kMoL: an open-source machine and federated learning library for drug discovery
Abstract Machine learning is quickly becoming integral to drug discovery pipelines, particularly quantitative structure-activity relationship (QSAR) and absorption, distribution, metabolism, and excretion (ADME) tasks. Graph Convolutional Network (GCN) models have proven especially promising due to...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | Journal of Cheminformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13321-025-00967-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850045780747878400 |
|---|---|
| author | Romeo Cozac Haris Hasic Jun Jin Choong Vincent Richard Loic Beheshti Cyrille Froehlich Takuto Koyama Shigeyuki Matsumoto Ryosuke Kojima Hiroaki Iwata Aki Hasegawa Takao Otsuka Yasushi Okuno |
| author_facet | Romeo Cozac Haris Hasic Jun Jin Choong Vincent Richard Loic Beheshti Cyrille Froehlich Takuto Koyama Shigeyuki Matsumoto Ryosuke Kojima Hiroaki Iwata Aki Hasegawa Takao Otsuka Yasushi Okuno |
| author_sort | Romeo Cozac |
| collection | DOAJ |
| description | Abstract Machine learning is quickly becoming integral to drug discovery pipelines, particularly quantitative structure-activity relationship (QSAR) and absorption, distribution, metabolism, and excretion (ADME) tasks. Graph Convolutional Network (GCN) models have proven especially promising due to their inherent ability to model molecular structures using graph-based representations. However, maximizing the potential of such models in practice is challenging, as companies prioritize data privacy and security over collaboration initiatives to improve model performance and robustness. kMoL is an open-source machine learning library with integrated federated learning capabilities developed to address such challenges. Its key features include state-of-the-art model architectures, Bayesian optimization, explainability, and federated learning mechanisms. It demonstrates extensive customization possibilities, advanced security features, straightforward implementation of user-specific models, and high adaptability to custom datasets without additional programming requirements. kMoL is evaluated through locally trained benchmark settings and distributed federated learning experiments using various datasets to assess the features and flexibility of the library, as well as the ability to facilitate fast and practical experimentation. Additionally, results of these experiments provide further insights into the performance trade-offs associated with federated learning strategies, presenting valuable guidance for deploying machine learning models in a privacy-preserving manner within drug discovery pipelines. kMoL is available on GitHub at https://github.com/elix-tech/kmol . Scientific contribution The primary scientific contribution of this research project is the introduction and evaluation of kMoL, an open-source machine learning library with integrated federated learning capabilities. By demonstrating advanced customization and security capabilities without additional programming requirements, kMoL represents an accessible yet secure open-source platform for collaborative drug discovery projects. Additionally, the experiment results provide further insights into the performance trade-offs associated with federated learning strategies, presenting valuable guidance for deploying machine learning models in a privacy-preserving manner within drug discovery pipelines. |
| format | Article |
| id | doaj-art-94e5d65782d34c2092dae0abf0605d39 |
| institution | DOAJ |
| issn | 1758-2946 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cheminformatics |
| spelling | doaj-art-94e5d65782d34c2092dae0abf0605d392025-08-20T02:54:37ZengBMCJournal of Cheminformatics1758-29462025-02-0117111510.1186/s13321-025-00967-9kMoL: an open-source machine and federated learning library for drug discoveryRomeo Cozac0Haris Hasic1Jun Jin Choong2Vincent Richard3Loic Beheshti4Cyrille Froehlich5Takuto Koyama6Shigeyuki Matsumoto7Ryosuke Kojima8Hiroaki Iwata9Aki Hasegawa10Takao Otsuka11Yasushi Okuno12Elix, Inc.Elix, Inc.Elix, Inc.Elix, Inc.Elix, Inc.Elix, Inc.Graduate School of Medicine, Kyoto UniversityGraduate School of Medicine, Kyoto UniversityGraduate School of Medicine, Kyoto UniversityGraduate School of Medicine, Kyoto UniversityGraduate School of Medicine, Kyoto UniversityGraduate School of Medicine, Kyoto UniversityGraduate School of Medicine, Kyoto UniversityAbstract Machine learning is quickly becoming integral to drug discovery pipelines, particularly quantitative structure-activity relationship (QSAR) and absorption, distribution, metabolism, and excretion (ADME) tasks. Graph Convolutional Network (GCN) models have proven especially promising due to their inherent ability to model molecular structures using graph-based representations. However, maximizing the potential of such models in practice is challenging, as companies prioritize data privacy and security over collaboration initiatives to improve model performance and robustness. kMoL is an open-source machine learning library with integrated federated learning capabilities developed to address such challenges. Its key features include state-of-the-art model architectures, Bayesian optimization, explainability, and federated learning mechanisms. It demonstrates extensive customization possibilities, advanced security features, straightforward implementation of user-specific models, and high adaptability to custom datasets without additional programming requirements. kMoL is evaluated through locally trained benchmark settings and distributed federated learning experiments using various datasets to assess the features and flexibility of the library, as well as the ability to facilitate fast and practical experimentation. Additionally, results of these experiments provide further insights into the performance trade-offs associated with federated learning strategies, presenting valuable guidance for deploying machine learning models in a privacy-preserving manner within drug discovery pipelines. kMoL is available on GitHub at https://github.com/elix-tech/kmol . Scientific contribution The primary scientific contribution of this research project is the introduction and evaluation of kMoL, an open-source machine learning library with integrated federated learning capabilities. By demonstrating advanced customization and security capabilities without additional programming requirements, kMoL represents an accessible yet secure open-source platform for collaborative drug discovery projects. Additionally, the experiment results provide further insights into the performance trade-offs associated with federated learning strategies, presenting valuable guidance for deploying machine learning models in a privacy-preserving manner within drug discovery pipelines.https://doi.org/10.1186/s13321-025-00967-9Machine learningFederated learningDrug discoveryDeep learningGraph convolutional networksDistributed learning |
| spellingShingle | Romeo Cozac Haris Hasic Jun Jin Choong Vincent Richard Loic Beheshti Cyrille Froehlich Takuto Koyama Shigeyuki Matsumoto Ryosuke Kojima Hiroaki Iwata Aki Hasegawa Takao Otsuka Yasushi Okuno kMoL: an open-source machine and federated learning library for drug discovery Journal of Cheminformatics Machine learning Federated learning Drug discovery Deep learning Graph convolutional networks Distributed learning |
| title | kMoL: an open-source machine and federated learning library for drug discovery |
| title_full | kMoL: an open-source machine and federated learning library for drug discovery |
| title_fullStr | kMoL: an open-source machine and federated learning library for drug discovery |
| title_full_unstemmed | kMoL: an open-source machine and federated learning library for drug discovery |
| title_short | kMoL: an open-source machine and federated learning library for drug discovery |
| title_sort | kmol an open source machine and federated learning library for drug discovery |
| topic | Machine learning Federated learning Drug discovery Deep learning Graph convolutional networks Distributed learning |
| url | https://doi.org/10.1186/s13321-025-00967-9 |
| work_keys_str_mv | AT romeocozac kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT harishasic kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT junjinchoong kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT vincentrichard kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT loicbeheshti kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT cyrillefroehlich kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT takutokoyama kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT shigeyukimatsumoto kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT ryosukekojima kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT hiroakiiwata kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT akihasegawa kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT takaootsuka kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery AT yasushiokuno kmolanopensourcemachineandfederatedlearninglibraryfordrugdiscovery |