Uncovering the functional diversity of rare CRISPR-Cas systems with deep terascale clustering
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Microbial systems underpin many biotechnologies, including CRISPR, but the exponential growth of sequence databases makes it difficult to find previously unidentified systems. In this work, we develop the fast locality-sensitive hashing–based clustering (FLSHclust) algorithm, which performs deep clustering on massive datasets in linearithmic time. We incorporated FLSHclust into a CRISPR discovery pipeline and identified 188 previously unreported CRISPR-linked gene modules, revealing many additional biochemical functions coupled to adaptive immunity. We experimentally characterized three HNH nuclease–containing CRISPR systems, including the first type IV system with a specified interference mechanism, and engineered them for genome editing. We also identified and characterized a candidate type VII system, which we show acts on RNA. This work opens new avenues for harnessing CRISPR and for the broader exploration of the vast functional diversity of microbial proteins.
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
Highly accurate protein structure prediction with AlphaFold
Jumper, J., Evans, R., Pritzel, A., Green, T., Figurnov, M., Ronneberger, O., Tunyasuvunakool, K., Bates, R., Žídek, A., Potapenko, A., et al. (2021) · Nature · doi:10.1038/s41586-021-03819-2 · Cited by 43,764
Cutadapt removes adapter sequences from high-throughput sequencing reads
Martin, M. (2011) · EMBnet.journal · doi:10.14806/ej.17.1.200 · Cited by 33,889
UniProt: a worldwide hub of protein knowledge
The UniProt Consortium (2019) · Nucleic Acids Research · doi:10.1093/nar/gky1049 · Cited by 7,698 · cited 1×
“However, existing ,suchasall-against-allcomparisonsand proteinclustering( 9 ), which quickly become impractical for mining exponentially growing datasets containing billions of proteins ( 10 ).”
BackgroundFrom Louvain to Leiden: guaranteeing well-connected communities
Traag, V. A., Waltman, L., & van Eck, N. J. (2019) · Scientific Reports · doi:10.1038/s41598-019-41695-z · Cited by 5,635
MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets
Steinegger, M., & Söding, J. (2017) · Nature Biotechnology · doi:10.1038/nbt.3988 · Cited by 4,840
Approximate nearest neighbors: towards removing the curse of dimensionality
Indyk, P., & Motwani, R. (1998) · Proceedings of the thirtieth annual ACM symposium on Theory of computing - STOC '98 · doi:10.1145/276698.276876 · Cited by 4,188
The mechanism of double-strand DNA break repair by the nonhomologous DNA end-joining pathway
Lieber, M. R. (2010) · Annual Review of Biochemistry · doi:10.1146/annurev.biochem.052308.093131 · Cited by 2,882
UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches
Suzek, B. E., Wang, Y., Huang, H., McGarvey, P. B., Wu, C. H., & the UniProt Consortium (2015) · Bioinformatics · doi:10.1093/bioinformatics/btu739 · Cited by 1,928
Clustering huge protein sequence sets in linear time
Steinegger, M., & Söding, J. (2018) · Nature Communications · doi:10.1038/s41467-018-04964-5 · Cited by 875 · cited 4×
“However, existing methods rely on algorithms that have quadratic runtime, such as all-against-all comparisons and protein clustering (9), which quickly become impractical for mining exponentially growing datasets containing billions of proteins (11).”
MethodInfluentialThe widespread IS200/IS605 transposon family encodes diverse programmable RNA-guided endonucleases
Altae-Tran, H., Kannan, S., Demircioglu, F. E., Oshiro, R., Nety, S. P., McKay, L. J., Dlakić, M., Inskeep, W. P., Makarova, K. S., Macrae, R. K., et al. (2021) · Science · doi:10.1126/science.abj6856 · Cited by 407 · cited 8×
“Finally, we identified putative new functional systems associated with regularly interspaced repeat arrays with hypervariable spacers, analogous to CRISPR arrays and ω RNA arrays (25), but lacking any cas genes (Fig.”
BackgroundInfluentialSelf-citation
Cited by
Past, present, and future of CRISPR genome editing technologies
Pacesa, M., Pelea, O., & Jinek, M. (2024) · Cell · doi:10.1016/j.cell.2024.01.042 · Cited by 609
“101,105,114,117,118 Of particular interest are ‘‘minimal,’’ compact type V nucleases that hold promise for applications in which packaging the gene editor components into size-limited viral vectors (such as AAV) is necessary.”
Semantic design of functional de novo genes from a genomic language model
(2025) · doi:10.1038/s41586-025-09749-7 · Cited by 35
Discovering CRISPR-Cas system with self-processing pre-crRNA capability by foundation models
Li, W., Jiang, X., Wang, W., Hou, L., Cai, R., Li, Y., Gu, Q., Chen, Q., Ma, P., Tang, J., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-54365-0 · Cited by 21
(2024) · doi:10.1038/s41467-024-51695-x · Cited by 19
Guo, J., Gong, L., Yu, H., Li, M., Liu, Z., Fan, S., Yang, C., Zhao, D., Han, J., & Xiang, H. (2024) · doi:10.1101/2024.01.26.577312 · Cited by 19
(2025) · doi:10.1016/j.molcel.2025.01.020 · Cited by 7
Wandera, K. G., Schmelz, S., Migur, A., Kibe, A., Lukat, P., Achmedov, T., Caliskan, N., Blankenfeldt, W., & Beisel, C. L. (2024) · doi:10.1101/2024.11.17.623997 · Cited by 7
Metadata
- Authors
- Altae-Tran, H., Kannan, S., Suberski, A. J., Mears, K. S., Demircioglu, F. E., Moeller, L., Kocalar, S., Oshiro, R., Makarova, K. S., Macrae, R. K., Koonin, E. V., & Zhang, F.
- Venue
- Science
- Published
- 2023-11-24
- Volume
- 382
- Issue
- 6673
- Pages
- eadi1910-eadi1910
- ISSN
- 0036-8075 (ISSN-L)
- 1095-9203
- OpenAlex
- W4388936915
- Cited by
- 158
- References
- 13
- FWCI
- 11.81
- Type
- journal article
- Language
- en
- Open access
- hybrid
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
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.