Structure-aware graph learning links peptide geometry to pathogen-specific antimicrobial potency
Year: 2026
Type: article
Abstract: . Capacity-matched ablations supported complementary contributions from predicted structure. Retrospective ranking recovered more known active peptides than the evaluated comparator, supporting further evaluation of GeoMIC for experimental candidate prioritization.
Source: Chemical Communications
DOI: 10.1039/d6cc03538h
Institutions: Monash University, The Alfred Hospital, University of Pennsylvania
Language: English
Subfield: Microbiology
Field: Immunology and Microbiology
Domain: Life Sciences
Keyword: antimicrobial peptides
Open Access status: hybrid
Awards: An integrated virtual cell approach towards elucidating the systems pharmacology of antibiotics against Pseudomonas aeruginosa, Integrative systems pharmacology, neutron reflectometry and molecular dynamics approaches to unravelling the interactions between polymyxins and bacterial membranes, Enhancing mTORC1 therapeutic discovery with machine learning-driven structural biology
OpenAlex ID: W7224020142
