Machine learning predicts new anti-CRISPR proteins

The increasing use of CRISPR-Cas9 in medicine, agriculture and synthetic biology has accelerated the drive to discover new CRISPR-Cas inhibitors as potential mechanisms of control for gene editing applications. Many such anti-CRISPRs have been found in mobile genetic elements that disable the CRISPR-Cas adaptive immune system. However, comparing all currently known anti-CRISPRs does not reveal a shared set of properties that can be used for facile bioinformatic identification of new anti-CRISPR families. Here, we describe AcRanker, a machine learning based method for identifying new potential anti-CRISPRs directly from proteomes using protein sequence information only. Using a training set of known anti-CRISPRs, we built a model based on XGBoost ranking and extensively benchmarked it through non-redundant cross-validation and external validation. We then applied AcRanker to predict candidate anti-CRISPRs from self-targeting bacterial genomes and discovered two previously unknown anti-CRISPRs: AcrllA16 (ML1) and AcrIIA17 (ML8). We show that AcrIIA16 strongly inhibits Streptococcus iniae Cas9 (SinCas9) and weakly inhibits Streptococcus pyogenes Cas9 (SpyCas9). We also show that AcrIIA17 inhibits both SpyCas9 and SauCas9 with low potency. The addition of AcRanker to the anti-CRISPR discovery toolkit allows researchers to directly rank potential anti-CRISPR candidate genes for increased speed in testing and validation of new anti-CRISPRs. A web server implementation for AcRanker is available online at http://acranker.pythonanywhere.com/.

[1]  Hui Yang,et al.  Inhibition Mechanism of an Anti-CRISPR Suppressor AcrIIA4 Targeting SpyCas9. , 2017, Molecular cell.

[2]  Ilya J Finkelstein,et al.  Functional metagenomics-guided discovery of potent Cas9 inhibitors in the human microbiome , 2019, eLife.

[3]  J. Keith Joung,et al.  Discovery of widespread type I and type V CRISPR-Cas inhibitors , 2018, Science.

[4]  Ge-Fei Hao,et al.  Anti-CRISPRdb: a comprehensive online resource for anti-CRISPR proteins , 2017, Nucleic Acids Res..

[5]  Kira S. Makarova,et al.  Anti-CRISPRs on the march , 2018, Science.

[6]  Karen L. Maxwell,et al.  Phages Fight Back: Inactivation of the CRISPR-Cas Bacterial Immune System by Anti-CRISPR Proteins , 2016, PLoS pathogens.

[7]  Barry L. Stoddard,et al.  Functional metagenomics-guided discovery of potent Cas9 inhibitors in the human microbiome , 2019, bioRxiv.

[8]  Alan R. Davidson,et al.  A New Group of Phage Anti-CRISPR Genes Inhibits the Type I-E CRISPR-Cas System of Pseudomonas aeruginosa , 2014, mBio.

[9]  Ying Gao,et al.  Bioinformatics Applications Note Sequence Analysis Cd-hit Suite: a Web Server for Clustering and Comparing Biological Sequences , 2022 .

[10]  David A. Scott,et al.  In vivo genome editing using Staphylococcus aureus Cas9 , 2015, Nature.

[11]  Rodolphe Barrangou,et al.  The roles of CRISPR-Cas systems in adaptive immunity and beyond. , 2015, Current opinion in immunology.

[12]  S. Ehrlich,et al.  Clustered regularly interspaced short palindrome repeats (CRISPRs) have spacers of extrachromosomal origin. , 2005, Microbiology.

[13]  Samuel Kilcher,et al.  Listeria phages induce Cas9 degradation to protect lysogenic genomes , 2019, bioRxiv.

[14]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[15]  David S. Wishart,et al.  PHASTER: a better, faster version of the PHAST phage search tool , 2016, Nucleic Acids Res..

[16]  Philippe Horvath,et al.  An anti-CRISPR from a virulent streptococcal phage inhibits Streptococcus pyogenes Cas9 , 2017, Nature Microbiology.

[17]  Alan R. Davidson,et al.  Disabling a Type I-E CRISPR-Cas Nuclease with a Bacteriophage-Encoded Anti-CRISPR Protein , 2017, mBio.

[18]  George A. O'Toole,et al.  Friendly Fire : Biological Functions and Consequences of Chromosomal-Targeting by 1 CRISPR-Cas Systems 2 , 2016 .

[19]  Aili Li,et al.  CRISPR/Cas9: A powerful tool for crop genome editing , 2016 .

[20]  Heidi Ledford,et al.  CRISPR: gene editing is just the beginning , 2016, Nature.

[21]  Eleazar Eskin,et al.  The Spectrum Kernel: A String Kernel for SVM Protein Classification , 2001, Pacific Symposium on Biocomputing.

