{"id":"https://openalex.org/W4382631636","doi":"https://doi.org/10.1093/bioinformatics/btad209","title":"SemiBin2: self-supervised contrastive learning leads to better MAGs for short- and long-read sequencing","display_name":"SemiBin2: self-supervised contrastive learning leads to better MAGs for short- and long-read sequencing","publication_year":2023,"publication_date":"2023-05-24","ids":{"openalex":"https://openalex.org/W4382631636","doi":"https://doi.org/10.1093/bioinformatics/btad209","pmid":"https://pubmed.ncbi.nlm.nih.gov/37387171"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad209","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad209","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i21/50741692/btad209.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i21/50741692/btad209.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017191357","display_name":"Shaojun Pan","orcid":"https://orcid.org/0000-0002-5270-5614"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Pan","raw_affiliation_strings":["Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China","Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education , Shanghai 200433, China"],"raw_orcid":"https://orcid.org/0000-0002-5270-5614","affiliations":[{"raw_affiliation_string":"Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210164150"]},{"raw_affiliation_string":"Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education , Shanghai 200433, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049435754","display_name":"Xing\u2010Ming Zhao","orcid":"https://orcid.org/0000-0002-4531-3970"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I2802974365","display_name":"Shanghai Innovative Research Center of Traditional Chinese Medicine","ror":"https://ror.org/01gnagj68","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802974365"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing-Ming Zhao","raw_affiliation_strings":["Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China","Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education , Shanghai 200433, China","MOE Frontiers Center for Brain Science, Fudan University , Shanghai 200433, China","Zhangjiang Fudan International Innovation Center , Shanghai 201203, China"],"raw_orcid":"https://orcid.org/0000-0002-4531-3970","affiliations":[{"raw_affiliation_string":"Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210164150"]},{"raw_affiliation_string":"Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education , Shanghai 200433, China","institution_ids":[]},{"raw_affiliation_string":"MOE Frontiers Center for Brain Science, Fudan University , Shanghai 200433, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Zhangjiang Fudan International Innovation Center , Shanghai 201203, China","institution_ids":["https://openalex.org/I2802974365"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078114370","display_name":"Lu\u00eds Pedro Coelho","orcid":"https://orcid.org/0000-0002-9280-7885"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luis Pedro Coelho","raw_affiliation_strings":["Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China","Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education , Shanghai 200433, China"],"raw_orcid":"https://orcid.org/0000-0002-9280-7885","affiliations":[{"raw_affiliation_string":"Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University , Shanghai 200433, China","institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210164150"]},{"raw_affiliation_string":"Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education , Shanghai 200433, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":18.7488,"has_fulltext":true,"cited_by_count":196,"citation_normalized_percentile":{"value":0.99716473,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"39","issue":"Supplement_1","first_page":"i21","last_page":"i29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.6572999954223633,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.6572999954223633,"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/T10885","display_name":"Gene expression and cancer classification","score":0.10819999873638153,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.06379999965429306,"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/computer-science","display_name":"Computer science","score":0.6778647899627686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4438111186027527},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36477339267730713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6778647899627686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4438111186027527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36477339267730713}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btad209","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad209","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i21/50741692/btad209.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:37387171","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37387171","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10311329","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10311329","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10311329/pdf/btad209.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad209","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad209","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/Supplement_1/i21/50741692/btad209.