{"id":22096170,"url":"https://github.com/aspirincode/genippi","last_synced_at":"2025-07-24T22:31:38.940Z","repository":{"id":199533841,"uuid":"550730645","full_name":"AspirinCode/GENiPPI","owner":"AspirinCode","description":"Interface-aware molecular generative framework for protein-protein interaction modulators","archived":false,"fork":false,"pushed_at":"2024-11-17T06:35:43.000Z","size":11494,"stargazers_count":11,"open_issues_count":0,"forks_count":4,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-11-17T07:29:32.637Z","etag":null,"topics":["cwgan-gp","drug-design","genippi","gnns","molecular-generative-models","protein-protein-interaction","protein-protein-interface","qed","qeppi"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/AspirinCode.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-10-13T08:30:16.000Z","updated_at":"2024-11-17T06:35:47.000Z","dependencies_parsed_at":null,"dependency_job_id":"ffc81580-a93d-48ab-8f3b-e91a7aab2cc1","html_url":"https://github.com/AspirinCode/GENiPPI","commit_stats":null,"previous_names":["aspirincode/genippi"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AspirinCode%2FGENiPPI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AspirinCode%2FGENiPPI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AspirinCode%2FGENiPPI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AspirinCode%2FGENiPPI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AspirinCode","download_url":"https://codeload.github.com/AspirinCode/GENiPPI/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":227482494,"owners_count":17779968,"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":["cwgan-gp","drug-design","genippi","gnns","molecular-generative-models","protein-protein-interaction","protein-protein-interface","qed","qeppi"],"created_at":"2024-12-01T04:09:50.771Z","updated_at":"2025-07-24T22:31:38.912Z","avatar_url":"https://github.com/AspirinCode.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![License: GNU](https://img.shields.io/badge/License-GNU-yellow)](https://github.com/AspirinCode/GENiPPI)\n[![ J. Cheminform.](https://img.shields.io/badge/%20J%20Cheminform%20(2024)-red)](https://doi.org/10.1186/s13321-024-00930-0)\n[![bioRxiv](https://img.shields.io/badge/bioRxiv%202023.10.10.557742-green)](https://doi.org/10.1101/2023.10.10.557742)\n[![Zenodo](https://img.shields.io/badge/10.5281%2Fzenodo.13968591-gray)](https://zenodo.org/records/13968592)\n\n\n# GENiPPI\n\n**Interface-aware molecular generative framework for protein-protein interaction modulators**\n\nProtein-protein interactions (PPIs) play a crucial role in numerous biochemical and biological processes. Although several structure-based molecular generative models have been developed, PPI interfaces and compounds targeting PPIs exhibit distinct physicochemical properties compared to traditional binding pockets and small-molecule drugs. As a result, generating compounds that effectively target PPIs, particularly by considering PPI complexes or interface hotspot residues, remains a significant challenge. In this work, we constructed a comprehensive dataset of PPI interfaces with active and inactive compound pairs. Based on this, we propose a novel molecular generative framework tailored to PPI interfaces, named GENiPPI. Our evaluation demonstrates that GENiPPI captures the implicit relationships between the PPI interfaces and the active molecules, and can generate novel compounds that target these interfaces. Moreover, GENiPPI can generate structurally diverse novel compounds with limited PPI interface modulators. To the best of our knowledge, this is the first exploration of a structure-based molecular generative model focused on PPI interfaces, which could facilitate the design of PPI modulators. The PPI interface-based molecular generative model enriches the existing landscape of structure-based (pocket/interface) molecular generative model.\n\n\n## Framework of GENiPPI\n![Model Architecture of GENiPPI](https://github.com/AspirinCode/GENiPPI/blob/main/figure/GENiPPI_framework.png)\n\n\n## Acknowledgements\nThe code in this repository is based on their source code release (https://github.com/AspirinCode/iPPIGAN and https://github.com/kiharalab/GNN_DOVE). If you find this code useful, please consider citing their work.\n\n\n## News!\n\n**[2024/12/20]** Available [online](https://doi.org/10.1186/s13321-024-00930-0) **Journal of Cheminformatics**, 2024.  \n\n**[2024/11/11]** Accepted in **Journal of Cheminformatics**, 2024.  \n\n**[2024/03/15]** submission to **Journal of Cheminformatics**, 2024.  \n\n**[2023/10/10]** submission to **bioRxiv**, 2023.  \n\n\n## Requirements\n```python\nPython==3.6\npytorch==1.7.1\ntorchvision==0.8.2\ntensorflow==2.5\nkeras==2.2.2\nRDKit==2020.09.1.0\nHTMD==1.13.9\nMultiwfn==3.7\nmoleculekit==0.6.7\n```\n\nhttps://github.com/rdkit/rdkit\n\nhttps://github.com/Acellera/htmd\n\nhttps://github.com/Acellera/moleculekit\n\nhttp://sobereva.com/multiwfn/\n\n\n## Installation\n\n```python\nconda env create -f environment.yml\n\nOR\n\nconda create --name GENiPPI python=3.6 conda\n\npip install -r requirements.txt\n\n\nOR\n\nconda config --add channels acellera\nconda install -c acellera htmd=1.13.9\n\n#pytorch==1.7.1\nconda install pytorch==1.7.1 torchvision==0.8.2 torchaudio==0.7.2 cudatoolkit=11.0 -c pytorch\n#keras\nconda install keras==2.2.2\n\n```\n\n\n\n## Training\n\n\n```python\n\n#the training model\n# 0 : train\npython train.py [File Index] 0\n\n#example\npython train.py 1 0\npython train.py 2 0\n...\n\n#fine-tuning\n# 1 : fine tuning\npython train.py [File Index] 1\n\n#example\npython train.py 2 1\npython train.py 3 1\npython train.py 4 1\n...\n```\n\nFor the generation stage the model files are available. It is possible to use the ones that are generated during the training step or you can download the ones that we have already generated model files from Google Drive. \n\n\n\n## Generation\nnovel compound generation please follow notebook:\n\n```python\npython gen_wgan.py\n\nor\n\nGENiPPI_generate.ipynb\n```\n\n## Model Metrics\n### MOSES\nMolecular Sets (MOSES), a benchmarking platform to support research on machine learning for drug discovery. MOSES implements several popular molecular generation models and provides a set of metrics to evaluate the quality and diversity of generated molecules. With MOSES, MOSES aim to standardize the research on molecular generation and facilitate the sharing and comparison of new models.\nhttps://github.com/molecularsets/moses\n\n\n### QEPPI\nquantitative estimate of protein-protein interaction targeting drug-likeness\n\nhttps://github.com/ohuelab/QEPPI\n\n*  Kosugi T, Ohue M. Quantitative estimate index for early-stage screening of compounds targeting protein-protein interactions. International Journal of Molecular Sciences, 22(20): 10925, 2021. doi: 10.3390/ijms222010925\nAnother QEPPI publication (conference paper)\n\n*  Kosugi T, Ohue M. Quantitative estimate of protein-protein interaction targeting drug-likeness. In Proceedings of The 18th IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB 2021), 2021. doi: 10.1109/CIBCB49929.2021.9562931 (PDF) * © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.\n\n\n\n## Analysis\n\n\n### Molecular shape\n\n**calculate NPR and PMI descriptors**\n\n```python\nChem.Descriptors3D.NPR1(mol)\nChem.Descriptors3D.NPR2(mol)\n\nChem.rdMolDescriptors.CalcPMI1\nChem.rdMolDescriptors.CalcPMI2\nChem.rdMolDescriptors.CalcPMI3\n```\n\nhttps://greglandrum.github.io/rdkit-blog/posts/2022-06-22-variability-of-pmi-descriptors.html\n\n\n**calculate PBF descriptors**\n\n```python\nChem.rdMolDescriptors.CalcPBF(mol)\n```\n\n**reference**  \nFirth, N.C., Brown, N. and Blagg, J., 2012. Plane of best fit: a novel method to characterize the three-dimensionality of molecules. Journal of chemical information and modeling, 52(10), pp.2516-2525.\n\n\n### TMAP visualization of chemical space\n\nhttps://github.com/reymond-group/mhfp\n\nhttps://github.com/reymond-group/faerun-python\n\n\n\n```python\n\npip install mhfp\npip install faerun\n\n```\n\n**reference code**  \nhttps://tmap.gdb.tools/?ref=gdb.unibe.ch#ex-chembl\n\n\n## License\nCode is released under GNU AFFERO GENERAL PUBLIC LICENSE.\n\n\n## Cite:\n\n\n*  Jianmin Wang, Jiashun Mao, Chunyan Li, Hongxin Xiang, Xun Wang, Shuang Wang, Zixu Wang, Yangyang Chen, Yuquan Li, Kyoung Tai No, Tao Song, Xiangxiang Zeng; Interface-aware molecular generative framework for protein-protein interaction modulators.  J Cheminform (2024). doi: https://doi.org/10.1186/s13321-024-00930-0\n\n*  Jianmin Wang, Yanyi Chu, Jiashun Mao, Hyeon-Nae Jeon, Haiyan Jin, Amir Zeb, Yuil Jang, Kwang-Hwi Cho, Tao Song, Kyoung Tai No, De novo molecular design with deep molecular generative models for PPI inhibitors, Briefings in Bioinformatics, 2022;, bbac285, https://doi.org/10.1093/bib/bbac285\n\n* J. Wang, P. Zhou, Z. Wang, W. Long, Y. Chen, K.T. No, D. Ouyang, J. Mao, X. Zeng, Diffusion-based generative drug-like molecular editing with chemical natural language, Journal of Pharmaceutical Analysis, https://doi.org/10.1016/j.jpha.2024.101137.  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faspirincode%2Fgenippi","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faspirincode%2Fgenippi","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faspirincode%2Fgenippi/lists"}