{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:14:17Z","timestamp":1787008457323,"version":"3.56.0"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"16","license":[{"start":{"date-parts":[[2021,2,18]],"date-time":"2021-02-18T00:00:00Z","timestamp":1613606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100003150","name":"Le Fonds Qu\u00e9b\u00e9cois de la Recherche sur la Nature et les Technologies","doi-asserted-by":"crossref","award":["173878"],"award-info":[{"award-number":["173878"]}],"id":[{"id":"10.13039\/501100003150","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["249644"],"award-info":[{"award-number":["249644"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Off-target predictions are crucial in gene editing research. Recently, significant progress has been made in the field of prediction of off-target mutations, particularly with CRISPR-Cas9 data, thanks to the use of deep learning. CRISPR-Cas9 is a gene editing technique which allows manipulation of DNA fragments. The sgRNA-DNA (single guide RNA-DNA) sequence encoding for deep neural networks, however, has a strong impact on the prediction accuracy. We propose a novel encoding of sgRNA-DNA sequences that aggregates sequence data with no loss of information.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In our experiments, we compare the proposed sgRNA-DNA sequence encoding applied in a deep learning prediction framework with state-of-the-art encoding and prediction methods. We demonstrate the superior accuracy of our approach in a simulation study involving Feedforward Neural Networks (FNNs), Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) as well as the traditional Random Forest (RF), Naive Bayes (NB) and Logistic Regression (LR) classifiers. We highlight the quality of our results by building several FNNs, CNNs and RNNs with various layer depths and performing predictions on two popular gene editing datasets (CRISPOR and GUIDE-seq). In all our experiments, the new encoding led to more accurate off-target prediction results, providing an improvement of the area under the Receiver Operating Characteristic (ROC) curve up to 35%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The code and data used in this study are available at: https:\/\/github.com\/dagrate\/dl-offtarget.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btab112","type":"journal-article","created":{"date-parts":[[2021,2,18]],"date-time":"2021-02-18T02:12:53Z","timestamp":1613614373000},"page":"2299-2307","source":"Crossref","is-referenced-by-count":55,"title":["Accurate deep learning off-target prediction with novel sgRNA-DNA sequence encoding in CRISPR-Cas9 gene editing"],"prefix":"10.1093","volume":"37","author":[{"given":"Jeremy","family":"Charlier","sequence":"first","affiliation":[{"name":"D\u00e9partement d\u2019Informatique, Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al , Montr\u00e9al, QC H2X 3Y7, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Nadon","sequence":"additional","affiliation":[{"name":"McGill University and Genome Quebec Innovation Centre , Montreal, QC H3A 0C7, Canada"},{"name":"Department of Human Genetics, McGill University , Montreal, QC H3A 0C7, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3753-5925","authenticated-orcid":false,"given":"Vladimir","family":"Makarenkov","sequence":"additional","affiliation":[{"name":"D\u00e9partement d\u2019Informatique, Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al , Montr\u00e9al, QC H2X 3Y7, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,2,18]]},"reference":[{"key":"2023051609080555000_btab112-B1","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach. Learn"},{"key":"2023051609080555000_btab112-B2","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1038\/nature24268","article-title":"Enhanced proofreading governs crispr\u2013cas9 targeting accuracy","volume":"550","author":"Chen","year":"2017","journal-title":"Nature"},{"key":"2023051609080555000_btab112-B3","author":"Cho","year":"2014"},{"key":"2023051609080555000_btab112-B4","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1101\/gr.162339.113","article-title":"Analysis of off-target effects of crispr\/cas-derived RNA-guided endonucleases and nickases","volume":"24","author":"Cho","year":"2014","journal-title":"Genome Res"},{"key":"2023051609080555000_btab112-B5","author":"Chollet","year":"2015"},{"key":"2023051609080555000_btab112-B6","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1038\/nbt.3437","article-title":"Optimized sgrna design to maximize activity and minimize off-target effects of