{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T00:57:13Z","timestamp":1794272233844,"version":"4.9.0"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T00:00:00Z","timestamp":1731974400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T00:00:00Z","timestamp":1731974400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"DOI":"10.1038\/s41467-024-54365-0","type":"journal-article","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T11:01:54Z","timestamp":1732014114000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Discovering CRISPR-Cas system with self-processing pre-crRNA capability by foundation models"],"prefix":"10.1038","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0900-8749","authenticated-orcid":false,"given":"Wenhui","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianyue","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wuke","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liya","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runze","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7342-7456","authenticated-orcid":false,"given":"Yongqian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuxi","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinchang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6794-1663","authenticated-orcid":false,"given":"Peixiang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menghao","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2423-8411","authenticated-orcid":false,"given":"Guohui","family":"Chuai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingxu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7630-8162","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2578-1221","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,19]]},"reference":[{"key":"54365_CR1","doi-asserted-by":"publisher","first-page":"20180087","DOI":"10.1098\/rstb.2018.0087","volume":"374","author":"EV Koonin","year":"2019","unstructured":"Koonin, E. V. & Makarova, K. S. Origins and evolution of CRISPR-Cas systems. Philos. Trans. R. Soc. B 374, 20180087 (2019).","journal-title":"Philos. Trans. R. Soc. B"},{"key":"54365_CR2","doi-asserted-by":"publisher","first-page":"eadd8643","DOI":"10.1126\/science.add8643","volume":"379","author":"JY Wang","year":"2023","unstructured":"Wang, J. Y. & Doudna, J. A. CRISPR technology: a decade of genome editing is only the beginning. Science 379, eadd8643 (2023).","journal-title":"Science"},{"key":"54365_CR3","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1038\/nrmicro.2016.184","volume":"15","author":"S Shmakov","year":"2017","unstructured":"Shmakov, S. et al. Diversity and evolution of class 2 CRISPR\u2013Cas systems. Nat. Rev. Microbiol 15, 169\u2013182 (2017).","journal-title":"Nat. Rev. Microbiol"},{"key":"54365_CR4","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1038\/nature21059","volume":"542","author":"D Burstein","year":"2017","unstructured":"Burstein, D. et al. New CRISPR\u2013Cas systems from uncultivated microbes. Nature 542, 237\u2013241 (2017).","journal-title":"Nature"},{"key":"54365_CR5","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1126\/science.aav4294","volume":"362","author":"LB Harrington","year":"2018","unstructured":"Harrington, L. B. et al. Programmed DNA destruction by miniature CRISPR-Cas14 enzymes. Science 362, 839\u2013842 (2018).","journal-title":"Science"},{"key":"54365_CR6","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1126\/science.aav7271","volume":"363","author":"WX Yan","year":"2019","unstructured":"Yan, W. X. et al. Functionally diverse type V CRISPR-Cas systems. Science 363, 88\u201391 (2019).","journal-title":"Science"},{"key":"54365_CR7","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1126\/science.abb1400","volume":"369","author":"P Pausch","year":"2020","unstructured":"Pausch, P. et al. CRISPR-Cas\u03a6 from huge phages is a hypercompact genome editor. Science 369, 333\u2013337 (2020).","journal-title":"Science"},{"key":"54365_CR8","doi-asserted-by":"publisher","first-page":"4574","DOI":"10.1016\/j.cell.2022.10.020","volume":"185","author":"B Al-Shayeb","year":"2022","unstructured":"Al-Shayeb, B. et al. Diverse virus-encoded CRISPR-Cas systems include streamlined genome editors. Cell 185, 4574\u20134586.e16 (2022).","journal-title":"Cell"},{"key":"54365_CR9","doi-asserted-by":"publisher","first-page":"4487","DOI":"10.1016\/j.molcel.2022.11.003","volume":"82","author":"WY Wu","year":"2022","unstructured":"Wu, W. Y. et al. The miniature