Custom CRISPR–Cas9 PAM variants via scalable engineering and machine learning

Rachel A. Silverstein, Nahye Kim, Ann-Sophie Kroell, Russell T. Walton, Justin Delano, Rossano M. Butcher, Martin Pacesa, Blaire K. Smith, Kathleen A. Christie, Leillani L. Ha, Ronald J. Meis, Aaron B. Clark, Aviv D. Spinner, Cicera R. Lazzarotto, Yichao Li, Azusa Matsubara, Elizabeth O. Urbina, Gary A. Dahl, Bruno E. Correia, Debora S. Marks, Shengdar Q. Tsai, Luca Pinello, Suk See Ravin, Qin Liu and Benjamin P. Kleinstiver ()
Additional contact information
Rachel A. Silverstein: Harvard Medical School
Nahye Kim: Massachusetts General Hospital
Ann-Sophie Kroell: Massachusetts General Hospital
Russell T. Walton: Massachusetts General Hospital
Justin Delano: Harvard Medical School
Rossano M. Butcher: Massachusetts Eye and Ear
Martin Pacesa: École Polytechnique Fédérale de Lausanne and Swiss Institute of Bioinformatics
Blaire K. Smith: Massachusetts General Hospital
Kathleen A. Christie: Massachusetts General Hospital
Leillani L. Ha: Massachusetts General Hospital
Ronald J. Meis: CELLSCRIPT
Aaron B. Clark: CELLSCRIPT
Aviv D. Spinner: Harvard Medical School
Cicera R. Lazzarotto: St. Jude Children’s Research Hospital
Yichao Li: St. Jude Children’s Research Hospital
Azusa Matsubara: St. Jude Children’s Research Hospital
Elizabeth O. Urbina: St. Jude Children’s Research Hospital
Gary A. Dahl: CELLSCRIPT
Bruno E. Correia: École Polytechnique Fédérale de Lausanne and Swiss Institute of Bioinformatics
Debora S. Marks: Broad Institute of Harvard and MIT
Shengdar Q. Tsai: St. Jude Children’s Research Hospital
Luca Pinello: Harvard Medical School
Suk See Ravin: National Institutes of Health
Qin Liu: Massachusetts Eye and Ear
Benjamin P. Kleinstiver: Massachusetts General Hospital

Nature, 2025, vol. 643, issue 8071, 539-550

Abstract: Abstract Engineering and characterizing proteins can be time-consuming and cumbersome, motivating the development of generalist CRISPR–Cas enzymes1–4 to enable diverse genome-editing applications. However, such enzymes have caveats such as an increased risk of off-target editing3,5,6. Here, to enable scalable reprogramming of Cas9 enzymes, we combined high-throughput protein engineering with machine learning to derive bespoke editors that are more uniquely suited to specific targets. Through structure–function-informed saturation mutagenesis and bacterial selections, we obtained nearly 1,000 engineered SpCas9 enzymes and characterized their protospacer-adjacent motif (PAM)7 requirements to train a neural network that relates amino acid sequence to PAM specificity. By utilizing the resulting PAM machine learning algorithm (PAMmla) to predict the PAMs of 64 million SpCas9 enzymes, we identified efficacious and specific enzymes that outperform evolution-based and engineered SpCas9 enzymes as nucleases and base editors in human cells while reducing off-targets. An in silico-directed evolution method enables user-directed Cas9 enzyme design, including for allele-selective targeting of the RHOP23H allele in human cells and mice. Together, PAMmla integrates machine learning and protein engineering to curate a catalogue of SpCas9 enzymes with distinct PAM requirements, motivating a shift away from generalist enzymes towards safe and efficient bespoke Cas9 variants.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41586-025-09021-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:nature:v:643:y:2025:i:8071:d:10.1038_s41586-025-09021-y

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

DOI: 10.1038/s41586-025-09021-y

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

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