{"id":"https://openalex.org/W4315645662","doi":"https://doi.org/10.1186/s13321-022-00675-8","title":"Multimodal data fusion for supervised learning-based identification of USP7 inhibitors: a systematic comparison","display_name":"Multimodal data fusion for supervised learning-based identification of USP7 inhibitors: a systematic comparison","publication_year":2023,"publication_date":"2023-01-11","ids":{"openalex":"https://openalex.org/W4315645662","doi":"https://doi.org/10.1186/s13321-022-00675-8","pmid":"https://pubmed.ncbi.nlm.nih.gov/36631899"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-022-00675-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00675-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00675-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00675-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005814445","display_name":"Wenfeng Shen","orcid":"https://orcid.org/0000-0003-1366-9195"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen-feng Shen","raw_affiliation_strings":["School of Medicine & School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China"],"affiliations":[{"raw_affiliation_string":"School of Medicine & School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074068498","display_name":"He-wei Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He-wei Tang","raw_affiliation_strings":["School of Medicine & School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China"],"affiliations":[{"raw_affiliation_string":"School of Medicine & School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088068064","display_name":"Jiabo Li","orcid":"https://orcid.org/0000-0002-9288-9673"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia-bo Li","raw_affiliation_strings":["School of Medicine & School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China"],"affiliations":[{"raw_affiliation_string":"School of Medicine & School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331036","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-9161-1848"},"institutions":[{"id":"https://openalex.org/I177933477","display_name":"Second Military Medical University","ror":"https://ror.org/04tavpn47","country_code":"CN","type":"education","lineage":["https://openalex.org/I177933477"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Li","raw_affiliation_strings":["School of Pharmacy, Second Military Medical University, Shanghai, 200433, China. xiangli@smmu.edu.cn","School of Pharmacy, Second Military Medical University, Shanghai, 200433, China"],"affiliations":[{"raw_affiliation_string":"School of Pharmacy, Second Military Medical University, Shanghai, 200433, China. xiangli@smmu.edu.cn","institution_ids":[]},{"raw_affiliation_string":"School of Pharmacy, Second Military Medical University, Shanghai, 200433, China","institution_ids":["https://openalex.org/I177933477"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100366205","display_name":"Si Chen","orcid":"https://orcid.org/0000-0002-8202-8634"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Chen","raw_affiliation_strings":["School of Medicine & School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China. caroline-sisi-chen@hotmail.com","School of Medicine & School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China"],"affiliations":[{"raw_affiliation_string":"School of Medicine & School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China. caroline-sisi-chen@hotmail.com","institution_ids":[]},{"raw_affiliation_string":"School of Medicine & School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100331036"],"corresponding_institution_ids":["https://openalex.org/I177933477"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":5.0283,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.96047247,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"15","issue":"1","first_page":"5","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.9010000228881836,"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":0.7672308087348938},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.747565746307373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7062365412712097},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5746344327926636},{"id":"https://openalex.org/keywords/virtual-screening","display_name":"Virtual screening","score":0.4673099219799042},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4624280035495758},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.45297425985336304},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42816662788391113},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.41671180725097656},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.2455901801586151},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19903269410133362},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.19822734594345093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7672308087348938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.747565746307373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7062365412712097},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5746344327926636},{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.4673099219799042},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4624280035495758},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.45297425985336304},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42816662788391113},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.41671180725097656},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.2455901801586151},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19903269410133362},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.19822734594345093},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-022-00675-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00675-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00675-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:36631899","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36631899","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":"Journal of cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9835315","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9835315","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:f009b12afb704153b9920019a28a9aff","is_oa":true,"landing_page_url":"https://doaj.org/article/f009b12afb704153b9920019a28a9aff","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 15, Iss 1, Pp 1-16 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-022-00675-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-022-00675-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-022-00675-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324016","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883"},{"id":"https://openalex.org/F4320327803","display_name":"Shanghai Rising-Star Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4315645662.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W2083339697","https://openalex.org/W2098474053","https://openalex.org/W2148143831","https://openalex.org/W2327079070","https://openalex.org/W2472085920","https://openalex.org/W2541170635","https://openalex.org/W2604296437","https://openalex.org/W2766738665","https://openalex.org/W2768112882","https://openalex.org/W2934533499","https://openalex.org/W2959938226","https://openalex.org/W3011727199","https://openalex.org/W3013169228","https://openalex.org/W3015363152","https://openalex.org/W3081597552","https://openalex.org/W3087318293","https://openalex.org/W3093039828","https://openalex.org/W3094451547","https://openalex.org/W3095727459","https://openalex.org/W3159637815","https://openalex.org/W4205327406","https://openalex.org/W4206042814","https://openalex.org/W4240082606"],"related_works":["https://openalex.org/W4285741730","https://openalex.org/W4285046548","https://openalex.org/W3195168932","https://openalex.org/W1996541855","https://openalex.org/W2369569015","https://openalex.org/W4313488044","https://openalex.org/W4281757034","https://openalex.org/W4318350883","https://openalex.org/W4319309271","https://openalex.org/W2118927937"],"abstract_inverted_index":{"Ubiquitin-specific-processing":[0],"protease":[1],"7":[2],"(USP7)":[3],"is":[4,55,169,183,223],"a":[5,57,130,155],"promising":[6],"target":[7],"protein":[8],"for":[9,253],"cancer":[10],"therapy,":[11],"and":[12,41,87,105,129,152,174,199,208,217,226,260],"great":[13],"attention":[14],"has":[15],"been":[16,30],"given":[17],"to":[18,33,50,60,73,92],"the":[19,94,120,144,167,178,181,195,213,221,229,243],"identification":[20],"of":[21,119,132,135,143,157,197,215,245],"USP7":[22,35,62,76,246],"inhibitors.":[23,63,247],"Traditional":[24],"virtual":[25],"screening":[26],"methods":[27],"have":[28],"now":[29],"successfully":[31],"applied":[32],"discover":[34],"inhibitors":[36,77],"aiming":[37],"at":[38],"reducing":[39],"costs":[40],"speeding":[42],"up":[43],"time":[44],"in":[45,96,146,190,256],"several":[46],"studies.":[47],"However,":[48],"due":[49],"their":[51],"unsatisfactory":[52],"accuracy,":[53],"it":[54],"still":[56],"difficult":[58],"task":[59],"develop":[61],"In":[64,202],"this":[65],"study,":[66],"multiple":[67],"supervised":[68,236,258],"learning":[69,102,109,164,237],"classifiers":[70],"were":[71,89,112,139],"built":[72],"distinguish":[74],"active":[75],"from":[78],"inactive":[79],"ligands.":[80],"Physicochemical":[81],"descriptors,":[82],"MACCS":[83],"keys,":[84],"ECFP4":[85],"fingerprints":[86],"SMILES":[88,209],"first":[90],"calculated":[91],"represent":[93],"compounds":[95],"our":[97],"in-house":[98],"dataset.":[99],"Two":[100],"deep":[101],"(DL)":[103],"models":[104,111,145,161,165,219,259],"nine":[106],"classical":[107],"machine":[108],"(ML)":[110],"then":[113],"constructed":[114],"based":[115],"on":[116],"different":[117],"combinations":[118],"above":[121],"molecular":[122,261],"representations":[123,262],"under":[124],"three":[125],"activity":[126],"cutoff":[127],"values,":[128],"total":[131],"15":[133],"groups":[134],"experiments":[136,148],"(75":[137],"experiments)":[138],"implemented.":[140],"The":[141,159],"performance":[142,196,214],"these":[147],"was":[149,250],"evaluated,":[150],"compared":[151],"discussed":[153],"using":[154],"variety":[156],"metrics.":[158],"optimal":[160],"are":[162],"ensemble":[163],"when":[166,180,220],"dataset":[168,182,222],"balanced":[170],"or":[171],"severely":[172,224],"imbalanced,":[173,225],"SMILES-based":[175],"DL":[176,200,218],"performs":[177],"best":[179],"slightly":[184],"imbalanced.":[185],"Meanwhile,":[186],"multimodal":[187],"data":[188],"fusion":[189],"some":[191],"cases":[192],"can":[193,211],"improve":[194,212],"ML":[198,216],"models.":[201],"addition,":[203],"SMOTE,":[204],"unbiased":[205],"decoy":[206],"selection":[207],"enumeration":[210],"SMOTE":[227],"works":[228],"best.":[230],"Our":[231],"study":[232],"established":[233],"highly":[234],"accurate":[235],"classification":[238],"models,":[239],"which":[240],"would":[241],"accelerate":[242],"development":[244],"Some":[248],"guidance":[249],"also":[251],"provided":[252],"drug":[254],"researchers":[255],"selecting":[257],"as":[263,265],"well":[264],"handling":[266],"imbalanced":[267],"datasets.":[268]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}