CRISPR-Cas12m effector binds DNA to block transcription. Mol. Cell 82, 4487\u20134502.e7 (2022).","journal-title":"Mol. Cell"},{"key":"54365_CR10","doi-asserted-by":"publisher","unstructured":"Sun, A. et al. The compact Cas\u03c0 (Cas12l) \u2018bracelet\u2019 provides a unique structural platform for DNA manipulation. Cell Res. https:\/\/doi.org\/10.1038\/s41422-022-00771-2 (2023).","DOI":"10.1038\/s41422-022-00771-2"},{"key":"54365_CR11","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1038\/nature19802","volume":"538","author":"A East-Seletsky","year":"2016","unstructured":"East-Seletsky, A. et al. Two distinct RNase activities of CRISPR-C2c2 enable guide-RNA processing and RNA detection. Nature 538, 270\u2013273 (2016).","journal-title":"Nature"},{"key":"54365_CR12","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1016\/j.molcel.2017.04.008","volume":"66","author":"A East-Seletsky","year":"2017","unstructured":"East-Seletsky, A., O\u2019Connell, M. R., Burstein, D., Knott, G. J. & Doudna, J. A. RNA targeting by functionally orthogonal type VI-A CRISPR-Cas enzymes. Mol. Cell 66, 373\u2013383.e3 (2017).","journal-title":"Mol. Cell"},{"key":"54365_CR13","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1038\/nature24049","volume":"550","author":"OO Abudayyeh","year":"2017","unstructured":"Abudayyeh, O. O. et al. RNA targeting with CRISPR\u2013Cas13. Nature 550, 280\u2013284 (2017).","journal-title":"Nature"},{"key":"54365_CR14","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1016\/j.molcel.2018.02.028","volume":"70","author":"WX Yan","year":"2018","unstructured":"Yan, W. X. et al. Cas13d is a compact RNA-targeting type VI CRISPR effector positively modulated by a WYL-domain-containing accessory protein. Mol. Cell 70, 327\u2013339.e5 (2018).","journal-title":"Mol. Cell"},{"key":"54365_CR15","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1038\/s41592-021-01124-4","volume":"18","author":"C Xu","year":"2021","unstructured":"Xu, C. et al. Programmable RNA editing with compact CRISPR\u2013Cas13 systems from uncultivated microbes. Nat. Methods 18, 499\u2013506 (2021).","journal-title":"Nat. Methods"},{"key":"54365_CR16","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1038\/nature17945","volume":"532","author":"I Fonfara","year":"2016","unstructured":"Fonfara, I., Richter, H., Bratovi\u010d, M., Le Rhun, A. & Charpentier, E. The CRISPR-associated DNA-cleaving enzyme Cpf1 also processes precursor CRISPR RNA. Nature 532, 517\u2013521 (2016).","journal-title":"Nature"},{"key":"54365_CR17","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1038\/s41594-020-0499-0","volume":"27","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Li, Z., Xiao, R. & Chang, L. Mechanisms for target recognition and cleavage by the Cas12i RNA-guided endonuclease. Nat. Struct. Mol. Biol. 27, 1069\u20131076 (2020).","journal-title":"Nat. Struct. Mol. Biol."},{"key":"54365_CR18","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1038\/s41592-019-0508-6","volume":"16","author":"CC Campa","year":"2019","unstructured":"Campa, C. C., Weisbach, N. R., Santinha, A. J., Incarnato, D. & Platt, R. J. Multiplexed genome engineering by Cas12a and CRISPR arrays encoded on single transcripts. Nat. Methods 16, 887\u2013893 (2019).","journal-title":"Nat. Methods"},{"key":"54365_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30465-7","volume":"13","author":"C McGaw","year":"2022","unstructured":"McGaw, C. et al. Engineered Cas12i2 is a versatile high-efficiency platform for therapeutic genome editing. Nat. Commun. 13, 2833 (2022).","journal-title":"Nat. Commun."},{"key":"54365_CR20","doi-asserted-by":"publisher","first-page":"6614","DOI":"10.1093\/nar\/gkw569","volume":"44","author":"T Tatusova","year":"2016","unstructured":"Tatusova, T. et al. NCBI prokaryotic genome annotation pipeline. Nucleic Acids Res. 44, 6614\u20136624 (2016).","journal-title":"Nucleic Acids Res."},{"key":"54365_CR21","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1089\/crispr.2020.0059","volume":"3","author":"J Russel","year":"2020","unstructured":"Russel, J., Pinilla-Redondo, R., Mayo-Mu\u00f1oz, D., Shah, S. A. & S\u00f8rensen, S. J. CRISPRCasTyper: automated identification, annotation, and classification of CRISPR-Cas Loci. CRISPR J. 3, 462\u2013469 (2020).","journal-title":"CRISPR J."},{"key":"54365_CR22","doi-asserted-by":"publisher","first-page":"W6","DOI":"10.1093\/nar\/gkl164","volume":"34","author":"J Ye","year":"2006","unstructured":"Ye, J., McGinnis, S. & Madden, T. L. BLAST: improvements for better sequence analysis. Nucleic Acids Res. 34, W6\u2013W9 (2006).","journal-title":"Nucleic Acids Res."