Efficient exploration of peptide libraries using active learning with AlphaFold-based screening
Gaza, J.; Santos, J. B. W.; Singh, B.; Miranda Quintana, R. A.; Perez, A.
Show abstract
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.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Deep Local Analysis evaluates protein docking conformations with locally oriented cubes 94%
- Deep Local Analysis deconstructs protein-protein interfaces and accurately estimates binding affinity changes upon mutation 94%
- Mapping the space of protein binding sites with sequence-based protein language models 94%
Similar papers in this journal
Similar papers in this journal
- Learning Peptide Recognition Rules for a Low-Specificity Protein 96%
- COLLAPSE: A representation learning framework for identification and characterization of protein structural sites 95%
- Neural Network-Derived Potts Models for Structure-Based Protein Design using Backbone Atomic Coordinates and Tertiary Motifs 95%
Similar papers in this journal
- BOLD-GPCRs: A Transformer-Powered App for Predicting Ligand Bioactivity and Mutational Effects Across Class A GPCRs 94%
- Decoding protein-membrane binding interfaces from surface-fingerprint-based geometric deep learning and molecular dynamics simulations 94%
- Peptide-aware chemical language model successfully predicts membrane diffusion of cyclic peptides 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.