Custom CRISPR–Cas9 PAM variants via scalable engineering and machine learning
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
Engineering and characterizing proteins can be time-consuming and cumbersome, motivating the development of generalist CRISPR–Cas enzymes1, 2, 3–4 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. Combined high-throughput protein engineering with machine learning to curate libraries of CRISPR genome-editing enzymes with distinct genome targeting properties is described.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
UMAP: Uniform Manifold Approximation and Projection
McInnes, L., Healy, J., Saul, N., & Großberger, L. (2018) · Journal of Open Source Software · doi:10.21105/joss.00861 · Cited by 9,826
UCSF ChimeraX: Meeting modern challenges in visualization and analysis
Goddard, T. D., Huang, C. C., Meng, E. C., Pettersen, E. F., Couch, G. S., Morris, J. H., & Ferrin, T. E. (2018) · Protein Science · doi:10.1002/pro.3235 · Cited by 5,267
ClinVar: public archive of relationships among sequence variation and human phenotype
Landrum, M. J., Lee, J. M., Riley, G. R., Jang, W., Rubinstein, W. S., Church, D. M., & Maglott, D. R. (2014) · Nucleic Acids Research · doi:10.1093/nar/gkt1113 · Cited by 3,516
Hartong, D. T., Berson, E. L., & Dryja, T. P. (2006) · The Lancet · doi:10.1016/s0140-6736(06)69740-7 · Cited by 2,924
High-fidelity CRISPR-Cas9 nucleases with no detectable genome-wide off-target effects
Kleinstiver, B. P., Pattanayak, V., Prew, M. S., Tsai, S. Q., Nguyen, N. T., Zheng, Z., & Joung, J. K. (2016) · Nature · doi:10.1038/nature16526 · Cited by 2,673 · cited 3×
“…library of SpCas9 variant enzymes using a structure–function-informed approach based on SpCas9 structures 10 and previous engineering efforts 3,14,42,43 , simultaneously mutating six amino acid residues within the SpCas9 PI domain, resulting in a library with theoretical complexity of 64 million…”
Self-citationRNA-guided editing of bacterial genomes using CRISPR-Cas systems
Jiang, W., Bikard, D., Cox, D., Zhang, F., & Marraffini, L. A. (2013) · Nature Biotechnology · doi:10.1038/nbt.2508 · Cited by 2,429
GUIDE-seq enables genome-wide profiling of off-target cleavage by CRISPR-Cas nucleases
Tsai, S. Q., Zheng, Z., Nguyen, N. T., Liebers, M., Topkar, V. V., Thapar, V., Wyvekens, N., Khayter, C., Iafrate, A. J., Le, L. P., et al. (2015) · Nature Biotechnology · doi:10.1038/nbt.3117 · Cited by 2,268
Self-citationBase editing: precision chemistry on the genome and transcriptome of living cells
Rees, H. A., & Liu, D. R. (2018) · Nature Reviews Genetics · doi:10.1038/s41576-018-0059-1 · Cited by 1,675
Engineered CRISPR-Cas9 nucleases with altered PAM specificities
Kleinstiver, B. P., Prew, M. S., Tsai, S. Q., Topkar, V. V., Nguyen, N. T., Zheng, Z., Gonzales, A. P. W., Li, Z., Peterson, R. T., Yeh, J.-R. J., et al. (2015) · Nature · doi:10.1038/nature14592 · Cited by 1,624 · cited 9×
“These six amino acids modulate specificity for the 3rd and 4th PAM bases in the context of the engineered enzymes SpCas9-VRER, SpCas9-VRQR and SpG 3,14,42 (Supplementary Note 3).”
InfluentialSelf-citationEvolved Cas9 variants with broad PAM compatibility and high DNA specificity
Hu, J. H., Miller, S. M., Geurts, M. H., Tang, W., Chen, L., Sun, N., Zeina, C. M., Gao, X., Rees, H. A., Lin, Z., et al. (2018) · Nature · doi:10.1038/nature26155 · Cited by 1,552
Cited by
BAGEL: Protein engineering via exploration of an energy landscape
(2025) · doi:10.1371/journal.pcbi.1013774 · Cited by 7
Eaton, E. J., Wick, B. J., Chacón, J. S., Wang, A. J., Kluesner, M., Barnes, J. T., Kar, B., Wang, M., Johnson, M. J., Skeate, J. G., et al. (2026) · Molecular Therapy Nucleic Acids · doi:10.1016/j.omtn.2026.102908 · Cited by 2
Omura, S. N., Nakagawa, R., Kajimoto, S., Okazaki, S., Ishiguro, S., Mori, H., Onishi, K., Kashiwakura, Y., Hiramoto, T., Horinaka, K., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-71626-2 · Cited by 2
Self-citation
Metadata
- Authors
- Silverstein, R. A., Kim, N., Kroell, A.-S., Walton, R. T., Delano, J., Butcher, R. M., Pacesa, M., Smith, B. K., Christie, K. A., Ha, L. L., Meis, R. J., Clark, A. B., Spinner, A. D., Lazzarotto, C. R., Li, Y., Matsubara, A., Urbina, E. O., Dahl, G. A., Correia, B. E., Marks, D. S., Tsai, S. Q., Pinello, L., De Ravin, S. S., Liu, Q., & Kleinstiver, B. P.
- Venue
- Nature
- Published
- 2025-04-22
- Volume
- 643
- Issue
- 8071
- Pages
- 539-550
- ISSN
- 0028-0836 (ISSN-L)
- 1476-4687
- OpenAlex
- W4409666358
- Cited by
- 73
- References
- 29
- FWCI
- 18.66
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Custom CRISPR–Cas9 PAM variants via scalable engineering and machine learning. https://app.cochat.ai/papers/10.1038/s41586-025-09021-y
- The paper
- Silverstein, R. A., Kim, N., Kroell, A.-S., Walton, R. T., Delano, J., Butcher, R. M., Pacesa, M., Smith, B. K., Christie, K. A., Ha, L. L., Meis, R. J., Clark, A. B., Spinner, A. D., Lazzarotto, C. R., Li, Y., Matsubara, A., Urbina, E. O., Dahl, G. A., Correia, B. E., . . . Kleinstiver, B. P. (2025). Custom CRISPR–Cas9 PAM variants via scalable engineering and machine learning. Nature. https://doi.org/10.1038/s41586-025-09021-y
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.