},{"key":"54365_CR23","doi-asserted-by":"publisher","first-page":"W29","DOI":"10.1093\/nar\/gkr367","volume":"39","author":"RD Finn","year":"2011","unstructured":"Finn, R. D., Clements, J. & Eddy, S. R. HMMER web server: interactive sequence similarity searching. Nucleic Acids Res. 39, W29\u2013W37 (2011).","journal-title":"Nucleic Acids Res."},{"key":"54365_CR24","doi-asserted-by":"publisher","DOI":"10.1126\/science.adi1910","volume":"382","author":"H Altae-Tran","year":"2023","unstructured":"Altae-Tran, H. et al. Uncovering the functional diversity of rare CRISPR-Cas systems with deep terascale clustering. Science 382, eadi1910 (2023).","journal-title":"Science"},{"key":"54365_CR25","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","volume":"596","author":"J Jumper","year":"2021","unstructured":"Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583\u2013589 (2021).","journal-title":"Nature"},{"key":"54365_CR26","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1126\/science.abj8754","volume":"373","author":"M Baek","year":"2021","unstructured":"Baek, M. et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science 373, 871\u2013876 (2021).","journal-title":"Science"},{"key":"54365_CR27","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","volume":"379","author":"Z Lin","year":"2023","unstructured":"Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 1123\u20131130 (2023).","journal-title":"Science"},{"key":"54365_CR28","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1038\/s41579-019-0299-x","volume":"18","author":"KS Makarova","year":"2020","unstructured":"Makarova, K. S. et al. Evolutionary classification of CRISPR\u2013Cas systems: a burst of class 2 and derived variants. Nat. Rev. Microbiol. 18, 67\u201383 (2020).","journal-title":"Nat. Rev. Microbiol."},{"key":"54365_CR29","doi-asserted-by":"crossref","unstructured":"Adler, B. A. et al. CasPEDIA Database: a functional classification system for class 2 CRISPR-Cas enzymes. Nucleic Acids Research 52, D590\u2013D596 (2024).","DOI":"10.1093\/nar\/gkad1228"},{"key":"54365_CR30","doi-asserted-by":"crossref","unstructured":"Hsu, C. et al. Learning Inverse Folding from Millions of Predicted Structures. http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2022.04.10.487779 (2022).","DOI":"10.1101\/2022.04.10.487779"},{"key":"54365_CR31","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-Net: convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015 (eds. Navab, N., Hornegger, J., Wells, W. M. & Frangi, A. F.) Vol. 9351 234\u2013241 (Springer International Publishing, Cham, 2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"54365_CR32","doi-asserted-by":"crossref","unstructured":"Vig, J. et al. BERTology Meets Biology: Interpreting Attention in Protein Language Models. Preprint at http:\/\/arxiv.org\/abs\/2006.15222 (2021).","DOI":"10.1101\/2020.06.26.174417"},{"key":"54365_CR33","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.1038\/s41594-023-01042-3","volume":"30","author":"SN Omura","year":"2023","unstructured":"Omura, S. N. et al. Mechanistic and evolutionary insights into a type V-M CRISPR\u2013Cas effector enzyme. Nat. Struct. Mol. Biol. 30, 1172\u20131182 (2023).","journal-title":"Nat. Struct. Mol. Biol."},{"key":"54365_CR34","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1126\/science.aar6245","volume":"360","author":"JS Chen","year":"2018","unstructured":"Chen, J. S. et al. CRISPR-Cas12a target binding unleashes indiscriminate single-stranded DNase activity. Science 360, 436\u2013439 (2018).","journal-title":"Science"},{"key":"54365_CR35","doi-asserted-by":"publisher","unstructured":"Flamholz, Z. N., Biller, S. J. & Kelly, L. Large language models improve annotation of prokaryotic viral proteins. Nat. Microbiol. https:\/\/doi.org\/10.1038\/s41564-023-01584-8 (2024).","DOI":"10.1038\/s41564-023-01584-8"},{"key":"54365_CR36","doi-asserted-by":"publisher","first-page":"D753","DOI":"10.1093\/nar\/gkac1080","volume":"51","author":"L Richardson","year":"2023","unstructured":"Richardson, L. et al. MGnify: the microbiome sequence data analysis resource in 2023. Nucleic Acids Res. 51, D753\u2013D759 (2023).","journal-title":"Nucleic Acids Res."