Systematic multi-trait AAV capsid engineering for efficient gene delivery

Fatma-Elzahraa Eid (), Albert T. Chen, Ken Y. Chan, Qin Huang, Qingxia Zheng, Isabelle G. Tobey, Simon Pacouret, Pamela P. Brauer, Casey Keyes, Megan Powell, Jencilin Johnston, Binhui Zhao, Kasper Lage, Alice F. Tarantal, Yujia A. Chan and Benjamin E. Deverman ()
Additional contact information
Fatma-Elzahraa Eid: Broad Institute of MIT and Harvard
Albert T. Chen: Broad Institute of MIT and Harvard
Ken Y. Chan: Broad Institute of MIT and Harvard
Qin Huang: Broad Institute of MIT and Harvard
Qingxia Zheng: Broad Institute of MIT and Harvard
Isabelle G. Tobey: Broad Institute of MIT and Harvard
Simon Pacouret: Broad Institute of MIT and Harvard
Pamela P. Brauer: Broad Institute of MIT and Harvard
Casey Keyes: Broad Institute of MIT and Harvard
Megan Powell: Broad Institute of MIT and Harvard
Jencilin Johnston: Broad Institute of MIT and Harvard
Binhui Zhao: Broad Institute of MIT and Harvard
Kasper Lage: Broad Institute of MIT and Harvard
Alice F. Tarantal: University of California
Yujia A. Chan: Broad Institute of MIT and Harvard
Benjamin E. Deverman: Broad Institute of MIT and Harvard

Nature Communications, 2024, vol. 15, issue 1, 1-14

Abstract: Abstract 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 library variants on all six predetermined criteria. Furthermore, the models, trained only on mouse in vivo and human in vitro Fit4Function data, accurately predicted AAV capsid variant biodistribution in macaque. Top candidates exhibited production yields comparable to AAV9, efficient murine liver transduction, up to 1000-fold greater human hepatocyte transduction, and increased enrichment relative to AAV9 in a screen for liver transduction in macaques. The Fit4Function strategy ultimately makes it possible to predict cross-species traits of peptide-modified AAV capsids and is a critical step toward assembling an ML atlas that predicts AAV capsid performance across dozens of traits.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-50555-y Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-50555-y

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-50555-y

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().