Peptide News Digest

#Ai-Discovery

3 stories

Research · View digest

Chemical Communications (RSC) 2026: Generative AI Peptide Drug Design Review Frames the Methods Wave Behind the NK2R Competition and the GLP-1 De Novo Programs

A Chemical Communications (Royal Society of Chemistry) 2026 review on peptide-based drug design using generative AI synthesizes the methods landscape behind the wave of community competitions and pharmaceutical-industry de novo programs that landed in 2026. The review covers ProteoGPT and related protein-language-model architectures, AlphaFold3-based pose prediction, diffusion-model peptide structure generation, and the experimental-validation cycle that turns AI designs into bench-tested candidates. It frames the Tsinghua FRCBS NK2R Peptide Design Competition and the published ultra-long-acting GLP-1 receptor agonist de novo design work as proof-points that the AI-design stack has crossed the threshold from generative novelty to drug-discovery utility. The piece lands as the AI/peptide field tracks toward routine kilogram-scale syntheses (enlicitide PCSK9, others) and into Phase 1/2 candidates inside roughly 18 months from in silico design.

Research · View digest

UTHealth Houston BLMP6 Peptide Selectively Binds Fibulin-4 in Metastatic Triple-Negative Breast Cancer

Mikhail Kolonin's group at UTHealth Houston published preclinical data showing BLMP6, a peptide identified through AI-guided modeling, selectively binds fibulin-4 — a protein highly expressed on metastatic triple-negative breast cancer cells — and not on noninvasive breast cancer or normal breast tissue. A BLMP6 conjugate carrying monomethyl auristatin E suppressed metastasis and improved survival in mouse models, and BLMP6-based fluorescent imaging probes successfully detected metastatic lesions. The paper, published in Molecular Therapy Oncology, identifies fibulin-4 as a new theranostic target.

Research · View digest

Nature Communications: Few-Shot AI Pipeline Designs Antimicrobial Peptides Against Carbapenem-Resistant Acinetobacter baumannii

A Nature Communications paper describes a deep-learning pipeline that uses pre-trained protein language models combined with few-shot fine-tuning to identify antimicrobial peptides effective against Acinetobacter baumannii, a WHO critical-priority pathogen. The classification, ranking, and regression modules collaboratively prioritize candidates with high predicted activity, expanding the chemical space accessible to data-poor AMR targets. Lead candidates showed potent in vitro activity against carbapenem-resistant clinical isolates.