Deep Learning Framework NeoPep Enables Accurate De Novo Design of Functional Peptides
Researchers have developed NeoPep, a generative deep-learning framework that can design functional peptides from scratch by encoding biophysical principles learned from over 5 million peptide-protein complexes. The system achieved hit rates of 12.5-66.7% across 10 diverse targets, generating potent binders, agonists, and antagonists without requiring defined binding sites or structural information. This advancement could accelerate peptide-based therapeutics and bioengineering applications by reducing reliance on experimental structure determination.
NeoPep represents a significant advance in computational peptide design by integrating biophysical principles into a generative deep-learning model trained on experimentally determined structures, sequence mimics, and structure ensembles totaling over 5 million peptide-protein complexes. The framework demonstrated strong prospective performance across 10 challenging targets, with hit rates ranging from 12.5% to 66.7% for generating peptide binders, agonists, and antagonists. Beyond de novo design, NeoPep supports structure and sequence redesign modes, achieving atomic-level conformational accuracy (C RMSD < 2.0 Å) validated against cryo-EM structures. The system's ability to discriminate subtle context differences and generate highly selective peptides enabled a 43.3-fold improvement in potency through iterative redesign. These capabilities address a major challenge in peptide therapeutics—the difficulty of modeling delicate peptide-protein interactions—and could substantially accelerate drug discovery and bioengineering applications.
What's missing
The study does not discuss potential limitations of the training data composition (e.g., whether certain peptide classes or interaction types are underrepresented), computational costs or scalability considerations, or how performance might generalize to peptide targets not well-represented in the training set. Additionally, the timeline and specific experimental validation methods for the prospective applications are not detailed.
What different sources said
- bioRxivCenter
Accurate de novo design of peptides from programming biophysical landscape
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.