{"id":29625242,"url":"https://github.com/novartis/tat","last_synced_at":"2025-07-21T06:07:44.896Z","repository":{"id":219859544,"uuid":"750073157","full_name":"Novartis/TAT","owner":"Novartis","description":"Transcriptomics-to-Activity Transformer (TAT) is a deep learning model to predict compound bioactivity in a dose-response assay using compound-induced transcriptomic profiles over concentration.","archived":false,"fork":false,"pushed_at":"2024-01-30T00:17:23.000Z","size":30,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-04-16T11:10:10.417Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Novartis.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}},"created_at":"2024-01-29T23:41:51.000Z","updated_at":"2024-02-14T06:14:51.000Z","dependencies_parsed_at":"2024-01-30T03:25:46.464Z","dependency_job_id":"c7253431-c061-4856-bbb6-1359654a7286","html_url":"https://github.com/Novartis/TAT","commit_stats":null,"previous_names":["novartis/tat"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Novartis/TAT","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Novartis%2FTAT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Novartis%2FTAT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Novartis%2FTAT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Novartis%2FTAT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Novartis","download_url":"https://codeload.github.com/Novartis/TAT/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Novartis%2FTAT/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266248501,"owners_count":23899056,"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":[],"created_at":"2025-07-21T06:07:44.332Z","updated_at":"2025-07-21T06:07:44.883Z","avatar_url":"https://github.com/Novartis.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TAT\n\n**T**ranscriptomics-to-**A**ctivity **T**ransformer is a deep learning\nmodel to predict compound bioactivity in a dose-response assay using\ncompound-induced transcriptomic profiles over concentration.\n\n## Contents\n\n- `tat`: Python source code for TAT.\n\n## System requirements\n\n### Hardware\n#### GPUs\n\nWe have tested TAT on machines with the following GPUs:\n\n- NVIDIA Tesla V100\n- NVIDIA Ampere A100\n\n### Software\n\n#### Operating systems\n\nWe have tested TAT on machines with the following systems:\n\n- Red Hat Enterprise Linux 8\n- CentOS Linux 7\n\n\n#### Software dependencies\n\n- python 3.8.15\n- pandas 1.5.2\n- numpy 1.23.5\n- pytorch 1.12.1.post200\n- rdkit 2022.09.3\n- scikit-learn 1.2.0\n- matplotlib 3.6.2\n- seaborn 0.12.2\n- skorch 0.9.0\n\n\n## Installation\n\n* Install the python libraries mentioned in **Software dependencies**\n  above into your python environment.\n\n## Example dataset\n\nAn example dataset with transcriptional signatures over concentration\ncan be downloaded from https://broad.io/rosetta/. The example dataset\nis `LINCS-Pilot1`.\n\n## Training and validating a model\n\nWith the example LINCS dataset, we show how to build a TAT model that\ntakes as input the transcriptional signatures over concentration of\ncompounds to predict a compound-induced morphological feature in a\nCell Painting assay.\n\nMake sure to modify the data directory path in `preprocess.py` to\nensure that the code finds the LINCS data.\n\n```\ncd ./tat\npython preprocess.py\npython model_build.py\n```\n\n\n## License\n\nCopyright 2024 Novartis Institutes for BioMedical Research Inc.\n\nLicensed under the Apache License, Version 2.0 (the \"License\");\nyou may not use this file except in compliance with the License.\nYou may obtain a copy of the License at\n\n    http://www.apache.org/licenses/LICENSE-2.0\n\nUnless required by applicable law or agreed to in writing, software\ndistributed under the License is distributed on an \"AS IS\" BASIS,\nWITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\nSee the License for the specific language governing permissions and\nlimitations under the License.\n\n\nSee LICENSE.txt\n\n# Contact\n\nwilliam_jose.godinez_navarro@novartis.com\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnovartis%2Ftat","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnovartis%2Ftat","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnovartis%2Ftat/lists"}