Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site Design

Hannes Stark, Bowen Jing, Regina Barzilay, Tommi Jaakkola
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:46468-46494, 2024.

Abstract

A significant amount of protein function requires binding small molecules, including enzymatic catalysis. As such, designing binding pockets for small molecules has several impactful applications ranging from drug synthesis to energy storage. Towards this goal, we first develop HarmonicFlow, an improved generative process over 3D protein-ligand binding structures based on our self-conditioned flow matching objective. FlowSite extends this flow model to jointly generate a protein pocket’s discrete residue types and the molecule’s binding 3D structure. We show that HarmonicFlow improves upon state-of-the-art generative processes for docking in simplicity, generality, and average sample quality in pocket-level docking. Enabled by this structure modeling, FlowSite designs binding sites substantially better than baseline approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-stark24a, title = {Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site Design}, author = {Stark, Hannes and Jing, Bowen and Barzilay, Regina and Jaakkola, Tommi}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {46468--46494}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/stark24a/stark24a.pdf}, url = {https://proceedings.mlr.press/v235/stark24a.html}, abstract = {A significant amount of protein function requires binding small molecules, including enzymatic catalysis. As such, designing binding pockets for small molecules has several impactful applications ranging from drug synthesis to energy storage. Towards this goal, we first develop HarmonicFlow, an improved generative process over 3D protein-ligand binding structures based on our self-conditioned flow matching objective. FlowSite extends this flow model to jointly generate a protein pocket’s discrete residue types and the molecule’s binding 3D structure. We show that HarmonicFlow improves upon state-of-the-art generative processes for docking in simplicity, generality, and average sample quality in pocket-level docking. Enabled by this structure modeling, FlowSite designs binding sites substantially better than baseline approaches.} }
Endnote
%0 Conference Paper %T Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site Design %A Hannes Stark %A Bowen Jing %A Regina Barzilay %A Tommi Jaakkola %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-stark24a %I PMLR %P 46468--46494 %U https://proceedings.mlr.press/v235/stark24a.html %V 235 %X A significant amount of protein function requires binding small molecules, including enzymatic catalysis. As such, designing binding pockets for small molecules has several impactful applications ranging from drug synthesis to energy storage. Towards this goal, we first develop HarmonicFlow, an improved generative process over 3D protein-ligand binding structures based on our self-conditioned flow matching objective. FlowSite extends this flow model to jointly generate a protein pocket’s discrete residue types and the molecule’s binding 3D structure. We show that HarmonicFlow improves upon state-of-the-art generative processes for docking in simplicity, generality, and average sample quality in pocket-level docking. Enabled by this structure modeling, FlowSite designs binding sites substantially better than baseline approaches.
APA
Stark, H., Jing, B., Barzilay, R. & Jaakkola, T.. (2024). Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site Design. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:46468-46494 Available from https://proceedings.mlr.press/v235/stark24a.html.

Related Material