Data-driven research in structural bioinformatics: from proteins to biomolecular interactions
Mardi 3 novembre 2026Horaire : 11 h
Justas Dapkūnas
Modern research in structural bioinformatics is largely based on training machine learning models and therefore depends crucially on the available experimental data. In this presentation, we will discuss how data availability shapes the possibilities for conducting research in computational structural biology. The level of data readiness differs significantly between established protein bioinformatics resources and smaller databases collecting data on specific topics. Data on protein sequences and structures are readily available in databases such as UniProt and Protein Data Bank (PDB). This enables the development of derivative resources, such as the PPI3D database and web server [1], aimed at facilitating the research on biomolecular interactions. PPI3D automatically retrieves data from the PDB every week, identifies protein-protein and protein-nucleic acid interactions, and clusters similar interaction interfaces and binding sites. This easy-to-use resource, combined with data from other bioinformatics databases, enables the training of machine learning models, for example, for predicting interaction sites on protein molecules. However, when simple information on interactions or knowledge of the structures of interacting proteins is insufficient and the binding affinity estimates are needed, automated analysis of the data is not yet possible and data quality remains the major problem. To this end, manually curated datasets are widely used, but in most cases they are not frequently updated (even such widely cited resources as our SKEMPI database [2]), sometimes still contain errors that need to be corrected before the data can be used, or even disappear behind paywalls. In the future, as machine learning gains even more importance in structural bioinformatics, high-quality, accessible, and reusable data resources will become increasingly critical.
[1] J. Dapkūnas et al., Nucleic Acids Res. 52, W264-W271 (2024).
[2] J. Jankauskaitė et al., Bioinformatics. 35, 462-469 (2019).
Campus Pierre et Marie Curie, salle Gérard Noguez (24-25/405)
lionel.tabourier (at) nulllip6.fr