{"id":"https://openalex.org/W2600971009","doi":"https://doi.org/10.1021/acs.jcim.7b00049","title":"Structural and Sequence Similarity Makes a Significant Impact on Machine-Learning-Based Scoring Functions for Protein\u2013Ligand Interactions","display_name":"Structural and Sequence Similarity Makes a Significant Impact on Machine-Learning-Based Scoring Functions for Protein\u2013Ligand Interactions","publication_year":2017,"publication_date":"2017-03-30","ids":{"openalex":"https://openalex.org/W2600971009","doi":"https://doi.org/10.1021/acs.jcim.7b00049","mag":"2600971009","pmid":"https://pubmed.ncbi.nlm.nih.gov/28358210"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.7b00049","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.7b00049","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","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/A5101621563","display_name":"Yang Li","orcid":"https://orcid.org/0000-0001-7304-3851"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Li","raw_affiliation_strings":["College\rof Life Sciences, Nankai University, Tianjin 300071, China","School\rof Mathematical Sciences, Nankai University, Tianjin 300071, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College\rof Life Sciences, Nankai University, Tianjin 300071, China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"School\rof Mathematical Sciences, Nankai University, Tianjin 300071, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107636936","display_name":"Jianyi Yang","orcid":"https://orcid.org/0000-0003-2912-7737"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyi Yang","raw_affiliation_strings":["School\rof Mathematical Sciences, Nankai University, Tianjin 300071, China"],"raw_orcid":"https://orcid.org/0000-0003-2912-7737","affiliations":[{"raw_affiliation_string":"School\rof Mathematical Sciences, Nankai University, Tianjin 300071, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101621563"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":7.11,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.97526047,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"57","issue":"4","first_page":"1007","last_page":"1012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9969000220298767,"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/T11882","display_name":"Plant biochemistry and biosynthesis","score":0.9854000210762024,"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/machine-learning","display_name":"Machine learning","score":0.7078709602355957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7035683393478394},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6936802864074707},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.687463641166687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.563962459564209},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5596656203269958},{"id":"https://openalex.org/keywords/matthews-correlation-coefficient","display_name":"Matthews correlation coefficient","score":0.534643828868866},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5212417244911194},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4601382315158844},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44674739241600037},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.438811719417572},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4231151044368744},{"id":"https://openalex.org/keywords/pearson-product-moment-correlation-coefficient","display_name":"Pearson product-moment correlation coefficient","score":0.4172508418560028},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3372323215007782},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23166972398757935},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.18178164958953857},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13791027665138245},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13299095630645752}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7078709602355957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7035683393478394},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6936802864074707},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.687463641166687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.563962459564209},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5596656203269958},{"id":"https://openalex.org/C164085508","wikidata":"https://www.wikidata.org/wiki/Q4811327","display_name":"Matthews correlation coefficient","level":3,"score":0.534643828868866},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5212417244911194},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4601382315158844},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44674739241600037},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.438811719417572},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4231151044368744},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.4172508418560028},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3372323215007782},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23166972398757935},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.18178164958953857},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13791027665138245},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13299095630645752},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.7b00049","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.7b00049","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:28358210","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28358210","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 chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5299999713897705,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G4191431376","display_name":null,"funder_award_id":"81520108019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4514259272","display_name":null,"funder_award_id":"2014CB542800","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G8147118672","display_name":null,"funder_award_id":"11501306","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/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1950993160","https://openalex.org/W1974324284","https://openalex.org/W1992441011","https://openalex.org/W1993046136","https://openalex.org/W1993403967","https://openalex.org/W2003356525","https://openalex.org/W2013085020","https://openalex.org/W2020372058","https://openalex.org/W2022998385","https://openalex.org/W2025006523","https://openalex.org/W2038542598","https://openalex.org/W2040990879","https://openalex.org/W2047886533","https://openalex.org/W2049185580","https://openalex.org/W2050237550","https://openalex.org/W2053253524","https://openalex.org/W2060320699","https://openalex.org/W2073021822","https://openalex.org/W2074231493","https://openalex.org/W2075020622","https://openalex.org/W2101234009","https://openalex.org/W2102245393","https://openalex.org/W2114162221","https://openalex.org/W2115540209","https://openalex.org/W2128332459","https://openalex.org/W2134967712","https://openalex.org/W2148512505","https://openalex.org/W2158360182","https://openalex.org/W2160916136","https://openalex.org/W2161151688","https://openalex.org/W2163816950","https://openalex.org/W2169678694","https://openalex.org/W2471677683"],"related_works":["https://openalex.org/W829658220","https://openalex.org/W2740316168","https://openalex.org/W4225403114","https://openalex.org/W2953914733","https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961"],"abstract_inverted_index":{"The":[0],"prediction":[1],"of":[2,20,42,54,73,101,122,162,181],"protein-ligand":[3],"binding":[4],"affinity":[5],"has":[6],"recently":[7],"been":[8,67],"improved":[9],"remarkably":[10],"by":[11,87,134],"machine-learning-based":[12,74,118,140],"scoring":[13,57,153],"functions.":[14],"For":[15],"example,":[16],"using":[17],"a":[18,114],"set":[19,41],"simple":[21],"descriptors":[22],"representing":[23],"the":[24,28,31,39,43,52,60,71,77,90,96,102,130,144,151,158,160,179],"atomic":[25],"distance":[26],"counts,":[27],"RF-Score":[29],"improves":[30],"Pearson":[32],"correlation":[33],"coefficient":[34],"to":[35,69,129,177],"about":[36],"0.8":[37],"on":[38,59,117,143],"core":[40],"PDBbind":[44,103],"2007":[45],"database,":[46],"which":[47],"is":[48,167],"significantly":[49],"higher":[50],"than":[51],"performance":[53,72,161],"any":[55,155],"conventional":[56,152,163],"function":[58],"same":[61],"benchmark.":[62],"A":[63],"few":[64],"studies":[65],"have":[66],"made":[68],"discuss":[70],"methods,":[75],"but":[76],"reason":[78],"for":[79],"this":[80,85],"improvement":[81],"remains":[82],"unclear.":[83],"In":[84],"study,":[86],"systemically":[88],"controlling":[89],"structural":[91,109],"and":[92,98,110,137],"sequence":[93,111,138],"similarity":[94,112],"between":[95],"training":[97,123,146,173],"test":[99,131],"proteins":[100,124,132],"benchmark,":[104],"we":[105],"demonstrate":[106],"that":[107,125],"protein":[108],"makes":[113],"significant":[115],"impact":[116],"methods.":[119],"After":[120],"removal":[121],"are":[126,175],"highly":[127],"similar":[128],"identified":[133],"structure":[135],"alignment":[136],"alignment,":[139],"methods":[141],"trained":[142],"new":[145],"sets":[147],"do":[148],"not":[149],"outperform":[150],"functions":[154,164],"more.":[156],"On":[157],"contrary,":[159],"like":[165],"X-Score":[166],"relatively":[168],"stable":[169],"no":[170],"matter":[171],"what":[172],"data":[174],"used":[176],"fit":[178],"weights":[180],"its":[182],"energy":[183],"terms.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}