moPPIt: De Novo Generation of Motif-Specific Peptide Binders via Conditional Uniform Discrete Diffusion
Track: Machine learning: computational method and/or computational results
Nature Biotechnology: Yes
Keywords: Discrete diffusion, peptide design, conditional generation
TL;DR: moPPIt generates motif-specific peptide binders from protein sequences alone via a transformer-guided uniform discrete diffusion model.
Abstract: The ability to precisely target specific motifs on disease-related proteins, whether conserved epitopes on viral proteins, intrinsically disordered regions within transcription factors, or breakpoint junctions in fusion oncoproteins, is essential for modulating their function while minimizing off-target effects. Current methods often fall short in achieving this specificity due to a lack of reliable structural information. In this work, we introduce moPPIt, a motif-specific PPI targeting algorithm, for de novo generation of motif-specific peptide binders from the target protein sequence alone. At the core of moPPIt is BindEvaluator, a transformer-based model that interpolates protein language model embeddings of two proteins via a series of multi-headed self-attention blocks, with a key focus on local motif features. Trained on over 510,000 annotated PPIs, BindEvaluator accurately predicts binding sites given protein-protein sequence pairs with a test AUC > 0.94, improving to AUC > 0.96 when fine-tuned on peptide-protein pairs. Additionally, we present PepUDLM, a uniform diffusion language model that generates diverse and biologically plausible peptides. By integrating BindEvaluator into PepUDLM’s sampling process, moPPIt generates peptides that bind specifically to user-defined residues on target proteins. We demonstrate moPPIt's efficacy in computationally designing binders to specific motifs, first on targets with known binding peptides and then extending to structured and disordered targets with no known binders. In total, moPPIt serves as a powerful tool for developing highly specific peptide therapeutics without relying on target structure or structure-dependent latent spaces.
Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.
Presenter: ~Tong_Chen13
Format: Yes, the presenting author will definitely attend in person because they attending ICLR for other complementary reasons.
Funding: No, the presenting author of this submission does *not* fall under ICLR’s funding aims, or has sufficient alternate funding.
Submission Number: 14
Loading