters tags to only have Hetionet tags. 95 | Please refer to [Hetnet ID Extractor Section](#hetnet-id-extractor) for parameter details. 96 | 97 | -------------------------------------------------------------------------------- /config_files/README.md: -------------------------------------------------------------------------------- 1 | # Configuration Files 2 | 3 | ## File Description 4 | 5 | | File | Description | 6 | | --- | --- | 7 | | [pubtator central config](pubtator_central_config.json) | This is a configuration file for parsing Pubtator Central. | 8 | | [pubtator config](pubtator_config.json) | This is a configuration file for parsing Pubtator (older version of Pubtator Central). | 9 | | [tests config](tests_config.json) | This is a configuration file for testing the pubtator system. Feel free to ignore this file. | 10 | 11 | ## Usage 12 | 13 | Each configuration file is in json format and contains parameters for each step within the pubtator pipeline. 14 | All files are organized by order of operation, which means the very first step occurs at the top and the subsequent step comes right afterwards. 15 | Every step can be skipped, which allows one to continue the pipeline at any step one chooses. 16 | Please refer to [CONFIG.md](CONFIG.md) for more details on each pipeline step and their respective parameters. 17 | 18 | Example config file: 19 | ```json 20 | { 21 | "pipeline step 1":{ 22 | "param1":"param1_value", 23 | "param2":"param2_value", 24 | "skip":false 25 | }, 26 | "pipeline step 2":{ 27 | "param1":"param1_value", 28 | "param2":"param2_value", 29 | "skip":false 30 | }, 31 | "pipeline step 3":{ 32 | "param1":"param1_value", 33 | "param2":"param2_value", 34 | "skip":false 35 | } 36 | } 37 | ``` 38 | -------------------------------------------------------------------------------- /config_files/pubtator_central_config.json: -------------------------------------------------------------------------------- 1 | { 2 | "repository_download":{ 3 | "url":"ftp://ftp.ncbi.nlm.nih.gov/pub/lu/PubTatorCentral/bioconcepts2pubtatorcentral.offset.gz", 4 | "download_folder":"download", 5 | "skip":false 6 | }, 7 | 8 | "pubtator_to_xml": { 9 | "documents":"download/bioconcepts2pubtatorcentral.offset.gz", 10 | "output":"data/pubtator-central-docs.xml.xz", 11 | "skip":false 12 | }, 13 | 14 | "extract_tags":{ 15 | "input":"data/pubtator-central-docs.xml.xz", 16 | "output":"data/pubtator-central-tags.tsv.xz", 17 | "skip":false 18 | }, 19 | 20 | "hetnet_id_extractor":{ 21 | "input":"data/pubtator-central-tags.tsv.xz", 22 | "output":"data/pubtator-central-hetnet-tags.tsv.xz", 23 | "skip":false 24 | }, 25 | 26 | "map_pmids_to_pmcids":{ 27 | "input":"data/pubtator-central-tags.tsv.xz", 28 | "output":"data/pubtator-pmids-to-pmcids.tsv", 29 | "debug":false, 30 | "skip":false 31 | }, 32 | 33 | "download_full_text":{ 34 | "input":"data/pubtator-pmids-to-pmcids.tsv", 35 | "document_batch":100, 36 | "output":" data/pubtator-central-full-text.xml", 37 | "temp_dir":"data/temp", 38 | "log_file":"batch_log.tsv", 39 | "skip":false 40 | }, 41 | 42 | "extract_full_text_tags":{ 43 | "input":"data/pubtator-central-full-text.xml", 44 | "output":"data/pubtator-central-full-text-tags.tsv.xz", 45 | "skip":false 46 | }, 47 | 48 | "hetnet_id_extractor_full_text":{ 49 | "input":"data/pubtator-central-full-text-tags.tsv.xz", 50 | "output":"data/pubtator-central-full-hetnet-tags.tsv.xz", 51 | "skip":false 52 | } 53 | 54 | } 55 | -------------------------------------------------------------------------------- /config_files/pubtator_config.json: -------------------------------------------------------------------------------- 1 | { 2 | "repository_download":{ 3 | "url":"ftp://ftp.ncbi.nlm.nih.gov/pub/lu/PubTator/bioconcepts2pubtator_offsets.gz", 4 | "download_folder":"download", 5 | "skip":false 6 | }, 7 | 8 | "pubtator_to_xml": { 9 | "documents":"download/bioconcepts2pubtator_offsets.gz", 10 | "output":"data/pubtator-docs.xml.xz", 11 | "skip":false 12 | }, 13 | 14 | "extract_tags":{ 15 | "input":"data/pubtator-docs.xml.xz", 16 | "output":"data/pubtator-tags.tsv.xz", 17 | "skip":false 18 | }, 19 | 20 | "hetnet_id_extractor":{ 21 | "input":"data/pubtator-tags.tsv.xz", 22 | "output":"data/pubtator-hetnet-tags.tsv.xz", 23 | "skip":false 24 | } 25 | } 26 | -------------------------------------------------------------------------------- /config_files/tests_config.json: -------------------------------------------------------------------------------- 1 | { 2 | "repository_download":{ 3 | "url":"ftp://ftp.ncbi.nlm.nih.gov/pub/lu/PubTatorCentral/bioconcepts2pubtatorcentral.offset.gz", 4 | "download_folder":"download", 5 | "skip":true 6 | }, 7 | 8 | "pubtator_to_xml": { 9 | "documents":"data/example/1-sample-annotations.txt", 10 | "output":"data/example/2-sample-docs.xml", 11 | "skip":false 12 | }, 13 | 14 | "extract_tags":{ 15 | "input":"data/example/2-sample-docs.xml", 16 | "output":"data/example/3-sample-tags.tsv", 17 | "skip":false 18 | }, 19 | 20 | "hetnet_id_extractor":{ 21 | "input":"data/example/3-sample-tags.tsv", 22 | "output":"data/example/4-hetnet-tags.tsv", 23 | "skip":false 24 | }, 25 | 26 | "map_pmids_to_pmcids":{ 27 | "input":"data/example/3-sample-tags.tsv", 28 | "output":"data/example/5-sample-pmids-to-pmcids.tsv", 29 | "debug":true, 30 | "skip":false 31 | }, 32 | 33 | "download_full_text":{ 34 | "input":"data/example/5-sample-pmids-to-pmcids.tsv", 35 | "document_batch":100, 36 | "output":"data/example/6-sample-full-text.xml", 37 | "temp_dir":"data/temp", 38 | "log_file":"batch_log.tsv", 39 | "skip":false 40 | }, 41 | 42 | "extract_full_text_tags":{ 43 | "input":"data/example/6-sample-full-text.xml", 44 | "output":"data/example/7-sample-full-text-tags.tsv", 45 | "skip":false 46 | }, 47 | 48 | "hetnet_id_extractor_full_text":{ 49 | "input":"data/example/7-sample-full-text-tags.tsv", 50 | "output":"data/example/8-hetnet-full-text-tags.tsv", 51 | "skip":false 52 | } 53 | 54 | } 55 | -------------------------------------------------------------------------------- /data/.gitattributes: -------------------------------------------------------------------------------- 1 | pubtator-hetnet-tags.tsv.xz filter=lfs diff=lfs merge=lfs -text 2 | -------------------------------------------------------------------------------- /data/example/5-sample-pmids-to-pmcids.tsv: -------------------------------------------------------------------------------- 1 | Journal Title ISSN eISSN Year Volume Issue Page DOI PMCID PMID Manuscript Id Release Date 2 | J Cell Biol 0021-9525 1540-8140 1992 117.0 2 427 10.1083/jcb.117.2.427 PMC2289422 1560033 live 3 | J Cell Biol 0021-9525 1540-8140 1992 117.0 2 269 10.1083/jcb.117.2.269 PMC2289423 1313813 live 4 | J Cell Biol 0021-9525 1540-8140 1992 117.0 2 311 10.1083/jcb.117.2.311 PMC2289424 1560028 live 5 | J Cell Biol 0021-9525 1540-8140 1992 117.0 2 437 10.1083/jcb.117.2.437 PMC2289425 1373145 live 6 | J Cell Biol 0021-9525 1540-8140 1992 117.0 2 245 10.1083/jcb.117.2.245 PMC2289426 1560026 live 7 | J Cell Biol 0021-9525 1540-8140 1992 117.0 2 291 10.1083/jcb.117.2.291 PMC2289427 1313814 live 8 | J Cell Biol 0021-9525 1540-8140 1992 117.0 2 461 10.1083/jcb.117.2.461 PMC2289428 1560035 live 9 | J Cell Biol 0021-9525 1540-8140 1992 117.0 2 337 10.1083/jcb.117.2.337 PMC2289429 1373142 live 10 | J Cell Biol 0021-9525 1540-8140 1992 117.0 2 327 10.1083/jcb.117.2.327 PMC2289430 1560029 live 11 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 659 10.1083/jcb.117.3.659 PMC2289434 1374069 live 12 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 493 10.1083/jcb.117.3.493 PMC2289435 1315314 live 13 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 679 10.1083/jcb.117.3.679 PMC2289436 1572896 live 14 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 629 10.1083/jcb.117.3.629 PMC2289437 1315318 live 15 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 515 10.1083/jcb.117.3.515 PMC2289438 1572893 live 16 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 687 10.1083/jcb.117.3.687 PMC2289439 1572897 live 17 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 595 10.1083/jcb.117.3.595 PMC2289440 1533397 live 18 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 505 10.1083/jcb.117.3.505 PMC2289441 1315315 live 19 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 607 10.1083/jcb.117.3.607 PMC2289442 1374068 live 20 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 583 10.1083/jcb.117.3.583 PMC2289443 1374067 live 21 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 483 10.1083/jcb.117.3.483 PMC2289444 1374066 live 22 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 565 10.1083/jcb.117.3.565 PMC2289445 1315317 live 23 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 617 10.1083/jcb.117.3.617 PMC2289446 1349305 live 24 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 539 10.1083/jcb.117.3.539 PMC2289447 1572894 live 25 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 551 10.1083/jcb.117.3.551 PMC2289448 1572895 live 26 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 671 10.1083/jcb.117.3.671 PMC2289449 1533398 live 27 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 531 10.1083/jcb.117.3.531 PMC2289450 1315316 live 28 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 573 10.1083/jcb.117.3.573 PMC2289451 1533396 live 29 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 473 10.1083/jcb.117.3.473 PMC2289452 1572892 live 30 | J Cell Biol 0021-9525 1540-8140 1992 117.0 3 643 10.1083/jcb.117.3.643 PMC2289453 1315319 live 31 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 895 10.1083/jcb.117.4.895 PMC2289454 1374413 live 32 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 863 10.1083/jcb.117.4.863 PMC2289455 1577862 live 33 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 745 10.1083/jcb.117.4.745 PMC2289456 1577854 live 34 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 729 10.1083/jcb.117.4.729 PMC2289457 1577853 live 35 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 757 10.1083/jcb.117.4.757 PMC2289458 1577855 live 36 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 717 10.1083/jcb.117.4.717 PMC2289459 1577852 live 37 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 849 10.1083/jcb.117.4.849 PMC2289460 1577861 live 38 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 787 10.1083/jcb.117.4.787 PMC2289461 1577858 live 39 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 825 10.1083/jcb.117.4.825 PMC2289462 1349609 live 40 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 775 10.1083/jcb.117.4.775 PMC2289463 1577857 live 41 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 889 10.1083/jcb.117.4.889 PMC2289464 1315783 live 42 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 841 10.1083/jcb.117.4.841 PMC2289465 1577860 live 43 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 765 10.1083/jcb.117.4.765 PMC2289466 1577856 live 44 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 903 10.1083/jcb.117.4.903 PMC2289467 1577863 live 45 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 813 10.1083/jcb.117.4.813 PMC2289468 1349608 live 46 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 701 10.1083/jcb.117.4.701 PMC2289469 1577851 live 47 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 799 10.1083/jcb.117.4.799 PMC2289470 1577859 live 48 | J Cell Biol 0021-9525 1540-8140 1992 117.0 4 877 10.1083/jcb.117.4.877 PMC2289471 1315782 live 49 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1109 10.1083/jcb.117.5.1109 PMC2289472 1374416 live 50 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1085 10.1083/jcb.117.5.1085 PMC2289473 1577867 live 51 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1119 10.1083/jcb.117.5.1119 PMC2289474 1577869 live 52 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1067 10.1083/jcb.117.5.1067 PMC2289475 1315784 live 53 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1041 10.1083/jcb.117.5.1041 PMC2289476 1533642 live 54 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1023 10.1083/jcb.117.5.1023 PMC2289477 1577865 live 55 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 987 10.1083/jcb.117.5.987 PMC2289478 1315787 live 56 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 935 10.1083/jcb.117.5.935 PMC2289479 1315786 live 57 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1055 10.1083/jcb.117.5.1055 PMC2289480 1533643 live 58 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1077 10.1083/jcb.117.5.1077 PMC2289481 1374414 live 59 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1093 10.1083/jcb.117.5.1093 PMC2289482 1577868 live 60 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1031 10.1083/jcb.117.5.1031 PMC2289483 1577866 live 61 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1007 10.1083/jcb.117.5.1007 PMC2289484 1577864 live 62 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 921 10.1083/jcb.117.5.921 PMC2289485 1315785 live 63 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 959 10.1083/jcb.117.5.959 PMC2289486 1374417 live 64 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 975 10.1083/jcb.117.5.975 PMC2289487 1577871 live 65 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 949 10.1083/jcb.117.5.949 PMC2289488 1577870 live 66 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 1101 10.1083/jcb.117.5.1101 PMC2289489 1374415 live 67 | J Cell Biol 0021-9525 1540-8140 1992 117.0 5 997 10.1083/jcb.117.5.997 PMC2289490 1577872 live 68 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1223 10.1083/jcb.117.6.1223 PMC2289491 1607384 live 69 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1181 10.1083/jcb.117.6.1181 PMC2289492 1607382 live 70 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1251 10.1083/jcb.117.6.1251 PMC2289493 1607387 live 71 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1197 10.1083/jcb.117.6.1197 PMC2289494 1318883 live 72 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1137 10.1083/jcb.117.6.1137 PMC2289495 1607378 live 73 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1321 10.1083/jcb.117.6.1321 PMC2289496 1376731 live 74 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1277 10.1083/jcb.117.6.1277 PMC2289497 1607389 live 75 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1161 10.1083/jcb.117.6.1161 PMC2289498 1607380 live 76 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1231 10.1083/jcb.117.6.1231 PMC2289499 1607385 live 77 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1211 10.1083/jcb.117.6.1211 PMC2289500 1607383 live 78 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1351 10.1083/jcb.117.6.1351 PMC2289501 1607393 live 79 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1151 10.1083/jcb.117.6.1151 PMC2289502 1607379 live 80 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1331 10.1083/jcb.117.6.1331 PMC2289503 1607392 live 81 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1171 10.1083/jcb.117.6.1171 PMC2289504 1607381 live 82 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1311 10.1083/jcb.117.6.1311 PMC2289505 1607391 live 83 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1299 10.1083/jcb.117.6.1299 PMC2289506 1318884 live 84 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1263 10.1083/jcb.117.6.1263 PMC2289507 1607388 live 85 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1343 10.1083/jcb.117.6.1343 PMC2289508 1376732 live 86 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1241 10.1083/jcb.117.6.1241 PMC2289509 1607386 live 87 | J Cell Biol 0021-9525 1540-8140 1992 117.0 6 1289 10.1083/jcb.117.6.1289 PMC2289510 1607390 live 88 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 51 10.1083/jcb.118.1.51 PMC2289512 1352300 live 89 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 43 10.1083/jcb.118.1.43 PMC2289513 1320035 live 90 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 203 10.1083/jcb.118.1.203 PMC2289514 1618904 live 91 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 1 10.1083/jcb.118.1.1 PMC2289515 1618896 live 92 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 177 10.1083/jcb.118.1.177 PMC2289517 1618903 live 93 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 23 10.1083/jcb.118.1.23 PMC2289518 1618905 live 94 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 163 10.1083/jcb.118.1.163 PMC2289519 1618902 live 95 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 95 10.1083/jcb.118.1.95 PMC2289520 1618910 live 96 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 11 10.1083/jcb.118.1.11 PMC2289521 1618898 live 97 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 33 10.1083/jcb.118.1.33 PMC2289522 1618906 live 98 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 131 10.1083/jcb.118.1.131 PMC2289524 1618900 live 99 | J Cell Biol 0021-9525 1540-8140 1992 118.0 1 71 10.1083/jcb.118.1.71 PMC2289525 1618908 live 100 | Acta Neuropathol Commun 2051-5960 2014 2 176 10.1186/s40478-014-0176-9 PMC4272812 25497491 live 101 | BMC Med Educ 1472-6920 2014 14 258 10.1186/s12909-014-0258-1 PMC4272813 25491129 live 102 | Gut Pathog 1757-4749 2014 6 46 10.1186/s13099-014-0046-9 PMC4272814 25530808 live 103 | Clin Epigenetics 1868-7075 1868-7083 2014 6 1 32 10.1186/s13148-014-0032-6 PMC4272815 25530820 live 104 | Aquat Toxicol 0166-445X 1879-1514 2014 0 192 10.1016/j.aquatox.2014.11.016 PMC4272816 25481785 NIHMS645550 live 105 | BMC Med Educ 1472-6920 2014 14 263 10.1186/s12909-014-0263-4 PMC4272818 25495467 live 106 | Prehosp Emerg Care 1090-3127 1545-0066 2014 18 3 368 