{"id":21441748,"url":"https://github.com/dmis-lab/moable","last_synced_at":"2025-07-14T17:32:07.403Z","repository":{"id":97388621,"uuid":"334101923","full_name":"dmis-lab/moable","owner":"dmis-lab","description":"Predicting mechanism of action of novelcompounds using compound structure andtranscriptomic signature co-embedding","archived":false,"fork":false,"pushed_at":"2023-10-17T12:43:48.000Z","size":32478,"stargazers_count":13,"open_issues_count":3,"forks_count":1,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-05-14T00:23:19.892Z","etag":null,"topics":["pytorch"],"latest_commit_sha":null,"homepage":"https://doi.org/10.1093/bioinformatics/btab275","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dmis-lab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2021-01-29T09:49:51.000Z","updated_at":"2024-03-21T01:55:40.000Z","dependencies_parsed_at":"2023-10-20T19:23:24.020Z","dependency_job_id":null,"html_url":"https://github.com/dmis-lab/moable","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmis-lab%2Fmoable","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmis-lab%2Fmoable/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmis-lab%2Fmoable/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmis-lab%2Fmoable/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dmis-lab","download_url":"https://codeload.github.com/dmis-lab/moable/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225990493,"owners_count":17556152,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["pytorch"],"created_at":"2024-11-23T01:41:31.006Z","updated_at":"2024-11-23T01:41:31.512Z","avatar_url":"https://github.com/dmis-lab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MoAble\n\nA Pytorch Implementation of paper\n\n[Predicting mechanism of action of novelcompounds using compound structure andtranscriptomic signature co-embedding](https://doi.org/10.1093/bioinformatics/btab275)\n\nGwanghoon Jang, Sungjoon Park*, Sanghoon Lee, Sunkyu Kim, Sejeong Park, Jaewoo Kang*\n\nBioinformatics, Volume 37, Issue Supplement_1, July 2021, Pages i376–i382\n\nPresented at ISMB/ECCB 2021\n\n## Abstract\n\nIdentifying mechanism of actions (MoA) of novel compounds is crucial in drug discovery. Careful understanding of MoA can avoid potential side effects of drug candidates. Efforts have been madeto identify MoA using the transcriptomic signatures induced by compounds. However, those approachesfail to reveal MoAs in the absence of actual compound signatures.\n\nWe present MoAble, which predicts MoAs without requiring compound signatures. We train adeep learning-based co-embedding model to map compound signatures and compound structure intothe same embedding space. The model generates low-dimensional compound signature representationfrom the compound structure. To predict MoAs, pathway enrichment analysis is performed based on theconnectivity between embedding vectors of compounds and those of genetic perturbation. Results showthat MoAble is comparable to the methods that use actual compound signatures. We demonstrate thatMoAble can be used to reveal MoAs of novel compounds without measuring compound signatures withthe same prediction accuracy as measuring it.\n\n## Overview of MoAble\n\n![overview](https://user-images.githubusercontent.com/56992294/106699777-dbf52a80-6626-11eb-824a-cf41530380d5.png)\n\n## Resources\n\n### Data\n- [moable v1.21 (pytorch)](https://drive.google.com/drive/folders/1ZDerqTBeRvSWPshfODixjjvafpjjF9Mh?usp=sharing)\n- [moable v1.22 (pytorch)](https://drive.google.com/drive/folders/1joHoFUSYEyULwTFgL61oT294kptjVW8O?usp=sharing)\n\n\n## Requirements\n\n```bash\n$ conda create -n MoAble python=3.6\n$ conda activate MoAble\n$ conda install numpy pandas requests scikit-learn\n$ conda install -c rdkit rdkit\n$ conda install -c conda-forge -c bioconda gseapy\n$ conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch -c nvidia\n```\nNote that Pytorch has to be installed depending on the version of CUDA.\n\n## Predict MoA\n\nThe source code is for predicting MoAs of novel compounds with MoAble.\n\n```bash\n$ python prediction.py \n```\n\nGP embedding vectors, GP signature data, and pretrained model checkpoint are required to run the code. \n\nGP data can be downloaded from the Google Drive link in the resources section. \n\n## License\n\nThis software is copyrighted by Data Mining and Information Systems Lab @ Korea University.\n\nThe source code and data can be used only for NON COMMERCIAL purposes. \n\nPlease contact Gwanghoon Jang (jghoon (at) korea.ac.kr) for more details regarding the license.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdmis-lab%2Fmoable","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdmis-lab%2Fmoable","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdmis-lab%2Fmoable/lists"}