De Novo Multi Mechanism Antimicrobial Peptide Design via Multimodal Deep Learning

ABSTRACTArtificial intelligence (AI) driven discovery of antimicrobial peptides (AMPs) is yet to fully utilize their three dimensional (3D) structural characteristics, microbial species specific antimicrobial activities, and mechanisms. Here, we constructed a QLAPD database comprising the sequence, structures, and antimicrobial properties of 12 914 AMPs. QLAPD underlies a multimodal, multitask, multilabel, and conditionally controlled AMP discovery (M3 CAD) pipeline, proposed for the de novo design of multi mechanism AMPs to combat multidrug resistant organisms (MDROs). This pipeline integrates generation, regression, and classification modules, using an innovative 3D voxel coloring method to capture the nuanced physicochemical context of amino acids, thus enhancing structural characterizations. QLX 3DV 1 and QLX 3DV 2, identified through M3 CAD, were found to demonstrate multiple antimicrobial mechanisms, notable activity against MDROs, and low toxicity. In vivo experiments were used to validate their antimicrobial effects with limited local and systemic toxicity. Overall, integrating 3D features, species specific antimicrobial activities, and mechanisms enhanced AI driven AMP discovery, making the M3 CAD pipeline a viable tool for de novo AMP design.Current AI driven peptide discovery often overlooks complex structural data. This study presents M3 CAD, a generative pipeline that leverages 3D voxel coloring and a massive database of over 12 000 peptides to capture nuanced physicochemical contexts. This innovative framework enables the precise design of multi mechanism antimicrobial peptides that effectively clear multidrug resistant infections while maintaining high safety profiles.