10.3109/10903127.2013.869642 PMC4272820 24548058 NIHMS644369 live 107 | Skelet Muscle 2044-5040 2014 4 23 10.1186/s13395-014-0023-5 PMC4272821 25530839 live 108 | BMC Genet 1471-2156 2014 15 144 10.1186/s12863-014-0144-1 PMC4272822 25511509 live 109 | Radiat Oncol 1748-717X 2014 9 277 10.1186/s13014-014-0277-4 PMC4272823 25497602 live 110 | Drug Alcohol Depend 0376-8716 1879-0046 2014 0 52 10.1016/j.drugalcdep.2014.11.003 PMC4272824 25439054 NIHMS643973 live 111 | Sci Transl Med 1946-6234 1946-6242 2014 6 246 246ra96 10.1126/scitranslmed.3008680 PMC4272825 25101886 NIHMS623565 live 112 | Blood Cells Mol Dis 1079-9796 1096-0961 2013 52 1 68 10.1016/j.bcmd.2013.07.003 PMC4272826 23910958 NIHMS648290 live 113 | Mater Sociomed 1512-7680 1986-597X 2014 26 5 329 10.5455/msm.2014.26.329-334 PMC4272827 25568633 live 114 | Mater Sociomed 1512-7680 1986-597X 2014 26 5 303 10.5455/msm.2014.26.303-305 PMC4272828 25568626 live 115 | Mater Sociomed 1512-7680 1986-597X 2014 26 5 306 10.5455/msm.2014.26.306-308 PMC4272829 25568627 live 116 | Mater Sociomed 1512-7680 1986-597X 2014 26 5 335 10.5455/msm.2014.26.335-338 PMC4272830 25568634 live 117 | Mater Sociomed 1512-7680 1986-597X 2014 26 5 297 10.5455/msm.2014.26.297-302 PMC4272831 25568625 live 118 | Acta Inform Med 0353-8109 1986-5988 2014 22 5 329 10.5455/aim.2014.22.329-332 PMC4272832 25568583 live 119 | Acta Inform Med 0353-8109 1986-5988 2014 22 5 302 10.5455/aim.2014.22.302-305 PMC4272833 25568577 live 120 | Mater Sociomed 1512-7680 1986-597X 2014 26 5 292 10.5455/msm.2014.26.292-296 PMC4272834 25568624 live 121 | Acta Inform Med 0353-8109 1986-5988 2014 22 5 292 10.5455/aim.2014.22.292-296 PMC4272835 25568575 live 122 | Mater Sociomed 1512-7680 1986-597X 2014 26 5 309 10.5455/msm.2014.26.309-312 PMC4272836 25568628 live 123 | Acta Inform Med 0353-8109 1986-5988 2014 22 5 341 10.5455/aim.2014.22.341-346 PMC4272837 25568585 live 124 | Mater Sociomed 1512-7680 1986-597X 2014 26 5 343 10.5455/msm.2014.26.343-347 PMC4272838 25568636 live 125 | Acta Inform Med 0353-8109 1986-5988 2014 22 5 333 10.5455/aim.2014.22.333-340 PMC4272839 25568584 live 126 | Mater Sociomed 1512-7680 1986-597X 2014 26 5 348 10.5455/msm.2014.26.348-351 PMC4272840 25568637 live 127 | Acta Inform Med 0353-8109 1986-5988 2014 22 5 350 10.5455/aim.2014.22.350-350 PMC4272841 25568587 live 128 | Mater Sociomed 1512-7680 1986-597X 2014 26 5 321 10.5455/msm.2014.26.321-323 PMC4272842 25568631 live 129 | Acta Inform Med 0353-8109 1986-5988 2014 22 5 325 10.5455/aim.2014.22.325-328 PMC4272843 25568582 live 130 | Acta Inform Med 0353-8109 1986-5988 2014 22 5 347 10.5455/aim.2014.22.347-349 PMC4272844 25568586 live 131 | Mater Sociomed 1512-7680 1986-597X 2014 26 5 318 10.5455/msm.2014.26.318-320 PMC4272845 25568630 live 132 | Acta Inform Med 0353-8109 1986-5988 2014 22 5 297 10.5455/aim.2014.22.297-301 PMC4272846 25568576 live 133 | Acta Inform Med 0353-8109 1986-5988 2014 22 5 315 10.5455/aim.2014.22.315-319 PMC4272847 25568580 live 134 | -------------------------------------------------------------------------------- /data/example/8-hetnet-full-text-tags.tsv: -------------------------------------------------------------------------------- 1 | pubmed_id type identifier offset end 2 | 2289422 Compound DB00126 514 527 3 | 2289422 Compound DB09541 514 527 4 | 2289422 Compound DB00755 1544 1557 5 | 2289423 Compound DB00134 524 534 6 | 2289423 Compound DB00134 606 616 7 | 2289423 Compound DB00065 1042 1046 8 | 2289423 Compound DB00065 1224 1228 9 | 2289423 Compound DB00065 1331 1337 10 | 2289423 Compound DB00065 1523 1529 11 | 2289423 Compound DB00065 1569 1575 12 | 2289423 Compound DB00065 2016 2020 13 | 2289424 Compound DB00145 590 597 14 | 2289424 Compound DB00135 598 606 15 | 2289424 Compound DB00135 1143 1151 16 | 2289424 Compound DB00145 1155 1162 17 | 2289424 Compound DB00145 1679 1686 18 | 2289424 Compound DB00135 1687 1695 19 | 2289425 Gene 7531 297 301 20 | 2289427 Gene 1877 543 546 21 | 2289428 Gene 838 634 667 22 | 2289428 Gene 496 681 691 23 | 2289428 Gene 3054 1095 1101 24 | 2289428 Gene 3054 1417 1423 25 | 2289429 Compound DB00065 26 30 26 | 2289429 Disease DOID:2531 450 457 27 | 2289429 Compound DB00065 570 574 28 | 2289429 Compound DB00065 1541 1545 29 | 2289429 Compound DB00065 1630 1634 30 | 2289430 Compound DB03193 994 1006 31 | 2289434 Gene 3054 63 69 32 | 2289434 Gene 3054 471 477 33 | 2289434 Gene 3054 517 523 34 | 2289434 Gene 3054 611 617 35 | 2289434 Gene 3054 713 719 36 | 2289434 Gene 838 821 827 37 | 2289434 Gene 838 933 939 38 | 2289434 Gene 3054 1008 1014 39 | 2289434 Gene 3054 1029 1035 40 | 2289434 Gene 22999 1075 1090 41 | 2289434 Disease DOID:1909 1237 1245 42 | 2289434 Gene 3054 1401 1407 43 | 2289434 Gene 3054 1419 1425 44 | 2289434 Gene 3054 1591 1597 45 | 2289434 Gene 3054 1790 1796 46 | 2289434 Gene 22999 2082 2097 47 | 2289434 Gene 3054 2157 2163 48 | 2289434 Gene 3054 2240 2246 49 | 2289436 Gene 540 0 31 50 | 2289436 Gene 540 449 480 51 | 2289436 Gene 540 482 490 52 | 2289436 Gene 540 1563 1571 53 | 2289437 Gene 1876 14 38 54 | 2289437 Gene 1876 130 154 55 | 2289437 Gene 1876 156 159 56 | 2289437 Compound DB00624 205 217 57 | 2289437 Gene 1876 386 389 58 | 2289437 Gene 1876 488 491 59 | 2289437 Gene 1877 627 639 60 | 2289437 Gene 1877 712 724 61 | 2289437 Gene 1877 833 845 62 | 2289437 Gene 1876 1004 1007 63 | 2289437 Gene 1876 1204 1207 64 | 2289440 Gene 55829 281 300 65 | 2289440 Gene 55829 302 305 66 | 2289440 Gene 55829 416 419 67 | 2289440 Gene 55829 496 499 68 | 2289440 Gene 55829 660 663 69 | 2289440 Gene 55829 859 862 70 | 2289440 Gene 1545 907 913 71 | 2289440 Gene 1545 1255 1261 72 | 2289440 Gene 55829 1439 1442 73 | 2289440 Gene 1545 1512 1518 74 | 2289440 Gene 55829 1648 1651 75 | 2289440 Gene 1545 1671 1678 76 | 2289441 Compound DB09152 264 265 77 | 2289441 Gene 3908 889 892 78 | 2289443 Gene 55643 62 75 79 | 2289443 Gene 55643 278 281 80 | 2289443 Gene 55643 361 364 81 | 2289443 Gene 55643 585 588 82 | 2289443 Gene 55643 769 772 83 | 2289443 Gene 55643 857 860 84 | 2289443 Gene 55643 906 909 85 | 2289443 Gene 55643 1175 1178 86 | 2289445 Gene 8829 95 121 87 | 2289445 Compound DB00065 210 214 88 | 2289445 Gene 8829 293 345 89 | 2289445 Gene 8829 406 409 90 | 2289445 Gene 8829 527 530 91 | 2289445 Gene 8829 1041 1044 92 | 2289445 Gene 539 1180 1185 93 | 2289445 Gene 8829 1438 1441 94 | 2289446 Gene 4580 999 1004 95 | 2289447 Compound DB00171 603 606 96 | 2289447 Compound DB00640 603 606 97 | 2289447 Gene 2591 820 836 98 | 2289449 Disease DOID:219 259 279 99 | 2289449 Compound DB00974 852 856 100 | 2289449 Compound DB09153 870 874 101 | 2289449 Gene 22999 957 972 102 | 2289449 Gene 22999 1079 1094 103 | 2289449 Gene 22999 1176 1191 104 | 2289450 Gene 4502 58 99 105 | 2289450 Gene 4502 101 104 106 | 2289450 Gene 4502 201 204 107 | 2289450 Gene 4502 433 436 108 | 2289450 Gene 4502 527 530 109 | 2289450 Compound DB00171 1073 1076 110 | 2289450 Compound DB00640 1073 1076 111 | 2289450 Gene 4502 1185 1188 112 | 2289451 Compound DB00171 1235 1238 113 | 2289451 Compound DB00640 1235 1238 114 | 2289452 Compound DB00171 823 826 115 | 2289452 Compound DB00640 823 826 116 | 2289452 Compound DB00171 861 864 117 | 2289452 Compound DB00640 861 864 118 | 2289452 Compound DB00171 975 978 119 | 2289452 Compound DB00640 975 978 120 | 2289453 Compound DB00151 647 656 121 | 2289453 Compound DB09485 647 656 122 | 2289453 Compound DB00928 1553 1564 123 | 2289453 Gene 1850 1586 1590 124 | 2289453 Gene 22999 1685 1700 125 | 2289454 Compound DB00316 108 109 126 | 2289454 Gene 539 432 442 127 | 2289454 Gene 539 444 473 128 | 2289454 Gene 539 475 482 129 | 2289454 Gene 389 486 496 130 | 2289454 Gene 389 498 539 131 | 2289454 Gene 389 541 547 132 | 2289454 Gene 2260 555 565 133 | 2289454 Gene 2260 567 574 134 | 2289454 Gene 539 759 769 135 | 2289454 Gene 539 1061 1072 136 | 2289454 Gene 539 1286 1296 137 | 2289457 Gene 173 49 56 138 | 2289457 Gene 173 216 223 139 | 2289457 Compound DB09341 235 242 140 | 2289457 Compound DB11280 235 242 141 | 2289457 Gene 173 254 261 142 | 2289457 Compound DB09341 272 279 143 | 2289457 Compound DB11280 272 279 144 | 2289457 Gene 173 500 507 145 | 2289457 Compound DB09341 649 656 146 | 2289457 Compound DB11280 649 656 147 | 2289462 Compound DB00541 1918 1929 148 | 2289465 Gene 3908 0 3 149 | 2289465 Gene 3908 168 198 150 | 2289465 Gene 3908 200 203 151 | 2289465 Gene 3908 416 419 152 | 2289465 Gene 3908 571 574 153 | 2289465 Gene 3908 871 874 154 | 2289465 Gene 3908 892 895 155 | 2289465 Gene 3908 1046 1049 156 | 2289465 Gene 3908 1254 1257 157 | 2289465 Gene 3908 1331 1334 158 | 2289470 Compound DB00065 86 90 159 | 2289470 Compound DB00065 130 134 160 | 2289470 Compound DB00065 207 211 161 | 2289470 Compound DB00065 477 481 162 | 2289470 Compound DB00065 755 759 163 | 2289470 Compound DB00065 893 897 164 | 2289470 Compound DB00065 941 945 165 | 2289470 Compound DB00065 1006 1010 166 | 2289470 Compound DB00065 1208 1212 167 | 2289470 Compound DB00065 1238 1242 168 | 2289470 Compound DB00065 1368 1372 169 | 2289470 Compound DB00065 1404 1408 170 | 2289470 Compound DB00065 1448 1452 171 | 2289470 Compound DB00065 1501 1505 172 | 2289470 Compound DB00065 1574 1580 173 | 2289470 Compound DB00065 1630 1636 174 | 2289470 Compound DB00065 1673 1677 175 | 2289472 Compound DB00065 136 140 176 | 2289472 Compound DB00065 218 222 177 | 2289472 Compound DB00065 399 403 178 | 2289472 Compound DB00065 665 669 179 | 2289472 Compound DB00065 831 835 180 | 2289472 Compound DB00065 1162 1166 181 | 2289473 Gene 1876 184 203 182 | 2289473 Gene 1876 205 208 183 | 2289473 Gene 1876 559 562 184 | 2289473 Gene 1876 785 788 185 | 2289473 Gene 1876 835 838 186 | 2289473 Gene 4487 1059 1063 187 | 2289473 Gene 2538 1068 1076 188 | 2289474 Disease DOID:2994 424 443 189 | 2289474 Compound DB00974 630 634 190 | 2289474 Compound DB00974 1133 1137 191 | 2289480 Compound DB00171 1241 1244 192 | 2289480 Compound DB00640 1241 1244 193 | 2289484 Gene 7594 4 12 194 | 2289484 Gene 55553 24 37 195 | 2289484 Gene 7594 1101 1109 196 | 2289484 Gene 55553 1139 1152 197 | 2289484 Gene 55553 1156 1169 198 | 2289484 Gene 55553 1323 1336 199 | 2289484 Gene 55553 1474 1487 200 | 2289489 Gene 3772 757 767 201 | 2289489 Gene 3772 926 936 202 | 2289490 Gene 7594 720 728 203 | 2289490 Gene 7594 1457 1465 204 | 2289491 Gene 23480 44 50 205 | 2289491 Gene 23480 250 256 206 | 2289491 Gene 23480 335 341 207 | 2289491 Gene 23480 379 385 208 | 2289491 Gene 23480 468 474 209 | 2289491 Gene 23480 588 594 210 | 2289491 Gene 23480 651 657 211 | 2289491 Gene 23480 772 778 212 | 2289491 Gene 23480 893 899 213 | 2289491 Gene 23480 985 991 214 | 2289491 Gene 23480 1109 1115 215 | 2289491 Compound DB00171 1152 1155 216 | 2289491 Compound DB00640 1152 1155 217 | 2289491 Compound DB00171 1271 1276 218 | 2289491 Compound DB00640 1271 1276 219 | 2289491 Gene 23480 1306 1312 220 | 2289491 Gene 23480 1362 1368 221 | 2289491 Compound DB00171 1398 1403 222 | 2289491 Compound DB00640 1398 1403 223 | 2289491 Gene 23480 1455 1461 224 | 2289491 Gene 23480 1646 1652 225 | 2289491 Gene 23480 1698 1704 226 | 2289492 Compound DB00171 116 119 227 | 2289492 Compound DB00640 116 119 228 | 2289492 Gene 173 120 127 229 | 2289492 Gene 173 192 199 230 | 2289492 Gene 173 589 596 231 | 2289492 Gene 173 832 839 232 | 2289492 Gene 173 911 918 233 | 2289492 Disease DOID:1826 1006 1024 234 | 2289492 Gene 173 1070 1077 235 | 2289492 Gene 173 1161 1168 236 | 2289492 Compound DB00171 1217 1220 237 | 2289492 Compound DB00640 1217 1220 238 | 2289492 Compound DB00171 1296 1299 239 | 2289492 Compound DB00640 1296 1299 240 | 2289492 Compound DB00171 1385 1388 241 | 2289492 Compound DB00640 1385 1388 242 | 2289492 Gene 173 1465 1472 243 | 2289492 Compound DB00171 1529 1532 244 | 2289492 Compound DB00640 1529 1532 245 | 2289492 Gene 173 1594 1616 246 | 2289492 Compound DB00171 1691 1694 247 | 2289492 Compound DB00640 1691 1694 248 | 2289492 Gene 173 1709 1716 249 | 2289492 Compound DB09353 1755 1756 250 | 2289492 Gene 173 1868 1890 251 | 2289492 Gene 173 2034 2041 252 | 2289492 Compound DB00171 2117 2120 253 | 2289492 Compound DB00640 2117 2120 254 | 2289492 Gene 173 2134 2141 255 | 2289492 Disease DOID:1826 2369 2387 256 | 2289495 Compound DB00171 838 841 257 | 2289495 Compound DB00640 838 841 258 | 2289495 Compound DB00171 1582 1585 259 | 2289495 Compound DB00640 1582 1585 260 | 2289496 Gene 22999 46 61 261 | 2289496 Gene 22999 149 164 262 | 2289496 Compound DB00172 1561 1568 263 | 2289496 Compound DB00172 1709 1716 264 | 2289496 Compound DB00133 1859 1865 265 | 2289496 Compound DB00135 1870 1878 266 | 2289498 Gene 328 59 63 267 | 2289498 Gene 328 414 418 268 | 2289498 Gene 328 560 564 269 | 2289498 Gene 328 776 780 270 | 2289498 Gene 328 982 986 271 | 2289498 Gene 328 1033 1037 272 | 2289498 Gene 328 1501 1505 273 | 2289498 Gene 328 1652 1656 274 | 2289498 Gene 328 1907 1911 275 | 2289499 Compound DB00171 464 467 276 | 2289499 Compound DB00640 464 467 277 | 2289499 Compound DB09407 662 667 278 | 2289499 Compound DB09407 937 942 279 | 2289499 Compound DB00171 1067 1070 280 | 2289499 Compound DB00640 1067 1070 281 | 2289500 Compound DB00608 966 977 282 | 2289500 Compound DB00608 1102 1113 283 | 2289501 Disease DOID:12365 0 19 284 | 2289501 Compound DB01109 574 581 285 | 2289501 Disease DOID:12365 1114 1131 286 | 2289501 Compound DB00686 1160 1180 287 | 2289501 Compound DB01109 1186 1193 288 | 2289501 Compound DB01109 1581 1588 289 | 2289503 Disease DOID:1909 88 96 290 | 2289503 Gene 2253 214 218 291 | 2289503 Disease DOID:1909 242 250 292 | 2289503 Disease DOID:1909 405 413 293 | 2289503 Compound DB01109 466 473 294 | 2289503 Disease DOID:1909 500 508 295 | 2289503 Disease DOID:1909 711 719 296 | 2289503 Gene 2253 725 729 297 | 2289503 Gene 2253 838 842 298 | 2289503 Gene 2253 995 999 299 | 2289503 Gene 2253 1107 1111 300 | 2289503 Disease DOID:1909 1132 1140 301 | 2289503 Gene 2253 1204 1208 302 | 2289503 Gene 2253 1325 1329 303 | 2289503 Gene 2253 1391 1395 304 | 2289503 Gene 2253 1587 1591 305 | 2289503 Disease DOID:1909 1635 1648 306 | 2289503 Disease DOID:1909 1740 1748 307 | 2289503 Gene 2253 1762 1766 308 | 2289503 Gene 2253 1844 1848 309 | 2289503 Gene 2253 1869 1873 310 | 2289503 Disease DOID:1909 1908 1916 311 | 2289503 Gene 2253 1950 1954 312 | 2289503 Compound DB09153 2020 2024 313 | 2289503 Gene 2253 2081 2085 314 | 2289503 Gene 2253 2140 2144 315 | 2289503 Gene 2253 2247 2251 316 | 2289503 Disease DOID:1909 2261 2269 317 | 2289503 Disease DOID:1909 2393 2401 318 | 2289504 Compound DB09353 1795 1796 319 | 2289505 Disease DOID:1192 66 79 320 | 2289505 Disease DOID:1192 176 189 321 | 2289505 Compound DB01394 624 634 322 | 2289506 Gene 3856 53 63 323 | 2289506 Gene 3856 314 324 324 | 2289506 Gene 3856 326 330 325 | 2289506 Gene 3856 386 390 326 | 2289506 Gene 9670 424 428 327 | 2289506 Gene 3856 556 560 328 | 2289506 Gene 3856 636 640 329 | 2289506 Gene 3856 689 693 330 | 2289506 Gene 3856 857 861 331 | 2289506 Gene 3856 1081 1085 332 | 2289506 Gene 3856 1545 1549 333 | 2289506 Gene 3856 1835 1839 334 | 2289507 Gene 55829 34 53 335 | 2289507 Gene 55829 291 310 336 | 2289507 Gene 55829 500 519 337 | 2289507 Gene 55829 562 581 338 | 2289507 Gene 55829 878 897 339 | 2289507 Gene 55829 1109 1128 340 | 2289507 Compound DB01229 1331 1336 341 | 2289507 Gene 55829 1419 1438 342 | 2289508 Gene 55890 435 440 343 | 2289508 Gene 55890 493 498 344 | 2289508 Gene 55890 645 650 345 | 2289508 Compound DB08818 753 763 346 | 2289509 Gene 23480 403 409 347 | 2289509 Gene 23480 669 675 348 | 2289509 Compound DB00171 713 716 349 | 2289509 Compound DB00640 713 716 350 | 2289509 Gene 23480 980 986 351 | 2289509 Gene 23480 1057 1063 352 | 2289510 Compound DB01394 126 136 353 | 2289510 Compound DB01394 315 325 354 | 2289510 Compound DB01394 1651 1661 355 | 2289510 Compound DB01394 1913 1923 356 | 2289510 Compound DB01394 2282 2292 357 | 2289510 Compound DB01394 2390 2400 358 | 2289514 Disease DOID:2355 607 618 359 | 2289515 Compound DB00171 928 931 360 | 2289515 Compound DB00640 928 931 361 | 2289517 Compound DB00065 1949 1953 362 | 2289524 Gene 1876 0 19 363 | 2289524 Gene 1876 643 662 364 | 2289524 Gene 1876 664 667 365 | 2289524 Gene 1876 719 722 366 | 2289524 Gene 1876 873 876 367 | 2289525 Gene 23480 1683 1689 368 | 2289525 Gene 23480 1931 1937 369 | 4272812 Gene 293 10 25 370 | 4272812 Disease DOID:14330 41 60 371 | 4272812 Disease DOID:14330 61 80 372 | 4272812 Disease DOID:14330 82 84 373 | 4272812 Gene 293 303 318 374 | 4272812 Gene 293 320 329 375 | 4272812 Gene 293 446 455 376 | 4272812 Disease DOID:14330 495 497 377 | 4272812 Disease DOID:14330 557 559 378 | 4272812 Gene 293 765 774 379 | 4272812 Gene 293 817 826 380 | 4272812 Gene 293 1051 1060 381 | 4272812 Gene 55937 1069 1074 382 | 4272812 Gene 293 1203 1212 383 | 4272812 Compound DB00988 1334 1342 384 | 4272812 Compound DB00988 1344 1346 385 | 4272812 Gene 293 1377 1386 386 | 4272812 Disease DOID:14330 1495 1497 387 | 4272812 Disease DOID:14330 1604 1623 388 | 4272812 Disease DOID:14330 1625 1627 389 | 4272812 Disease DOID:14330 1854 1856 390 | 4272812 Disease DOID:2377 1862 1880 391 | 4272812 Disease DOID:14330 2071 2073 392 | 4272812 Disease DOID:14330 2199 2201 393 | 4272812 Disease DOID:14330 2530 2532 394 | 4272812 Disease DOID:14330 2683 2685 395 | 4272812 Disease DOID:1319 3924 3936 396 | 4272812 Disease DOID:1319 4111 4123 397 | 4272812 Disease DOID:14330 4473 4475 398 | 4272812 Disease DOID:14330 4915 4917 399 | 4272812 Disease DOID:10652 5011 5030 400 | 4272812 Disease DOID:14330 5036 5047 401 | 4272812 Gene 293 6252 6261 402 | 4272812 Gene 