PuSH - Publikationsserver des Helmholtz Zentrums München

Yu, Y.* ; Gawlitt, S.* ; Barros De Andrade E Sousa, L. ; Merdivan, E. ; Piraud, M. ; Beisel, C.L.* ; Barquist, L.*

Improved prediction of bacterial CRISPRi guide efficiency from depletion screens through mixed-effect machine learning and data integration.

Genome Biol. 25:13 (2024)
Verlagsversion DOI PMC
Creative Commons Lizenzvertrag
CRISPR interference (CRISPRi) is the leading technique to silence gene expression in bacteria; however, design rules remain poorly defined. We develop a best-in-class prediction algorithm for guide silencing efficiency by systematically investigating factors influencing guide depletion in genome-wide essentiality screens, with the surprising discovery that gene-specific features substantially impact prediction. We develop a mixed-effect random forest regression model that provides better estimates of guide efficiency. We further apply methods from explainable AI to extract interpretable design rules from the model. This study provides a blueprint for predictive models for CRISPR technologies where only indirect measurements of guide activity are available.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Korrespondenzautor
Schlagwörter Gene; Design; Sgrnas
ISSN (print) / ISBN 1474-760X
e-ISSN 1465-6906
Zeitschrift Genome Biology
Quellenangaben Band: 25, Heft: 1, Seiten: , Artikelnummer: 13 Supplement: ,
Verlag BioMed Central
Verlagsort Campus, 4 Crinan St, London N1 9xw, England
Nichtpatentliteratur Publikationen
Begutachtungsstatus Peer reviewed
Institut(e) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Förderungen Bayerisches Staatsministerium für Bildung und Kultus, Wissenschaft und Kunst