{"id":"https://openalex.org/W4293026694","doi":"https://doi.org/10.1093/bib/bbac335","title":"CRISPRCasStack: a stacking strategy-based ensemble learning framework for accurate identification of Cas proteins","display_name":"CRISPRCasStack: a stacking strategy-based ensemble learning framework for accurate identification of Cas proteins","publication_year":2022,"publication_date":"2022-08-23","ids":{"openalex":"https://openalex.org/W4293026694","doi":"https://doi.org/10.1093/bib/bbac335","pmid":"https://pubmed.ncbi.nlm.nih.gov/35998924"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbac335","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac335","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100671125","display_name":"Tianjiao Zhang","orcid":"https://orcid.org/0000-0001-9807-8620"},"institutions":[{"id":"https://openalex.org/I47689461","display_name":"Northeast Forestry University","ror":"https://ror.org/02yxnh564","country_code":"CN","type":"education","lineage":["https://openalex.org/I47689461"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianjiao Zhang","raw_affiliation_strings":["College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China"],"raw_orcid":"https://orcid.org/0000-0001-9807-8620","affiliations":[{"raw_affiliation_string":"College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China","institution_ids":["https://openalex.org/I47689461"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014202593","display_name":"Yuran Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I47689461","display_name":"Northeast Forestry University","ror":"https://ror.org/02yxnh564","country_code":"CN","type":"education","lineage":["https://openalex.org/I47689461"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuran Jia","raw_affiliation_strings":["College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China"],"raw_orcid":"https://orcid.org/0000-0002-0688-4666","affiliations":[{"raw_affiliation_string":"College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China","institution_ids":["https://openalex.org/I47689461"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427008","display_name":"Hongfei Li","orcid":"https://orcid.org/0000-0003-4104-3966"},"institutions":[{"id":"https://openalex.org/I47689461","display_name":"Northeast Forestry University","ror":"https://ror.org/02yxnh564","country_code":"CN","type":"education","lineage":["https://openalex.org/I47689461"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Li","raw_affiliation_strings":["College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China"],"raw_orcid":"https://orcid.org/0000-0003-4104-3966","affiliations":[{"raw_affiliation_string":"College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China","institution_ids":["https://openalex.org/I47689461"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083609728","display_name":"Dali Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I47689461","display_name":"Northeast Forestry University","ror":"https://ror.org/02yxnh564","country_code":"CN","type":"education","lineage":["https://openalex.org/I47689461"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dali Xu","raw_affiliation_strings":["College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China","institution_ids":["https://openalex.org/I47689461"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044980866","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0003-2466-4314"},"institutions":[{"id":"https://openalex.org/I47689461","display_name":"Northeast Forestry University","ror":"https://ror.org/02yxnh564","country_code":"CN","type":"education","lineage":["https://openalex.org/I47689461"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China"],"raw_orcid":"https://orcid.org/0000-0003-2466-4314","affiliations":[{"raw_affiliation_string":"College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China","institution_ids":["https://openalex.org/I47689461"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100649978","display_name":"Guohua Wang","orcid":"https://orcid.org/0000-0001-7381-2374"},"institutions":[{"id":"https://openalex.org/I47689461","display_name":"Northeast Forestry University","ror":"https://ror.org/02yxnh564","country_code":"CN","type":"education","lineage":["https://openalex.org/I47689461"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guohua Wang","raw_affiliation_strings":["College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Computer Engineering, Northeast Forestry University , Harbin, 150040 , China","institution_ids":["https://openalex.org/I47689461"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100649978"],"corresponding_institution_ids":["https://openalex.org/I47689461"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":1.343,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.80097605,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"23","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10878","display_name":"CRISPR and Genetic Engineering","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10878","display_name":"CRISPR and Genetic Engineering","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/crispr","display_name":"CRISPR","score":0.811392068862915},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6965076923370361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6647199392318726},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6324125528335571},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.5420665740966797},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.3541490137577057},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30086392164230347},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.22076332569122314}],"concepts":[{"id":"https://openalex.org/C98108389","wikidata":"https://www.wikidata.org/wiki/Q412563","display_name":"CRISPR","level":3,"score":0.811392068862915},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6965076923370361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6647199392318726},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6324125528335571},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.5420665740966797},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3541490137577057},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30086392164230347},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.22076332569122314},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000072669","descriptor_name":"Gene Editing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000072669","descriptor_name":"Gene Editing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000072669","descriptor_name":"Gene