293 6790 6799 403 | 4272812 Gene 293 7067 7076 404 | 4272812 Gene 293 7162 7171 405 | 4272812 Gene 293 7219 7228 406 | 4272812 Gene 8534 7480 7518 407 | 4272812 Gene 8534 7520 7526 408 | 4272812 Gene 8534 7748 7754 409 | 4272812 Disease DOID:10652 8359 8378 410 | 4272812 Disease DOID:14330 9978 9980 411 | 4272812 Gene 293 10499 10508 412 | 4272812 Gene 55937 10599 10604 413 | 4272812 Disease DOID:14330 11206 11208 414 | 4272812 Disease DOID:14330 11225 11227 415 | 4272812 Disease DOID:14330 11445 11447 416 | 4272812 Gene 293 11470 11479 417 | 4272812 Disease DOID:14330 11530 11532 418 | 4272812 Disease DOID:14330 11638 11640 419 | 4272812 Gene 293 11661 11670 420 | 4272812 Gene 293 12094 12103 421 | 4272812 Disease DOID:14330 12493 12495 422 | 4272812 Disease DOID:14330 12550 12552 423 | 4272812 Disease DOID:14330 12667 12669 424 | 4272812 Disease DOID:14330 12941 12943 425 | 4272812 Disease DOID:14330 13140 13142 426 | 4272812 Disease DOID:14330 13232 13243 427 | 4272812 Gene 293 13535 13544 428 | 4272812 Gene 293 13546 13550 429 | 4272812 Gene 293 13704 13708 430 | 4272812 Gene 293 13843 13852 431 | 4272812 Gene 293 13854 13858 432 | 4272812 Disease DOID:14330 13985 13987 433 | 4272812 Gene 293 14040 14044 434 | 4272812 Disease DOID:14330 14089 14091 435 | 4272812 Gene 293 14192 14196 436 | 4272812 Disease DOID:14330 14268 14270 437 | 4272812 Gene 293 14410 14414 438 | 4272812 Disease DOID:14330 14475 14477 439 | 4272812 Gene 293 14797 14801 440 | 4272812 Disease DOID:14330 14879 14881 441 | 4272812 Disease DOID:14330 14981 14983 442 | 4272812 Gene 293 14994 14998 443 | 4272812 Gene 293 15071 15080 444 | 4272812 Gene 293 15382 15386 445 | 4272812 Gene 293 15448 15457 446 | 4272812 Gene 293 15556 15560 447 | 4272812 Disease DOID:14330 15683 15685 448 | 4272812 Gene 293 15984 15988 449 | 4272812 Disease DOID:14330 16084 16086 450 | 4272812 Gene 293 16106 16110 451 | 4272812 Disease DOID:14330 16251 16253 452 | 4272812 Disease DOID:14330 16436 16438 453 | 4272812 Disease DOID:14330 16540 16542 454 | 4272812 Disease DOID:14330 16604 16606 455 | 4272812 Disease DOID:14330 16660 16662 456 | 4272812 Disease DOID:14330 16731 16761 457 | 4272812 Disease DOID:14330 16783 16785 458 | 4272812 Disease DOID:14330 18531 18533 459 | 4272812 Disease DOID:14330 18667 18669 460 | 4272812 Gene 293 18935 18944 461 | 4272812 Disease DOID:14330 19100 19111 462 | 4272812 Disease DOID:14330 19145 19147 463 | 4272812 Disease DOID:14330 19264 19266 464 | 4272812 Gene 293 20236 20251 465 | 4272812 Disease DOID:14330 20697 20699 466 | 4272812 Compound DB00988 20843 20851 467 | 4272812 Compound DB01235 20843 20851 468 | 4272812 Disease DOID:14330 20863 20865 469 | 4272812 Disease DOID:14330 21011 21013 470 | 4272812 Gene 293 21179 21188 471 | 4272812 Disease DOID:14330 22419 22421 472 | 4272812 Compound DB00988 22536 22544 473 | 4272812 Disease DOID:14330 22775 22777 474 | 4272812 Disease DOID:14330 22991 22993 475 | 4272812 Gene 293 23064 23073 476 | 4272812 Disease DOID:14330 23155 23157 477 | 4272812 Disease DOID:14330 23528 23530 478 | 4272812 Disease DOID:14330 24663 24665 479 | 4272812 Gene 293 24883 24887 480 | 4272812 Disease DOID:14330 25202 25204 481 | 4272812 Gene 55937 25307 25312 482 | 4272812 Gene 293 25352 25361 483 | 4272812 Disease DOID:14330 25436 25438 484 | 4272812 Gene 293 25634 25643 485 | 4272812 Gene 55937 25703 25708 486 | 4272812 Disease DOID:14330 26093 26095 487 | 4272812 Disease DOID:14330 26266 26268 488 | 4272812 Gene 293 26558 26567 489 | 4272812 Gene 293 27052 27061 490 | 4272812 Gene 293 27175 27184 491 | 4272812 Compound DB01032 27270 27280 492 | 4272812 Gene 293 27419 27428 493 | 4272812 Gene 293 27765 27774 494 | 4272812 Gene 293 27962 27971 495 | 4272812 Compound DB01032 28135 28145 496 | 4272812 Disease DOID:14330 28521 28523 497 | 4272812 Gene 293 28825 28834 498 | 4272812 Disease DOID:14330 28924 28926 499 | 4272812 Gene 293 28947 28956 500 | 4272812 Gene 293 29199 29208 501 | 4272812 Gene 293 29296 29305 502 | 4272812 Gene 293 29581 29590 503 | 4272812 Disease DOID:14330 29788 29790 504 | 4272812 Disease DOID:14330 30105 30107 505 | 4272812 Gene 293 30194 30203 506 | 4272812 Disease DOID:14330 30845 30847 507 | 4272812 Gene 293 31103 31112 508 | 4272812 Gene 293 31566 31575 509 | 4272812 Disease DOID:14330 31661 31663 510 | 4272812 Disease DOID:14330 31780 31782 511 | 4272812 Gene 293 31977 31986 512 | 4272812 Gene 293 32563 32572 513 | 4272812 Gene 293 32675 32684 514 | 4272812 Gene 293 32731 32740 515 | 4272812 Gene 293 32855 32864 516 | 4272812 Gene 293 32912 32921 517 | 4272812 Disease DOID:14330 33006 33008 518 | 4272812 Gene 293 33050 33059 519 | 4272812 Gene 307 33369 33389 520 | 4272812 Gene 293 33555 33564 521 | 4272812 Disease DOID:14330 33632 33634 522 | 4272812 Gene 293 33759 33768 523 | 4272812 Gene 293 34299 34308 524 | 4272812 Disease DOID:14330 34614 34616 525 | 4272812 Gene 293 34842 34851 526 | 4272812 Gene 293 35104 35113 527 | 4272812 Gene 293 35247 35256 528 | 4272812 Disease DOID:14330 35453 35455 529 | 4272812 Disease DOID:14330 35877 35879 530 | 4272812 Gene 293 36090 36099 531 | 4272812 Gene 293 36120 36129 532 | 4272812 Gene 293 36298 36307 533 | 4272812 Gene 293 36820 36829 534 | 4272812 Disease DOID:14330 36834 36836 535 | 4272812 Gene 5182 36887 36891 536 | 4272812 Gene 293 37011 37020 537 | 4272812 Gene 293 37075 37084 538 | 4272812 Gene 5182 37190 37194 539 | 4272812 Gene 293 37277 37286 540 | 4272812 Gene 293 37365 37374 541 | 4272812 Gene 55937 37476 37481 542 | 4272812 Gene 433 37493 37497 543 | 4272812 Disease DOID:14330 37714 37716 544 | 4272812 Gene 433 37748 37752 545 | 4272812 Gene 433 37838 37857 546 | 4272812 Gene 433 37897 37901 547 | 4272812 Gene 293 37927 37936 548 | 4272812 Gene 433 37987 37991 549 | 4272812 Gene 293 38005 38014 550 | 4272812 Gene 293 38040 38049 551 | 4272812 Gene 293 38161 38170 552 | 4272812 Gene 433 38237 38241 553 | 4272812 Gene 540 38267 38276 554 | 4272812 Disease DOID:14330 38351 38353 555 | 4272812 Gene 540 38412 38421 556 | 4272812 Disease DOID:14330 38514 38516 557 | 4272812 Gene 540 38535 38544 558 | 4272812 Gene 540 38758 38767 559 | 4272812 Gene 55937 38870 38875 560 | 4272812 Gene 540 38929 38938 561 | 4272812 Disease DOID:14330 39006 39008 562 | 4272812 Compound DB00988 39131 39133 563 | 4272812 Gene 55937 39268 39273 564 | 4272812 Gene 293 39310 39319 565 | 4272812 Gene 293 39439 39448 566 | 4272812 Gene 293 39633 39642 567 | 4272812 Gene 293 39811 39820 568 | 4272812 Gene 293 39886 39895 569 | 4272812 Gene 293 40044 40053 570 | 4272812 Gene 293 40228 40237 571 | 4272812 Disease DOID:14330 40373 40375 572 | 4272812 Disease DOID:14330 40553 40555 573 | 4272812 Disease DOID:14330 40644 40646 574 | 4272812 Gene 293 40717 40726 575 | 4272812 Gene 293 40820 40829 576 | 4272812 Gene 293 40950 40954 577 | 4272812 Disease DOID:14330 41063 41065 578 | 4272812 Gene 293 41115 41124 579 | 4272812 Disease DOID:14330 41185 41187 580 | 4272812 Gene 55937 41209 41214 581 | 4272812 Gene 293 41235 41244 582 | 4272812 Gene 55937 41299 41304 583 | 4272812 Gene 55937 41354 41359 584 | 4272812 Gene 55937 41549 41554 585 | 4272812 Gene 55937 41889 41894 586 | 4272812 Disease DOID:14330 41990 41992 587 | 4272812 Gene 293 42054 42063 588 | 4272812 Disease DOID:14330 42218 42220 589 | 4272812 Gene 293 42685 42694 590 | 4272812 Disease DOID:14330 43099 43101 591 | 4272812 Compound DB00988 43188 43196 592 | 4272812 Gene 293 43248 43257 593 | 4272812 Compound DB00988 43267 43269 594 | 4272812 Gene 293 43328 43337 595 | 4272812 Gene 307 43347 43367 596 | 4272812 Compound DB00988 43478 43484 597 | 4272812 Compound DB01235 43478 43484 598 | 4272812 Compound DB00988 43488 43490 599 | 4272812 Compound DB00988 43516 43518 600 | 4272812 Gene 293 43572 43581 601 | 4272812 Gene 55937 43587 43592 602 | 4272812 Gene 293 43649 43658 603 | 4272812 Gene 55937 43686 43691 604 | 4272812 Gene 293 43710 43719 605 | 4272812 Gene 293 43906 43915 606 | 4272812 Compound DB00988 43984 43986 607 | 4272812 Gene 55547 44104 44107 608 | 4272812 Compound DB00988 44381 44383 609 | 4272812 Compound DB00988 44435 44437 610 | 4272812 Compound DB00988 44484 44486 611 | 4272812 Gene 293 44506 44515 612 | 4272812 Disease DOID:14330 44809 44811 613 | 4272812 Gene 293 44838 44847 614 | 4272812 Gene 55937 44900 44905 615 | 4272812 Compound DB00988 45004 45006 616 | 4272812 Gene 293 45040 45055 617 | 4272812 Compound DB00988 45081 45083 618 | 4272812 Gene 293 45099 45108 619 | 4272812 Disease DOID:14330 45181 45183 620 | 4272812 Disease DOID:14330 45259 45261 621 | 4272812 Gene 293 45413 45422 622 | 4272812 Gene 293 45493 45502 623 | 4272812 Gene 293 45587 45596 624 | 4272812 Gene 293 45722 45731 625 | 4272812 Gene 293 45785 45794 626 | 4272812 Gene 293 45842 45851 627 | 4272812 Gene 293 46074 46083 628 | 4272812 Gene 293 46129 46138 629 | 4272812 Gene 293 46226 46235 630 | 4272812 Gene 293 46313 46322 631 | 4272812 Compound DB00988 46334 46336 632 | 4272812 Gene 293 46394 46403 633 | 4272812 Compound DB00988 46408 46410 634 | 4272812 Gene 293 46436 46445 635 | 4272812 Gene 293 46651 46660 636 | 4272812 Gene 293 46696 46705 637 | 4272812 Gene 293 46922 46931 638 | 4272812 Gene 293 47212 47221 639 | 4272812 Gene 293 47525 47534 640 | 4272812 Gene 293 47862 47871 641 | 4272812 Gene 293 47920 47929 642 | 4272812 Gene 293 48027 48036 643 | 4272812 Compound DB00172 48351 48358 644 | 4272812 Gene 293 48442 48451 645 | 4272812 Gene 55937 48963 48968 646 | 4272812 Gene 55937 49068 49073 647 | 4272812 Gene 55937 49126 49131 648 | 4272812 Gene 293 49288 49297 649 | 4272812 Gene 293 49373 49382 650 | 4272812 Gene 293 49447 49456 651 | 4272812 Gene 293 49785 49794 652 | 4272812 Gene 293 50773 50782 653 | 4272812 Gene 293 50888 50892 654 | 4272812 Gene 293 50981 50990 655 | 4272812 Gene 293 51149 51158 656 | 4272812 Gene 293 51355 51364 657 | 4272812 Gene 293 51433 51442 658 | 4272812 Gene 293 51632 51641 659 | 4272812 Gene 293 51702 51711 660 | 4272812 Gene 293 52074 52078 661 | 4272812 Disease DOID:14330 52087 52089 662 | 4272812 Gene 293 52149 52158 663 | 4272812 Gene 293 52364 52373 664 | 4272812 Compound DB00133 52517 52523 665 | 4272812 Gene 293 52540 52549 666 | 4272812 Compound DB00133 52650 52656 667 | 4272812 Gene 293 52729 52738 668 | 4272812 Gene 293 52821 52830 669 | 4272812 Gene 293 52898 52907 670 | 4272812 Gene 293 53323 53332 671 | 4272812 Gene 293 53397 53406 672 | 4272812 Disease DOID:14330 53421 53432 673 | 4272812 Gene 293 53592 53601 674 | 4272812 Gene 293 53779 53788 675 | 4272812 Gene 293 53991 54000 676 | 4272812 Gene 293 54125 54134 677 | 4272812 Disease DOID:14330 54158 54160 678 | 4272812 Gene 293 54267 54276 679 | 4272812 Gene 55937 54294 54299 680 | 4272812 Compound DB00988 54466 54474 681 | 4272812 Disease DOID:14330 54541 54543 682 | 4272812 Disease DOID:14330 54544 54563 683 | 4272812 Disease DOID:14330 54717 54736 684 | 4272812 Disease DOID:14330 54795 54812 685 | 4272812 Disease DOID:14330 54834 54853 686 | 4272812 Gene 293 54929 54944 687 | 4272812 Disease DOID:14330 54978 54997 688 | 4272812 Compound DB00988 55028 55036 689 | 4272812 Disease DOID:14330 55052 55071 690 | 4272812 Disease DOID:14330 55096 55115 691 | 4272812 Disease DOID:14330 55183 55213 692 | 4272812 Disease DOID:10652 55309 55341 693 | 4272812 Disease DOID:14330 55354 55371 694 | 4272812 Disease DOID:14330 55496 55515 695 | 4272812 Disease DOID:14330 55592 55611 696 | 4272812 Disease DOID:14330 55626 55663 697 | 4272812 Gene 293 55666 55681 698 | 4272812 Gene 293 55941 55956 699 | 4272812 Gene 293 56010 56025 700 | 4272812 Disease DOID:14330 56150 56169 701 | 4272812 Gene 293 56277 56281 702 | 4272812 Gene 293 56282 56297 703 | 4272812 Disease DOID:14330 56354 56373 704 | 4272812 Gene 293 56603 56618 705 | 4272812 Gene 293 56634 56649 706 | 4272812 Disease DOID:14330 56885 56902 707 | 4272812 Gene 8534 57066 57072 708 | 4272812 Gene 293 57398 57413 709 | 4272812 Disease DOID:14330 57469 57488 710 | 4272812 Disease DOID:14330 57547 57566 711 | 4272812 Gene 293 57584 57599 712 | 4272812 Disease DOID:14330 57699 57718 713 | 4272812 Disease DOID:14330 57765 57784 714 | 4272812 Disease DOID:14330 57841 57860 715 | 4272812 Disease DOID:14330 57933 57952 716 | 4272812 Disease DOID:14330 57955 57998 717 | 4272812 Disease DOID:14330 58031 58074 718 | 4272812 Disease DOID:14330 58100 58117 719 | 4272812 Disease DOID:14330 58164 58192 720 | 4272812 Disease DOID:14330 58358 58377 721 | 4272812 Gene 293 58380 58395 722 | 4272812 Disease DOID:14330 58422 58441 723 | 4272812 Disease DOID:14330 58496 58528 724 | 4272812 Gene 293 58654 58669 725 | 4272812 Disease DOID:14330 58673 58692 726 | 4272812 Gene 293 58722 58737 727 | 4272812 Disease DOID:14330 58778 58797 728 | 4272812 Gene 293 58854 58869 729 | 4272812 Gene 293 58903 58918 730 | 4272812 Gene 293 58951 58966 731 | 4272812 Disease DOID:14330 59007 59024 732 | 4272812 Gene 293 59181 59185 733 | 4272812 Disease DOID:14330 59191 59219 734 | 4272812 Disease DOID:14330 59236 59264 735 | 4272812 Gene 293 59295 59310 736 | 4272812 Disease DOID:14330 59341 59358 737 | 4272812 Gene 293 59410 59425 738 | 4272812 Gene 293 59427 59431 739 | 4272812 Disease DOID:14330 59459 59478 740 | 4272812 Gene 293 59481 59496 741 | 4272812 Disease DOID:14330 59533 59552 742 | 4272812 Gene 293 59555 59570 743 | 4272812 Disease DOID:14330 59604 59623 744 | 4272812 Gene 293 59698 59713 745 | 4272812 Disease DOID:14330 59821 59840 746 | 4272812 Disease DOID:14330 59856 59882 747 | 4272812 Gene 293 59903 59918 748 | 4272812 Gene 293 60019 60034 749 | 4272812 Gene 293 60168 60183 750 | 4272812 Gene 293 60327 60342 751 | 4272812 Compound DB00988 60394 60402 752 | 4272812 Gene 293 60493 60508 753 | 4272812 Gene 293 60631 60635 754 | 4272812 Disease DOID:14330 60683 60700 755 | 4272812 Disease DOID:14330 60763 60782 756 | 4272812 Disease DOID:14330 60883 60902 757 | 4272812 Disease DOID:14330 60959 60978 758 | 4272812 Disease DOID:14330 61034 61051 759 | 4272812 Disease DOID:14330 61118 61135 760 | 4272812 Disease DOID:14330 61210 61229 761 | 4272812 Gene 293 61457 61472 762 | 4272812 Gene 293 61506 61521 763 | 4272812 Disease DOID:14330 61563 61595 764 | 4272812 Disease DOID:14330 61659 61688 765 | 4272812 Disease DOID:14330 61796 61829 766 | 4272812 Gene 293 61895 61910 767 | 4272812 Gene 293 61921 61936 768 | 4272812 Disease DOID:14330 62027 62044 769 | 4272812 Disease DOID:14330 62104 62121 770 | 4272812 Disease DOID:14330 62341 62360 771 | 4272812 Disease DOID:14330 62419 62438 772 | 4272812 Disease DOID:14330 62725 62744 773 | 4272812 Disease DOID:14330 62832 62851 774 | 4272812 Compound DB00988 62856 62862 775 | 4272812 Compound DB01235 62856 62862 776 | 4272812 Disease DOID:14330 62954 62973 777 | 4272812 Gene 293 63093 63108 778 | 4272812 Gene 293 63278 63293 779 | 4272812 Disease DOID:14330 63406 63425 780 | 4272812 Disease DOID:14330 63449 63468 781 | 4272812 Disease DOID:14330 63658 63677 782 | 4272812 Compound DB01577 63834 63849 783 | 4272812 Gene 293 63911 63926 784 | 4272812 Disease DOID:14330 63971 63990 785 | 4272812 Disease DOID:14330 64002 64004 786 | 4272812 Compound DB01032 64283 64293 787 | 4272812 Gene 293 64409 64424 788 | 4272812 Disease DOID:14330 64499 64518 789 | 4272812 Disease DOID:14330 64565 64584 790 | 4272812 Disease DOID:14330 64659 64678 791 | 4272812 Disease DOID:14330 64740 64759 792 | 4272812 Gene 293 64847 64862 793 | 4272812 Gene 293 64940 64955 794 | 4272812 Gene 293 65117 65132 795 | 4272812 Gene 293 65201 65216 796 | 4272812 Disease DOID:14330 65256 65275 797 | 4272812 Disease DOID:14330 65315 65366 798 | 4272812 Disease DOID:14330 65406 65425 799 | 4272812 Disease DOID:14330 65506 65525 800 | 4272812 Disease DOID:14330 65795 65814 801 | 4272812 Disease DOID:14330 66149 66168 802 | 4272812 Disease DOID:14330 66268 66285 803 | 4272812 Disease DOID:14330 66315 66334 804 | 4272812 Disease DOID:14330 66417 66434 805 | 4272812 Disease DOID:14330 66495 66514 806 | 4272812 Compound DB00988 66583 66591 807 | 4272812 Gene 293 66608 66623 808 | 4272812 Disease DOID:14330 66669 66688 809 | 4272812 Disease DOID:14330 66718 66737 810 | 4272812 Gene 293 66753 66768 811 | 4272812 Disease DOID:14330 66925 66944 812 | 4272812 Gene 293 66980 66995 813 | 4272812 Gene 293 67141 67156 814 | 4272812 Disease DOID:14330 67178 67197 815 | 4272812 Gene 293 67198 67213 816 | 4272812 Gene 293 67510 67525 817 | 4272812 Disease DOID:14330 67814 67833 818 | 4272812 Disease DOID:14330 68110 68129 819 | 4272812 Gene 293 68147 68162 820 | 4272812 Disease DOID:14330 68210 68229 821 | 4272812 Gene 293 68263 68278 822 | 4272812 Gene 5182 68444 68448 823 | 4272812 Compound DB00988 68485 68493 824 | 4272812 Gene 293 68507 68522 825 | 4272812 Gene 293 68532 68547 826 | 4272812 Gene 4509 68575 68580 827 | 4272812 Gene 433 68590 68594 828 | 4272812 Compound DB00988 68615 68623 829 | 4272812 Gene 433 68632 68636 830 | 4272812 Gene 293 68677 68692 831 | 4272812 Disease DOID:14330 68702 68721 832 | 4272812 Gene 433 68754 68758 833 | 4272812 Disease DOID:14330 68820 68839 834 | 4272812 Gene 540 68842 68875 835 | 4272812 Disease DOID:14330 68954 68973 836 | 4272812 Gene 540 68976 68986 837 | 4272812 Disease DOID:14330 69033 69052 838 | 4272812 Gene 540 69090 69123 839 | 4272812 Gene 540 69254 69264 840 | 4272812 Gene 540 69359 69369 841 | 4272812 Compound DB00988 69383 69391 842 | 4272812 Gene 293 69396 69411 843 | 4272812 Gene 55937 69427 69432 844 | 4272812 Disease DOID:14330 69534 69553 845 | 4272812 Gene 293 69564 69579 846 | 4272812 Gene 293 69661 69676 847 | 4272812 Gene 55937 69762 69767 848 | 4272812 Disease