Biology subjects

Santos, J. B. W.

Publications and source records attributed to Santos, J. B. W..

3 recordsLinked to original sources

bioRxiv2026

Efficient exploration of peptide libraries using active learning with AlphaFold-based screening

We previously showed that AlphaFold2 can be used to screen for peptide-binding epitopes targeting the extraterminal (ET) domain of Bromodomain and Extraterminal (BET) proteins from candidate protein partners identified in pull-down experiments. However, such approaches require large numbers of AlphaFold2 calculations, making exhaustive screening impractical for larger datasets, such as viral proteomes that may target the ET domain. In many cases, identifying a substantial fraction of binders--even without exhaustive coverage--would already provide valuable biological insight into these interaction networks. Here, we show that an active learning strategy based on Thompson sampling (TS) can efficiently explore peptide sequence space. Using a library derived from BRD3 pull-down experiments, TS recovers 50% of all binders using 15% of the queries required by exhaustive sampling (3.3 times improvement over random sampling). Moreover, TS consistently identifies experimentally known binding epitopes with substantially fewer queries. Because the approach relies only on binary labels, it is readily transferable to other protein-peptide systems where AF-based binding classification is applicable, as well as to peptide-property predictors for properties such as solubility or aggregation propensity.

bioinformatics↗

bioRxiv2025

Scaling k-Means for Multi-Million Frames: A Stratified NANI Approach for Large-Scale MD Simulations

We present improved k-means clustering initialization strategies for molecular dynamics (MD) simulations, implemented as part of the N-ary Natural Initiation (NANI) method. Two new deterministic seeding strategies: strat_all and strat_reduced, extend the original NANI approaches and dramatically reduce the clustering runtime while preserving the quality of clustering results. These methods also preserve NANIs reproducible partitioning of well-separated and compact clusters while avoiding the costly iterative seed selection procedures of previous implementations. Testing on the {beta}-heptapeptide and the HP35 systems shows that these new flavors achieved Calinski-Harabasz and Davies-Bouldin scores comparable to the previous NANI variant, indicating that the efficiency gains come with no quality decrease. We also show how these new variants can be used to greatly speed up our previously proposed Hierarchical Extended Linkage Method (HELM). These enhancements extend the reach of NANI to accelerate large-scale MD analysis both in stand-alone k-means clustering and as a component of hybrid workflows, and remove a key barrier to routine, scalable, and reproducible exploration of complex conformational ensembles. The improved NANI implementation is accessible through our MDANCE package: https://github.com/mqcomplab/MDANCE.

biophysics↗

bioRxiv2025

Hierarchical Extended Linkage Method (HELM)'s Deep Dive into Hybrid Clustering Strategies

Clustering remains a key tool in the analysis of molecular dynamics (MD) simulations, from the preparation of kinetic models to the study of mechanistic pathways and structural determination. It is no surprise then that multiple algorithms are currently used in the MD community, with k-means and hierarchical approaches being arguably the two most popular approaches. The former is very attractive from a purely computational point of view, demanding minimal memory and time resources, but at the price of being able to partition the data in very restrictive ways. Hierarchical strategies, on the other hand, can generate arbitrary partitions, but with steep memory and time requirements due to their need to build a pairwise distance matrix for all the considered conformations/frames. Here we propose a new hybrid paradigm, the Hierarchical Extended Linkage Method (HELM), that retains the efficiency of k-means while incorporating the flexibility of hierarchical methods. The key ingredient is the use of n-ary difference functions as a way to stabilize the k-means results and efficiently build the hierarchy of subsets. We showcase the applicability of this strategy over protein-DNA and protein folding studies, including the complete analysis of simulations with over 1.5 million frames. HELM is freely available in our MDANCE clustering package.

biophysics↗