Editing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D001105","descriptor_name":"Archaea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001105","descriptor_name":"Archaea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D001105","descriptor_name":"Archaea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064113","descriptor_name":"CRISPR-Cas Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D064113","descriptor_name":"CRISPR-Cas Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D064113","descriptor_name":"CRISPR-Cas Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbac335","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac335","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35998924","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35998924","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G1091266728","display_name":"\u57fa\u4e8e\u5dee\u5f02-\u5171\u8868\u8fbe\u7f51\u7edc\u7684\u5355\u7ec6\u80de\u5173\u952e\u57fa\u56e0\u8bc6\u522b\u4e0e\u7ec6\u80de\u5206\u7c7b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072095","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1602592530","display_name":null,"funder_award_id":"2021YFC2100100","funder_id":"https://openalex.org/F4320321620","funder_display_name":"Northeast Forestry University"},{"id":"https://openalex.org/G2264365526","display_name":null,"funder_award_id":"2019A04","funder_id":"https://openalex.org/F4320321620","funder_display_name":"Northeast Forestry University"},{"id":"https://openalex.org/G3076383002","display_name":null,"funder_award_id":"2572021BH01","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5259564614","display_name":"\u7ed3\u5408\u7532\u57fa\u5316DNA\u7684\u8f6c\u5f55\u56e0\u5b50\u8bc6\u522b\u53ca\u5176\u8c03\u63a7\u529f\u80fd\u7814\u7a76","funder_award_id":"61771165","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6890957027","display_name":null,"funder_award_id":"62172087","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321620","display_name":"Northeast Forestry University","ror":"https://ror.org/02yxnh564"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W1965404910","https://openalex.org/W1977429572","https://openalex.org/W1981005463","https://openalex.org/W1993711987","https://openalex.org/W1996768014","https://openalex.org/W2036956828","https://openalex.org/W2051210555","https://openalex.org/W2056132907","https://openalex.org/W2091169672","https://openalex.org/W2111373249","https://openalex.org/W2114358087","https://openalex.org/W2135621733","https://openalex.org/W2135689945","https://openalex.org/W2143485490","https://openalex.org/W2147863530","https://openalex.org/W2164807693","https://openalex.org/W2170747616","https://openalex.org/W2171464043","https://openalex.org/W2199695484","https://openalex.org/W2224398381","https://openalex.org/W2295598076","https://openalex.org/W2513235972","https://openalex.org/W2564226239","https://openalex.org/W2587186776","https://openalex.org/W2587588342","https://openalex.org/W2601885162","https://openalex.org/W2739999456","https://openalex.org/W2768348081","https://openalex.org/W2803245377","https://openalex.org/W2806146459","https://openalex.org/W2899105530","https://openalex.org/W2911354827","https://openalex.org/W2911964244","https://openalex.org/W2962862931","https://openalex.org/W2968536921","https://openalex.org/W2969086705","https://openalex.org/W2980789587","https://openalex.org/W2995081665","https://openalex.org/W3042599313","https://openalex.org/W3095583226","https://openalex.org/W3108496856","https://openalex.org/W3108711749","https://openalex.org/W3109626990","https://openalex.org/W3111496797","https://openalex.org/W3116452748","https://openalex.org/W3128972055","https://openalex.org/W3135329715","https://openalex.org/W3167995117","https://openalex.org/W3186424370","https://openalex.org/W3188619241","https://openalex.org/W3197248033","https://openalex.org/W3199970975","https://openalex.org/W4206971440","https://openalex.org/W4214518133","https://openalex.org/W4239510810","https://openalex.org/W4295313945","https://openalex.org/W6737947904","https://openalex.org/W6745609711","https://openalex.org/W6748281036","https://openalex.org/W6791421521"],"related_works":["https://openalex.org/W4303438490","https://openalex.org/W4231090388","https://openalex.org/W4234181674","https://openalex.org/W2476759866","https://openalex.org/W4252682676","https://openalex.org/W4241224164","https://openalex.org/W4237139593","https://openalex.org/W4256107661","https://openalex.org/W2624482434","https://openalex.org/W4250173751"],"abstract_inverted_index":{"CRISPR-Cas":[0,34,47,184],"system":[1,6],"is":[2,40,192],"an":[3],"adaptive":[4],"immune":[5],"widely":[7],"found":[8],"in":[9,26,46,142,186],"most":[10,23],"bacteria":[11],"and":[12,31,36,67,72,81,107,147,159,174,183],"archaea":[13],"to":[14,137,171],"defend":[15],"against":[16],"exogenous":[17],"gene":[18,65,68],"invasion.":[19],"One":[20],"of":[21,29,43,51,75,161],"the":[22,27,41,58,131,139,156,162],"critical":[24],"steps":[25],"study":[28],"exploring":[30],"classifying":[32],"novel":[33,52,116],"systems":[35],"their":[37],"functional":[38],"diversity":[39],"identification":[42,99,105],"Cas":[44,53,76,88,97,122,177,179],"proteins":[45,54,77,89],"systems.":[48],"The":[49,189],"discovery":[50],"has":[55],"also":[56,167],"laid":[57],"foundation":[59],"for":[60,96,121],"technologies":[61],"such":[62],"as":[63],"CRISPR-Cas-based":[64],"editing":[66],"therapy.":[69],"Currently,":[70],"accurate":[71],"efficient":[73],"screening":[74],"from":[78],"metagenomic":[79],"sequences":[80,83],"proteomic":[82],"remains":[84],"a":[85,115,169],"challenge.":[86],"For":[87],"with":[90],"low":[91],"sequence":[92],"conservation,":[93],"existing":[94,163],"tools":[95],"protein":[98,123],"based":[100],"on":[101],"homology":[102],"cannot":[103],"guarantee":[104],"accuracy":[106,157],"efficiency.":[108],"In":[109,127],"this":[110],"paper,":[111],"we":[112,129],"have":[113,150],"developed":[114],"stacking-based":[117],"ensemble":[118],"learning":[119],"framework":[120],"identification,":[124],"called":[125],"CRISPRCasStack.":[126,143],"particular,":[128],"applied":[130],"SHAP":[132],"(SHapley":[133],"Additive":[134],"exPlanations)":[135],"method":[136],"analyze":[138,175],"features":[140],"used":[141],"Sufficient":[144],"experimental":[145],"validation":[146],"independent":[148],"testing":[149],"demonstrated":[151],"that":[152],"CRISPRCasStack":[153,190],"can":[154],"address":[155],"deficiencies":[158],"inefficiencies":[160],"state-of-the-art":[164],"tools.":[165],"We":[166],"provide":[168],"toolkit":[170,191],"accurately":[172],"identify":[173],"potential":[176],"proteins,":[178],"operons,":[180],"CRISPR":[181],"arrays":[182],"locus":[185],"prokaryotic":[187],"sequences.":[188],"available":[193],"at":[194],"https://github.com/yrjia1015/CRISPRCasStack.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}