crispr-cas9","volume":"34","author":"Doench","year":"2016","journal-title":"Nat. Biotechnol"},{"key":"2023051609080555000_btab112-B7","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1038\/nbt.3101","article-title":"Genome-wide detection of DNA double-stranded breaks induced by engineered nucleases","volume":"33","author":"Frock","year":"2015","journal-title":"Nat. Biotechnol"},{"key":"2023051609080555000_btab112-B8","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1109\/TSMC.1983.6313076","article-title":"Neocognitron: a neural network model for a mechanism of visual pattern recognition","volume":"SMC-13","author":"Fukushima","year":"1983","journal-title":"IEEE Trans. Syst. Man Cybern"},{"key":"2023051609080555000_btab112-B9","first-page":"315","author":"Glorot","year":"2011"},{"key":"2023051609080555000_btab112-B10","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"2023051609080555000_btab112-B11","doi-asserted-by":"crossref","first-page":"4154","DOI":"10.1172\/JCI72992","article-title":"Expanding the genetic editing tool kit: zfns, talens, and crispr-cas9","volume":"124","author":"Gupta","year":"2014","journal-title":"J. Clin. Investig"},{"key":"2023051609080555000_btab112-B12","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1186\/s13059-016-1012-2","article-title":"Evaluation of off-target and on-target scoring algorithms and integration into the guide RNA selection tool crispor","volume":"17","author":"Haeussler","year":"2016","journal-title":"Genome Biol"},{"key":"2023051609080555000_btab112-B13","first-page":"5353","author":"He","year":"2015"},{"key":"2023051609080555000_btab112-B14","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1016\/B978-0-08-051055-2.50029-8","volume-title":"Machine Learning","author":"Hinton","year":"1990"},{"key":"2023051609080555000_btab112-B15","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"2023051609080555000_btab112-B16","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1038\/nbt.2647","article-title":"Dna targeting specificity of RNA-guided cas9 nucleases","volume":"31","author":"Hsu","year":"2013","journal-title":"Nat. Biotechnol"},{"key":"2023051609080555000_btab112-B17","doi-asserted-by":"crossref","first-page":"1262","DOI":"10.1016\/j.cell.2014.05.010","article-title":"Development and applications of crispr-cas9 for genome engineering","volume":"157","author":"Hsu","year":"2014","journal-title":"Cell"},{"key":"2023051609080555000_btab112-B18","author":"Ioffe","year":"2015"},{"key":"2023051609080555000_btab112-B19","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1007\/s13238-017-0477-4","article-title":"Addressing challenges in the clinical applications associated with crispr\/cas9 technology and ethical questions to prevent its misuse","volume":"8","author":"Kang","year":"2017","journal-title":"Protein Cell"},{"key":"2023051609080555000_btab112-B20","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1038\/nmeth.3284","article-title":"Digenome-seq: genome-wide profiling of crispr-cas9 off-target effects in human cells","volume":"12","author":"Kim","year":"2015","journal-title":"Nat. Methods"},{"key":"2023051609080555000_btab112-B21","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1101\/gr.199588.115","article-title":"Genome-wide target specificities of crispr-cas9 nucleases revealed by multiplex digenome-seq","volume":"26","author":"Kim","year":"2016","journal-title":"Genome Res"},{"key":"2023051609080555000_btab112-B22","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.cell.2016.10.044","article-title":"Crispr-based technologies for the manipulation of eukaryotic genomes","volume":"168","author":"Komor","year":"2017","journal-title":"Cell"},{"key":"2023051609080555000_btab112-B23","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/0893-6080(90)90044-L","article-title":"A time-delay neural network architecture for isolated word recognition","volume":"3","author":"Lang","year":"1990","journal-title":"Neural Netw"},{"key":"2023051609080555000_btab112-B24","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/s13238-015-0153-5","article-title":"Crispr\/cas9-mediated gene editing in human tripronuclear zygotes","volume":"6","author":"Liang","year":"2015","journal-title":"Protein Cell"},{"key":"2023051609080555000_btab112-B25","doi-asserted-by":"crossref","first-page":"i656","DOI":"10.1093\/bioinformatics\/bty554","article-title":"Off-target predictions in crispr-cas9 gene editing using deep learning","volume":"34","author":"Lin","year":"2018","journal-title":"Bioinformatics"},{"key":"2023051609080555000_btab112-B26","doi-asserted-by":"crossref","first-page":"1903562","DOI":"10.1002\/advs.201903562","article-title":"Crispr-net: a recurrent