{"id":"https://openalex.org/W2935793619","doi":"https://doi.org/10.1093/bib/bbz037","title":"A feature-based approach to predict hot spots in protein\u2013DNA binding interfaces","display_name":"A feature-based approach to predict hot spots in protein\u2013DNA binding interfaces","publication_year":2019,"publication_date":"2019-03-08","ids":{"openalex":"https://openalex.org/W2935793619","doi":"https://doi.org/10.1093/bib/bbz037","mag":"2935793619","pmid":"https://pubmed.ncbi.nlm.nih.gov/30957840"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbz037","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbz037","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/A5100733720","display_name":"Sijia Zhang","orcid":"https://orcid.org/0000-0002-7549-782X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijia Zhang","raw_affiliation_strings":["Institutes of Physical Science and Information Technology, School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Institutes of Physical Science and Information Technology, School of Computer Science and Technology, Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089791620","display_name":"Le Zhao","orcid":"https://orcid.org/0000-0002-1213-1126"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Zhao","raw_affiliation_strings":["Institutes of Physical Science and Information Technology, School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Institutes of Physical Science and Information Technology, School of Computer Science and Technology, Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064185915","display_name":"Chun-Hou Zheng","orcid":"https://orcid.org/0000-0002-2695-1926"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun-Hou Zheng","raw_affiliation_strings":["Institutes of Physical Science and Information Technology, School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Institutes of Physical Science and Information Technology, School of Computer Science and Technology, Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065943710","display_name":"Junfeng Xia","orcid":"https://orcid.org/0000-0003-3024-1705"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junfeng Xia","raw_affiliation_strings":["Institutes of Physical Science and Information Technology, School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Institutes of Physical Science and Information Technology, School of Computer Science and Technology, Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065943710"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":2.3866,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.8946754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"21","issue":"3","first_page":"1038","last_page":"1046"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9997000098228455,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9997000098228455,"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":0.9986000061035156,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7647842168807983},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6781983375549316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6582996845245361},{"id":"https://openalex.org/keywords/hot-spot","display_name":"Hot spot (computer programming)","score":0.6537771224975586},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6181881427764893},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6037023067474365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5378512740135193},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5357427000999451},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5071396827697754},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48088791966438293},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44006410241127014},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43794605135917664},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4312152862548828}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7647842168807983},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6781983375549316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6582996845245361},{"id":"https://openalex.org/C199672914","wikidata":"https://www.wikidata.org/wiki/Q4241353","display_name":"Hot spot (computer programming)","level":2,"score":0.6537771224975586},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6181881427764893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6037023067474365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5378512740135193},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5357427000999451},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5071396827697754},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48088791966438293},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44006410241127014},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43794605135917664},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4312152862548828},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbz037","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbz037","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:30957840","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30957840","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":[],"awards":[{"id":"https://openalex.org/G247010507","display_name":null,"funder_award_id":"61873001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2483327137","display_name":null,"funder_award_id":"11835014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5573161910","display_name":null,"funder_award_id":"61672037