I’m exploring whether we can recover protein conformational ensembles from existing experimental data using steered generative models. See this post on diffuse.science and the recent Stacks publication on sampleworks for recent work.
Structural biology increasingly relies on machine learning-based structure predictors, enabling accurate atomic-level structure prediction at scale. However, predicting conformational ensembles rather than single structures remains a fundamental challenge. These predictors are trained on static PDB structures that are themselves imperfect representations of the underlying experiments. X-ray crystallography and cryo-EM measure ensemble-averaged signals over many molecular conformations, yet this heterogeneity is compressed into a single set of coordinates. Recent inference-time guidance methods offer a promising path forward by steering structure predictors toward agreement with experimental data, including ensembles. However, existing approaches are bespoke to specific models, making systematic comparison across predictors, guidance strategies, and loss functions difficult. Here, we present sampleworks, a modular framework for generating and evaluating biomolecular conformational ensembles from structure predictors guided by experimental data. As an initial benchmark, we asked whether three current structure predictors, Boltz-2, Protenix, and RosettaFold3, can recover experimentally supported alternative conformations when guided by simulated, noise-free electron density maps. We assembled a dataset of 791 segments from 40 high-resolution PDB entries, which have multiple physically plausible and experimentally supported conformations, but which are absent from structure predictor training data. Without guidance, predicted baseline ensembles were strongly biased toward whichever conformation dominates the training set. Density guidance substantially improved the ability to capture multiple states, but still retained biases that reflect the training set conformational distribution. Together, these results show that current structure predictors can be steered toward experimental data but do not yet reliably generalize to physically plausible ensembles. sampleworks provides a platform for diagnosing these limitations and developing ensemble-aware structure predictors that better reflect the heterogeneous data measured by structural biology data.
@article{chrispensSampleworksModularPlatform2026,title={{sampleworks}: {A} Modular Platform for Experimentally Guided Biomolecular Ensemble Generation},author={Chrispens, Karson and Collins, Marcus D. and Mai, Doris and Wankowicz, Stephanie A. and {van den Bedem}, Henry and Fraser, James S.},year={2026},month=jun,journal={The Stacks},publisher={Radial},doi={10.82153/jkxj-tw08},langid={english},}
Mutations in the kinase and juxtamembrane domains of the MET Receptor Tyrosine Kinase are responsible for oncogenesis in various cancers and can drive resistance to MET-directed treatments. Determining the most effective inhibitor for each mutational profile is a major challenge for MET-driven cancer treatment in precision medicine. Here, we used a deep mutational scan (DMS) of ~5764 MET kinase domain variants to profile the growth of each mutation against a panel of 11 inhibitors that are reported to target the MET kinase domain. We validate previously identified resistance mutations, pinpoint common resistance sites across type I, type II, and type I \frac12 inhibitors, unveil unique resistance and sensitizing mutations for each inhibitor, and verify non-cross-resistant sensitivities for type I and type II inhibitor pairs. We augment a protein language model with biophysical and chemical features to improve the predictive performance for inhibitor-treated datasets. Together, our study demonstrates a pooled experimental pipeline for identifying resistance mutations, provides a reference dictionary for mutations that are sensitized to specific therapies, and offers insights for future drug development.
@article{estevamMappingKinaseDomain2025,title={Mapping Kinase Domain Resistance Mechanisms for the {{MET}} Receptor Tyrosine Kinase via Deep Mutational Scanning},author={Estevam, Gabriella O and Linossi, Edmond and Rao, Jingyou and Macdonald, Christian B and Ravikumar, Ashraya and Chrispens, Karson M and Capra, John A and {Coyote-Maestas}, Willow and Pimentel, Harold and Collisson, Eric A and Jura, Natalia and Fraser, James S},editor={Seeliger, Markus A and Andreotti, Amy H},year={2025},month=feb,journal={eLife},volume={13},pages={RP101882},publisher={eLife Sciences Publications, Ltd},issn={2050-084X},doi={10.7554/eLife.101882},urldate={2025-03-30},langid={english},keywords={drug discovery,mutagenesis,protein kinase},}
Antibodies are engineerable quantities in medicine. Learning antibody molecular recognition would enable the in silico design of high affinity binders against nearly any proteinaceous surface. Yet, publicly available experiment antibody sequence-binding datasets may not contain the mutagenic, antigenic, or antibody sequence diversity necessary for deep learning approaches to capture molecular recognition. In part, this is because limited experimental platforms exist for assessing quantitative and simultaneous sequence-function relationships for multiple antibodies. Here we present MAGMA-seq, an integrated technology that combines multiple antigens and multiple antibodies and determines quantitative biophysical parameters using deep sequencing. We demonstrate MAGMA-seq on two pooled libraries comprising mutants of nine different human antibodies spanning light chain gene usage, CDR H3 length, and antigenic targets. We demonstrate the comprehensive mapping of potential antibody development pathways, sequence-binding relationships for multiple antibodies simultaneously, and identification of paratope sequence determinants for binding recognition for broadly neutralizing antibodies (bnAbs). MAGMA-seq enables rapid and scalable antibody engineering of multiple lead candidates because it can measure binding for mutants of many given parental antibodies in a single experiment.
@article{petersenIntegratedTechnologyQuantitative2024,title={An Integrated Technology for Quantitative Wide Mutational Scanning of Human Antibody {{Fab}} Libraries},author={Petersen, Brian M. and Kirby, Monica B. and Chrispens, Karson M. and Irvin, Olivia M. and Strawn, Isabell K. and Haas, Cyrus M. and Walker, Alexis M. and Baumer, Zachary T. and Ulmer, Sophia A. and Ayala, Edgardo and Rhodes, Emily R. and Guthmiller, Jenna J. and Steiner, Paul J. and Whitehead, Timothy A.},year={2024},month=may,journal={Nature Communications},volume={15},number={1},pages={3974},publisher={Nature Publishing Group},issn={2041-1723},doi={10.1038/s41467-024-48072-z},urldate={2024-05-16},copyright={2024 The Author(s)},langid={english},keywords={Antibodies,Applied immunology,Assay systems,Molecular engineering},}