DOID:14330 69901 69920 849 | 4272812 Gene 293 69923 69938 850 | 4272812 Disease DOID:14330 69975 69994 851 | 4272812 Gene 293 70053 70068 852 | 4272812 Compound DB00988 70076 70084 853 | 4272812 Gene 293 70299 70314 854 | 4272812 Gene 293 70358 70373 855 | 4272812 Gene 307 70399 70419 856 | 4272812 Gene 293 70443 70458 857 | 4272812 Gene 307 70504 70524 858 | 4272812 Gene 293 70563 70578 859 | 4272812 Compound DB00988 70666 70674 860 | 4272812 Gene 293 70714 70729 861 | 4272812 Compound DB00988 70884 70892 862 | 4272812 Compound DB00988 71115 71123 863 | 4272812 Gene 293 71209 71224 864 | 4272812 Compound DB00988 71274 71282 865 | 4272812 Gene 293 71477 71492 866 | 4272812 Compound DB00988 71539 71547 867 | 4272812 Compound DB00988 71576 71584 868 | 4272812 Gene 293 71599 71614 869 | 4272812 Disease DOID:14330 71837 71856 870 | 4272812 Gene 293 71872 71887 871 | 4272812 Disease DOID:14330 71911 71943 872 | 4272812 Gene 293 71976 71991 873 | 4272812 Gene 293 72103 72118 874 | 4272812 Gene 293 72131 72146 875 | 4272812 Gene 293 72224 72239 876 | 4272812 Gene 293 72321 72336 877 | 4272812 Gene 293 72398 72413 878 | 4272812 Compound DB00988 72470 72478 879 | 4272812 Gene 293 72519 72534 880 | 4272812 Gene 293 72611 72626 881 | 4272812 Gene 293 72647 72662 882 | 4272812 Gene 293 72752 72767 883 | 4272812 Disease DOID:14330 72826 72845 884 | 4272812 Gene 293 72847 72862 885 | 4272812 Gene 293 72885 72900 886 | 4272812 Disease DOID:14330 72979 72998 887 | 4272812 Gene 293 73083 73098 888 | 4272812 Disease DOID:14330 73131 73150 889 | 4272812 Gene 293 73227 73242 890 | 4272812 Gene 293 73344 73359 891 | 4272812 Gene 293 73495 73510 892 | 4272812 Gene 293 73564 73579 893 | 4272812 Gene 293 73636 73651 894 | 4272812 Gene 293 73704 73719 895 | 4272812 Gene 293 73844 73859 896 | 4272812 Compound DB00988 73877 73885 897 | 4272812 Gene 293 73886 73901 898 | 4272812 Compound DB00988 73909 73917 899 | 4272812 Compound DB00988 73922 73928 900 | 4272812 Compound DB01235 73922 73928 901 | 4272812 Disease DOID:14330 73976 73987 902 | 4272812 Disease DOID:10652 73992 74011 903 | 4272812 Gene 293 74039 74054 904 | 4272812 Disease DOID:14330 74134 74162 905 | 4272812 Gene 293 74343 74358 906 | 4272812 Disease DOID:14330 74391 74410 907 | 4272812 Compound DB00133 74442 74445 908 | 4272812 Gene 293 74459 74474 909 | 4272812 Disease DOID:14330 74522 74539 910 | 4272812 Disease DOID:14330 74666 74685 911 | 4272812 Gene 293 74743 74758 912 | 4272812 Gene 293 75024 75039 913 | 4272813 Disease DOID:10763 8551 8563 914 | 4272814 Compound DB00172 172 179 915 | 4272814 Compound DB00172 1443 1450 916 | 4272814 Compound DB06756 1455 1470 917 | 4272814 Compound DB00149 6340 6347 918 | 4272814 Compound DB00167 6348 6358 919 | 4272814 Compound DB09341 7806 7813 920 | 4272814 Compound DB11280 7806 7813 921 | 4272814 Compound DB00125 7821 7829 922 | 4272814 Compound DB00167 7837 7847 923 | 4272814 Compound DB00161 7855 7861 924 | 4272814 Compound DB09153 8118 8122 925 | 4272814 Compound DB00172 10539 10546 926 | 4272814 Compound DB09153 10584 10588 927 | 4272814 Compound DB09153 10837 10841 928 | 4272814 Compound DB00172 10926 10933 929 | 4272814 Compound DB09153 10961 10965 930 | 4272814 Compound DB09153 11167 11171 931 | 4272814 Compound DB09153 11305 11309 932 | 4272814 Compound DB09153 11332 11336 933 | 4272814 Compound DB09153 11690 11694 934 | 4272814 Compound DB09153 11847 11851 935 | 4272814 Compound DB09153 13006 13010 936 | 4272814 Compound DB09153 13116 13120 937 | 4272814 Compound DB09153 13355 13359 938 | 4272814 Compound DB09153 13527 13531 939 | 4272814 Compound DB00172 15754 15761 940 | 4272814 Compound DB09153 16186 16190 941 | 4272814 Compound DB09153 16262 16266 942 | 4272814 Compound DB09153 17944 17948 943 | 4272814 Compound DB09153 18860 18864 944 | 4272814 Disease DOID:2531 19260 19262 945 | 4272814 Disease DOID:2531 19360 19362 946 | 4272814 Compound DB00172 19678 19685 947 | 4272814 Compound DB00583 20252 20261 948 | 4272814 Compound DB06756 20603 20618 949 | 4272815 Gene 208 39 43 950 | 4272815 Gene 208 419 433 951 | 4272815 Gene 208 435 439 952 | 4272815 Gene 208 513 517 953 | 4272815 Gene 208 1362 1366 954 | 4272815 Gene 208 3555 3559 955 | 4272815 Gene 210 3564 3568 956 | 4272815 Gene 208 3592 3596 957 | 4272815 Gene 208 3945 3949 958 | 4272815 Gene 208 3995 3999 959 | 4272815 Gene 208 5240 5244 960 | 4272815 Gene 3908 6982 6987 961 | 4272815 Compound DB00118 7304 7324 962 | 4272815 Compound DB09153 7438 7442 963 | 4272815 Compound DB00974 7467 7471 964 | 4272815 Compound DB03255 7497 7503 965 | 4272815 Compound DB00898 7527 7534 966 | 4272815 Gene 208 8557 8561 967 | 4272815 Gene 208 8580 8584 968 | 4272815 Gene 3908 9704 9709 969 | 4272815 Gene 3908 9804 9809 970 | 4272815 Gene 3908 9965 9970 971 | 4272815 Gene 208 10047 10051 972 | 4272815 Gene 208 10591 10595 973 | 4272815 Gene 3908 11045 11050 974 | 4272815 Gene 3908 12858 12863 975 | 4272815 Gene 208 13101 13105 976 | 4272815 Gene 3908 13245 13250 977 | 4272815 Gene 208 13399 13403 978 | 4272815 Gene 208 13552 13556 979 | 4272815 Gene 208 13595 13599 980 | 4272815 Gene 208 13982 13986 981 | 4272815 Gene 208 16816 16820 982 | 4272815 Gene 208 16937 16941 983 | 4272815 Gene 208 17978 17982 984 | 4272815 Gene 208 18502 18506 985 | 4272815 Gene 208 18601 18605 986 | 4272815 Gene 80218 20601 20606 987 | 4272815 Disease DOID:10283 21495 21510 988 | 4272816 Compound DB09140 2791 2797 989 | 4272816 Compound DB01390 7472 7490 990 | 4272816 Compound DB09153 12535 12539 991 | 4272818 Gene 4359 10741 10744 992 | 4272818 Gene 4359 10759 10762 993 | 4272818 Gene 4257 18215 18223 994 | 4272820 Disease DOID:1826 94 112 995 | 4272820 Compound DB00829 290 298 996 | 4272820 Compound DB00186 300 309 997 | 4272820 Compound DB00683 315 324 998 | 4272820 Compound DB00829 458 466 999 | 4272820 Compound DB00186 468 477 1000 | 4272820 Compound DB00683 483 492 1001 | 4272820 Compound DB00829 1182 1190 1002 | 4272820 Compound DB00683 1221 1230 1003 | 4272820 Compound DB00186 1256 1265 1004 | 4272820 Compound DB00186 1521 1530 1005 | 4272820 Compound DB00683 1540 1549 1006 | 4272820 Compound DB00829 1553 1561 1007 | 4272820 Compound DB00683 1586 1595 1008 | 4272820 Compound DB00829 1600 1608 1009 | 4272820 Compound DB00186 1706 1715 1010 | 4272820 Disease DOID:1826 1883 1901 1011 | 4272820 Compound DB00683 2014 2023 1012 | 4272820 Disease DOID:1826 2063 2070 1013 | 4272820 Compound DB00829 2356 2364 1014 | 4272820 Compound DB00186 2369 2378 1015 | 4272820 Compound DB00683 2428 2437 1016 | 4272820 Compound DB00829 2630 2638 1017 | 4272820 Compound DB00186 2640 2649 1018 | 4272820 Compound DB00683 2655 2664 1019 | 4272820 Compound DB00186 3058 3067 1020 | 4272820 Compound DB00829 3332 3340 1021 | 4272820 Compound DB00829 3462 3470 1022 | 4272820 Compound DB00186 3472 3481 1023 | 4272820 Compound DB00683 3487 3496 1024 | 4272820 Compound DB00186 5897 5906 1025 | 4272820 Compound DB00683 5919 5928 1026 | 4272820 Compound DB00829 5932 5940 1027 | 4272820 Compound DB00829 6415 6423 1028 | 4272820 Compound DB00683 6428 6437 1029 | 4272820 Compound DB00829 6546 6554 1030 | 4272820 Compound DB00683 6585 6594 1031 | 4272820 Compound DB00186 6620 6629 1032 | 4272820 Compound DB00186 6815 6824 1033 | 4272820 Compound DB00683 6903 6912 1034 | 4272820 Compound DB00829 6917 6925 1035 | 4272820 Compound DB00186 7051 7060 1036 | 4272820 Compound DB00186 7087 7096 1037 | 4272820 Compound DB00683 7499 7508 1038 | 4272820 Compound DB00829 7512 7520 1039 | 4272820 Compound DB00186 7539 7548 1040 | 4272820 Compound DB00683 7816 7825 1041 | 4272820 Compound DB00829 7830 7838 1042 | 4272820 Compound DB00186 7932 7941 1043 | 4272820 Compound DB00186 8190 8199 1044 | 4272820 Compound DB00683 8204 8213 1045 | 4272820 Compound DB00683 8349 8358 1046 | 4272820 Compound DB00186 8396 8405 1047 | 4272820 Compound DB00829 8629 8637 1048 | 4272820 Compound DB00683 8726 8735 1049 | 4272820 Compound DB00186 8767 8776 1050 | 4272820 Compound DB00829 8881 8889 1051 | 4272820 Compound DB00186 8894 8903 1052 | 4272820 Compound DB00829 9015 9023 1053 | 4272820 Compound DB00829 9072 9080 1054 | 4272820 Compound DB00186 9139 9148 1055 | 4272820 Compound DB00186 9510 9519 1056 | 4272820 Compound DB00186 10068 10077 1057 | 4272820 Compound DB00186 10351 10360 1058 | 4272820 Compound DB00186 10942 10951 1059 | 4272820 Compound DB00186 10966 10975 1060 | 4272820 Compound DB00186 11152 11161 1061 | 4272820 Compound DB00683 11241 11250 1062 | 4272820 Compound DB00829 11254 11262 1063 | 4272820 Compound DB00683 11470 11479 1064 | 4272820 Compound DB00186 11484 11493 1065 | 4272820 Compound DB00186 12292 12301 1066 | 4272820 Compound DB00683 12490 12499 1067 | 4272820 Compound DB00829 12504 12512 1068 | 4272820 Compound DB00186 12623 12632 1069 | 4272820 Compound DB00186 21395 21404 1070 | 4272820 Compound DB00829 21406 21414 1071 | 4272820 Disease DOID:1826 21465 21483 1072 | 4272820 Disease DOID:1826 21542 21560 1073 | 4272820 Compound DB00683 21562 21571 1074 | 4272820 Compound DB00829 21579 21587 1075 | 4272820 Disease DOID:1826 21609 21627 1076 | 4272820 Compound DB00302 21891 21906 1077 | 4272820 Compound DB00829 22161 22169 1078 | 4272820 Compound DB00186 22174 22183 1079 | 4272820 Compound DB00683 22233 22242 1080 | 4272820 Compound DB00186 22247 22256 1081 | 4272820 Compound DB00186 22534 22543 1082 | 4272820 Compound DB00829 23149 23157 1083 | 4272820 Compound DB00186 23314 23323 1084 | 4272820 Compound DB00683 23487 23496 1085 | 4272821 Gene 55665 1357 1361 1086 | 4272821 Gene 55665 1975 1979 1087 | 4272821 Gene 7857 4230 4234 1088 | 4272821 Gene 392 4737 4741 1089 | 4272821 Gene 55665 5500 5504 1090 | 4272821 Gene 55665 5644 5648 1091 | 4272821 Gene 55665 5716 5720 1092 | 4272821 Gene 55665 5799 5803 1093 | 4272821 Compound DB00994 7101 7109 1094 | 4272821 Compound DB03904 9026 9030 1095 | 4272821 Compound DB03904 9432 9436 1096 | 4272821 Gene 1477 10665 10668 1097 | 4272821 Gene 1854 11060 11068 1098 | 4272821 Compound DB00529 11390 11393 1099 | 4272821 Compound DB09499 11739 11757 1100 | 4272821 Compound DB03166 11919 11930 1101 | 4272821 Compound DB03166 12271 12282 1102 | 4272821 Compound DB00529 12466 12469 1103 | 4272821 Compound DB02772 12509 12516 1104 | 4272821 Gene 8315 13771 13774 1105 | 4272821 Gene 1521 13798 13803 1106 | 4272821 Gene 8315 13919 13922 1107 | 4272821 Compound DB00529 13978 13981 1108 | 4272821 Compound DB03619 13992 14012 1109 | 4272821 Compound DB05780 13992 14012 1110 | 4272821 Compound DB03166 15081 15092 1111 | 4272821 Compound DB03166 15114 15125 1112 | 4272821 Compound DB00151 16000 16008 1113 | 4272821 Compound DB09485 16000 16008 1114 | 4272821 Gene 55665 16839 16843 1115 | 4272821 Gene 997 16896 16899 1116 | 4272821 Gene 997 16952 16955 1117 | 4272821 Gene 1854 19854 19862 1118 | 4272821 Gene 1854 20507 20515 1119 | 4272821 Gene 7857 20519 20523 1120 | 4272821 Gene 1854 21063 21071 1121 | 4272821 Gene 1854 21154 21162 1122 | 4272821 Gene 55665 26686 26690 1123 | 4272821 Gene 55665 27253 27257 1124 | 4272821 Gene 55665 27352 27356 1125 | 4272821 Gene 55665 27543 27547 1126 | 4272821 Compound DB11101 28107 28110 1127 | 4272821 Compound DB11101 28136 28139 1128 | 4272821 Gene 55665 28973 28977 1129 | 4272821 Gene 55665 29021 29025 1130 | 4272821 Gene 55665 29158 29162 1131 | 4272821 Gene 55665 29489 29493 1132 | 4272821 Gene 55665 35569 35573 1133 | 4272821 Gene 55665 35678 35682 1134 | 4272821 Gene 55665 36395 36399 1135 | 4272821 Gene 7857 36931 36935 1136 | 4272821 Gene 55665 40692 40696 1137 | 4272821 Gene 55665 40798 40802 1138 | 4272821 Gene 55665 40978 40982 1139 | 4272821 Gene 55665 41320 41324 1140 | 4272821 Gene 55665 41523 41527 1141 | 4272821 Compound DB00529 43516 43519 1142 | 4272821 Gene 7857 46777 46781 1143 | 4272821 Gene 5144 46791 46796 1144 | 4272821 Gene 55665 47337 47341 1145 | 4272822 Gene 3329 14345 14349 1146 | 4272822 Gene 22999 15000 15005 1147 | 4272822 Gene 9670 16056 16060 1148 | 4272822 Compound DB00065 18261 18265 1149 | 4272822 Compound DB09152 22416 22424 1150 | 4272822 Compound DB00131 23275 23278 1151 | 4272822 Compound DB00640 23275 23278 1152 | 4272822 Compound DB03904 27005 27009 1153 | 4272822 Compound DB00145 28092 28099 1154 | 4272822 Compound DB03904 28136 28140 1155 | 4272822 Compound DB04077 28169 28178 1156 | 4272822 Compound DB09462 28169 28178 1157 | 4272822 Compound DB00898 28377 28384 1158 | 4272822 Compound DB03166 28393 28404 1159 | 4272822 Compound DB00898 28693 28700 1160 | 4272822 Compound DB03843 28939 28951 1161 | 4272822 Compound DB03843 29137 29149 1162 | 4272822 Compound DB00145 29208 29215 1163 | 4272822 Compound DB00134 30967 30977 1164 | 4272822 Disease DOID:9970 35033 35040 1165 | 4272822 Gene 3329 35193 35197 1166 | 4272822 Gene 22999 35441 35456 1167 | 4272822 Gene 22999 35563 35578 1168 | 4272822 Disease DOID:2994 35856 35865 1169 | 4272822 Gene 136 35978 35988 1170 | 4272822 Compound DB00065 36954 36958 1171 | 4272822 Disease DOID:1324 37265 37291 1172 | 4272823 Disease DOID:10283 60 75 1173 | 4272823 Disease DOID:10283 125 140 1174 | 4272823 Disease DOID:10283 474 489 1175 | 4272823 Disease DOID:10283 560 585 1176 | 4272823 Disease DOID:10283 2526 2541 1177 | 4272823 Disease DOID:10283 4997 5012 1178 | 4272823 Disease DOID:10283 5033 5048 1179 | 4272823 Disease DOID:10283 5096 5111 1180 | 4272823 Disease DOID:10283 5847 5872 1181 | 4272823 Disease DOID:10283 6562 6587 1182 | 4272823 Disease DOID:10283 6682 6697 1183 | 4272823 Gene 1068 7509 7512 1184 | 4272823 Disease DOID:10283 12066 12081 1185 | 4272823 Compound DB00936 12342 12349 1186 | 4272823 Compound DB00945 12342 12349 1187 | 4272823 Disease DOID:10283 14250 14265 1188 | 4272823 Disease DOID:10283 15815 15830 1189 | 4272823 Disease DOID:10283 16390 16405 1190 | 4272823 Disease DOID:10283 18807 18822 1191 | 4272823 Disease DOID:10283 19733 19748 1192 | 4272823 Disease DOID:10283 21825 21840 1193 | 4272823 Disease DOID:10283 24648 24663 1194 | 4272823 Disease DOID:10652 29484 29486 1195 | 4272823 Disease DOID:10283 29975 29990 1196 | 4272823 Disease DOID:10283 30043 30058 1197 | 4272823 Disease DOID:10283 30179 30204 1198 | 4272823 Disease DOID:10283 30327 30342 1199 | 4272823 Disease DOID:10283 30385 30400 1200 | 4272823 Disease DOID:10283 30467 30482 1201 | 4272823 Disease DOID:10283 30574 30589 1202 | 4272823 Disease DOID:10283 30862 30877 1203 | 4272823 Disease DOID:10283 31035 31050 1204 | 4272823 Disease DOID:10283 31240 31255 1205 | 4272823 Disease DOID:10283 31318 31333 1206 | 4272823 Disease DOID:10283 31465 31490 1207 | 4272823 Disease DOID:10283 31538 31553 1208 | 4272823 Disease DOID:10283 32431 32456 1209 | 4272823 Disease DOID:10283 32643 32658 1210 | 4272823 Disease DOID:10283 32685 32700 1211 | 4272823 Disease DOID:10283 32843 32858 1212 | 4272823 Disease DOID:10283 32917 32942 1213 | 4272823 Disease DOID:10283 33016 33041 1214 | 4272823 Disease DOID:10283 33163 33188 1215 | 4272823 Disease DOID:10283 33293 33318 1216 | 4272823 Disease DOID:10283 33468 33483 1217 | 4272823 Disease DOID:10283 33544 33567 1218 | 4272823 Disease DOID:10283 33730 33745 1219 | 4272823 Disease DOID:10283 34088 34113 1220 | 4272823 Disease DOID:10283 34201 34226 1221 | 4272823 Disease DOID:10283 34372 34387 1222 | 4272823 Disease DOID:10283 34486 34501 1223 | 4272823 Disease DOID:10283 34569 34584 1224 | 4272823 Disease DOID:10283 34784 34809 1225 | 4272823 Disease DOID:10283 34901 34916 1226 | 4272823 Disease DOID:10283 34967 34982 1227 | 4272823 Disease DOID:10283 35040 35067 1228 | 4272823 Disease DOID:10283 35353 35378 1229 | 4272824 Compound DB00907 39 46 1230 | 4272824 Compound DB00907 227 234 1231 | 4272824 Compound DB01579 279 294 1232 | 4272824 Compound DB01576 299 312 1233 | 4272824 Compound DB00907 335 342 1234 | 4272824 Compound DB00907 364 371 1235 | 4272824 Compound DB00907 518 525 1236 | 4272824 Compound DB00907 767 774 1237 | 4272824 Compound DB00907 1021 1028 1238 | 4272824 Compound DB00907 1095 1102 1239 | 4272824 Compound DB00907 1617 1624 1240 | 4272824 Compound DB00907 1693 1700 1241 | 4272824 Compound DB00907 1849 1856 1242 | 4272824 Compound DB00907 2760 2767 1243 | 4272824 Compound DB00907 3716 3723 1244 | 4272824 Compound DB00907 3884 3891 1245 | 4272824 Compound DB00907 4000 4007 1246 | 4272824 Compound DB00907 4214 4221 1247 | 4272824 Compound DB00907 4326 4333 1248 | 4272824 Compound DB00907 4820 4827 1249 | 4272824 Compound DB00907 5326 5333 1250 | 4272824 Compound DB00907 5569 5576 1251 | 4272824 Compound DB00907 5693 5700 1252 | 4272824 Compound DB01576 5747 5760 1253 | 4272824 Compound DB01579 5762 5777 1254 | 4272824 Compound DB00830 5783 5796 1255 | 4272824 Compound DB00907 7688 7695 1256 | 4272824 Compound DB00907 7985 7992 1257 | 4272824 Compound DB00907 8367 8374 1258 | 4272824 Compound DB00907 8470 8477 1259 | 4272824 Compound DB00907 8545 8552 1260 | 4272824 Compound DB01576 9161 9174 1261 | 4272824 Compound DB01579 9196 9215 1262 | 4272824 Compound DB00830 9238 9255 1263 | 4272824 Compound DB09153 9324 9330 1264 | 4272824 Compound DB00907 9401 9408 1265 | 4272824 Compound DB00907 9533 9540 1266 | 4272824 Compound DB00907 9785 9792 1267 | 4272824 Compound DB00907 9836 9843 1268 | 4272824 Compound DB00907 10065 10072 1269 | 4272824 Compound DB00907 10189 10196 1270 | 4272824 Compound DB00907 10265 10272 1271 | 4272824 Compound DB00907 10907 10914 1272 | 4272824 Compound DB00907 11232 11239 1273 | 4272824 Compound DB00907 13405 13412 1274 | 4272824 Compound DB01576 14224 14237 1275 | 4272824 Compound DB00907 14271 14278 1276 | 4272824 Compound DB01576 14380 14393 1277 | 