{"id":20690285,"url":"https://github.com/merck/molprop","last_synced_at":"2025-10-05T20:54:02.162Z","repository":{"id":222554199,"uuid":"757140534","full_name":"Merck/MolPROP","owner":"Merck","description":"fuses molecular language and graph representation for property prediction","archived":false,"fork":false,"pushed_at":"2024-06-01T00:14:18.000Z","size":694,"stargazers_count":19,"open_issues_count":0,"forks_count":4,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-08-31T18:05:26.821Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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/Merck.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE/gnu-gpl-v3.0.md","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":"2024-02-13T22:03:47.000Z","updated_at":"2025-08-12T13:14:10.000Z","dependencies_parsed_at":"2024-02-18T05:22:45.386Z","dependency_job_id":null,"html_url":"https://github.com/Merck/MolPROP","commit_stats":null,"previous_names":["merck/molprop"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Merck/MolPROP","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Merck%2FMolPROP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Merck%2FMolPROP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Merck%2FMolPROP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Merck%2FMolPROP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Merck","download_url":"https://codeload.github.com/Merck/MolPROP/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Merck%2FMolPROP/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278518906,"owners_count":26000177,"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","status":"online","status_checked_at":"2025-10-05T02:00:06.059Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2024-11-16T23:12:31.289Z","updated_at":"2025-10-05T20:54:02.140Z","avatar_url":"https://github.com/Merck.png","language":"Python","readme":"# MolPROP: Molecular Property Predictions with Multimodal Language and Graph Fusion\n\nfuses molecular language and graph representation for property prediction\n\ncurrent models include:\n- language -- ChemBERTa-2-77M-MLM, ChemBERTa-2-77M-MTR\n- graph -- GCN, GAT, GATv2\n\n```\n@article{rollins2024,\n        title = {{MolPROP}: {Molecular} {Property} {Prediction} with {Multimodal} {Language} and {Graph} {Fusion}},\n        journal = {Journal of Cheminformatics},\n        author = {Rollins, Zachary A and Cheng, Alan C and Metwally, Essam},\n        month = may,\n        year = {2024}}\n```\n\n![image info](pics/fig1.png)\n\n## requirements\n- git lfs (for locally stored language models)\n    - install git lfs for your machine: https://github.com/git-lfs/git-lfs\n    - chemberta requires local installation to config: https://huggingface.co/DeepChem\n- molprop.yaml\n```\n    conda env create --name molprop --file molprop.yaml\n```\n\n## preprocess data\n### data splitting\n- data splits to reproduce manuscript results are provided: ./data/*csv\n- data should be in data directory (e.g., csv format) and organized such that SMILES string and endpoints are in separate columns\n- data can be split using the Bemis-Murko scaffold split implemented by DeepChem\n- explore the help options to execute the data split procedure\n```\n    python ./data/split.py --help\n```\n## train and hyperparameter tune\n- training and tuning execution is specified by the configuration files (config/setup.json)\n```\n    python ./src/train_tune.py\n```\n\n### hyperparameter tune\n- setup[\"training\"][\"ray_tune\"] == True\n- specify hyperparameter search space in the '__main__' of ./src/train_tune.py\n- ray cluster must be initialized before hyperparameter tuning execution\n- submit PBS script with specified num_cpus and num_gpus\n- start ray cluster\n```\n    ray start --head --num-cpus=8 --num-gpus=4 --temp-dir=\"/absolute/path/to/temporary/storage/\"\n    python ./src/train_tune.py\n```\n\n### inference and holdout\n- test trained/validated models on holdout by specifying config/setup.json\n- MolPROP models trained on data in manuscript are located in models/weights\n- setup['holdout']['model_path']\n- setup['holdout']['holdout_data_path]\n```\n    python ./src/holdout.py\n```\n\n\n### logging information and model storage\n- train_tune.log files are recorded and saved for every time stamped batch run\n- runs are also recorded on tensorboard\n- ***** = unqiue file identifier (e.g., time stamp or number)\n```\n    logs/batch_*****/train_tune.log\n    logs/batch_*****/events.out.tfevents.***** (setup[\"training\"][\"ray_tune\"] == False)\n    logs/batch_*****/ray_tune/hp_tune_*****/checkpoint_*****/events.out.tfevents.***** (setup[\"training\"][\"ray_tune\"] == True)\n```\n\n- hyperparameter tune runs are implemented by ray tune and models are stored\n- non-hyperparameter tuned models are also stored\n```\n    logs/batch_*****/ray_tune/hp_tune_*****/checkpoint_*****/dict_checkpoint.pkl (setup[\"training\"][\"ray_tune\"] == True)\n    models/weights/batch_*****/MOLPROP*****.pth (setup[\"training\"][\"ray_tune\"] == False)\n```\n\n# License\n    MolPROP fuses molecular language and graph for property prediction.\n    Copyright © 2023 Merck \u0026 Co., Inc., Rahway, NJ, USA and its affiliates. All rights reserved.\n\n    This program is free software: you can redistribute it and/or modify\n    it under the terms of the GNU General Public License as published by\n    the Free Software Foundation, either version 3 of the License, or\n    (at your option) any later version.\n\n    This program is distributed in the hope that it will be useful,\n    but WITHOUT ANY WARRANTY; without even the implied warranty of\n    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the\n    GNU General Public License for more details.\n\n    You should have received a copy of the GNU General Public License\n    along with this program.  If not, see \u003chttp://www.gnu.org/licenses/\u003e.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmerck%2Fmolprop","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmerck%2Fmolprop","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmerck%2Fmolprop/lists"}