{"id":19849499,"url":"https://github.com/filipspl/tox24challenge","last_synced_at":"2026-03-19T12:02:38.788Z","repository":{"id":256504247,"uuid":"852081464","full_name":"filipsPL/tox24challenge","owner":"filipsPL","description":"Dataset used in Tox24 challenge","archived":false,"fork":false,"pushed_at":"2024-09-11T01:41:46.000Z","size":2685,"stargazers_count":1,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-11T12:49:14.267Z","etag":null,"topics":["dataset","machine-learning","molecular-descriptors","qsar","tox24","toxicity-prediction"],"latest_commit_sha":null,"homepage":"","language":null,"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/filipsPL.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-09-04T07:34:01.000Z","updated_at":"2024-09-04T08:25:59.000Z","dependencies_parsed_at":"2024-09-11T06:41:37.466Z","dependency_job_id":"e8ed15bd-2ff9-4ff0-855d-d802e99640de","html_url":"https://github.com/filipsPL/tox24challenge","commit_stats":null,"previous_names":["filipspl/tox24challenge"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filipsPL%2Ftox24challenge","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filipsPL%2Ftox24challenge/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filipsPL%2Ftox24challenge/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/filipsPL%2Ftox24challenge/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/filipsPL","download_url":"https://codeload.github.com/filipsPL/tox24challenge/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241229433,"owners_count":19930796,"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":["dataset","machine-learning","molecular-descriptors","qsar","tox24","toxicity-prediction"],"created_at":"2024-11-12T13:21:18.722Z","updated_at":"2026-01-27T18:08:12.697Z","avatar_url":"https://github.com/filipsPL.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"Tox24 Challenge Dataset\n===========\n\nThis repository contains molecular structures and descriptors for the Tox24 challenge prepared by me (team name: **filipsPL**). The goal of the challenge was to predict the in vitro activity of compounds' activity against [Transthyretin (TTR)](https://en.wikipedia.org/wiki/Transthyretin) using chemical structure data.\n\n- [Tox24 Challenge Dataset](#tox24-challenge-dataset)\n  - [Dataset](#dataset)\n  - [Descriptors](#descriptors)\n  - [Importance of features](#importance-of-features)\n  - [The Challenge Results](#the-challenge-results)\n  - [References](#references)\n\n\n## Dataset\n\nThis repository includes:\n\n- The chemical structures in SMILES format, provided by the organizers and curated by me using my RDKit pipeline `data/smiles_org+fixed.csv`.\n- Training set - a diversified set of 1000 compounds, used for training models `data/train.csv.xz`\n- Validation set: a diversified set of 100 compounds, used for final validation of models `data/validation.csv.xz`\n- Test set: 500 compounds used to make predictions. It contains a leaderboard set (200 compounds) and a blind set (300 compounds) `data/test.csv.xz`. 💡 This set contains compounds with known and unknown activity. Compounds with known activity are also the members of the Training/Validation set.\n\n## Descriptors\n\nThe csv files contain 2D descriptors of molecules, including:\n\n- DRKitDescriptors (2D)\n- molecular fingerprints:\n  - CDK:\n    - CDKECFP4\n    - CDKEState\n    - CDKFCFP4\n    - CDKmolprop\n    - CDKpubchem\n    - CDKstandard\n  - Indigo fingerprints:\n    - IndigoResonanceSubstructure\n    - IndigoSimilarity\n  - RDKit fingerprints:\n    - RDkitFP-AtomPair\n    - RDkitFP-Avalon\n    - RDkitFP-FeatMorgan4\n    - RDkitFP-Layered\n    - RDkitFP-MACCS\n    - RDkitFP-Morgan2\n    - RDkitFP-Morgan3\n    - RDkitFP-Morgan4\n    - RDkitFP-Pattern\n    - RDkitFP-RDKit\n    - RDkitFP-Torsion\n\n## Importance of features\n\nFeature importances according to the final catboost model\n\n![bar plot](feature_importance.png)\n\n\n## The Challenge Results\n\nBar plot showing RMSE of submitted predictions (by me, based on the official results). Congratulations to the winning team Amidoff 🎉!\n\n![rank](ranking.png)\n\n## References\n\n1. [OCHEM Platform for Tox24](https://ochem.eu/static/challenge.do)\n2. [Chem. Res. Toxicol. 2024, 37, 6, 825–826](https://pubs.acs.org/doi/10.1021/acs.chemrestox.4c00192)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffilipspl%2Ftox24challenge","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffilipspl%2Ftox24challenge","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffilipspl%2Ftox24challenge/lists"}