},{"key":"54365_CR37","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1038\/s41586-021-04233-4","volume":"601","author":"LP Coelho","year":"2022","unstructured":"Coelho, L. P. et al. Towards the biogeography of prokaryotic genes. Nature 601, 252\u2013256 (2022).","journal-title":"Nature"},{"key":"54365_CR38","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1038\/s41587-020-0718-6","volume":"39","author":"S Nayfach","year":"2021","unstructured":"Nayfach, S. et al. A genomic catalog of Earth\u2019s microbiomes. Nat. Biotechnol. 39, 499\u2013509 (2021).","journal-title":"Nat. Biotechnol."},{"key":"54365_CR39","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1016\/j.gpb.2021.05.001","volume":"20","author":"J Zhu","year":"2022","unstructured":"Zhu, J. et al. Over 50,000 metagenomically assembled draft genomes for the human oral microbiome reveal new taxa. Genom. Proteom. Bioinform. 20, 246\u2013259 (2022).","journal-title":"Genom. Proteom. Bioinform."},{"key":"54365_CR40","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1038\/s41587-022-01367-2","volume":"40","author":"Y Liu","year":"2022","unstructured":"Liu, Y. et al. A genome and gene catalog of glacier microbiomes. Nat. Biotechnol. 40, 1341\u20131348 (2022).","journal-title":"Nat. Biotechnol."},{"key":"54365_CR41","doi-asserted-by":"publisher","first-page":"D733","DOI":"10.1093\/nar\/gkac1037","volume":"51","author":"AP Camargo","year":"2023","unstructured":"Camargo, A. P. et al. IMG\/VR v4: an expanded database of uncultivated virus genomes within a framework of extensive functional, taxonomic, and ecological metadata. Nucleic Acids Res. 51, D733\u2013D743 (2023).","journal-title":"Nucleic Acids Res."},{"key":"54365_CR42","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1038\/s41564-021-00928-6","volume":"6","author":"S Nayfach","year":"2021","unstructured":"Nayfach, S. et al. Metagenomic compendium of 189,680 DNA viruses from the human gut microbiome. Nat. Microbiol. 6, 960\u2013970 (2021).","journal-title":"Nat. Microbiol."},{"key":"54365_CR43","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1016\/j.chom.2019.08.008","volume":"26","author":"P Soto-Perez","year":"2019","unstructured":"Soto-Perez, P. et al. CRISPR-Cas system of a prevalent human gut bacterium reveals hyper-targeting against phages in a human virome catalog. Cell Host Microbe 26, 325\u2013335.e5 (2019).","journal-title":"Cell Host Microbe"},{"key":"54365_CR44","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.1016\/j.cell.2021.01.029","volume":"184","author":"LF Camarillo-Guerrero","year":"2021","unstructured":"Camarillo-Guerrero, L. F., Almeida, A., Rangel-Pineros, G., Finn, R. D. & Lawley, T. D. Massive expansion of human gut bacteriophage diversity. Cell 184, 1098\u20131109.e9 (2021).","journal-title":"Cell"},{"key":"54365_CR45","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1089\/phage.2021.0007","volume":"2","author":"R Cook","year":"2021","unstructured":"Cook, R. et al. INfrastructure for a PHAge REference Database: identification of large-scale biases in the current collection of cultured phage genomes. Phage 2, 214\u2013223 (2021).","journal-title":"Phage"},{"key":"54365_CR46","doi-asserted-by":"publisher","first-page":"66","DOI":"10.3390\/v8030066","volume":"8","author":"T Mihara","year":"2016","unstructured":"Mihara, T. et al. Linking virus genomes with host taxonomy. Viruses 8, 66 (2016).","journal-title":"Viruses"},{"key":"54365_CR47","doi-asserted-by":"publisher","first-page":"D273","DOI":"10.1093\/nar\/gkab1111","volume":"50","author":"GP Schmartz","year":"2022","unstructured":"Schmartz, G. P. et al. PLSDB: advancing a comprehensive database of bacterial plasmids. Nucleic Acids Res. 50, D273\u2013D278 (2022).","journal-title":"Nucleic Acids Res."},{"key":"54365_CR48","doi-asserted-by":"publisher","first-page":"2580","DOI":"10.1128\/JB.01654-07","volume":"190","author":"D Pickard","year":"2008","unstructured":"Pickard, D. et al. Molecular characterization of the Salmonella enterica serovar typhi Vi-typing bacteriophage E1. J. Bacteriol. 190, 2580\u20132587 (2008).","journal-title":"J. Bacteriol."},{"key":"54365_CR49","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-8-209","volume":"8","author":"C Bland","year":"2007","unstructured":"Bland, C. et al. CRISPR Recognition Tool (CRT): a tool for automatic detection of clustered regularly interspaced palindromic repeats. BMC Bioinform. 8, 209 (2007).","journal-title":"BMC Bioinform."},{"key":"54365_CR50","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Dollar, P. Focal Loss for Dense Object Detection. IEEE Trans. Pattern Anal. Mach. Intell. 