Dagstuhl Seminar 24451 focused on how machine learning (ML) is revolutionizing computational biology and chemistry by enhancing the prediction and design of protein-protein and protein-ligand interactions. Key topics included integrating biological and chemical knowledge into ML models, addressing data quality and availability issues, and fostering interdisciplinary collaborations. Theoretical discussions explored representation learning, generative models, and protein language models as efficient alternatives to traditional methods. Practical sessions emphasized the importance of experimental constraints in ML workflows and proposed standards for balanced datasets. The seminar concluded by encouraging collaboration between computational and wet-lab researchers, setting the groundwork for future innovations in protein science and drug discovery.
@Article{bitbol_et_al:DagRep.14.11.1, author = {Bitbol, Anne-Florence and Listgarten, Jennifer and Pluskal, Tomas and Bushuiev, Anton and Bushuiev, Roman}, title = {{Machine Learning for Protein-Protein and Protein-Ligand Interactions (Dagstuhl Seminar 24451)}}, pages = {1--15}, journal = {Dagstuhl Reports}, ISSN = {2192-5283}, year = {2025}, volume = {14}, number = {11}, editor = {Bitbol, Anne-Florence and Listgarten, Jennifer and Pluskal, Tomas and Bushuiev, Anton and Bushuiev, Roman}, publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik}, address = {Dagstuhl, Germany}, URL = {https://drops.dagstuhl.de/entities/document/10.4230/DagRep.14.11.1}, URN = {urn:nbn:de:0030-drops-228223}, doi = {10.4230/DagRep.14.11.1}, annote = {Keywords: biological machine learning, ligand, molecular interactions, protein} }
Feedback for Dagstuhl Publishing