PepDDG
Peptide–protein binding ΔΔG prediction via information channel decomposition.
Acceptance reported by Richard; public author list and publication link pending verification.
PEPTIDE AI / SELECTED RESEARCH
Peptide representations and learning lead this collection. PepDDG, PepLand, and PepHarmony connect peptide sequence, structure, and function; selected molecular methods and clinical modeling appear below.
Peptide–protein binding ΔΔG prediction via information channel decomposition.
Acceptance reported by Richard; public author list and publication link pending verification.
Multi-view heterogeneous graphs for peptide representations across natural and non-natural amino acids.
Sequence–structure contrastive learning for peptide representation.
Quantitative definition and benchmarking of activity cliffs in antimicrobial peptides.
Few-shot and contrastive learning for scarce and imbalanced molecular property labels.
Multimodal molecular graphs and chemical knowledge, using ChatGPT-generated knowledge in the reported implementation.
Recognizing chemical structures from images.
Helper-enhanced feature selection via Pareto-optimized genetic search.
Interpretable prognostic feature selection and compression for electronic health records.
Adversarial heterogeneous graph attention for fair electronic-health-record representations.