biostudies-literatureEid FEU.S. Department of Health & Human Services | NIH | National Institute of Mental Health (NIMH)Apertura Gene TherapyNIMH NIH HHSU.S. Department of Health & Human Services | NIH | NIH Office of the DirectorU.S. Department of Health & Human Services | NIH | National Institute of Mental HealthU.S. Department of Health & Human Services | NIH | NIH Office of the Director (OD)Broad Institute Shark Tank AwardBroad Ignite AwardBroad Institute | Stanley Center for Psychiatric Research, Broad InstituteNIDDK NIH HHSNINDS NIH HHSNovo Nordisk FondenNIH HHS6602https://www.ebi.ac.uk/biostudies/studies/S-EPMC11297966biostudies-literatureUnknown15(1)Broadening gene therapy applications requires manufacturable vectors that efficiently transduce target cells in humans and preclinical models. Conventional selections of adeno-associated virus (AAV) capsid libraries are inefficient at searching the vast sequence space for the small fraction of vectors possessing multiple traits essential for clinical translation. Here, we present Fit4Function, a generalizable machine learning (ML) approach for systematically engineering multi-trait AAV capsids. By leveraging a capsid library that uniformly samples the manufacturable sequence space, reproducible screening data are generated to train accurate sequence-to-function models. Combining six models, we designed a multi-trait (liver-targeted, manufacturable) capsid library and validated 88% of libraNature communicationsSystematic multi-trait AAV capsid engineering for efficient gene delivery.PMC11297966U01 MH121499U42 OD027094UG3MH120096UG3 NS111689R01 DK078616UG3 MH120096R01 MH109903UM1 DK078616P51-OD011107UG3NS111689U01 DK078616P51 OD011107NNF21SA0072102Deverman BEZhao BLage KZheng QTarantal AFEid FEHuang QChan YAKeyes CJohnston JPacouret STobey IGChen ATChan KYBrauer PPPowell MfalseSystematic multi-trait AAV capsid engineering for efficient gene delivery.Broadening gene therapy applications requires manufacturable vectors that efficiently transduce target cells in humans and preclinical models. Conventional selections of adeno-associated virus (AAV) capsid libraries are inefficient at searching the vast sequence space for the small fraction of vectors possessing multiple traits essential for clinical translation. Here, we present Fit4Function, a generalizable machine learning (ML) approach for systematically engineering multi-trait AAV capsids. By leveraging a capsid library that uniformly samples the manufacturable sequence space, reproducible screening data are generated to train accurate sequence-to-function models. Combining six models, we designed a multi-trait (liver-targeted, manufacturable) capsid library and validated 88% of libra2024-01-01T00:00:00Z2024 Aug2026-06-01T22:18:22.086Z2025-02-19T04:39:55.156ZS-EPMC112979663909758310.1038/s41467-024-50555-y