Inverse problems with experiment-guided AlphaFold

Sai Advaith Maddipatla, Nadav Bojan, Meital Bojan, Sanketh Vedula, Paul Schanda, Ailie Marx, Alexander Bronstein
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:42366-42393, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-maddipatla25a, title = {Inverse problems with experiment-guided {A}lpha{F}old}, author = {Maddipatla, Sai Advaith and Bojan, Nadav and Bojan, Meital and Vedula, Sanketh and Schanda, Paul and Marx, Ailie and Bronstein, Alexander}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {42366--42393}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/maddipatla25a/maddipatla25a.pdf}, url = {https://proceedings.mlr.press/v267/maddipatla25a.html}, 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.} }
Endnote
%0 Conference Paper %T Inverse problems with experiment-guided AlphaFold %A Sai Advaith Maddipatla %A Nadav Bojan %A Meital Bojan %A Sanketh Vedula %A Paul Schanda %A Ailie Marx %A Alexander Bronstein %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-maddipatla25a %I PMLR %P 42366--42393 %U https://proceedings.mlr.press/v267/maddipatla25a.html %V 267 %X 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.
APA
Maddipatla, S.A., Bojan, N., Bojan, M., Vedula, S., Schanda, P., Marx, A. & Bronstein, A.. (2025). Inverse problems with experiment-guided AlphaFold. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:42366-42393 Available from https://proceedings.mlr.press/v267/maddipatla25a.html.

Related Material