42, 318\u2013327 (2020).","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"54365_CR51","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1038\/s41592-022-01585-1","volume":"19","author":"C Zhang","year":"2022","unstructured":"Zhang, C., Shine, M., Pyle, A. M. & Zhang, Y. US-align: universal structure alignments of proteins, nucleic acids, and macromolecular complexes. Nat. Methods 19, 1109\u20131115 (2022).","journal-title":"Nat. Methods"},{"key":"54365_CR52","doi-asserted-by":"publisher","first-page":"1422","DOI":"10.1093\/bioinformatics\/btp163","volume":"25","author":"PJA Cock","year":"2009","unstructured":"Cock, P. J. A. et al. Biopython: freely available Python tools for computational molecular biology and bioinformatics. Bioinformatics 25, 1422\u20131423 (2009).","journal-title":"Bioinformatics"},{"key":"54365_CR53","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1093\/molbev\/mst010","volume":"30","author":"K Katoh","year":"2013","unstructured":"Katoh, K. & Standley, D. M. MAFFT multiple sequence alignment software version 7: improvements in performance and usability. Mol. Biol. Evol. 30, 772\u2013780 (2013).","journal-title":"Mol. Biol. Evol."},{"key":"54365_CR54","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1093\/molbev\/msu300","volume":"32","author":"L-T Nguyen","year":"2015","unstructured":"Nguyen, L.-T., Schmidt, H. A., Von Haeseler, A. & Minh, B. Q. IQ-TREE: a fast and effective stochastic algorithm for estimating maximum-likelihood phylogenies. Mol. Biol. Evol. 32, 268\u2013274 (2015).","journal-title":"Mol. Biol. Evol."},{"key":"54365_CR55","doi-asserted-by":"publisher","first-page":"W293","DOI":"10.1093\/nar\/gkab301","volume":"49","author":"I Letunic","year":"2021","unstructured":"Letunic, I. & Bork, P. Interactive Tree Of Life (iTOL) v5: an online tool for phylogenetic tree display and annotation. Nucleic Acids Res. 49, W293\u2013W296 (2021).","journal-title":"Nucleic Acids Res."},{"key":"54365_CR56","doi-asserted-by":"publisher","first-page":"D523","DOI":"10.1093\/nar\/gkac1052","volume":"51","author":"The UniProt Consortium.","year":"2023","unstructured":"The UniProt Consortium. et al. UniProt: the universal protein knowledgebase in 2023. Nucleic Acids Res. 51, D523\u2013D531 (2023).","journal-title":"Nucleic Acids Res."},{"key":"54365_CR57","doi-asserted-by":"publisher","first-page":"2957","DOI":"10.1093\/bioinformatics\/btr507","volume":"27","author":"T Mago\u010d","year":"2011","unstructured":"Mago\u010d, T. & Salzberg, S. L. FLASH: fast length adjustment of short reads to improve genome assemblies. Bioinformatics 27, 2957\u20132963 (2011).","journal-title":"Bioinformatics"},{"key":"54365_CR58","doi-asserted-by":"publisher","first-page":"5016","DOI":"10.1093\/nar\/gkaa208","volume":"48","author":"T Karvelis","year":"2020","unstructured":"Karvelis, T. et al. PAM recognition by miniature CRISPR\u2013Cas12f nucleases triggers programmable double-stranded DNA target cleavage. Nucleic Acids Res. 48, 5016\u20135023 (2020).","journal-title":"Nucleic Acids Res."},{"key":"54365_CR59","doi-asserted-by":"publisher","unstructured":"Wenhui, L. CHOOSER model weights and a minimum dataset. Zenodo https:\/\/doi.org\/10.5281\/ZENODO.13906238 (2024).","DOI":"10.5281\/ZENODO.13906238"},{"key":"54365_CR60","doi-asserted-by":"publisher","unstructured":"ZhejiangLab-BioGene. zjlab-BioGene\/CHOOSER: v1.0. Zenodo https:\/\/doi.org\/10.5281\/ZENODO.13906792 (2024).","DOI":"10.5281\/ZENODO.13906792"}],"updated-by":[{"DOI":"10.1038\/s41467-025-55913-y","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T00:00:00Z","timestamp":1736380800000}}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-024-54365-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-024-54365-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-024-54365-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T03:04:08Z","timestamp":1736478248000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-024-54365-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,19]]},"references-count":60,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["54365"],"URL":"https:\/\/doi.org\/10.1038\/s41467-024-54365-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.03.11.583506","asserted-by":"object"}]},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,19]]},"assertion":[{"value":"25 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41467-025-55913-y","URL":"https:\/\/doi.org\/10.1038\/s41467-025-55913-y","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10024"}}