Publications

2026

1. ICLR 2026

   Representing local protein environments with atomistic foundation models

   Meital Bojan, Sanketh Vedula, Advaith Maddipatla, and 5 more authors

   In International Conference on Learning Representations 2026, Apr 2026

   Abs PDF Code

   The local structure of a protein strongly impacts its function and interactions with other molecules. Therefore, a concise, informative representation of a local protein environment is essential for modeling and designing proteins and biomolecular interactions. However, these environments’ extensive structural and chemical variability makes them challenging to model, and such representations remain under-explored. In this work, we propose a novel representation for a local protein environment derived from the intermediate features of atomistic foundation models (AFMs). We demonstrate that this embedding effectively captures both local structure (e.g., secondary motifs), and chemical features (e.g., amino-acid identity and protonation state). We further show that the AFM-derived representation space exhibits meaningful structure, enabling the construction of data-driven priors over the distribution of biomolecular environments. Finally, in the context of biomolecular NMR spectroscopy, we demonstrate that the proposed representations enable a first-of-its-kind physics-informed chemical shift predictor that achieves state-of-the-art accuracy. Our results demonstrate the surprising effectiveness of atomistic foundation models and their emergent representations for protein modeling beyond traditional molecular simulations. We believe this will open new lines of work in constructing effective functional representations for protein environments.

2. Nature Biotech

   Experiment-guided AlphaFold3 resolves accurate protein ensembles

   Advaith Maddipatla, Nadav Bojan Sellam, Meital Bojan, and 5 more authors

   In Nature Biotechnology, May 2026

   Abs

   AlphaFold3 predicts highly accurate protein structures from sequence, but tends to collapse to a single dominant conformation, even when the underlying structure is inherently heterogeneous. Moreover, its predictions are oblivious to experimental conditions that can alter local sequence conformation. In this work we show that AlphaFold3 can be guided to match data obtained by NMR spectroscopy, X-ray crystallography and cryo-EM experiments. We demonstrate that this methodology can generate ensembles of conformations having less distance restraint violations than traditionally resolved NMR structures and uncover unmodelled alternate conformations detectable in electron density. We show that AlphaFold3 can also be guided by cryo-electron microscopy maps and that doing so in combination with NMR parameters improves model quality. This methodology paves the way for the development of experimentally aware predictive models that capture the ensemble nature of protein structures.Competing Interest StatementThe authors have declared no competing interest.

3. ICML 2026

   Advaith Maddipatla, Anar Rzayev, Marco Pegoraro, and 5 more authors

   In International Conference on Machine Learning 2026, ICLR 2026 Workshop on Generative and Experimental Perspectives for Biomolecular Design (Oral Presentation), May 2026

   Abs PDF

   Protein function relies on dynamic conformational ensembles, yet current generative models like AlphaFold3 often fail to produce ensembles that match experimental data. Recent experiment-guided generators attempt to address this by steering the reverse diffusion process. However, these methods are limited by fixed sampling horizons and sensitivity to initialization, often yielding thermodynamically implausible results. We introduce a general inference-time optimization framework to solve these challenges. First, we optimize over latent representations to maximize ensemble log-likelihood, rather than perturbing structures post hoc. This approach eliminates dependence on diffusion length, removes initialization bias, and easily incorporates external constraints. Second, we present novel sampling schemes for drawing Boltzmann-weighted ensembles. By combining structural priors from AlphaFold3 with force-field-based priors, we sample from their product distribution while balancing experimental likelihoods. Our results show that this framework consistently outperforms state-of-the-art guidance, improving diversity, physical energy, and agreement with data in X-ray crystallography and NMR, often fitting the experimental data better than deposited PDB structures. Finally, inference-time optimization experiments maximizing ipTM scores reveal that perturbing AlphaFold3 embeddings can artificially inflate model confidence. This exposes a vulnerability in current design metrics, whose mitigation could offer a pathway to reduce false discovery rates in binder engineering.

4. B2M

   Density-guided AlphaFold3 uncovers unmodelled conformations in β2-microglobulin

   Sai Advaith Maddipatla, Sanketh Vedula, Alexander M Bronstein, and 1 more author

   bioRxiv, May 2026

   Abs PDF Code

   Although X-ray crystallography captures the ensemble of conformations present within the crystal lattice, models typically depict only the most dominant conformation, obscuring the existence of alternative states. Applying the electron density-guided AlphaFold3 approach to β2-Microglobulin highlights how ensembles of alternate backbone conformations can be systematically modeled directly from crystallographic maps. This study also highlights how the detection of conformational ensembles is affected by the local quality of electron density and subtle variations in crystallization conditions and lattice packing. These results demonstrate that density-guided AlphaFold3 can uncover conformational heterogeneity missed by conventional refinement, offering a robust, systematic framework to capture the full structural landscape of proteins in crystals and enhancing the interpretive power of macromolecular crystallography.Competing Interest StatementThe authors have declared no competing interest.Eric and Wendy Schmidt Center at the Broad Institute of MIT and HarvardHelmsley Fellowships Program for Sustainability and HealthIsraeli Science Foundation grantISTA HPC Cluster

2025

1. ICML 2025

   Inverse problems with experiment-guided AlphaFold

   Advaith Maddipatla, Nadav Bojan Sellam, Meital Bojan, and 4 more authors

   In International Conference on Machine Learning 2025, ICLR 2025 Workshop on Generative and Experimental Perspectives for Biomolecular Design (Spotlight Presentation), Jul 2025

   Abs PDF Code

   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, and generates high-accuracy NMR ensembles orders of magnitude faster than the status quo. Notably, we demonstrate that our ensembles outperform AlphaFold3 and sometimes better fit experimental data than publicly deposited structures to the Protein Data Bank (PDB). We believe that this approach will unlock building predictive models that fully embrace experimentally observed conformational diversity.

2024

1. MLSB 2024

   Generative modeling of protein ensembles guided by crystallographic electron densities

   Advaith Maddipatla, Nadav Bojan Sellam, Sanketh Vedula, and 2 more authors

   In Machine Learning for Structural Biology Workshop at NeurIPS 2024 (Oral Presentation), Dec 2024

   Abs PDF Code

   Proteins are dynamic, adopting ensembles of conformations. The nature of this conformational heterogenity is imprinted in the raw electron density measurements obtained from X-ray crystallography experiments. Fitting an ensemble of protein structures to these measurements is a challenging, ill-posed inverse problem. We propose a non-i.i.d. ensemble guidance approach to solve this problem using existing protein structure generative models and demonstrate that it accurately recovers complicated multi-modal alternate protein backbone conformations observed in certain single crystal measurements.