4272824 Compound DB00907 14439 14446 1278 | 4272824 Compound DB01576 14488 14501 1279 | 4272824 Compound DB01576 14565 14578 1280 | 4272824 Compound DB01576 14754 14767 1281 | 4272824 Compound DB01579 14990 15009 1282 | 4272824 Compound DB00907 15043 15050 1283 | 4272824 Compound DB01579 15152 15167 1284 | 4272824 Compound DB00907 15228 15235 1285 | 4272824 Compound DB01579 15277 15296 1286 | 4272824 Compound DB01579 15419 15438 1287 | 4272824 Compound DB01579 15555 15574 1288 | 4272824 Compound DB00830 15932 15949 1289 | 4272824 Compound DB00907 15983 15990 1290 | 4272824 Compound DB00830 16092 16105 1291 | 4272824 Compound DB00907 16165 16172 1292 | 4272824 Compound DB00830 16214 16231 1293 | 4272824 Compound DB00830 16482 16499 1294 | 4272824 Compound DB00907 16578 16585 1295 | 4272824 Compound DB00907 16643 16650 1296 | 4272824 Compound DB00907 16759 16766 1297 | 4272824 Compound DB00907 16858 16865 1298 | 4272824 Compound DB00907 17060 17067 1299 | 4272824 Disease DOID:1826 17657 17661 1300 | 4272824 Disease DOID:1826 17729 17733 1301 | 4272824 Compound DB00907 17994 18001 1302 | 4272824 Compound DB00907 19759 19766 1303 | 4272824 Compound DB09153 21246 21252 1304 | 4272824 Compound DB00907 21276 21283 1305 | 4272824 Compound DB00907 21321 21328 1306 | 4272824 Compound DB00907 21373 21380 1307 | 4272824 Compound DB00907 21550 21557 1308 | 4272824 Compound DB00907 21826 21833 1309 | 4272824 Compound DB00907 22361 22368 1310 | 4272824 Compound DB00907 22452 22459 1311 | 4272824 Compound DB00907 22517 22524 1312 | 4272824 Compound DB00907 22584 22591 1313 | 4272824 Compound DB01576 22931 22944 1314 | 4272824 Compound DB00907 23075 23082 1315 | 4272824 Compound DB00907 23169 23176 1316 | 4272824 Compound DB00907 23199 23206 1317 | 4272824 Compound DB00907 23322 23329 1318 | 4272824 Compound DB00907 23358 23365 1319 | 4272824 Compound DB00907 23413 23420 1320 | 4272824 Compound DB01576 23470 23483 1321 | 4272824 Compound DB00907 23729 23736 1322 | 4272824 Compound DB00907 24013 24020 1323 | 4272824 Compound DB09153 24136 24142 1324 | 4272824 Compound DB00907 24372 24379 1325 | 4272824 Compound DB00907 24593 24600 1326 | 4272824 Compound DB00907 25462 25469 1327 | 4272824 Compound DB01576 25697 25710 1328 | 4272824 Compound DB00907 25980 25987 1329 | 4272824 Compound DB00907 26325 26332 1330 | 4272824 Compound DB01576 26791 26804 1331 | 4272824 Compound DB01579 26809 26824 1332 | 4272824 Compound DB00907 26898 26905 1333 | 4272824 Compound DB01576 27051 27064 1334 | 4272824 Compound DB01579 27069 27084 1335 | 4272824 Compound DB00907 28035 28042 1336 | 4272824 Compound DB00182 28376 28387 1337 | 4272824 Compound DB00907 28401 28408 1338 | 4272824 Compound DB00988 28541 28549 1339 | 4272824 Compound DB00368 28550 28564 1340 | 4272824 Compound DB00907 28600 28607 1341 | 4272824 Compound DB00907 28814 28821 1342 | 4272824 Compound DB01579 28907 28922 1343 | 4272824 Compound DB00907 28941 28948 1344 | 4272824 Compound DB00907 29695 29702 1345 | 4272824 Compound DB00898 29815 29822 1346 | 4272824 Compound DB00898 29847 29854 1347 | 4272824 Compound DB00907 30402 30409 1348 | 4272824 Compound DB00907 30801 30808 1349 | 4272824 Compound DB00907 31019 31026 1350 | 4272824 Compound DB01576 31073 31086 1351 | 4272824 Compound DB00907 31100 31107 1352 | 4272824 Compound DB00184 31389 31397 1353 | 4272824 Compound DB00907 31702 31709 1354 | 4272824 Compound DB00907 31813 31820 1355 | 4272824 Compound DB00907 32303 32310 1356 | 4272824 Compound DB00907 32336 32343 1357 | 4272824 Compound DB01576 32386 32399 1358 | 4272824 Compound DB00907 32433 32440 1359 | 4272824 Compound DB01576 32542 32555 1360 | 4272824 Compound DB00907 32671 32678 1361 | 4272824 Compound DB01576 32801 32814 1362 | 4272824 Compound DB01579 33065 33084 1363 | 4272824 Compound DB00907 33118 33125 1364 | 4272824 Compound DB01579 33227 33246 1365 | 4272824 Compound DB00907 33362 33369 1366 | 4272824 Compound DB01579 33492 33511 1367 | 4272824 Compound DB00830 33762 33779 1368 | 4272824 Compound DB00907 33813 33820 1369 | 4272824 Compound DB00830 33922 33939 1370 | 4272824 Compound DB00907 34055 34062 1371 | 4272824 Compound DB00830 34185 34202 1372 | 4272824 Compound DB00907 34451 34458 1373 | 4272824 Compound DB00907 34482 34489 1374 | 4272824 Compound DB00907 34715 34722 1375 | 4272824 Compound DB00830 34845 34862 1376 | 4272824 Compound DB01576 35105 35118 1377 | 4272824 Compound DB00907 35151 35158 1378 | 4272824 Compound DB00907 35388 35395 1379 | 4272824 Compound DB00907 35436 35443 1380 | 4272824 Compound DB00830 39820 39837 1381 | 4272825 Compound DB08820 12 21 1382 | 4272825 Compound DB09280 231 241 1383 | 4272825 Compound DB09280 243 249 1384 | 4272825 Compound DB08820 323 332 1385 | 4272825 Disease DOID:1793 2276 2284 1386 | 4272825 Compound DB08820 3269 3275 1387 | 4272825 Compound DB08820 3277 3286 1388 | 4272825 Compound DB09280 4889 4895 1389 | 4272825 Compound DB09280 4897 4907 1390 | 4272825 Compound DB09280 5035 5041 1391 | 4272825 Compound DB08820 6870 6876 1392 | 4272825 Disease DOID:3083 6953 6990 1393 | 4272825 Disease DOID:3083 6992 6996 1394 | 4272825 Compound DB00594 7969 7978 1395 | 4272825 Compound DB00594 8654 8663 1396 | 4272825 Compound DB09280 9558 9564 1397 | 4272825 Compound DB09280 10176 10182 1398 | 4272825 Compound DB09280 10316 10322 1399 | 4272825 Compound DB09280 11590 11596 1400 | 4272825 Compound DB09280 12393 12399 1401 | 4272825 Compound DB08820 15926 15932 1402 | 4272825 Compound DB00594 15977 15986 1403 | 4272825 Compound DB01093 16542 16546 1404 | 4272825 Gene 788 16690 16693 1405 | 4272825 Compound DB00594 16745 16754 1406 | 4272825 Compound DB00646 16964 16972 1407 | 4272825 Gene 788 17220 17223 1408 | 4272825 Gene 6267 17531 17534 1409 | 4272825 Gene 6268 18080 18083 1410 | 4272825 Compound DB00171 19118 19121 1411 | 4272825 Compound DB00640 19118 19121 1412 | 4272825 Compound DB09280 21313 21319 1413 | 4272825 Compound DB09280 21527 21533 1414 | 4272825 Disease DOID:3083 24758 24795 1415 | 4272825 Disease DOID:3083 24797 24801 1416 | 4272825 Disease DOID:3083 24968 24972 1417 | 4272825 Compound DB08820 25156 25162 1418 | 4272825 Disease DOID:3083 25722 25726 1419 | 4272825 Compound DB00594 27495 27504 1420 | 4272825 Compound DB09280 29680 29686 1421 | 4272825 Compound DB08820 29723 29729 1422 | 4272825 Gene 3071 32871 32874 1423 | 4272825 Compound DB09280 33351 33357 1424 | 4272825 Compound DB03843 33723 33731 1425 | 4272825 Compound DB00065 34154 34158 1426 | 4272825 Compound DB09341 34210 34217 1427 | 4272825 Compound DB11280 34210 34217 1428 | 4272825 Compound DB00594 34571 34580 1429 | 4272825 Compound DB08820 34654 34660 1430 | 4272825 Compound DB00646 34854 34862 1431 | 4272825 Compound DB00594 37066 37075 1432 | 4272825 Compound DB00594 37240 37249 1433 | 4272825 Compound DB00594 37543 37552 1434 | 4272825 Gene 788 38185 38188 1435 | 4272825 Compound DB00646 38221 38229 1436 | 4272825 Gene 6267 38312 38315 1437 | 4272825 Gene 6268 38391 38394 1438 | 4272825 Compound DB00203 40393 40403 1439 | 4272825 Compound DB08820 41099 41108 1440 | 4272825 Compound DB08820 41305 41314 1441 | 4272825 Compound DB08820 41576 41585 1442 | 4272825 Compound DB00646 43138 43146 1443 | 4272825 Compound DB08820 45285 45294 1444 | 4272825 Compound DB08820 45338 45347 1445 | 4272825 Compound DB08820 45529 45538 1446 | 4272825 Compound DB08820 45984 45993 1447 | 4272825 Compound DB00065 46104 46108 1448 | 4272825 Compound DB00065 46275 46279 1449 | 4272825 Compound DB08820 46464 46473 1450 | 4272825 Compound DB01093 47487 47491 1451 | 4272825 Compound DB01093 48197 48201 1452 | 4272825 Compound DB01093 52058 52062 1453 | 4272825 Compound DB08820 52140 52146 1454 | 4272825 Compound DB00646 53018 53026 1455 | 4272825 Compound DB00646 53155 53163 1456 | 4272825 Compound DB08820 53647 53653 1457 | 4272826 Disease DOID:2531 104 113 1458 | 4272826 Disease DOID:2531 181 190 1459 | 4272826 Gene 11214 603 607 1460 | 4272826 Disease DOID:2531 775 784 1461 | 4272826 Disease DOID:2531 1098 1107 1462 | 4272826 Disease DOID:2531 1149 1158 1463 | 4272826 Disease DOID:2531 1418 1427 1464 | 4272826 Disease DOID:2531 1581 1589 1465 | 4272826 Disease DOID:2531 1761 1769 1466 | 4272826 Disease DOID:2531 1898 1906 1467 | 4272826 Gene 11214 2009 2013 1468 | 4272826 Disease DOID:2531 2086 2094 1469 | 4272826 Disease DOID:2531 2212 2221 1470 | 4272826 Disease DOID:2531 2293 2302 1471 | 4272826 Disease DOID:2531 2532 2541 1472 | 4272826 Disease DOID:2531 2654 2663 1473 | 4272826 Disease DOID:2531 2722 2731 1474 | 4272826 Disease DOID:2531 2864 2873 1475 | 4272826 Disease DOID:2531 2993 3002 1476 | 4272826 Disease DOID:2531 3169 3177 1477 | 4272826 Compound DB00759 3531 3543 1478 | 4272826 Compound DB00759 3593 3605 1479 | 4272826 Disease DOID:2531 4478 4496 1480 | 4272826 Disease DOID:2531 5058 5066 1481 | 4272826 Disease DOID:2531 6664 6672 1482 | 4272826 Disease DOID:2531 6825 6834 1483 | 4272826 Disease DOID:2531 7057 7066 1484 | 4272826 Disease DOID:2531 7071 7080 1485 | 4272826 Disease DOID:2531 7090 7108 1486 | 4272826 Disease DOID:2531 7206 7215 1487 | 4272826 Disease DOID:2531 7256 7265 1488 | 4272826 Disease DOID:2531 7315 7323 1489 | 4272826 Disease DOID:2531 7393 7402 1490 | 4272826 Disease DOID:2531 7454 7463 1491 | 4272826 Disease DOID:2531 7567 7576 1492 | 4272826 Disease DOID:2531 7662 7671 1493 | 4272826 Gene 11214 7860 7864 1494 | 4272826 Disease DOID:2531 7888 7897 1495 | 4272826 Gene 11214 7998 8002 1496 | 4272826 Gene 11214 8187 8191 1497 | 4272826 Disease DOID:2531 8207 8216 1498 | 4272826 Disease DOID:2531 8341 8350 1499 | 4272826 Disease DOID:2531 8396 8405 1500 | 4272826 Disease DOID:2531 8654 8663 1501 | 4272826 Disease DOID:2531 8859 8868 1502 | 4272826 Disease DOID:2531 8954 8963 1503 | 4272826 Disease DOID:2531 9685 9694 1504 | 4272826 Disease DOID:2531 10149 10158 1505 | 4272826 Disease DOID:2531 10461 10470 1506 | 4272826 Disease DOID:2531 10674 10682 1507 | 4272826 Disease DOID:2531 10735 10744 1508 | 4272826 Disease DOID:2531 10873 10882 1509 | 4272826 Disease DOID:2531 10983 10992 1510 | 4272826 Disease DOID:2531 11018 11027 1511 | 4272826 Disease DOID:2531 11166 11175 1512 | 4272826 Disease DOID:2531 11376 11385 1513 | 4272826 Disease DOID:2531 11491 11500 1514 | 4272826 Disease DOID:2531 11949 11958 1515 | 4272826 Disease DOID:2531 12222 12231 1516 | 4272826 Disease DOID:2531 12376 12385 1517 | 4272826 Disease DOID:2531 12618 12627 1518 | 4272826 Disease DOID:2531 12771 12780 1519 | 4272826 Disease DOID:2531 12878 12887 1520 | 4272826 Disease DOID:2531 13266 13275 1521 | 4272826 Disease DOID:2531 13511 13520 1522 | 4272826 Disease DOID:2531 13623 13632 1523 | 4272826 Disease DOID:2531 13667 13676 1524 | 4272826 Disease DOID:2531 13911 13920 1525 | 4272826 Disease DOID:2531 14299 14308 1526 | 4272826 Disease DOID:2531 14483 14492 1527 | 4272826 Disease DOID:2531 14669 14677 1528 | 4272826 Disease DOID:2531 14735 14744 1529 | 4272826 Disease DOID:2531 14850 14859 1530 | 4272826 Disease DOID:2531 15029 15038 1531 | 4272826 Disease DOID:2531 15064 15073 1532 | 4272826 Disease DOID:2531 15287 15296 1533 | 4272826 Disease DOID:2531 15424 15433 1534 | 4272826 Disease DOID:2531 15622 15631 1535 | 4272826 Gene 11214 16527 16531 1536 | 4272826 Gene 11214 16577 16581 1537 | 4272826 Disease DOID:2531 16627 16636 1538 | 4272826 Disease DOID:2531 16823 16832 1539 | 4272826 Disease DOID:2531 17665 17674 1540 | 4272826 Disease DOID:2531 17797 17806 1541 | 4272826 Disease DOID:2531 17887 17896 1542 | 4272826 Disease DOID:2531 17996 18005 1543 | 4272826 Gene 3854 18231 18235 1544 | 4272826 Disease DOID:2531 18891 18900 1545 | 4272826 Disease DOID:2531 19108 19117 1546 | 4272826 Disease DOID:2531 19322 19331 1547 | 4272826 Gene 3854 19775 19802 1548 | 4272826 Gene 3854 19804 19808 1549 | 4272826 Disease DOID:2531 20067 20076 1550 | 4272826 Gene 3854 20176 20180 1551 | 4272826 Disease DOID:2531 20428 20454 1552 | 4272826 Disease DOID:2531 22094 22135 1553 | 4272826 Gene 4072 22240 22244 1554 | 4272826 Disease DOID:0060073 22264 22285 1555 | 4272826 Disease DOID:2531 22354 22377 1556 | 4272826 Disease DOID:2531 22407 22429 1557 | 4272826 Gene 9762 22431 22435 1558 | 4272826 Gene 3783 22474 22481 1559 | 4272826 Disease DOID:2531 22519 22539 1560 | 4272826 Disease DOID:2531 22719 22728 1561 | 4272826 Disease DOID:2531 22884 22906 1562 | 4272826 Disease DOID:2531 22942 22964 1563 | 4272826 Gene 4051 23011 23048 1564 | 4272826 Gene 4051 23050 23053 1565 | 4272826 Gene 3014 23142 23146 1566 | 4272826 Gene 1549 23191 23196 1567 | 4272826 Disease DOID:2531 24573 24582 1568 | 4272826 Disease DOID:2531 25644 25652 1569 | 4272826 Gene 11214 25760 25764 1570 | 4272826 Disease DOID:2531 25832 25841 1571 | 4272826 Disease DOID:2531 26129 26145 1572 | 4272826 Disease DOID:2531 26244 26253 1573 | 4272826 Disease DOID:2531 26308 26326 1574 | 4272826 Disease DOID:2531 26531 26549 1575 | 4272826 Gene 1945 26857 26863 1576 | 4272826 Gene 3854 27572 27576 1577 | 4272826 Gene 3854 27580 27584 1578 | 4272826 Gene 3854 27586 27590 1579 | 4272826 Disease DOID:4989 28082 28092 1580 | 4272826 Disease DOID:2531 28219 28228 1581 | 4272826 Gene 3854 28372 28377 1582 | 4272826 Disease DOID:2531 28438 28446 1583 | 4272826 Gene 10990 28643 28648 1584 | 4272826 Gene 4072 29065 29069 1585 | 4272826 Disease DOID:2531 29124 29132 1586 | 4272826 Disease DOID:2531 29172 29200 1587 | 4272826 Gene 4072 29236 29240 1588 | 4272826 Disease DOID:2531 29346 29362 1589 | 4272826 Gene 3783 29408 29415 1590 | 4272826 Gene 9762 29441 29445 1591 | 4272826 Disease DOID:2531 29512 29520 1592 | 4272826 Disease DOID:2531 29799 29821 1593 | 4272826 Disease DOID:2531 29875 29878 1594 | 4272826 Gene 4051 29890 29893 1595 | 4272826 Disease DOID:2531 30039 30055 1596 | 4272826 Gene 2891 30129 30133 1597 | 4272826 Disease DOID:2531 30288 30296 1598 | 4272826 Disease DOID:2531 30373 30382 1599 | 4272826 Disease DOID:2531 30494 30503 1600 | 4272826 Disease DOID:2531 30574 30583 1601 | 4272826 Disease DOID:2531 30767 30776 1602 | 4272826 Disease DOID:2531 31165 31174 1603 | 4272826 Disease DOID:2531 31471 31480 1604 | 4272826 Disease DOID:2531 31611 31620 1605 | 4272826 Disease DOID:2531 31698 31707 1606 | 4272826 Disease DOID:2531 31859 31868 1607 | 4272826 Disease DOID:2531 31980 31989 1608 | 4272826 Disease DOID:2531 32059 32068 1609 | 4272826 Disease DOID:2531 32281 32290 1610 | 4272826 Disease DOID:2531 32678 32687 1611 | 4272826 Disease DOID:2531 32976 32985 1612 | 4272826 Gene 586 33176 33179 1613 | 4272826 Gene 586 33254 33257 1614 | 4272826 Disease DOID:2531 33360 33369 1615 | 4272826 Disease DOID:2531 33711 33720 1616 | 4272826 Disease DOID:2531 33832 33841 1617 | 4272826 Disease DOID:2531 33908 33917 1618 | 4272826 Disease DOID:2531 34230 34238 1619 | 4272826 Disease DOID:2531 34517 34525 1620 | 4272826 Disease DOID:2531 34646 34655 1621 | 4272826 Disease DOID:2531 34718 34726 1622 | 4272826 Disease DOID:2531 35009 35018 1623 | 4272826 Disease DOID:2531 35434 35443 1624 | 4272826 Disease DOID:2531 36157 36166 1625 | 4272826 Disease DOID:2531 36210 36219 1626 | 4272826 Disease DOID:2531 36346 36381 1627 | 4272826 Disease DOID:2531 37751 37759 1628 | 4272826 Disease DOID:2531 38023 38031 1629 | 4272826 Disease DOID:2531 38107 38115 1630 | 4272826 Disease DOID:2531 38528 38600 1631 | 4272826 Gene 4072 39126 39130 1632 | 4272826 Gene 9762 39357 39361 1633 | 4272826 Gene 3014 40021 40025 1634 | 4272826 Gene 1549 40140 40145 1635 | 4272827 Disease DOID:6364 3254 3277 1636 | 4272827 Disease DOID:10763 8424 8436 1637 | 4272827 Disease DOID:2841 8451 8457 1638 | 4272827 Gene 55534 10416 10419 1639 | 4272827 Disease DOID:9970 12653 12660 1640 | 4272827 Disease DOID:10763 13699 13711 1641 | 4272827 Disease DOID:2841 13713 13719 1642 | 4272827 Gene 55534 14878 14881 1643 | 4272827 Disease DOID:9970 25028 25035 1644 | 4272828 Disease DOID:3393 3881 3902 1645 | 4272828 Disease DOID:2531 4069 4084 1646 | 4272828 Disease DOID:2355 4110 4145 1647 | 4272828 Disease DOID:3083 9516 9553 1648 | 4272828 Disease DOID:3393 10312 10333 1649 | 4272828 Compound DB01225 12312 12322 1650 | 4272828 Compound DB01225 12451 12461 1651 | 4272829 Disease DOID:11476 1376 1388 1652 | 4272829 Disease DOID:11476 1470 1482 1653 | 4272829 Disease DOID:9970 1869 1876 1654 | 4272829 Disease DOID:9970 2454 2459 1655 | 4272829 Disease DOID:9970 4195 4200 1656 | 4272829 Disease DOID:11476 4499 4511 1657 | 4272829 Disease DOID:11476 4571 4583 1658 | 4272829 Disease DOID:9970 5895 5900 1659 | 4272829 Disease DOID:9970 5950 5955 1660 | 4272829 Disease DOID:11476 7723 7735 1661 | 4272829 Gene 173 7993 8000 1662 | 4272829 Disease DOID:9970 8166 8173 1663 | 4272829 Disease DOID:9970 8705 8710 1664 | 4272829 Disease DOID:9970 8957 8962 1665 | 4272829 Disease DOID:11476 9705 9717 1666 | 4272829 Disease DOID:11476 9814 9826 1667 | 4272829 Disease DOID:11476 10671 10695 1668 | 4272829 Disease DOID:9970 11069 11074 1669 | 4272829 Disease DOID:9970 11236 11243 1670 | 4272829 Disease DOID:11476 11259 11271 1671 | 4272829 Disease DOID:9970 11386 11393 1672 | 4272829 Disease DOID:9970 11701 11708 1673 | 4272829 Disease DOID:9970 11819 11826 1674 | 4272830 Disease DOID:1826 4209 4219 1675 | 4272830 Disease DOID:1826 4258 4269 1676 | 4272830 Disease DOID:1826 5706 5714 1677 | 4272830 Compound DB01212 5902 5913 1678 | 4272830 Compound DB00479 6099 6107 1679 | 4272830 Compound DB00798 6111 6121 1680 | 4272830 Compound DB00479 6123 6131 1681 | 4272830 Compound DB01015 6192 6208 1682 | 4272830 Compound DB00440 6213 6225 1683 | 4272830 Compound DB01212 6442 6453 1684 | 4272830 Compound