{"id":41192822,"url":"https://github.com/loucerac/drexml","last_synced_at":"2026-01-22T20:27:16.103Z","repository":{"id":60455806,"uuid":"362395439","full_name":"loucerac/drexml","owner":"loucerac","description":" (DRExM³L) Drug REpurposing using eXplainable Machine Learning and Mechanistic Models of signal transduction","archived":false,"fork":false,"pushed_at":"2025-11-20T19:25:48.000Z","size":85754,"stargazers_count":11,"open_issues_count":2,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-11-20T21:12:53.248Z","etag":null,"topics":["drug-repurposing","machine-learning","signaling-pathways"],"latest_commit_sha":null,"homepage":"https://loucerac.github.io/drexml/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/loucerac.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2021-04-28T08:32:57.000Z","updated_at":"2025-07-01T12:20:56.000Z","dependencies_parsed_at":"2024-02-27T06:32:06.494Z","dependency_job_id":"670a9452-168d-4c8f-9c65-f0e313880570","html_url":"https://github.com/loucerac/drexml","commit_stats":null,"previous_names":[],"tags_count":21,"template":false,"template_full_name":null,"purl":"pkg:github/loucerac/drexml","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loucerac%2Fdrexml","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loucerac%2Fdrexml/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loucerac%2Fdrexml/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loucerac%2Fdrexml/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/loucerac","download_url":"https://codeload.github.com/loucerac/drexml/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loucerac%2Fdrexml/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28670374,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-22T19:36:09.361Z","status":"ssl_error","status_checked_at":"2026-01-22T19:36:05.567Z","response_time":144,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["drug-repurposing","machine-learning","signaling-pathways"],"created_at":"2026-01-22T20:27:15.381Z","updated_at":"2026-01-22T20:27:16.041Z","avatar_url":"https://github.com/loucerac.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![DOI](https://img.shields.io/badge/DOI-10.1016/j.csbj.2024.02.027-FAB70C?logo=doi)](https://doi.org/10.1016/j.csbj.2024.02.027)\n[![DOI](https://zenodo.org/badge/362395439.svg)](https://zenodo.org/badge/latestdoi/362395439) \n[![PyPI version](https://badge.fury.io/py/drexml.svg)](https://badge.fury.io/py/drexml)\n[![pdm-managed](https://img.shields.io/badge/pdm-managed-blueviolet)](https://pdm.fming.dev)\n\n# Drug REpurposing using eXplainable Machine Learning and Mechanistic Models of signal transduction\n\nRepository for the `drexml` python package: (DRExM³L) Drug REpurposing using eXplainable Machine Learning and Mechanistic Models of signal transduction\n\n## Citation\n\nFind the associated publication [here](https://doi.org/10.1016/j.csbj.2024.02.027):\n\n\nEsteban-Medina M, de la Oliva Roque VM, Herráiz-Gil S, Peña-Chilet M, Dopazo J, Loucera C. drexml: A command line tool and Python package for drug repurposing. Computational and Structural Biotechnology Journal 2024;23:1129–43. https://doi.org/10.1016/j.csbj.2024.02.027.\n\n\nPart of the [Intelligent Biology and Medicine](https://www.sciencedirect.com/science/journal/20010370/vsi/10XRHM1G1LS) special issue:\n\nhttps://www.sciencedirect.com/journal/computational-and-structural-biotechnology-journal/special-issue/10XRHM1G1LS\n\n\nAnd the `BIB` file:\n\n```\n@article{EstebanMedina2024,\n  title = {drexml: A command line tool and Python package for drug repurposing},\n  volume = {23},\n  ISSN = {2001-0370},\n  url = {http://dx.doi.org/10.1016/j.csbj.2024.02.027},\n  DOI = {10.1016/j.csbj.2024.02.027},\n  journal = {Computational and Structural Biotechnology Journal},\n  publisher = {Elsevier BV},\n  author = {Esteban-Medina,  Marina and de la Oliva Roque,  Víctor Manuel and Herráiz-Gil,  Sara and Peña-Chilet,  María and Dopazo,  Joaquín and Loucera,  Carlos},\n  year = {2024},\n  month = dec,\n  pages = {1129–1143}\n}\n```\n\nThe article was written using `drexml` version `v1.1.0`. Install it using:\n```\npip install drexml==1.1.0\n```\nVersion `v1.1.1` improves the documentation and `README` by including a reference to the published article for easier access.