convolutional network quantifies crispr off-target activities with mismatches and indels","volume":"7","author":"Lin","year":"2020","journal-title":"Adv. Sci"},{"key":"2023051609080555000_btab112-B27","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1038\/nature23305","article-title":"Correction of a pathogenic gene mutation in human embryos","volume":"548","author":"Ma","year":"2017","journal-title":"Nature"},{"key":"2023051609080555000_btab112-B28","first-page":"26","article-title":"The pam requirement and expanding crispr beyond spcas9","volume":"2","author":"McDade","year":"2017","journal-title":"Addgene"},{"key":"2023051609080555000_btab112-B29","author":"Mnih","year":"2013"},{"key":"2023051609080555000_btab112-B30","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res"},{"key":"2023051609080555000_btab112-B31","doi-asserted-by":"crossref","first-page":"i757","DOI":"10.1093\/bioinformatics\/bty558","article-title":"Recognition of crispr\/cas9 off-target sites through ensemble learning of uneven mismatch distributions","volume":"34","author":"Peng","year":"2018","journal-title":"Bioinformatics"},{"key":"2023051609080555000_btab112-B32","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1038\/nature14299","article-title":"In vivo genome editing using Staphylococcus aureus cas9","volume":"520","author":"Ran","year":"2015","journal-title":"Nature"},{"key":"2023051609080555000_btab112-B33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-12-77","article-title":"proc: an open-source package for r and s+ to analyze and compare roc curves","volume":"12","author":"Robin","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2023051609080555000_btab112-B34","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1038\/nbt.2842","article-title":"Crispr-cas systems for editing, regulating and targeting genomes","volume":"32","author":"Sander","year":"2014","journal-title":"Nat. Biotechnol"},{"key":"2023051609080555000_btab112-B35","doi-asserted-by":"crossref","first-page":"891","DOI":"10.4161\/rna.23764","article-title":"Protospacer recognition motifs: mixed identities and functional diversity","volume":"10","author":"Shah","year":"2013","journal-title":"RNA Biol"},{"key":"2023051609080555000_btab112-B36","doi-asserted-by":"crossref","first-page":"e118","DOI":"10.1093\/nar\/gkv575","article-title":"Cas9-chromatin binding information enables more accurate crispr off-target prediction","volume":"43","author":"Singh","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2023051609080555000_btab112-B37","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res"},{"key":"2023051609080555000_btab112-B38","doi-asserted-by":"crossref","first-page":"e0124633","DOI":"10.1371\/journal.pone.0124633","article-title":"Cctop: an intuitive, flexible and reliable crispr\/cas9 target prediction tool","volume":"10","author":"Stemmer","year":"2015","journal-title":"PLoS One"},{"key":"2023051609080555000_btab112-B39","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1038\/nbt.3117","article-title":"Guide-seq enables genome-wide profiling of off-target cleavage by crispr-cas nucleases","volume":"33","author":"Tsai","year":"2015","journal-title":"Nat. Biotechnol"},{"key":"2023051609080555000_btab112-B40","volume-title":"Matrix Computations","author":"Van Loan","year":"1983"},{"key":"2023051609080555000_btab112-B41","first-page":"1","article-title":"Crispr-cas9 cleavage efficiency correlates strongly with target-sgrna folding stability: from physical mechanism to off-target assessment","volume":"7","author":"Xu","year":"2017","journal-title":"Sci. Rep"},{"key":"2023051609080555000_btab112-B42","doi-asserted-by":"crossref","first-page":"e264","DOI":"10.1038\/mtna.2015.37","article-title":"Off-target effects in crispr\/cas9-mediated genome engineering","volume":"4","author":"Zhang","year":"2015","journal-title":"Mol. Ther. Nucleic Acids"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab112\/38245800\/btab112.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/16\/2299\/50339138\/btab112.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/16\/2299\/50339138\/btab112.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T05:14:24Z","timestamp":1684214064000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/16\/2299\/6143578"}},"subtitle":[],"editor":[{"given":"Janet","family":"Kelso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,2,18]]},"references-count":42,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2021,8,25]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab112","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,8,15]]},"published":{"date-parts":[[2021,2,18]]}}}