AI in peptide work has moved past the marketing pitch. De novo peptide design platforms — Profluent's recombinase and AlphaGen work, Generate Biomedicines, Cradle, Insilico, Mexa-AI — are producing real binders against targets that defeat traditional libraries.
Protein language models and transformer architectures (DDA-BERT, ESM-style models, MSGA-BPred for B-cell epitopes) have moved into peptide identification, immunopeptidomics, and de novo discovery. AlphaGen-style platforms are generating cyclic and macrocyclic candidates for undruggable targets. Several AACR 2026 abstracts described AI-discovered peptides advancing toward IND, and a Nature Biomedical Engineering paper from HLB Innovation introduced HMD-AMP for antimicrobial peptide discovery.
The remaining gap is wet-lab validation throughput. Most AI hits still go through phage display or biocatalysis (peptide asparaginyl ligase, PAL) for cyclization. Stories here cover the platforms, the validations, and the deals.
Evaxion's AI-designed personalized neoantigen peptide vaccine EVX-01 combined with Keytruda produced a 75% objective response rate at 2 years in advanced melanoma patients, with 86% of vaccine targets triggering de novo T-cell responses. Data were presented April 22 at AACR 2026; 3-year follow-up expected in H2 2026. The 86% target-hit rate demonstrates AI-designed peptide neoantigen selection maturing for cancer vaccines.
Novigenix presented first human clinical data at AACR 2026 from its LITOSeek AI-enabled liquid biopsy platform showing dynamic immune-transcriptomic responses in metastatic GEP-NET patients treated with either [212Pb]DOTAMTATE (AlphaMedix) alpha-emitter PRRT or [177Lu]DOTATATE (Lutathera) beta-emitter PRRT. The platform may enable treatment stratification between alpha- and beta-emitter radionuclide therapies.
University of Nebraska Medical Center's Guangshun Wang lab released APD6, the expanded antimicrobial peptide database, containing 6,309 peptides (3,379 natural AMPs, 2,290 synthetic, 373 AI-predicted) as of January 2026. New features include the Antimicrobial Peptide Information Pipeline (AMPIP) and expanded functional wheel covering anticancer and antidiabetic activity — positioning APD6 as the most comprehensive reference for AMP drug discovery as AI-assisted antibiotic design accelerates.
A new Nature Biomedical Engineering paper introduces HMD-AMP, a protein language model-based approach that outperforms prior methods at identifying evolutionarily distant antimicrobial peptides. Applied to host and gut microbiome genomes of nine mammals, HMD-AMP revealed over 37 million predicted AMPs. Of 91 experimentally validated high-confidence sequences, 74 showed strong antibacterial activity and 48 were evolutionarily remote from known AMPs, including four with broad-spectrum activity at low toxicity.
A Nature Communications paper introduces CAMPER (Constraint-driven AMP Engineering with Ranking), a mechanistic AI framework that integrates machine learning with biophysical ranking to design membrane-targeting peptides against MRSA persisters and biofilms. The framework identified WP-CAMPER1, a 12-mer peptide that kills S. aureus MW2 at an MIC of 4 µg/mL; a 2% topical formulation reduced S. aureus burden by 2.5 log10 in a murine skin infection model.
Fifty 1 Labs (OTC:FITY) announced the expansion of its peptide discovery and clinical research strategy targeting musculoskeletal health, recovery, and performance. The company is building a proprietary peptide discovery engine focused on MSK biology, combining AI-enabled design with staged clinical development for muscle, tendon, ligament, and bone conditions — an area largely overlooked by the GLP-1 dominated peptide pipeline.
A study in Nature Microbiology used a generative protein language model (ProteoGPT) to discover novel antimicrobial peptides effective against multidrug-resistant bacteria. The AI-designed peptides showed comparable or superior efficacy to clinical antibiotics in mouse infection models, with reduced resistance development and no organ damage.
Stanford scientists used AI to identify BRP, a naturally occurring peptide that acts directly on the hypothalamus to suppress appetite — avoiding the gut-related side effects of current GLP-1 drugs. In animal studies, BRP reduced body weight and fat without nausea, constipation, or muscle loss. Published in Nature, with human trials planned.
Pinnacle closed an oversubscribed $89M Series B (total $134M) to advance AI-driven oral peptide therapeutics into clinical trials, focusing on immunology and cardiometabolic diseases.
Zealand Pharma announced a new Cambridge research hub combining 25+ years of peptide expertise with AI-driven drug discovery, expanding its obesity and metabolic health pipeline.
Novo Nordisk signed a deal worth up to $2.1 billion with Vivtex Corporation, an MIT spinoff co-founded by Bob Langer, to develop next-generation oral biologic medicines for obesity and diabetes. Vivtex's AI-driven platform screens thousands of drug delivery formulations per day with near-perfect correlation to human intestinal absorption.
A study published in Nature Microbiology used a generative AI approach to discover antimicrobial peptides effective against multidrug-resistant bacteria. The deep learning pipeline screened millions of candidate sequences, achieving a 94.4% success rate in lab validation, with two candidates showing exceptional efficacy and low resistance potential.