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1005508400","display_name":null,"funder_award_id":"31950410544","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1307575636","display_name":"\u9762\u5411\u8111\u75be\u75c5\u7684\u4eba\u4f53\u80a0\u9053\u5fae\u751f\u7269\u7ec4\u5b66\u6570\u636e\u6316\u6398\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61932008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5574148142","display_name":null,"funder_award_id":"2018SHZDZX01","funder_id":"https://openalex.org/F4320321851","funder_display_name":"Fudan University"},{"id":"https://openalex.org/G7846711397","display_name":null,"funder_award_id":"T2225015, 61932008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8573963713","display_name":null,"funder_award_id":"2020YFA0712403","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8776634001","display_name":null,"funder_award_id":"2020YFA0712403","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8899475930","display_name":null,"funder_award_id":"2018SHZDZX01","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8903503482","display_name":null,"funder_award_id":"T2225015","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/F4320321421","display_name":"Albert-Ludwigs-Universit\u00e4t Freiburg","ror":"https://ror.org/0245cg223"},{"id":"https://openalex.org/F4320321851","display_name":"Fudan University","ror":"https://ror.org/013q1eq08"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4382631636.pdf"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W151377110","https://openalex.org/W1878521557","https://openalex.org/W1982579644","https://openalex.org/W1982855075","https://openalex.org/W2001561488","https://openalex.org/W2095705004","https://openalex.org/W2101234009","https://openalex.org/W2102619694","https://openalex.org/W2103901746","https://openalex.org/W2112364185","https://openalex.org/W2121291798","https://openalex.org/W2127175247","https://openalex.org/W2157364932","https://openalex.org/W2159084616","https://openalex.org/W2164998314","https://openalex.org/W2170551349","https://openalex.org/W2575750030","https://openalex.org/W2590945262","https://openalex.org/W2735611463","https://openalex.org/W2740924709","https://openalex.org/W2745006471","https://openalex.org/W2753961085","https://openalex.org/W2754579667","https://openalex.org/W2789843538","https://openalex.org/W2800234325","https://openalex.org/W2913972921","https://openalex.org/W2927453907","https://openalex.org/W2938828179","https://openalex.org/W2938868597","https://openalex.org/W2941342985","https://openalex.org/W2950747344","https://openalex.org/W2950954328","https://openalex.org/W2952982270","https://openalex.org/W2966589940","https://openalex.org/W2977428858","https://openalex.org/W2981413553","https://openalex.org/W3006653136","https://openalex.org/W3043405618","https://openalex.org/W3091506611","https://openalex.org/W3120084484","https://openalex.org/W3137047737","https://openalex.org/W3144260862","https://openalex.org/W3168040031","https://openalex.org/W3205855923","https://openalex.org/W4200175714","https://openalex.org/W4205677193","https://openalex.org/W4206999279","https://openalex.org/W4221065320","https://openalex.org/W4225007447","https://openalex.org/W4226051960","https://openalex.org/W4283809266","https://openalex.org/W4285042422","https://openalex.org/W4292178604","https://openalex.org/W4294001681","https://openalex.org/W4313648386","https://openalex.org/W4385302529","https://openalex.org/W6674330103","https://openalex.org/W6675354045","https://openalex.org/W6683390034"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"MOTIVATION:":[0],"Metagenomic":[1],"binning":[2,24,29],"methods":[3],"to":[4,54,89,120],"reconstruct":[5,93],"metagenome-assembled":[6],"genomes":[7,135],"(MAGs)":[8],"from":[9,58],"environmental":[10],"samples":[11],"have":[12],"been":[13],"widely":[14],"used":[15,78,160],"in":[16,31,79,112,131,161],"large-scale":[17],"metagenomic":[18],"studies.":[19],"The":[20],"recently":[21],"proposed":[22],"semi-supervised":[23,76],"method,":[25],"SemiBin,":[26],"achieved":[27],"state-of-the-art":[28,86],"results":[30,73],"several":[32],"environments.":[33],"However,":[34],"this":[35],"required":[36],"annotating":[37],"contigs,":[38],"a":[39],"computationally":[40],"costly":[41],"and":[42,63,81,98,106,156],"potentially":[43],"biased":[44],"process.":[45],"RESULTS:":[46],"We":[47],"propose":[48,125],"SemiBin2,":[49],"which":[50],"uses":[51],"self-supervised":[52,69],"learning":[53,70,77],"learn":[55],"feature":[56],"embeddings":[57],"the":[59,75,103,137,157,162],"contigs.":[60],"In":[61],"simulated":[62],"real":[64,113],"datasets,":[65],"we":[66,123],"show":[67],"that":[68,82],"achieves":[71],"better":[72],"than":[74,136],"SemiBin1":[80],"SemiBin2":[83,91,119,147],"outperforms":[84],"other":[85],"binners.":[87],"Compared":[88],"SemiBin1,":[90],"can":[92,164],"8.3-21.5%":[94],"more":[95,133],"high-quality":[96,134],"bins":[97],"requires":[99],"only":[100],"25%":[101],"of":[102,108],"running":[104],"time":[105],"11%":[107],"peak":[109],"memory":[110],"usage":[111],"short-read":[114],"sequencing":[115],"samples.":[116],"To":[117],"extend":[118],"long-read":[121,142],"data,":[122],"also":[124],"ensemble-based":[126],"DBSCAN":[127],"clustering":[128],"algorithm,":[129],"resulting":[130],"13.1-26.3%":[132],"second":[138],"best":[139],"binner":[140],"for":[141],"data.":[143],"AVAILABILITY":[144],"AND":[145],"IMPLEMENTATION:":[146],"is":[148],"available":[149],"as":[150],"open":[151],"source":[152],"software":[153],"at":[154,167],"https://github.com/BigDataBiology/SemiBin/":[155],"analysis":[158],"scripts":[159],"study":[163],"be":[165],"found":[166],"https://github.com/BigDataBiology/SemiBin2_benchmark.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":59},{"year":2025,"cited_by_count":98},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":8}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