DB00479 6474 6482 1685 | 4272830 Compound DB00798 6486 6496 1686 | 4272831 Disease DOID:585 2640 2655 1687 | 4272831 Compound DB00624 3655 3667 1688 | 4272831 Compound DB04272 3735 3742 1689 | 4272831 Disease DOID:11819 5629 5642 1690 | 4272831 Compound DB00138 9715 9722 1691 | 4272831 Compound DB00138 25251 25258 1692 | 4272832 Compound DB00281 7765 7774 1693 | 4272832 Compound DB00281 8671 8680 1694 | 4272832 Compound DB06812 9232 9247 1695 | 4272832 Compound DB01109 14906 14913 1696 | 4272832 Compound DB01109 18708 18715 1697 | 4272833 Disease DOID:263 67 89 1698 | 4272833 Disease DOID:263 198 211 1699 | 4272833 Disease DOID:263 1543 1556 1700 | 4272833 Disease DOID:263 1691 1704 1701 | 4272833 Disease DOID:784 1709 1732 1702 | 4272833 Disease DOID:263 1928 1941 1703 | 4272833 Disease DOID:263 2703 2720 1704 | 4272833 Disease DOID:263 9169 9182 1705 | 4272833 Disease DOID:263 9504 9515 1706 | 4272833 Disease DOID:263 9517 9528 1707 | 4272833 Disease DOID:263 9621 9632 1708 | 4272833 Disease DOID:263 9671 9683 1709 | 4272833 Disease DOID:263 15603 15616 1710 | 4272833 Disease DOID:263 15804 15817 1711 | 4272833 Compound DB00898 17362 17369 1712 | 4272833 Compound DB00898 17638 17645 1713 | 4272833 Compound DB00898 17742 17749 1714 | 4272834 Disease DOID:2531 54 69 1715 | 4272834 Disease DOID:2531 427 430 1716 | 4272834 Disease DOID:2531 670 695 1717 | 4272834 Disease DOID:2531 1013 1036 1718 | 4272834 Disease DOID:2531 1690 1698 1719 | 4272834 Disease DOID:2531 1987 2012 1720 | 4272834 Disease DOID:2531 2261 2283 1721 | 4272834 Disease DOID:2531 2285 2288 1722 | 4272834 Disease DOID:2531 3269 3272 1723 | 4272834 Disease DOID:2531 3367 3370 1724 | 4272834 Compound DB00158 4204 4210 1725 | 4272834 Disease DOID:2531 4306 4309 1726 | 4272834 Disease DOID:2531 4354 4357 1727 | 4272834 Disease DOID:2531 4420 4423 1728 | 4272834 Disease DOID:2531 4793 4796 1729 | 4272834 Disease DOID:2531 5135 5138 1730 | 4272834 Disease DOID:2531 5190 5193 1731 | 4272834 Disease DOID:2355 5254 5260 1732 | 4272834 Disease DOID:2531 5365 5368 1733 | 4272834 Disease DOID:2531 5458 5466 1734 | 4272834 Disease DOID:2355 5566 5572 1735 | 4272834 Disease DOID:2531 5605 5608 1736 | 4272834 Disease DOID:2531 5651 5654 1737 | 4272834 Disease DOID:2531 6320 6323 1738 | 4272834 Disease DOID:2531 6482 6485 1739 | 4272834 Disease DOID:2531 6533 6536 1740 | 4272834 Disease DOID:2531 6622 6625 1741 | 4272834 Disease DOID:2531 6647 6650 1742 | 4272834 Disease DOID:2531 7330 7333 1743 | 4272834 Disease DOID:2531 7513 7516 1744 | 4272834 Disease DOID:2531 7595 7598 1745 | 4272834 Disease DOID:10763 7666 7678 1746 | 4272834 Disease DOID:2531 7786 7798 1747 | 4272834 Disease DOID:2531 7865 7868 1748 | 4272834 Disease DOID:3083 7899 7931 1749 | 4272834 Disease DOID:2531 8036 8039 1750 | 4272834 Disease DOID:2531 8058 8061 1751 | 4272834 Disease DOID:2531 8112 8115 1752 | 4272834 Disease DOID:2531 8366 8391 1753 | 4272834 Disease DOID:2531 8894 8917 1754 | 4272834 Compound DB01592 9177 9181 1755 | 4272834 Compound DB01592 9825 9829 1756 | 4272834 Disease DOID:2531 10064 10072 1757 | 4272834 Disease DOID:2531 10233 10236 1758 | 4272834 Disease DOID:2355 10681 10687 1759 | 4272834 Disease DOID:2531 10852 10875 1760 | 4272834 Disease DOID:2355 11317 11329 1761 | 4272834 Disease DOID:2355 11931 11937 1762 | 4272834 Disease DOID:2355 11946 11952 1763 | 4272834 Disease DOID:2355 11976 11982 1764 | 4272834 Disease DOID:2355 12099 12108 1765 | 4272834 Disease DOID:2355 12132 12141 1766 | 4272834 Disease DOID:2531 12563 12566 1767 | 4272834 Disease DOID:2531 16267 16270 1768 | 4272834 Disease DOID:2531 17048 17073 1769 | 4272834 Disease DOID:2531 17078 17093 1770 | 4272834 Disease DOID:2531 17095 17123 1771 | 4272834 Disease DOID:2531 17124 17139 1772 | 4272834 Disease DOID:2531 17236 17251 1773 | 4272834 Disease DOID:2531 17302 17327 1774 | 4272834 Disease DOID:2531 17385 17410 1775 | 4272834 Compound DB01592 17464 17468 1776 | 4272834 Disease DOID:2531 17517 17520 1777 | 4272834 Disease DOID:2355 17545 17551 1778 | 4272834 Disease DOID:2531 17556 17607 1779 | 4272834 Disease DOID:2531 17620 17633 1780 | 4272834 Disease DOID:2531 17634 17658 1781 | 4272834 Disease DOID:2531 17734 17759 1782 | 4272834 Disease DOID:2531 17802 17827 1783 | 4272834 Disease DOID:2355 17852 17858 1784 | 4272834 Disease DOID:2531 17891 17916 1785 | 4272834 Disease DOID:2531 18004 18029 1786 | 4272834 Disease DOID:2531 18155 18170 1787 | 4272834 Compound DB01592 18229 18233 1788 | 4272834 Disease DOID:2531 18247 18272 1789 | 4272834 Disease DOID:2531 18339 18364 1790 | 4272834 Disease DOID:2531 18491 18494 1791 | 4272834 Disease DOID:2355 18499 18514 1792 | 4272834 Compound DB01592 18549 18553 1793 | 4272834 Compound DB01592 18586 18590 1794 | 4272834 Disease DOID:2531 18639 18663 1795 | 4272834 Disease DOID:2531 18778 18803 1796 | 4272834 Disease DOID:2531 18882 18907 1797 | 4272834 Disease DOID:2531 18956 18981 1798 | 4272834 Gene 9098 19004 19009 1799 | 4272834 Gene 3802 19011 19014 1800 | 4272834 Gene 3040 19016 19020 1801 | 4272834 Gene 81697 19045 19049 1802 | 4272834 Gene 55661 19051 19055 1803 | 4272834 Disease DOID:2531 19086 19111 1804 | 4272834 Disease DOID:2531 19116 19139 1805 | 4272834 Disease DOID:2531 19167 19182 1806 | 4272834 Disease DOID:2531 19303 19327 1807 | 4272834 Disease DOID:2531 19438 19474 1808 | 4272834 Disease DOID:2531 19508 19523 1809 | 4272834 Disease DOID:2531 19664 19688 1810 | 4272834 Disease DOID:2531 19745 19771 1811 | 4272834 Disease DOID:2531 19796 19821 1812 | 4272834 Disease DOID:2531 19866 19891 1813 | 4272834 Disease DOID:2531 19908 19933 1814 | 4272834 Disease DOID:2531 19946 19974 1815 | 4272834 Disease DOID:2531 20215 20248 1816 | 4272834 Disease DOID:2531 20250 20253 1817 | 4272834 Disease DOID:2531 20330 20355 1818 | 4272834 Disease DOID:2531 20364 20379 1819 | 4272834 Disease DOID:2531 20456 20480 1820 | 4272834 Disease DOID:2531 20485 20500 1821 | 4272834 Disease DOID:2531 20597 20622 1822 | 4272834 Compound DB00928 20636 20647 1823 | 4272834 Disease DOID:2531 20690 20705 1824 | 4272834 Disease DOID:2531 20813 20838 1825 | 4272836 Disease DOID:824 4167 4180 1826 | 4272836 Disease DOID:216 4363 4376 1827 | 4272836 Gene 100508689 5098 5103 1828 | 4272836 Disease DOID:216 15128 15141 1829 | 4272836 Disease DOID:216 15339 15352 1830 | 4272838 Gene 9847 26681 26685 1831 | 4272839 Gene 317 1781 1784 1832 | 4272839 Gene 317 3623 3626 1833 | 4272839 Gene 317 4577 4580 1834 | 4272839 Disease DOID:7148 5472 5513 1835 | 4272839 Gene 317 6267 6270 1836 | 4272839 Gene 317 7717 7720 1837 | 4272839 Disease DOID:1936 13782 13797 1838 | 4272839 Gene 5865 15902 15905 1839 | 4272839 Gene 317 29224 29227 1840 | 4272839 Gene 317 29451 29454 1841 | 4272839 Disease DOID:8398 32359 32373 1842 | 4272839 Gene 317 36822 36825 1843 | 4272840 Disease DOID:2531 51 67 1844 | 4272840 Disease DOID:2531 68 84 1845 | 4272840 Disease DOID:2531 212 219 1846 | 4272840 Disease DOID:2531 384 400 1847 | 4272840 Compound DB01042 484 493 1848 | 4272840 Compound DB01041 518 529 1849 | 4272840 Compound DB08889 580 591 1850 | 4272840 Disease DOID:2531 807 823 1851 | 4272840 Disease DOID:2531 922 938 1852 | 4272840 Disease DOID:2531 1197 1213 1853 | 4272840 Compound DB08889 1373 1384 1854 | 4272840 Compound DB08910 1386 1398 1855 | 4272840 Compound DB06317 1400 1410 1856 | 4272840 Compound DB06769 1412 1424 1857 | 4272840 Disease DOID:2531 1518 1535 1858 | 4272840 Disease DOID:2531 1886 1893 1859 | 4272840 Disease DOID:2531 1991 1998 1860 | 4272840 Disease DOID:2531 2052 2069 1861 | 4272840 Disease DOID:2531 2284 2291 1862 | 4272840 Disease DOID:2531 2372 2392 1863 | 4272840 Disease DOID:2531 2445 2452 1864 | 4272840 Disease DOID:2531 2663 2670 1865 | 4272840 Gene 4257 3367 3373 1866 | 4272840 Gene 4257 3513 3518 1867 | 4272840 Disease DOID:2531 3865 3889 1868 | 4272840 Disease DOID:2531 4669 4676 1869 | 4272840 Disease DOID:2531 4806 4822 1870 | 4272840 Disease DOID:2531 5478 5493 1871 | 4272840 Compound DB01042 5919 5928 1872 | 4272840 Compound DB00860 5934 5946 1873 | 4272840 Compound DB00635 7125 7135 1874 | 4272840 Compound DB01042 7617 7626 1875 | 4272840 Compound DB00635 7627 7637 1876 | 4272840 Compound DB01041 7638 7649 1877 | 4272840 Compound DB01041 7915 7926 1878 | 4272840 Compound DB01041 8368 8379 1879 | 4272840 Compound DB00531 8478 8494 1880 | 4272840 Compound DB01234 8499 8512 1881 | 4272840 Compound DB01041 8745 8756 1882 | 4272840 Disease DOID:2531 8886 8893 1883 | 4272840 Disease DOID:2531 8934 8950 1884 | 4272840 Compound DB01234 9013 9025 1885 | 4272840 Compound DB01234 9065 9077 1886 | 4272840 Disease DOID:2531 9104 9120 1887 | 4272840 Disease DOID:2531 9436 9443 1888 | 4272840 Compound DB01042 9712 9721 1889 | 4272840 Compound DB00635 9722 9732 1890 | 4272840 Compound DB00188 10329 10339 1891 | 4272840 Compound DB00188 10603 10613 1892 | 4272840 Compound DB00635 10627 10637 1893 | 4272840 Compound DB01042 10691 10700 1894 | 4272840 Compound DB01041 10720 10731 1895 | 4272840 Disease DOID:2531 10937 10953 1896 | 4272840 Compound DB00188 10975 10985 1897 | 4272840 Compound DB00188 11112 11122 1898 | 4272840 Disease DOID:2531 11256 11272 1899 | 4272840 Compound DB01041 11290 11301 1900 | 4272840 Compound DB00188 11507 11517 1901 | 4272840 Disease DOID:2531 12422 12438 1902 | 4272840 Compound DB00188 12577 12587 1903 | 4272840 Compound DB01041 12857 12868 1904 | 4272840 Disease DOID:2531 13543 13559 1905 | 4272840 Disease DOID:2531 13635 13651 1906 | 4272840 Disease DOID:2531 13716 13723 1907 | 4272840 Disease DOID:2531 13739 13755 1908 | 4272840 Disease DOID:2531 13883 13890 1909 | 4272840 Disease DOID:2531 13990 13997 1910 | 4272840 Disease DOID:2531 14258 14274 1911 | 4272840 Disease DOID:2531 14533 14549 1912 | 4272840 Compound DB08889 14709 14720 1913 | 4272840 Compound DB08910 14722 14734 1914 | 4272840 Compound DB06317 14736 14746 1915 | 4272840 Compound DB06769 14748 14760 1916 | 4272840 Disease DOID:2531 14902 14918 1917 | 4272840 Disease DOID:2531 14951 14967 1918 | 4272840 Disease DOID:2531 14968 14984 1919 | 4272840 Disease DOID:2531 15018 15034 1920 | 4272840 Disease DOID:2531 15124 15131 1921 | 4272840 Disease DOID:2531 15165 15181 1922 | 4272840 Disease DOID:2531 15196 15211 1923 | 4272840 Disease DOID:2531 15246 15262 1924 | 4272840 Disease DOID:2531 15375 15382 1925 | 4272840 Disease DOID:2531 15401 15416 1926 | 4272840 Disease DOID:2531 15459 15474 1927 | 4272840 Disease DOID:2531 15567 15574 1928 | 4272840 Disease DOID:2531 15647 15654 1929 | 4272840 Disease DOID:2531 15744 15760 1930 | 4272840 Disease DOID:2531 15806 15813 1931 | 4272840 Disease DOID:2531 15859 15875 1932 | 4272840 Disease DOID:2531 15948 15955 1933 | 4272840 Disease DOID:2531 16024 16031 1934 | 4272840 Disease DOID:2531 16062 16069 1935 | 4272840 Disease DOID:2531 16128 16144 1936 | 4272840 Disease DOID:2531 16216 16223 1937 | 4272840 Disease DOID:2531 16282 16289 1938 | 4272840 Disease DOID:2531 16324 16340 1939 | 4272840 Disease DOID:2531 16410 16426 1940 | 4272840 Disease DOID:2531 16476 16492 1941 | 4272840 Disease DOID:2531 16542 16558 1942 | 4272840 Disease DOID:2531 16559 16566 1943 | 4272840 Compound DB01042 16629 16638 1944 | 4272840 Compound DB00635 16644 16654 1945 | 4272840 Disease DOID:2531 16672 16688 1946 | 4272840 Compound DB01042 16746 16755 1947 | 4272840 Compound DB00635 16760 16770 1948 | 4272840 Compound DB01041 16776 16787 1949 | 4272840 Compound DB01042 16795 16804 1950 | 4272840 Compound DB00635 16809 16819 1951 | 4272840 Disease DOID:2531 16909 16925 1952 | 4272840 Compound DB01042 16970 16979 1953 | 4272840 Compound DB00635 16984 16994 1954 | 4272840 Compound DB01041 17000 17011 1955 | 4272840 Disease DOID:2531 17065 17081 1956 | 4272840 Compound DB01041 17110 17121 1957 | 4272840 Compound DB01042 17130 17139 1958 | 4272840 Compound DB00635 17140 17150 1959 | 4272840 Disease DOID:2531 17168 17184 1960 | 4272840 Disease DOID:2531 17265 17272 1961 | 4272840 Compound DB01042 17285 17294 1962 | 4272840 Compound DB00635 17299 17309 1963 | 4272840 Compound DB01041 17315 17326 1964 | 4272840 Disease DOID:2531 17363 17379 1965 | 4272840 Compound DB01041 17412 17423 1966 | 4272840 Compound DB01042 17433 17442 1967 | 4272840 Compound DB00635 17448 17458 1968 | 4272840 Disease DOID:2531 17500 17516 1969 | 4272840 Compound DB01042 17542 17551 1970 | 4272840 Compound DB00635 17553 17563 1971 | 4272840 Compound DB01041 17569 17580 1972 | 4272840 Disease DOID:2531 17606 17622 1973 | 4272840 Compound DB01041 17682 17693 1974 | 4272840 Disease DOID:2531 17721 17728 1975 | 4272840 Compound DB00531 17813 17829 1976 | 4272840 Compound DB01041 17831 17842 1977 | 4272840 Disease DOID:2531 17904 17920 1978 | 4272840 Compound DB01234 18039 18052 1979 | 4272840 Disease DOID:2531 18092 18108 1980 | 4272840 Disease DOID:2531 18220 18227 1981 | 4272840 Disease DOID:2531 18282 18298 1982 | 4272840 Compound DB00635 18329 18339 1983 | 4272840 Disease DOID:2531 18365 18381 1984 | 4272840 Compound DB00635 18412 18422 1985 | 4272840 Compound DB01042 18437 18446 1986 | 4272840 Compound DB00635 18451 18461 1987 | 4272840 Disease DOID:2531 18476 18503 1988 | 4272840 Compound DB00188 18580 18590 1989 | 4272840 Compound DB01042 18592 18601 1990 | 4272840 Compound DB00635 18607 18617 1991 | 4272840 Compound DB00188 18626 18636 1992 | 4272840 Compound DB01041 18638 18649 1993 | 4272840 Compound DB00635 18655 18665 1994 | 4272840 Compound DB00188 18726 18736 1995 | 4272840 Compound DB01041 18741 18752 1996 | 4272840 Compound DB00188 18760 18770 1997 | 4272840 Compound DB00635 18775 18785 1998 | 4272840 Disease DOID:2531 18821 18837 1999 | 4272840 Compound DB00188 18858 18868 2000 | 4272840 Compound DB00188 18968 18978 2001 | 4272840 Compound DB01042 18979 18988 2002 | 4272840 Compound DB00635 18989 18999 2003 | 4272840 Disease DOID:2531 19025 19041 2004 | 4272840 Compound DB00188 19109 19119 2005 | 4272840 Disease DOID:2531 19123 19139 2006 | 4272840 Disease DOID:2531 19202 19209 2007 | 4272841 Gene 4598 812 815 2008 | 4272841 Gene 9230 3250 3254 2009 | 4272842 Compound DB00882 3581 3599 2010 | 4272842 Compound DB00783 4204 4213 2011 | 4272842 Compound DB00396 4218 4230 2012 | 4272844 Gene 4363 815 818 2013 | 4272844 Gene 4363 908 911 2014 | 4272844 Gene 4363 1029 1032 2015 | 4272844 Gene 4363 1201 1204 2016 | 4272844 Gene 4363 1353 1356 2017 | 4272844 Gene 4363 1475 1478 2018 | 4272844 Gene 4363 1592 1595 2019 | 4272844 Gene 4363 4978 4981 2020 | 4272844 Gene 4363 5148 5151 2021 | 4272844 Gene 4363 5320 5323 2022 | 4272844 Gene 4363 5492 5495 2023 | 4272844 Gene 4363 5644 5647 2024 | 4272844 Gene 4363 5788 5791 2025 | 4272844 Gene 4363 6009 6012 2026 | 4272844 Gene 4363 6159 6162 2027 | 4272844 Gene 4363 6428 6431 2028 | 4272844 Gene 4363 6458 6461 2029 | 4272844 Gene 4363 6593 6596 2030 | 4272844 Gene 4363 6642 6645 2031 | 4272844 Gene 4363 6765 6768 2032 | 4272844 Gene 4363 6918 6921 2033 | 4272844 Gene 4363 6974 6977 2034 | 4272844 Gene 4363 7102 7105 2035 | 4272844 Gene 4363 7244 7247 2036 | 4272844 Gene 4363 7315 7318 2037 | 4272844 Gene 4363 7438 7441 2038 | 4272844 Gene 4363 7587 7590 2039 | 4272844 Gene 4363 8969 8972 2040 | 4272844 Gene 4363 9033 9036 2041 | 4272844 Gene 4363 9129 9132 2042 | 4272844 Gene 4363 9204 9207 2043 | 4272844 Gene 4363 9438 9441 2044 | 4272844 Gene 4363 9468 9471 2045 | 4272844 Gene 4363 9552 9555 2046 | 4272844 Gene 4363 9640 9643 2047 | 4272844 Gene 4363 9931 9934 2048 | 4272844 Gene 4363 9969 9972 2049 | 4272844 Gene 4363 10268 10271 2050 | 4272844 Gene 4363 10796 10799 2051 | 4272845 Disease DOID:784 1778 1799 2052 | 4272845 Disease DOID:784 2031 2052 2053 | 4272845 Disease DOID:784 3208 3229 2054 | 4272845 Disease DOID:784 5092 5114 2055 | 4272845 Compound DB03904 8315 8319 2056 | 4272845 Compound DB03904 8670 8674 2057 | 4272845 Disease DOID:10763 12090 12102 2058 | 4272845 Disease DOID:784 13657 13678 2059 | 4272845 Disease DOID:784 14019 14040 2060 | 4272845 Disease DOID:10763 14235 14247 2061 | 4272845 Disease DOID:10763 14476 14488 2062 | 4272846 Disease DOID:2531 6177 6194 2063 | 4272846 Gene 3055 8039 8042 2064 | 4272846 Disease DOID:14330 8754 8774 2065 | 4272846 Disease DOID:14330 9650 9670 2066 | 4272846 Disease DOID:7148 11722 11759 2067 | 4272846 Disease DOID:7147 11764 11786 2068 | 4272846 Disease DOID:263 13013 13031 2069 | 4272846 Disease DOID:184 13035 13054 2070 | 4272846 Disease DOID:7147 16840 16862 2071 | 4272846 Disease DOID:7147 17876 17898 2072 | 4272847 Disease DOID:3083 24 61 2073 | 4272847 Disease DOID:3083 166 203 2074 | 4272847 Disease DOID:3083 300 337 2075 | 4272847 Disease DOID:3083 1526 1563 2076 | 4272847 Disease DOID:2841 3208 3214 2077 | 4272847 Disease DOID:3083 3997 4034 2078 | 4272847 Compound DB00184 5519 5527 2079 | 4272847 Compound DB00184 5717 5725 2080 | 4272847 Disease DOID:10763 7983 7995 2081 | 4272847 Disease DOID:10763 8161 8173 2082 | 4272847 Disease DOID:3083 17830 17862 2083 | 4272847 Disease DOID:3083 17978 18015 2084 | 4272847 Compound DB00184 18405 18413 2085 | 4272847 Disease DOID:3083 18889 18926 2086 | 4272847 Disease DOID:3083 19138 19150 2087 | 4272847 Disease DOID:3083 19224 19261 2088 | 4272847 Disease DOID:9352 19551 19576 2089 | 4272847 Disease DOID:3083 19634 19671 2090 | 4272847 Disease DOID:3083 19760 19797 2091 | -------------------------------------------------------------------------------- /data/example/README.md: -------------------------------------------------------------------------------- 1 | # Converting Pubtator Annotations to BioC XML 2 | 3 | This folder conatins two scirpts one that will convert [pubtator to bioC xml](pubtator_to_xml.py) and the other will [extract annoations](extract_tags.py) for snorkel to use. 4 | 5 | To run the pubtator converter use the following command: 6 | 7 | ``` 8 | python ../../scripts/pubtator_to_xml.py --documents 1-sample-annotations.txt --output 2-sample-docs.xml 9 | ``` 10 | 11 | To extract annotations from the BioC format use the following command: 12 | ``` 13 | python ../../scripts/extract_tags.py --input 2-sample-docs.xml --output 3-sample-tags.tsv 14 | ``` 15 | -------------------------------------------------------------------------------- /data/example/ncbi_pmid_to_pmcid_map.tsv.xz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/greenelab/pubtator/4a7d7bcce1854ea338aca2256b0125f35b79b010/data/example/ncbi_pmid_to_pmcid_map.tsv.xz -------------------------------------------------------------------------------- /data/temp/batch_log.tsv: -------------------------------------------------------------------------------- 1 | batch pmcid 2 | 0 PMC2289422 3 | 0 PMC2289423 4 | 0 PMC2289424 5 | 0 PMC2289425 6 | 0 PMC2289426 7 | 0 PMC2289427 8 | 0 PMC2289428 9 | 0 PMC2289429 10 | 0 PMC2289430 11 | 0 PMC2289434 12 | 0 PMC2289435 13 | 0 PMC2289436 14 | 0 PMC2289437 15 | 0 PMC2289438 16 | 0 PMC2289439 17 | 0 PMC2289440 18 | 0 PMC2289441 19 | 0 PMC2289442 20 | 0 PMC2289443 21 | 0 PMC2289444 22 | 0 PMC2289445 23 | 0 PMC2289446 24 | 0 PMC2289447 25 | 0 PMC2289448 26 | 0 PMC2289449 27 | 0 PMC2289450 28 | 0 PMC2289451 29 | 0 PMC2289452 30 | 0 PMC2289453 31 | 0 PMC2289454 32 | 0 PMC2289455 33 | 0 PMC2289456 34 | 0 PMC2289457 35 | 0 PMC2289458 36 | 0 PMC2289459 37 | 0 PMC2289460 38 | 0 PMC2289461 39 | 0 PMC2289462 40 | 0 PMC2289463 41 | 0 PMC2289464 42 | 0 PMC2289465 43 | 0 PMC2289466 44 | 0 PMC2289467 45 | 0 PMC2289468 46 | 0 PMC2289469 47 | 0 PMC2289470 48 | 0 PMC2289471 49 | 0 PMC2289472 50 | 0 PMC2289473 51 | 0 PMC2289474 52 | 0 PMC2289475 53 | 0 PMC2289476 54 | 0 PMC2289477 55 | 0 PMC2289478 56 | 0 PMC2289479 57 | 0 PMC2289480 58 | 0 PMC2289481 59 | 0 PMC2289482 60 | 0 PMC2289483 61 | 0 PMC2289484 62 | 0 PMC2289485 63 | 0 PMC2289486 64 | 0 PMC2289487 65 | 0 PMC2289488 66 | 0 PMC2289489 67 | 0 PMC2289490 68 | 0 PMC2289491 69 | 0 PMC2289492 70 | 0 PMC2289493 71 | 0 PMC2289494 72 | 0 PMC2289495 73 | 0 PMC2289496 74 | 0 PMC2289497 75 | 0 PMC2289498 76 | 0 PMC2289499 77 | 0 PMC2289500 78 | 0 PMC2289501 79 | 0 PMC2289502 80 | 0 PMC2289503 81 | 0 PMC2289504 82 | 0 PMC2289505 83 | 0 PMC2289506 84 | 0 PMC2289507 85 | 0 PMC2289508 86 | 0 PMC2289509 87 | 0 PMC2289510 88 | 0 PMC2289512 89 | 0 PMC2289513 90 | 0 PMC2289514 91 | 0 PMC2289515 92 | 0 PMC2289517 93 | 0 PMC2289518 94 | 0 PMC2289519 95 | 0 PMC2289520 96 | 0 PMC2289521 97 | 0 PMC2289522 98 | 0 PMC2289524 99 | 0 PMC2289525 100 | 0 PMC4272812 101 | 0 PMC4272813 102 | 1 PMC4272814 103 | 1 PMC4272815 104 | 1 PMC4272816 105 | 1 PMC4272818 106 | 1 PMC4272820 107 | 1 PMC4272821 108 | 1 PMC4272822 109 | 1 PMC4272823 110 | 1 PMC4272824 111 | 1 PMC4272825 112 | 1 PMC4272826 113 | 1 PMC4272827 114 | 1 PMC4272828 115 | 1 PMC4272829 116 | 1 PMC4272830 117 | 1 PMC4272831 118 | 1 PMC4272832 119 | 1 PMC4272833 120 | 1 PMC4272834 121 | 1 PMC4272835 122 | 1 PMC4272836 123 | 1 PMC4272837 124 | 1 PMC4272838 125 | 1 PMC4272839 126 | 1 PMC4272840 127 | 1 PMC4272841 128 | 1 PMC4272842 129 | 1 PMC4272843 130 | 1 PMC4272844 131 | 1 PMC4272845 132 | 1 PMC4272846 133 | 1 PMC4272847 134 | -------------------------------------------------------------------------------- /download/bioconcepts2pubtator_offsets.gz.log: -------------------------------------------------------------------------------- 1 | --2017-02-16 18:49:50-- ftp://ftp.ncbi.nlm.nih.gov/pub/lu/PubTator/bioconcepts2pubtator_offsets.gz 2 | => ‘download/.listing’ 3 | Resolving ftp.ncbi.nlm.nih.gov (ftp.ncbi.nlm.nih.gov)... 2607:f220:41e:250::12, 130.14.250.12 4 | Connecting to ftp.ncbi.nlm.nih.gov (ftp.ncbi.nlm.nih.gov)|2607:f220:41e:250::12|:21... connected. 5 | Logging in as anonymous ... Logged in! 6 | ==> SYST ... done. ==> PWD ... done. 7 | ==> TYPE I ... done. ==> CWD (1) /pub/lu/PubTator ... done. 8 | ==> EPSV ... done. ==> LIST ... done. 9 | 10 | 0K . 27.0K=0.05s 11 | 12 | 2017-02-16 18:49:51 (27.0 KB/s) - ‘download/.listing’ saved [1275] 13 | 14 | Removed ‘download/.listing’. 15 | Remote file no newer than local file ‘download/bioconcepts2pubtator_offsets.gz’ -- not retrieving. 16 | -------------------------------------------------------------------------------- /execute.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | from pathlib import Path 3 | import json 4 | 5 | import wget 6 | 7 | from scripts.download_full_text import download_full_text, merge_full_text 8 | from scripts.extract_tags import extract_annotations 9 | from scripts.hetnet_id_extractor import filter_tags 10 | from scripts.map_ids import map_ids 11 | from scripts.pubtator_to_xml import convert_pubtator 12 | 13 | parser = argparse.ArgumentParser( 14 | description='Runs Pubtator/Pubtator Central Parser Pipeline' 15 | ) 16 | 17 | parser.add_argument( 18 | "--config", help="The config file for the extractor.", 19 | default="config_files/pubtator_central_config.json" 20 | ) 21 | 22 | args = parser.parse_args() 23 | 24 | configuration = json.load(open(args.config, "r")) 25 | 26 | if ( 27 | "repository_download" in configuration and 28 | not configuration["repository_download"]["skip"] 29 | ): 30 | print("Executing repository_download...") 31 | wget.download( 32 | configuration["repository_download"]['url'], 33 | out=configuration["repository_download"]['download_folder'] 34 | ) 35 | 36 | del configuration["repository_download"] 37 | 38 | if ( 39 | "pubtator_to_xml" in configuration and 40 | not configuration["pubtator_to_xml"]["skip"] 41 | ): 42 | print("Executing pubtator_to_xml...") 43 | convert_pubtator( 44 | configuration["pubtator_to_xml"]['documents'], 45 | configuration["pubtator_to_xml"]['output'] 46 | ) 47 | 48 | del configuration["pubtator_to_xml"] 49 | 50 | if ( 51 | "extract_tags" in configuration and 52 | not configuration["extract_tags"]["skip"] 53 | ): 54 | print("Executing extract_tags...") 55 | extract_annotations( 56 | configuration["extract_tags"]["input"], 57 | configuration["extract_tags"]["output"] 58 | ) 59 | 60 | del configuration["extract_tags"] 61 | 62 | if ( 63 | "hetnet_id_extractor" in configuration and 64 | not configuration["hetnet_id_extractor"]["skip"] 65 | ): 66 | print("Executing hetnet_id_extractor...") 67 | filter_tags( 68 | configuration["hetnet_id_extractor"]["input"], 69 | configuration["hetnet_id_extractor"]["output"] 70 | ) 71 | 72 | del configuration["hetnet_id_extractor"] 73 | 74 | if ( 75 | "map_pmids_to_pmcids" in configuration and 76 | not configuration["map_pmids_to_pmcids"]["skip"] 77 | ): 78 | print("Executing map_pmids_to_pmcids...") 79 | map_ids( 80 | configuration["map_pmids_to_pmcids"]["input"], 81 | configuration["map_pmids_to_pmcids"]["output"], 82 | configuration["map_pmids_to_pmcids"]["debug"] 83 | ) 84 | 85 | del configuration["map_pmids_to_pmcids"] 86 | 87 | if ( 88 | "download_full_text" in configuration and 89 | not configuration["download_full_text"]["skip"] 90 | ): 91 | print("Executing download_full_text...") 92 | download_full_text( 93 | configuration["download_full_text"]["input"], 94 | configuration["download_full_text"]["document_batch"], 95 | configuration["download_full_text"]["temp_dir"], 96 | configuration["download_full_text"]["log_file"] 97 | ) 98 | 99 | merge_full_text( 100 | configuration["download_full_text"]["temp_dir"], 101 | configuration["download_full_text"]["output"] 102 | ) 103 | 104 | del configuration["download_full_text"] 105 | 106 | if ( 107 | "extract_full_text_tags" in configuration and 108 | not configuration["extract_full_text_tags"]["skip"] 109 | ): 110 | print("Executing extract_full_text_tags...") 111 | extract_annotations( 112 | configuration["extract_full_text_tags"]["input"], 113 | configuration["extract_full_text_tags"]["output"] 114 | ) 115 | 116 | del configuration["extract_full_text_tags"] 117 | 118 | if ( 119 | "hetnet_id_extractor_full_text" in configuration and 120 | not configuration["hetnet_id_extractor_full_text"]["skip"] 121 | ): 122 | print("Executing hetnet_id_extractor_full_text...") 123 | filter_tags( 124 | configuration["hetnet_id_extractor_full_text"]["input"], 125 | configuration["hetnet_id_extractor_full_text"]["output"] 126 | ) 127 | 128 | del configuration["hetnet_id_extractor_full_text"] 129 | 130 | if len(configuration) > 0: 131 | not_executed_commands = '\n'.join(configuration.keys()) 132 | print( 133 | "\n" 134 | "Commands not executed:\n" 135 | f"{not_executed_commands}" 136 | ) 137 | -------------------------------------------------------------------------------- /mapper/map_to_drugbank.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | 3 | # Map from DrugBank to MeSH using DrugCentral 4 | url = 'https://github.com/olegursu/drugtarget/blob/9a6d84bed8650c6c507a2d3d786814c774568610/identifiers.tsv?raw=true' 5 | drug_map_df = pd.read_table(url) 6 | 7 | drug_bank_df = drug_map_df[drug_map_df.ID_TYPE == 'DRUGBANK_ID'].rename(columns={"IDENTIFIER": "drugbank_id"}) 8 | mesh_map_df = drug_map_df[drug_map_df.ID_TYPE.str.contains('MESH')].rename(columns={"IDENTIFIER": "identifier"}) 9 | drug_bank_mesh_df = pd.merge(drug_bank_df[["DRUG_ID", "drugbank_id"]], mesh_map_df[["DRUG_ID", "identifier"]], on="DRUG_ID") 10 | drug_bank_mesh_df["source"] = "MESH" 11 | drug_bank_mesh_df = drug_bank_mesh_df.rename({}) 12 | 13 | # Grab the chebi to DB mapper 14 | url = 'https://raw.githubusercontent.com/dhimmel/drugbank/7b94454b14a2fa4bb9387cb3b4b9924619cfbd3e/data/mapping/chebi.tsv' 15 | chebi_map_df = pd.read_table(url) 16 | chebi_map_df["chebi_id"] = chebi_map_df["chebi_id"].astype(object) 17 | chebi_map_df = chebi_map_df.rename(columns={"chebi_id": "identifier"}) 18 | chebi_map_df["source"] = "CHEBI" 19 | 20 | final_df = drug_bank_mesh_df[["drugbank_id", "identifier", "source"]].append(chebi_map_df) 21 | final_df.to_csv("mapper/drugbank_mapper.tsv", sep="\t", index=False) 22 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | lxml==4.5.2 2 | pandas==0.25.3 3 | ratelimit==2.2.1 4 | requests==2.22.0 5 | tqdm==4.11.2 6 | wget==3.2 7 | numpy==1.23.1 8 | git+https://github.com/en-dash/PyBioC@a21bd181ce3b89de791db4bb7db6ca1c48167648 9 | -------------------------------------------------------------------------------- /scripts/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/greenelab/pubtator/4a7d7bcce1854ea338aca2256b0125f35b79b010/scripts/__init__.py -------------------------------------------------------------------------------- /scripts/download_full_text.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | from pathlib import Path 3 | import requests 4 | import time 5 | import os 6 | import sys 7 | 8 | import lxml.etree as ET 9 | from lxml.etree import XMLSyntaxError 10 | import pandas as pd 11 | from ratelimit import limits, sleep_and_retry 12 | import tqdm 13 | 14 | 15 | QUERY_RATE = 60*15 16 | @sleep_and_retry 17 | @limits(calls=10000, period=QUERY_RATE) 18 | def call_api(url): 19 | response = requests.get(url) 20 | 21 | if response.status_code != 200: 22 | raise Exception(response.text) 23 | 24 | return response 25 | 26 | def read_id_chunk(id_file, batch_size): 27 | """ 28 | Chunk the pandas dataframe so not everything is read into memory 29 | 30 | Keyword Arguments: 31 | id_file -- the file to read through pandas 32 | batch_size -- the size of each chunk 33 | """ 34 | for id_batch in pd.read_csv(id_file, sep="\t", chunksize=batch_size): 35 | yield id_batch 36 | 37 | def download_full_text(ids_file, document_batch, temp_dir, log_file="batch_log.tsv"): 38 | """ 39 | Download full text from Pubtator Central. 40 | This section involves heavy api calls and subject to get blocked. 41 | Email the researchers at pubtator if this script continues to be blocked 42 | 43 | Keywords arguments: 44 | ids_file -- The path containing the pmids to pmcids map 45 | document_batch -- the size of each id batch 46 | temp_dir -- the directory to hold full text batches from pubtator central api 47 | """ 48 | 49 | # Pubtator supports biocxml and json 50 | # This script only uses biocxml 51 | pubtator_central_api = "https://www.ncbi.nlm.nih.gov/research/pubtator-api/publications/export/biocxml?" 52 | 53 | # Create the directory if it doesn't exist 54 | Path(f"{temp_dir}").mkdir(parents=True, exist_ok=True) 55 | 56 | # Load a logger to track which ids have been queried 57 | log_file_path = Path(f"{temp_dir}/{log_file}") 58 | if not log_file_path.exists(): 59 | log = pd.DataFrame([], columns=["batch", "pmcid"]) 60 | log.to_csv( 61 | log_file_path.resolve(), 62 | sep="\t", index=False 63 | ) 64 | 65 | else: 66 | log = pd.read_csv( 67 | log_file_path.resolve(), 68 | sep="\t" 69 | ) 70 | 71 | # test each query against Pubtator's API 72 | for idx, pmcid_batch_df in tqdm.tqdm(enumerate(read_id_chunk(ids_file, document_batch))): 73 | 74 | # Measure the ids that haven't been seen by the logger 75 | already_seen = ( 76 | set(pmcid_batch_df.PMCID.values) 77 | .difference(set(log.pmcid.values)) 78 | ) 79 | 80 | # If all ids have been processed skip batch 81 | if len(already_seen) == 0: 82 | continue 83 | 84 | query = f"{pubtator_central_api}pmcids={','.join(pmcid_batch_df.PMCID.values)}" 85 | response = call_api(query) 86 | 87 | batch_file_path = Path(f"{temp_dir}/batch_{idx}.xml") 88 | with open(batch_file_path.resolve(), "wb") as xml_file: 89 | try: 90 | root = ET.fromstring( 91 | bytes(response.text, encoding="utf8") 92 | ) 93 | 94 | xml_file.write(ET.tostring(root, pretty_print=True)) 95 | 96 | # Save to the logger each pmcid batch 97 | ( 98 | log 99 | .assign( 100 | batch=[idx]*pmcid_batch_df.shape[0], 101 | pmcid=pmcid_batch_df.PMCID.values.tolist() 102 | ) 103 | .to_csv( 104 | f"{temp_dir}/{log_file}", sep="\t", 105 | mode="a", header=False, index=False 106 | ) 107 | ) 108 | 109 | except Exception as e: 110 | sys.stderr.write( 111 | f"There is an error processing batch {idx}." 112 | ) 113 | 114 | sys.stderr.write( 115 | f"Here is the query:{query}." 116 | ) 117 | 118 | 119 | def merge_full_text(temp_dir, output): 120 | """ 121 | Download full text from Pubtator Central. 122 | This section involves heavy api calls and subject to get blocked. 123 | Email the researchers at pubtator if this script continues to be blocked 124 | 125 | Keywords arguments: 126 | temp_dir -- The path containing the pmids to pmcids map 127 | output -- the size of each id batch 128 | """ 129 | batch_files = Path().rglob(f"{temp_dir}/*.xml") 130 | 131 | with open(output, "wb") as xml_file: 132 | first_file = True 133 | 134 | for file in tqdm.tqdm(batch_files): 135 | try: 136 | tree = ET.parse(str(file.resolve())) 137 | root = tree.getroot() 138 | 139 | # Write Header for output 140 | if first_file: 141 | # write opening tag to file 142 | xml_file.write(b"\n") 143 | 144 | for tag in root.getchildren(): 145 | if tag.tag == "date": 146 | tag.text = time.strftime("%Y/%m/%d") 147 | 148 | # skip document tags will incorporate later 149 | if tag.tag == "document": 150 | break 151 | 152 | xml_file.write(ET.tostring(tag, pretty_print=True)) 153 | 154 | first_file = False 155 | 156 | for document in root.xpath("document"): 157 | xml_file.write(ET.tostring(document, pretty_print=True)) 158 | 159 | except XMLSyntaxError as e: 160 | sys.stderr.write( 161 | f"Please check {file}! There is an error at: {e}", 162 | ) 163 | 164 | sys.stderr.write( 165 | "I am skipping this file.", 166 | ) 167 | 168 | xml_file.write(b"\n") 169 | 170 | if __name__ == '__main__': 171 | parser = argparse.ArgumentParser(description='Extracts the annotations from the BioC xml format') 172 | parser.add_argument("--input", help="a tsv file that contains pmids to query for full text", required=True) 173 | parser.add_argument("--document_batch", help="the number of documents to query at once", default=100, type=int) 174 | parser.add_argument("--temp_dir", help="The directory to store the temporary files", required=True, type=str) 175 | parser.add_argument("--log_file", help="The directory to store the temporary files", default="batch_log.tsv", type=str) 176 | parser.add_argument("--output", help="the name of the outputfile containing full text documents", default="pubtator_full_text.xml") 177 | args = parser.parse_args() 178 | 179 | download_full_text(args.input, args.document_batch, args.temp_dir, args.log_file) 180 | merge_full_text(args.temp_dir, args.output) 181 | -------------------------------------------------------------------------------- /scripts/extract_tags.