Inverse problems with experiment-guided AlphaFold

Sai Advaith Maddipatla, Nadav Bojan, Meital Bojan, Sanketh Vedula, Paul Schanda, Ailie Marx, Alexander Bronstein

TL;DR: We develop experiment-guided AlphaFold-3 to solve inverse problems in structural biology, leading to faster experimental cycles and improved modeling in X-ray crystallography and NMR spectroscopy.

Abstract: Proteins exist as a dynamic ensemble of multiple conformations, and these motions are often crucial for their functions. However, current structure prediction methods predominantly yield a single conformation, overlooking the conformational heterogeneity revealed by diverse experimental modalities. Here, we present a framework for building experiment-grounded protein structure generative models that infer conformational ensembles consistent with measured experimental data. The key idea is to treat state-of-the-art protein structure predictors (e.g., AlphaFold3) as sequence-conditioned structural priors, and cast ensemble modeling as posterior inference of protein structures given experimental measurements. Through extensive real-data experiments, we demonstrate the generality of our method to incorporate a variety of experimental measurements. In particular, our framework uncovers previously unmodeled conformational heterogeneity from crystallographic densities, generates high-accuracy NMR ensembles orders of magnitude faster than status quo, and incorporates pairwise cross-link constraints. Notably, we demonstrate that our ensembles outperform AlphaFold3 and sometimes better fit experimental data than publicly deposited structures to the protein database (PDB). We believe that this approach will unlock building predictive models that fully embrace experimentally observed conformational diversity.

Lay Summary: AlphaFold is a groundbreaking deep learning solution that predicts protein structure from a protein sequence. We are introducing experiment guided AlphaFold that solves the inverse problems from experiment observations (capturing all dynamic properties) and also leverage the evolutionary prior embedded within AlphaFold.

Application-Driven Machine Learning: This submission is on Application-Driven Machine Learning.

Primary Area: Applications->Chemistry, Physics, and Earth Sciences

Keywords: protein structure prediction, alphafold, protein generative models, experiment-grounded generative models

Submission Number: 15661