[22]  K. Maxwell,et al.  Meet the Anti-CRISPRs: Widespread Protein Inhibitors of CRISPR-Cas Systems. , 2019, The CRISPR journal.

[23]  Heng Zhang,et al.  Structural Basis for the Inhibition of CRISPR-Cas12a by Anti-CRISPR Proteins. , 2019, Cell host & microbe.

[24]  Jennifer A. Doudna,et al.  Disabling Cas9 by an anti-CRISPR DNA mimic , 2017, Science Advances.

[25]  Xu Peng,et al.  Publisher Correction: Anti-CRISPR proteins encoded by archaeal lytic viruses inhibit subtype I-D immunity , 2018, Nature Microbiology.

[26]  Caroline M. Ajo-Franklin,et al.  A flavin-based extracellular electron transfer mechanism in diverse gram-positive bacteria , 2018, Nature.

[27]  Ryan T Fuchs,et al.  Staphylococcus aureus Cas9 is a multiple-turnover enzyme. , 2019, RNA.

[28]  Christof Fellmann,et al.  Structural basis for AcrVA4 inhibition of specific CRISPR-Cas12a , 2019, eLife.

[29]  Juwen Shen,et al.  Predicting protein–protein interactions based only on sequences information , 2007, Proceedings of the National Academy of Sciences.

[30]  F. Zhang,et al.  CRISPR/Cas9 for genome editing: progress, implications and challenges. , 2014, Human molecular genetics.

[31]  Eva Nogales,et al.  Temperature-Responsive Competitive Inhibition of CRISPR-Cas9. , 2019, Molecular cell.

[32]  J. Doudna,et al.  The new frontier of genome engineering with CRISPR-Cas9 , 2014, Science.

[33]  R. Barrangou,et al.  CRISPR/Cas, the Immune System of Bacteria and Archaea , 2010, Science.

[34]  Nevan J. Krogan,et al.  Inhibition of CRISPR-Cas9 with Bacteriophage Proteins , 2017, Cell.

[35]  Jennifer A. Doudna,et al.  A Broad-Spectrum Inhibitor of CRISPR-Cas9 , 2017, Cell.

[36]  Ningning Li,et al.  An anti-CRISPR protein disables type V Cas12a by acetylation , 2019, Nature Structural & Molecular Biology.

[37]  Stefan Kol,et al.  Discovery and Characterization of Cas9 Inhibitors Disseminated across Seven Bacterial Phyla. , 2019, Cell host & microbe.

[38]  Jason Weston,et al.  A user's guide to support vector machines. , 2010, Methods in molecular biology.

[39]  Alan R. Davidson,et al.  Anti-CRISPR: discovery, mechanism and function , 2017, Nature Reviews Microbiology.

[40]  Peter C. Fineran,et al.  Inactivation of CRISPR-Cas systems by anti-CRISPR proteins in diverse bacterial species , 2016, Nature Microbiology.

[41]  Jennifer A. Doudna,et al.  CRISPR-Cas guides the future of genetic engineering , 2018, Science.

[42]  Philippe Horvath,et al.  Widespread anti-CRISPR proteins in virulent bacteriophages inhibit a range of Cas9 proteins , 2018, Nature Communications.

[43]  Jennifer A. Doudna,et al.  Two distinct RNase activities of CRISPR-C2c2 enable guide-RNA processing and RNA detection , 2016, Nature.

[44]  Engelbert Mephu Nguifo,et al.  Protein sequences classification by means of feature extraction with substitution matrices , 2010, BMC Bioinformatics.

[45]  Anita C. Schürch,et al.  CRISPR/Cas9-Mediated Genome Editing of Herpesviruses Limits Productive and Latent Infections , 2016, PLoS pathogens.

[46]  Alan R. Davidson,et al.  Multiple mechanisms for CRISPR–Cas inhibition by anti-CRISPR proteins , 2015, Nature.

[47]  Kyle E. Watters,et al.  Potent CRISPR-Cas9 inhibitors from Staphylococcus genomes , 2019, Proceedings of the National Academy of Sciences.

[48]  Alan R Davidson,et al.  The Discovery, Mechanisms, and Evolutionary Impact of Anti-CRISPRs. , 2017, Annual review of virology.

[49]  K. Maxwell,et al.  The Anti-CRISPR Story: A Battle for Survival. , 2017, Molecular cell.

[50]  Kyle E. Watters,et al.  Systematic discovery of natural CRISPR-Cas12a inhibitors , 2018, Science.

[51]  Alan R. Davidson,et al.  Bacteriophage genes that inactivate the CRISPR/Cas bacterial immune system , 2012, Nature.

[52]  Kyle E. Watters,et al.  Broad-spectrum enzymatic inhibition of CRISPR-Cas12a , 2019, Nature Structural & Molecular Biology.