\n\n## Setup\n\nTo install the `drexml` package use the following:\n\n```\nconda create -n drexml python=3.10\nconda activate drexml\npip install drexml\n```\n\nIf a CUDA~10.2/11.x (\u003c 12) compatible device is available use:\n\n```\nconda create -n drexml --override-channels -c \"nvidia/label/cuda-11.8.0\" -c conda-forge cuda cuda-nvcc cuda-toolkit gxx=11.2 python=3.10\nconda activate drexml\npip install --no-cache-dir --no-binary=shap drexml\n```\n\nTo install `drexml` in an existing environment, activate it and use:\n\n```\npip install drexml\n```\n\nNote that by default the `setup` will try to compile the `CUDA` modules, if not possible it will use the `CPU` modules.\n\n## Run\n\nTo run the program for a disease map that uses circuits from the preprocessed `KEGG` pathways and the `KDT` standard list, construct an environment file (e.g. `disease.env`):\n\n- using the following template if you have a set of seed genes (comma-separated):\n\n```\nseed_genes=2175,2176,2189\n```\n\n- using the following template if you want to use the DisGeNET [1] curated gene-disease associations as seeds.\n\n```\ndisease_id=\"C0015625\"\n```\n\n- using the following template if you know which circuits to include (the disease map):\n\n```\ncircuits=circuits.tsv.gz\n```\n\nThe `TSV` file `circuits.tsv` has the following format (tab delimited):\n\n```\nindex\tin_disease\nP-hsa03320-37\t0\nP-hsa03320-61\t0\nP-hsa03320-46\t0\nP-hsa03320-57\t0\nP-hsa03320-64\t0\nP-hsa03320-47\t0\nP-hsa03320-65\t0\nP-hsa03320-55\t0\nP-hsa03320-56\t0\nP-hsa03320-33\t0\nP-hsa03320-58\t0\nP-hsa03320-59\t0\nP-hsa03320-63\t0\nP-hsa03320-44\t0\nP-hsa03320-36\t0\nP-hsa03320-30\t0\nP-hsa03320-28\t1\n```\n\nwhere:\n\n- `index`: Hipathia circuit id\n- `in_disease`: (boolean) True/1 if a given circuit is part of the disease\n\nNote that in all cases you can restrict the circuits to the physiological list by setting `use_physio=true` in the `env` file.\n\nTo run the experiment using 10 CPU cores and 0 GPUs, run the following command within an activated environment:\n\n```\ndrexml run --n-gpus 0 --n-cpus 10 $DISEASE_PATH\n```\n\nwhere:\n\n- `--n-gpus` indicates the number of gpu devices to use in parallel (-1 -\u003e all) (0 -\u003e None)\n- `--n-cpus` indicates the number of cpu devices to use in parallel (-1 -\u003e all) 8\n- `DISEASE_PATH` indicates the path to the disease env file (e.g. `/path/to/disease/folder/disease.env`)\n\nUse the `--debug` option for testing that everything works using a few iterations.\n\nNote that the first time that the full program is run, it will take longer as it downloads the latest versions of each background dataset from Zenodo:\n\nhttps://doi.org/10.5281/zenodo.6020480\n\n## Contribute to development\n\nThe recommended setup is:\n\n- setup `pipx`\n- setup `miniforge`\n- use `pipx` to install `pdm`\n- ensure that `pdm` is version \u003e=2.1, otherwise update with `pipx`\n- use `pipx` to inject pdm-bump into `pdm`\n- use `pipx` to install `nox`\n- run `pdm config venv.backend conda`\n- run `make`, if you want to use a CUDA enabled GPU, use `make gpu=1`\n- (Recommended): For GPU development, clear the cache using `pdm cache clear` first\n\n## Documentation\n\nThe documentation can be found here:\n\nhttps://loucerac.github.io/drexml/\n\n\n## References\n[1] Janet Piñero, Juan Manuel Ramírez-Anguita, Josep Saüch-Pitarch, Francesco Ronzano, Emilio Centeno, Ferran Sanz, Laura I Furlong. The DisGeNET knowledge platform for disease genomics: 2019 update. Nucl. Acids Res. (2019) doi:10.1093/nar/gkz1021\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Floucerac%2Fdrexml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Floucerac%2Fdrexml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Floucerac%2Fdrexml/lists"}