NeuralPLexer3: Accurate Biomolecular Complex Structure Prediction with Flow Models

Zhuoran Qiao, Feizhi Ding, Thomas Dresselhaus, Mia A. Rosenfeld, Xiaotian Han, Owen Lewis Howell, Aniketh Iyengar, Stephen Opalenski, Anders S Christensen, Sai Krishna Sirumalla, Fred Manby, Thomas Miller, Matthew Welborn

Keywords: Co-folding, flow matching, biomolecules, computational drug discovery

TL;DR: We introduce NeuralPLexer 3, a physics‑guided flow‑based generative model that delivers state‑of‑the‑art, seconds‑fast predictions of diverse biomolecular complex structures.

Abstract: Biomolecular structure determination is essential to a mechanistic understanding of diseases and the development of novel therapeutics. Machine-learning-based structure prediction methods have made significant advancements by computationally predicting protein and bioassembly structures from sequences and molecular topology alone. Despite substantial progress in the field, challenges remain to deliver structure prediction models to real-world drug discovery. Here, we present NeuralPLexer3 -- a physics-inspired flow-based generative model that achieves state-of-the-art prediction accuracy on key biomolecular interaction types and improves training and sampling efficiency compared to its predecessors and alternative methodologies. Examined through existing and new benchmarks, NeuralPLexer3 excels in areas crucial to structure-based drug design, including blind docking, physical validity, and ligand-induced protein conformational changes.

Primary Area: Machine learning for sciences (e.g. climate, health, life sciences, physics, social sciences)

Submission Number: 23747