{"id":13958637,"url":"https://github.com/yvquanli/trimnet","last_synced_at":"2025-07-21T00:31:33.966Z","repository":{"id":45623131,"uuid":"282822372","full_name":"yvquanli/TrimNet","owner":"yvquanli","description":"Code for paper \"TrimNet: learning molecular representation from triplet messages for biomedicine \"","archived":false,"fork":false,"pushed_at":"2023-06-29T05:34:37.000Z","size":4015,"stargazers_count":51,"open_issues_count":0,"forks_count":19,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-11-28T02:34:57.515Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://academic.oup.com/bib/advance-article/doi/10.1093/bib/bbaa266/5955940","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/yvquanli.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2020-07-27T07:15:33.000Z","updated_at":"2024-11-20T10:04:35.000Z","dependencies_parsed_at":"2023-01-31T21:15:51.317Z","dependency_job_id":"ff533544-ee9b-466b-8d90-06f1508980b7","html_url":"https://github.com/yvquanli/TrimNet","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/yvquanli/TrimNet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yvquanli%2FTrimNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yvquanli%2FTrimNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yvquanli%2FTrimNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yvquanli%2FTrimNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yvquanli","download_url":"https://codeload.github.com/yvquanli/TrimNet/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yvquanli%2FTrimNet/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266221271,"owners_count":23894966,"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":"2024-08-08T13:01:47.124Z","updated_at":"2025-07-21T00:31:28.958Z","avatar_url":"https://github.com/yvquanli.png","language":"Python","funding_links":[],"categories":["分子"],"sub_categories":["网络服务_其他"],"readme":"# TrimNet\n\nTrimNet is a lightweight message passing neural network for multiple molecular property predictions.\n\nTrimNet can accurately complete multiple molecular properties prediction tasks with significant parameter reduction, including the quantum properties, bioactivity, physiology, and compound-protein interaction (CPI) prediction tasks.\n\n### Requirements \n\n```\nPyTorch \u003e= 1.4.0\ntorch-geometric \u003e= 1.3.2\nrdkit \u003e= '2019.03.4'\n```\n\n### Usage example\n\n**For quantum dataset**\n```sh\ngit clone https://github.com/yvquanli/trimnet\ncd ./TrimNet/trimnet_quantum/src\n# download dataset from https://s3-us-west-1.amazonaws.com/deepchem.io/datasets/molnet_publish/qm9.zip\n# unzip the file to trimnet_quantum/dataset/raw\npython run.py\n\nusage: python run.py [task] [depth] [cuda_device] [seed]\n```\n\n**For drug dataset**\n```sh\ngit clone https://github.com/yvquanli/trimnet\ncd ./TrimNet/trimnet_drug/source\npython run.py --dataset bace\n\nusage: python run.py [-h] [--data DATA] [--dataset DATASET] [--seed SEED]\n                     [--gpu GPU [GPU ...]] [--hid HID] [--heads HEADS]\n                     [--depth DEPTH] [--dropout DROPOUT] [--batch_size BATCH_SIZE]\n                     [--epochs EPOCHS] [--lr LR] [--weight_decay WEIGHT_DECAY]\n                     [--lr_scheduler_patience LR_SCHEDULER_PATIENCE]\n                     [--early_stop_patience EARLY_STOP_PATIENCE]\n                     [--lr_decay LR_DECAY] [--focalloss] [--eval]\n                     [--exps_dir EXPS_DIR] [--exp_name EXP_NAME]\n\n```\n\n\n## Authors \n\n* **Yuquan Li** - *Initial work, model design, benckmark on the qm9 dataset* - [Yuquan](https://github.com/yvquanli)\n* **Pengyong Li** - *Model design, benckmark on drug datasets and CPI datasets* - [Pengyong](https://github.com/pyli0628)\n\n## Citation\n\nPengyong Li, Yuquan Li, Chang-Yu Hsieh, et al. TrimNet: learning molecular representation from \nlet messages for biomedicine[J]. Briefings in bioinformatics, 2020.\n\n@article{10.1093/bib/bbaa266,  \n    author = {Li, Pengyong and Li, Yuquan and Hsieh, Chang-Yu and Zhang, Shengyu and Liu, Xianggen and Liu, Huanxiang and Song, Sen and Yao, Xiaojun},  \n    title = \"{TrimNet: learning molecular representation from triplet messages for biomedicine}\",  \n    journal = {Briefings in Bioinformatics},  \n    year = {2020},  \n    month = {11},  \n    issn = {1477-4054},  \n    doi = {10.1093/bib/bbaa266},  \n    url = {https://doi.org/10.1093/bib/bbaa266},  \n    note = {bbaa266},  \n}  \n\n## HOW USE DOCKER ON TrimNet project\n\n´´´ sudo docker build -t trimnet . ´´´\n\n´´´ sudo docker run triment . ´´´\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyvquanli%2Ftrimnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyvquanli%2Ftrimnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyvquanli%2Ftrimnet/lists"}