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | import csv 3 | import re 4 | 5 | from lxml import etree as ET 6 | import tqdm 7 | 8 | import scripts.utilities as utilities 9 | 10 | 11 | 12 | def extract_annotations(xml_path, tsv_path): 13 | """ 14 | Extract the annotations from pubtator xml formatted file 15 | Outputs a TSV file with the following header terms: 16 | Document - the corresponding pubmed id 17 | Type - the type of term (i.e. Chemical, Disease, Gene etc.) 18 | ID - the appropiate MESH or NCBI ID if known 19 | Offset - the character position where the term starts 20 | End - the character position where the term ends 21 | 22 | Keywords arguments: 23 | xml_path -- The path to the xml data file 24 | tsv_path -- the path to output the formatted data 25 | """ 26 | xml_opener = utilities.get_opener(xml_path) 27 | csv_opener = utilities.get_opener(tsv_path) 28 | with xml_opener(xml_path, "rb") as xml_file, csv_opener(tsv_path, "wt") as tsv_file: 29 | fieldnames = ['pubmed_id', 'type', 'identifier', 'offset', 'end'] 30 | writer = csv.DictWriter(tsv_file, fieldnames=fieldnames, delimiter='\t') 31 | writer.writeheader() 32 | tag_generator = ET.iterparse(xml_file, tag="document", recover=True, encoding="utf-8") 33 | 34 | try: 35 | for event, document in tqdm.tqdm(tag_generator): 36 | 37 | pubmed_id = document[0].text 38 | 39 | # cycle through all the annotation tags contained within document tag 40 | for annotation in document.iter('annotation'): 41 | 42 | # not all annotations will contain an ID 43 | if len(annotation) <= 3: 44 | continue 45 | 46 | for infon in annotation.iter('infon'): 47 | if infon.attrib["key"] == "type": 48 | ant_type = infon.text 49 | else: 50 | 51 | if not infon.text: 52 | continue 53 | 54 | ant_id = re.sub("(MESH:|CVCL:)", "", str(infon.text)) 55 | 56 | location, = annotation.iter('location') 57 | offset = int(location.attrib['offset']) 58 | end = offset + int(location.attrib['length']) 59 | row = {'pubmed_id': pubmed_id, 'type': ant_type, 'identifier': ant_id, 'offset': offset, 'end': end} 60 | writer.writerow(row) 61 | 62 | # prevent memory overload 63 | document.clear() 64 | 65 | except Exception as e: 66 | print(e) 67 | print(document[0].text) 68 | 69 | if __name__ == '__main__': 70 | parser = argparse.ArgumentParser(description='Export tags in a BioC XML file to a TSV table') 71 | parser.add_argument("--input", help="Path for the input BioC XML file", type=str, required=True) 72 | parser.add_argument("--output", nargs="?", help="Path for the output TSV file", required=True) 73 | 74 | args = parser.parse_args() 75 | 76 | extract_annotations(xml_path=args.input, tsv_path=args.output) 77 | -------------------------------------------------------------------------------- /scripts/hetnet_id_extractor.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | 3 | import pandas as pd 4 | import tqdm 5 | 6 | import scripts.utilities as utilities 7 | 8 | def filter_tags(infile, outfile): 9 | """ This method filters pubtator tags to consist of only 10 | hetnet tags 11 | 12 | Keyword arguments: 13 | infile -- the name of the file to read 14 | outfile -- the name of the output file 15 | """ 16 | 17 | print_header = True 18 | hetnet_chemical_df = load_chemical_df() 19 | hetnet_disease_df = load_disease_df() 20 | hetnet_gene_df = load_gene_df() 21 | csv_opener = utilities.get_opener(outfile) 22 | 23 | with csv_opener(outfile, "wt") as tsv_file: 24 | for extracted_tag_df in tqdm.tqdm(get_tag_chunks(infile)): 25 | 26 | # Covert chemical IDs 27 | chemical_merged_df = ( 28 | pd.merge( 29 | extracted_tag_df[extracted_tag_df["type"] == "Chemical"], 30 | hetnet_chemical_df[["drugbank_id", "identifier"]], 31 | left_on="identifier", 32 | right_on="identifier" 33 | ) 34 | .drop_duplicates() 35 | .replace({"type":{"Chemical": "Compound"}}) 36 | [["pubmed_id", "type", "offset", "end", "drugbank_id"]] 37 | .rename(columns={"drugbank_id": "identifier"}) 38 | ) 39 | 40 | # Convert Disease IDs 41 | disease_merged_df = ( 42 | pd.merge( 43 | extracted_tag_df[extracted_tag_df["type"] == "Disease"], 44 | hetnet_disease_df[["doid_code", "resource_id"]], 45 | left_on="identifier", 46 | right_on="resource_id" 47 | ) 48 | .drop_duplicates() 49 | [["pubmed_id", "type", "offset", "end", "doid_code"]] 50 | .rename(columns={"doid_code": "identifier"}) 51 | ) 52 | 53 | # Verify Gene IDs are human genes 54 | gene_df = extracted_tag_df[extracted_tag_df["type"] == "Gene"] 55 | gene_final_df = gene_df[gene_df["identifier"].isin(hetnet_gene_df["GeneID"])] 56 | 57 | final_df = ( 58 | gene_final_df 59 | .append(chemical_merged_df, sort=True) 60 | .append(disease_merged_df, sort=True) 61 | ) 62 | 63 | if print_header: 64 | ( 65 | final_df 66 | [["pubmed_id", "type", "identifier", "offset", "end"]] 67 | .sort_values(["pubmed_id", "offset"]) 68 | .to_csv(tsv_file, sep="\t", index=False) 69 | ) 70 | 71 | print_header = False 72 | else: 73 | ( 74 | final_df 75 | [["pubmed_id", "type", "identifier", "offset", "end"]] 76 | .sort_values(["pubmed_id", "offset"]) 77 | .to_csv(tsv_file, sep="\t", index=False, header=False) 78 | ) 79 | 80 | 81 | def get_tag_chunks(filename): 82 | """ Chunk the pandas dataframe so not everything is read into memory 83 | 84 | Keyword Arguments: 85 | filename -- the file to read through pandas 86 | """ 87 | chunksize = 10 ** 6 88 | for chunk in pd.read_table(filename, chunksize=chunksize): 89 | yield chunk 90 | 91 | 92 | def load_disease_df(): 93 | """ 94 | Load the mesh-hetnet id mapping table. 95 | Return a dataframe of id mappings 96 | """ 97 | url = 'https://raw.githubusercontent.com/dhimmel/disease-ontology/052ffcc960f5897a0575f5feff904ca84b7d2c1d/data/xrefs-prop-slim.tsv' 98 | disease_df = pd.read_table(url) 99 | return disease_df[disease_df["resource"] == "MSH"] 100 | 101 | 102 | def load_chemical_df(): 103 | """ 104 | Loads the chebi-mesh-drugbank id mapping table 105 | Return a dataframe with id mappings 106 | """ 107 | return pd.read_table("mapper/drugbank_mapper.tsv") 108 | 109 | 110 | def load_gene_df(): 111 | """ 112 | Loads the gene table from hetnets 113 | Return a dataframe with the gene ids 114 | """ 115 | url = 'https://raw.githubusercontent.com/dhimmel/entrez-gene/a7362748a34211e5df6f2d185bb3246279760546/data/genes-human.tsv' 116 | gene_df = pd.read_table(url).astype({"GeneID": str}) 117 | return gene_df[gene_df["type_of_gene"] == "protein-coding"] 118 | 119 | if __name__ == '__main__': 120 | parser = argparse.ArgumentParser(description='Filter extracted tags to contain Hetnet IDs in a TSV table') 121 | parser.add_argument("--input", help="Path for the tsv tag table", type=str, required=True) 122 | parser.add_argument("--output", nargs="?", help="Path for the output TSV file", type=str, required=True) 123 | 124 | args = parser.parse_args() 125 | 126 | filter_tags(infile=args.input, outfile=args.output) 127 | -------------------------------------------------------------------------------- /scripts/map_ids.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | import requests 3 | 4 | import lxml.etree as ET 5 | import pandas as pd 6 | import tqdm 7 | 8 | def read_tag_chunks(id_file, batch_size): 9 | """ 10 | Chunk the pandas dataframe so not everything is read into memory 11 | 12 | Keyword Arguments: 13 | id_file -- the file to read through pandas 14 | batch_size -- the size of each chunk 15 | """ 16 | for pmids_df in pd.read_csv(id_file, chunksize=batch_size, sep="\t"): 17 | yield ( 18 | pmids_df 19 | .drop_duplicates('pubmed_id') 20 | .rename(index=str, columns={"pubmed_id":"PMID"}) 21 | .astype({"PMID":str}) 22 | ) 23 | 24 | def map_ids(ids_file, id_output, debug): 25 | """ 26 | Extracts pmids from pubtator and then attempts to map pmids to pmcids 27 | This section is subject to be blocked since it relies on api calls. 28 | If this script continues to be blocked please email the researchers at pubtator 29 | 30 | Outputs a TSV file with the following header terms: 31 | pubmed_id - the corresponding pubmed id 32 | pmcids - the corresponding pubmed central ids 33 | 34 | Keywords arguments: 35 | ids_file -- The path to the extracted tag file 36 | email -- email to be reached at 37 | id_batch -- the id batch to query pubmed central from 38 | id_output --- the file name for the mapped ids 39 | """ 40 | if debug: 41 | pmids_to_pmcids = pd.read_csv( 42 | "data/example/ncbi_pmid_to_pmcid_map.tsv.xz", 43 | dtype={ 44 | "PMID": str, 45 | "Year": int, 46 | "Issue":str 47 | }, 48 | sep="\t" 49 | ) 50 | else: 51 | pmids_to_pmcids = pd.read_csv( 52 | "ftp://ftp.ncbi.nlm.nih.gov/pub/pmc/PMC-ids.csv.gz", 53 | dtype={ 54 | "PMID": str, 55 | "Year": int, 56 | "Issue":str 57 | } 58 | ) 59 | 60 | pmcid_batch = [] 61 | for pmids_df in tqdm.tqdm(read_tag_chunks(ids_file, 1e6)): 62 | mapped_ids = pmids_to_pmcids.merge(pmids_df[["PMID"]], on="PMID") 63 | 64 | if not mapped_ids.empty: 65 | pmcid_batch.append(mapped_ids) 66 | 67 | 68 | full_mapped_ids = pd.concat(pmcid_batch) 69 | ( 70 | full_mapped_ids 71 | .drop_duplicates() 72 | .to_csv(f"{id_output}", sep="\t", index=False) 73 | ) 74 | 75 | if __name__ == '__main__': 76 | parser = argparse.ArgumentParser(description='Extracts the annotations from the BioC xml format') 77 | parser.add_argument("--input", help="a tsv file that contains pmids to merge with pmcids list", required=True) 78 | parser.add_argument("--output", help="the name of the output file that contains mapped ids", default="pmids_to_pmcids_map.tsv") 79 | parser.add_argument("--debug", help="this flag is used to pre-load ncbi's pmid to pmcid id table", action="store_true") 80 | args = parser.parse_args() 81 | 82 | map_ids(args.input, args.output, args.debug) 83 | -------------------------------------------------------------------------------- /scripts/pubtator_to_xml.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | import csv 3 | import os 4 | import re 5 | import time 6 | 7 | from bioc import BioCWriter, BioCCollection, BioCDocument, BioCPassage 8 | from bioc import BioCAnnotation, BioCLocation 9 | from itertools import groupby 10 | from lxml.builder import E 11 | from lxml.etree import tostring 12 | import tqdm 13 | 14 | import scripts.utilities as utilities 15 | 16 | 17 | def bioconcepts2pubtator_annotations(tag, index): 18 | """Bioconcepts to Annotations 19 | Specifically for bioconcepts2pubtator and converts each annotation 20 | into an annotation object that BioC can parse. 21 | Keyword Arguments: 22 | tag -- the annotation line that was parsed into an array 23 | index -- the id of each document specific annotation 24 | """ 25 | 26 | annt = BioCAnnotation() 27 | annt.id = str(index) 28 | annt.infons["type"] = tag["type"] 29 | 30 | # If the annotation type is a Gene,Species, Mutation, SNP 31 | # Write out relevant tag 32 | tag_type = tag['type'] or '' 33 | tag_id = tag['tag_id'] 34 | if tag_type == "Gene": 35 | annt.infons["NCBI Gene"] = tag_id 36 | 37 | elif tag_type == "Species": 38 | annt.infons["NCBI Species"] = tag_id 39 | 40 | elif "Mutation" in tag_type: 41 | annt.infons["tmVar"] = tag_id 42 | 43 | elif "SNP" in tag_type: 44 | annt.infons["tmVar"] = tag_id 45 | 46 | else: 47 | # If there is no MESH ID for an annotation 48 | if tag_id: 49 | # check to see if there are multiple mesh tags 50 | if "|" in tag_id: 51 | # Write out each MESH id as own tag 52 | for tag_num, ids in enumerate(tag_id.split("|")): 53 | # Some ids dont have the MESH:#### form so added case to that 54 | if ":" not in ids: 55 | annt.infons["MESH {}".format(tag_num)] = tag_id 56 | else: 57 | term_type, term_id = ids.split(":") 58 | annt.infons["{} {}".format(term_type, tag_num)] = term_id 59 | else: 60 | # Some ids dont have the MESH:#### form so added case to that 61 | if ":" in tag_id: 62 | term_type, term_id = tag_id.split(":") 63 | annt.infons[term_type] = term_id 64 | else: 65 | annt.infons["MESH"] = tag_id 66 | else: 67 | annt.infons["MESH"] = "Unknown" 68 | 69 | location = BioCLocation() 70 | location.offset = str(tag["start"]) 71 | location.length = str(len(tag["term"])) 72 | annt.locations.append(location) 73 | annt.text = tag["term"] 74 | return annt 75 | 76 | 77 | def pubtator_stanza_to_article(lines): 78 | """Article Generator 79 | Returns an article that is a dictionary with the following keywords: 80 | pubmed_id - a document identifier 81 | Title- the title string 82 | Abstract- the abstract string 83 | Title_Annot- A filtered list of tags specific to the title 84 | Abstract_Annot- A filtered list of tags specific to the abstract 85 | Keywords: 86 | lines - this is a list of file lines passed from bioconcepts2pubtator_offsets function 87 | """ 88 | article = {} 89 | 90 | # title 91 | title_heading = lines[0].split('|') 92 | article["pubmed_id"] = title_heading[0] 93 | article["title"] = title_heading[2] 94 | title_len = len(title_heading[2]) 95 | 96 | # abstract 97 | abstract_heading = lines[1].split("|") 98 | article["abstract"] = abstract_heading[2] 99 | 100 | # Fix null characters 101 | fixed_lines = [ 102 | str_with_null.replace('\x00', '') 103 | for str_with_null in lines[2:] 104 | ] 105 | 106 | # set up the csv reader 107 | annts = ( 108 | csv.DictReader( 109 | fixed_lines, 110 | fieldnames=['pubmed_id', 'start', 'end', 'term', 'type', 'tag_id'], 111 | delimiter="\t", 112 | quoting=csv.QUOTE_NONE 113 | ) 114 | ) 115 | 116 | annts = list(annts) 117 | 118 | for annt in annts: 119 | for key in 'start', 'end': 120 | annt[key] = int(annt[key]) 121 | 122 | annts.sort(key=lambda x: x["start"]) 123 | article["title_annot"] = filter(lambda x: x["start"] < title_len, annts) 124 | article["abstract_annot"] = filter(lambda x: x["start"] > title_len, annts) 125 | 126 | return article 127 | 128 | 129 | def read_bioconcepts2pubtator_offsets(path): 130 | """Bioconcepts to pubtator 131 | 132 | Yields an article that is a dictionary described in the article generator 133 | function. 134 | 135 | Keywords: 136 | path - the path to the bioconcepts2putator_offset file (obtained from pubtator's ftp site: ftp://ftp.ncbi.nlm.nih.gov/pub/lu/PubTator/) 137 | """ 138 | opener = utilities.get_opener(path) 139 | f = opener(path, "rt") 140 | 141 | lines = (line.rstrip() for line in f) 142 | 143 | for k, g in groupby(lines, key=bool): 144 | # Group articles based on empty lines as separators. Only pass 145 | # on non-empty lines. 146 | g = list(g) 147 | if g[0]: 148 | yield pubtator_stanza_to_article(g) 149 | 150 | f.close() 151 | 152 | 153 | def convert_pubtator(input_path, output_path): 154 | """Convert pubtators annotation list to BioC XML 155 | Keyword Arguments: 156 | input_file -- the path of pubtators annotation file 157 | output_file -- the path to output the BioC XML file 158 | """ 159 | 160 | # Set up BioCWriter to write specifically Pubtator 161 | # Can change to incorporate other sources besides pubtator 162 | writer = BioCWriter() 163 | writer.collection = BioCCollection() 164 | collection = writer.collection 165 | collection.date = time.strftime("%Y/%m/%d") 166 | collection.source = "Pubtator" 167 | collection.key = "Pubtator.key" 168 | 169 | opener = utilities.get_opener(output_path) 170 | with opener(output_path, 'wb') as xml_file: 171 | 172 | # Have to manually do this because hangs otherwise 173 | # Write the head of the xml file 174 | xml_shell = writer.tostring('UTF-8') 175 | *xml_head, xml_tail = xml_shell.rstrip().split(b'\n') 176 | for line in xml_head: 177 | xml_file.write(line + b'\n') 178 | 179 | article_generator = read_bioconcepts2pubtator_offsets(input_path) 180 | # Write each article in BioC format 181 | for article in tqdm.tqdm(article_generator): 182 | try: 183 | # Skip the documents that have more than 1M characters 184 | # Pubtator contains sections that are large list of author 185 | # names which is why this check is needed 186 | if len(article['abstract']) > 1e5: 187 | continue 188 | 189 | document = BioCDocument() 190 | document.id = article["pubmed_id"] 191 | 192 | title_passage = BioCPassage() 193 | title_passage.put_infon('type', 'title') 194 | title_passage.offset = '0' 195 | title_passage.text = article["title"] 196 | 197 | abstract_passage = BioCPassage() 198 | abstract_passage.put_infon('type', 'abstract') 199 | abstract_passage.offset = str(len(article["title"]) + 1) 200 | abstract_passage.text = article["abstract"] 201 | 202 | id_index = 0 203 | for tag in article["title_annot"]: 204 | title_passage.annotations.append(bioconcepts2pubtator_annotations(tag, id_index)) 205 | id_index += 1 206 | 207 | for tag in article["abstract_annot"]: 208 | abstract_passage.annotations.append(bioconcepts2pubtator_annotations(tag, id_index)) 209 | id_index += 1 210 | 211 | document.add_passage(title_passage) 212 | document.add_passage(abstract_passage) 213 | 214 | step_parent = E('collection') 215 | writer._build_documents([document], step_parent) 216 | xml_file.write(tostring(step_parent[0], pretty_print=True)) 217 | step_parent.clear() 218 | 219 | except Exception as e: 220 | print(e) 221 | print(f"Article that broke: {article['pubmed_id']}") 222 | step_parent.clear() 223 | 224 | # Write the closing tag of the xml document 225 | xml_file.write(xml_tail + b'\n') 226 | 227 | 228 | if __name__ == '__main__': 229 | parser = argparse.ArgumentParser(description='Extracts the annotations from the BioC xml format') 230 | parser.add_argument("--documents", help="Path pointing to input file.", required=True) 231 | parser.add_argument("--output", help="Path for destination of output.", required=True) 232 | args = parser.parse_args() 233 | 234 | convert_pubtator(args.documents, args.output) 235 | -------------------------------------------------------------------------------- /scripts/utilities.py: -------------------------------------------------------------------------------- 1 | import mimetypes 2 | import importlib 3 | 4 | encoding_to_module = { 5 | 'gzip': 'gzip', 6 | 'bzip2': 'bz2', 7 | 'xz': 'lzma', 8 | } 9 | 10 | def get_opener(filename): 11 | """ 12 | Automatically detect compression and return the file opening function. 13 | """ 14 | type_, encoding = mimetypes.guess_type(filename) 15 | if encoding is None: 16 | opener = open 17 | else: 18 | module = encoding_to_module[encoding] 19 | opener = importlib.import_module(module).open 20 | return opener 21 | -------------------------------------------------------------------------------- /tests.sh: -------------------------------------------------------------------------------- 1 | set -o errexit 2 | 3 | python execute.py \ 4 | --config config_files/tests_config.json 5 | --------------------------------------------------------------------------------