Flow-based fragment identification via binding site-specific latent representations
Machine Learning: Science and Technology · 01.06.2026 · 7 (3) · 035015
DOI: 10.1088/2632-2153/ae5d85 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning: Science and Technology, online erschienen am 14.05.2026. Verfasst von Rebecca M Neeser und 5 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EPSRC Turing AI World-Leading Research Fellowship, VantAI, Swiss National Science Foundation.
Abstract (Originalsprache)
Fragment-based drug design is a promising strategy leveraging the binding of small chemical moieties that can efficiently guide drug discovery. The initial step of fragment identification remains challenging, as fragments often bind weakly and non-specifically. We developed a protein-fragment encoder that relies on a contrastive learning approach to map both molecular fragments and protein surfaces in a shared latent space. The encoder captures interaction-relevant features and achieves strong discrimination between binding and non-binding regions, reaching ROC–area under the curve values of 0.92 on pocket surfaces and enrichment factors of 22.85 across full protein surfaces. Building on this representation, our generative method LatentFrag produces chemically realistic fragment identities and positions conditioned on the protein surface. LatentFrag improves fragment recovery over docking-based virtual screening, achieving a sampling hit rate more than four times higher at a fraction of its computational cost providing a valuable starting point for fragment hit discovery. We further show the practical utility of LatentFrag and extend the workflow to full ligand design tasks. Together, these approaches contribute to advancing fragment identification and provide valuable tools for fragment-based drug discovery.
Förderung
- EPSRC Turing AI World-Leading Research Fellowship
- VantAI
- Swiss National Science Foundation
- EPSRC AI Hub
- HORIZON EUROPE Marie Sklodowska-Curie Actions
- NCCR Catalysis
Zitieren
APA
Neeser, R. M., Igashov, I., Schneuing, A., Bronstein, M., Schwaller, P., & Correia, B. (2026). Flow-based fragment identification via binding site-specific latent representations. Machine Learning: Science and Technology, 7(3), 035015. https://doi.org/10.1088/2632-2153/ae5d85
Vancouver
Neeser RM, Igashov I, Schneuing A, Bronstein M, Schwaller P, Correia B. Flow-based fragment identification via binding site-specific latent representations. Machine Learning: Science and Technology. 2026;7(3):035015. doi:10.1088/2632-2153/ae5d85
BibTeX
@article{Neeser2026,
author = {Neeser, Rebecca M and Igashov, Ilia and Schneuing, Arne and Bronstein, Michael and Schwaller, Philippe and Correia, Bruno},
title = {Flow-based fragment identification via binding site-specific latent representations},
journal = {Machine Learning: Science and Technology},
year = {2026},
volume = {7},
number = {3},
pages = {035015},
doi = {10.1088/2632-2153/ae5d85}
}
EUVIMED