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7652863277","display_name":null,"funder_award_id":"31301101","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W118535833","https://openalex.org/W1503104790","https://openalex.org/W1596947964","https://openalex.org/W1625079248","https://openalex.org/W1979366468","https://openalex.org/W1989181256","https://openalex.org/W1991048125","https://openalex.org/W1992116297","https://openalex.org/W2005750609","https://openalex.org/W2008056655","https://openalex.org/W2008708467","https://openalex.org/W2014776147","https://openalex.org/W2027542060","https://openalex.org/W2036743098","https://openalex.org/W2042714852","https://openalex.org/W2048917743","https://openalex.org/W2051710717","https://openalex.org/W2069217708","https://openalex.org/W2073229442","https://openalex.org/W2094764962","https://openalex.org/W2097356092","https://openalex.org/W2097944242","https://openalex.org/W2099485600","https://openalex.org/W2103525038","https://openalex.org/W2120744225","https://openalex.org/W2122137509","https://openalex.org/W2122401542","https://openalex.org/W2136206140","https://openalex.org/W2138769522","https://openalex.org/W2141624700","https://openalex.org/W2143426320","https://openalex.org/W2149997286","https://openalex.org/W2152365098","https://openalex.org/W2153635508","https://openalex.org/W2154053567","https://openalex.org/W2155770902","https://openalex.org/W2158714788","https://openalex.org/W2161199282","https://openalex.org/W2162980545","https://openalex.org/W2345718491","https://openalex.org/W2414912386","https://openalex.org/W2528774686","https://openalex.org/W2557117995","https://openalex.org/W2605361745","https://openalex.org/W2739876930","https://openalex.org/W2766389776","https://openalex.org/W2766808155","https://openalex.org/W2777941847","https://openalex.org/W2792363117","https://openalex.org/W2794024218","https://openalex.org/W2798552692","https://openalex.org/W2800333284","https://openalex.org/W2810225085","https://openalex.org/W2883467144","https://openalex.org/W2890951984","https://openalex.org/W2894836881","https://openalex.org/W2904602199","https://openalex.org/W6728150723","https://openalex.org/W6751150484","https://openalex.org/W6754842948","https://openalex.org/W6755276765"],"related_works":["https://openalex.org/W4367336074","https://openalex.org/W3154045278","https://openalex.org/W4379620016","https://openalex.org/W4393666307","https://openalex.org/W3210764983","https://openalex.org/W4393443811","https://openalex.org/W4367335949","https://openalex.org/W3089416646","https://openalex.org/W4396816114","https://openalex.org/W4380048833"],"abstract_inverted_index":{"DNA-binding":[0],"hot":[1,28,42,83,113,140,192,226],"spot":[2,84,141],"residues":[3,11],"of":[4,15,20,57,63,112,183,191],"proteins":[5],"are":[6,30,37],"dominant":[7],"and":[8,32,69,73,89,106,118,153,164,242],"fundamental":[9],"interface":[10],"that":[12,126,214],"contribute":[13],"most":[14],"the":[16,64,110,119,131,150,189,202,230],"binding":[17,185,196],"free":[18],"energy":[19],"protein-DNA":[21,195],"interfaces.":[22],"As":[23],"experimental":[24],"methods":[25,160],"for":[26,82,109,188,237],"identifying":[27],"spots":[29,43,114,193,227],"expensive":[31],"time":[33],"consuming,":[34],"computational":[35],"approaches":[36],"urgently":[38],"required":[39],"in":[40,194,224],"predicting":[41,225],"on":[44,130,139,161,201,209],"a":[45,54,61,177],"large":[46],"scale.":[47],"In":[48,168],"this":[49],"work,":[50],"we":[51,175],"systematically":[52],"assessed":[53],"wide":[55],"variety":[56],"114":[58],"features":[59,128,147],"from":[60],"combination":[62],"protein":[65],"sequence,":[66],"structure,":[67],"network":[68],"solvent":[70,132],"accessible":[71,133],"information":[72],"their":[74],"combinations":[75],"along":[76],"with":[77],"various":[78],"feature":[79],"selection":[80],"strategies":[81],"prediction.":[85],"We":[86],"then":[87],"trained":[88],"compared":[90,228],"four":[91],"commonly":[92],"used":[93],"machine":[94,100,158],"learning":[95,159],"models,":[96],"namely,":[97,180],"support":[98],"vector":[99],"(SVM),":[101],"random":[102],"forest,":[103],"Na\u00efve":[104],"Bayes":[105],"k-nearest":[107],"neighbor,":[108],"identification":[111],"using":[115,198],"10-fold":[116],"cross-validation":[117],"independent":[120,165],"test":[121,166],"set.":[122],"Our":[123],"results":[124,208],"show":[125],"(1)":[127],"based":[129,200],"surface":[134],"area":[135],"have":[136],"significant":[137],"effect":[138],"prediction;":[142],"(2)":[143],"different":[144],"but":[145],"complementary":[146],"generally":[148,221],"enhance":[149],"prediction":[151,190],"performance;":[152],"(3)":[154],"SVM":[155,199],"outperforms":[156],"other":[157],"both":[162],"training":[163],"sets.":[167],"an":[169],"effort":[170],"to":[171,219,229],"improve":[172],"predictive":[173],"performance,":[174],"developed":[176],"feature-based":[178],"method,":[179],"PrPDH":[181,238],"(Prediction":[182],"Protein-DNA":[184],"Hot":[186],"spots),":[187],"interfaces":[197],"selected":[203],"10":[204],"optimal":[205],"features.":[206],"Comparative":[207],"benchmark":[210],"data":[211],"sets":[212],"indicate":[213],"our":[215],"predictor":[216],"is":[217,239,243],"able":[218],"achieve":[220],"better":[222],"performance":[223],"state-of-the-art":[231],"predictors.":[232],"A":[233],"user-friendly":[234],"web":[235],"server":[236],"well":[240],"established":[241],"freely":[244],"available":[245],"at":[246],"http://bioinfo.ahu.edu.cn:8080/PrPDH.":[247]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}