{"id":"https://openalex.org/W3195367207","doi":"https://doi.org/10.1093/bioinformatics/btab603","title":"Improved datasets and evaluation methods for the automatic prediction of DNA-binding proteins","display_name":"Improved datasets and evaluation methods for the automatic prediction of DNA-binding proteins","publication_year":2021,"publication_date":"2021-08-18","ids":{"openalex":"https://openalex.org/W3195367207","doi":"https://doi.org/10.1093/bioinformatics/btab603","mag":"3195367207","pmid":"https://pubmed.ncbi.nlm.nih.gov/34415301"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab603","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab603","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/1/44/49006293/btab603.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/38/1/44/49006293/btab603.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019205480","display_name":"Alexander Zaitzeff","orcid":"https://orcid.org/0000-0001-9731-1873"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Zaitzeff","raw_affiliation_strings":["Two Six Research, Two Six Technologies , Arlington, VA 22203, USA"],"raw_orcid":"https://orcid.org/0000-0001-9731-1873","affiliations":[{"raw_affiliation_string":"Two Six Research, Two Six Technologies , Arlington, VA 22203, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038199555","display_name":"Nicholas Leiby","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicholas Leiby","raw_affiliation_strings":["Two Six Research, Two Six Technologies , Arlington, VA 22203, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Two Six Research, Two Six Technologies , Arlington, VA 22203, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014650825","display_name":"Francis C. Motta","orcid":"https://orcid.org/0000-0002-0364-5440"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francis C Motta","raw_affiliation_strings":["Department of Mathematical Sciences, Florida Atlantic University , Boca Raton, FL 33431, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematical Sciences, Florida Atlantic University , Boca Raton, FL 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065188919","display_name":"Steven B. Haase","orcid":"https://orcid.org/0000-0001-8127-8992"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven B Haase","raw_affiliation_strings":["Department of Biology, Duke University , Durham, NC 27708, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology, Duke University , Durham, NC 27708, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052322423","display_name":"Jedediah M. Singer","orcid":"https://orcid.org/0000-0002-5255-4473"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jedediah M Singer","raw_affiliation_strings":["Two Six Research, Two Six Technologies , Arlington, VA 22203, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Two Six Research, Two Six Technologies , Arlington, VA 22203, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.4885,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6219762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"38","issue":"1","first_page":"44","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9851999878883362,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9851999878883362,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.002899999963119626,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0024999999441206455,"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":0.6680466532707214},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5958203077316284},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5782209634780884},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5080506801605225},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5011105537414551},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.49083074927330017},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.463126003742218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4562396705150604},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4452216625213623},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.4392316937446594},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.4236268401145935},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.41783949732780457},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16289642453193665},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11762484908103943},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09562218189239502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6680466532707214},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5958203077316284},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5782209634780884},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5080506801605225},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5011105537414551},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.49083074927330017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.463126003742218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4562396705150604},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4452216625213623},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.4392316937446594},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.4236268401145935},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.41783949732780457},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16289642453193665},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11762484908103943},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09562218189239502},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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":"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":"D004247","descriptor_name":"DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004268","descriptor_name":"DNA-Binding Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btab603","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab603","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/1/44/49006293/btab603.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34415301","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34415301","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btab603","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab603","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/1/44/49006293/btab603.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4014406470","display_name":null,"funder_award_id":"-17-C-","funder_id":"https://openalex.org/F4320306078","funder_display_name":"U.S. Department of Defense"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5705546835","display_name":null,"funder_award_id":"FA8750-17-C-0231","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7810741018","display_name":null,"funder_award_id":"FA8750-17-C-0231","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3195367207.pdf","grobid_xml":"https://content.openalex.org/works/W3195367207.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1490286156","https://openalex.org/W1659313070","https://openalex.org/W1892469892","https://openalex.org/W1992116297","https://openalex.org/W2003893812","https://openalex.org/W2010688088","https://openalex.org/W2055043387","https://openalex.org/W2070980386","https://openalex.org/W2083563185","https://openalex.org/W2102551551","https://openalex.org/W2103017472","https://openalex.org/W2144939151","https://openalex.org/W2149851123","https://openalex.org/W2173801226","https://openalex.org/W2322691988","https://openalex.org/W2337731955","https://openalex.org/W2470414691","https://openalex.org/W2557229948","https://openalex.org/W2557383173","https://openalex.org/W2748005921","https://openalex.org/W2757522837","https://openalex.org/W2766430481","https://openalex.org/W2769306988","https://openalex.org/W2771169143","https://openalex.org/W2777094228","https://openalex.org/W2804549231","https://openalex.org/W2883467144","https://openalex.org/W2890911678","https://openalex.org/W2895810213","https://openalex.org/W2900353268","https://openalex.org/W2943495267","https://openalex.org/W2946492269","https://openalex.org/W2950595506","https://openalex.org/W2955151077","https://openalex.org/W2957436444","https://openalex.org/W2984726926","https://openalex.org/W3015361967","https://openalex.org/W3020418214","https://openalex.org/W3126039337","https://openalex.org/W3136918052","https://openalex.org/W6762363781","https://openalex.org/W6776502655","https://openalex.org/W6790156245"],"related_works":["https://openalex.org/W2094822546","https://openalex.org/W4388708026","https://openalex.org/W1969080446","https://openalex.org/W3108941781","https://openalex.org/W1578069856","https://openalex.org/W2134206588","https://openalex.org/W2084200259","https://openalex.org/W2065993463","https://openalex.org/W4400576356","https://openalex.org/W2401071219"],"abstract_inverted_index":{"MOTIVATION:":[0],"Accurate":[1],"automatic":[2],"annotation":[3,90],"of":[4,24,35,56,59,101,168,173,179],"protein":[5,29,66,89,144,180],"function":[6],"relies":[7],"on":[8,108,189],"both":[9],"innovative":[10],"models":[11,127,170,185,198],"and":[12,44,68,104,176,208,222,245],"robust":[13],"datasets.":[14],"Due":[15],"to":[16,42,112,171,187],"their":[17],"importance":[18],"in":[19,63,204],"biological":[20],"processes,":[21],"the":[22,33,39,57,60,99,109,125,148,166,196,205],"identification":[23],"DNA-binding":[25,65,102,174,190],"proteins":[26,103],"directly":[27],"from":[28,50,141],"sequence":[30],"has":[31],"been":[32],"focus":[34,188],"many":[36],"studies.":[37],"However,":[38],"datasets":[40,61,72,111],"used":[41,62],"train":[43],"evaluate":[45,165],"these":[46,74,169],"methods":[47],"have":[48],"suffered":[49],"substantial":[51],"flaws.":[52],"We":[53,76,92,164],"describe":[54],"some":[55,211],"weaknesses":[58],"previous":[64],"literature":[67],"provide":[69,120,210],"several":[70],"new":[71,78,96,133],"addressing":[73],"problems.":[75],"suggest":[77],"evaluative":[79],"benchmark":[80],"tasks":[81],"that":[82],"more":[83],"realistically":[84],"assess":[85],"real-world":[86],"performance":[87,107],"for":[88,98,224,234],"models.":[91,116,150],"propose":[93],"a":[94,142,155],"simple":[95],"model":[97,159],"prediction":[100],"compare":[105],"its":[106],"improved":[110],"two":[113],"previously":[114],"published":[115,143],"In":[117],"addition,":[118],"we":[119],"extensive":[121],"tests":[122],"showing":[123],"how":[124],"best":[126,197],"predict":[128],"across":[129,194,202,215],"taxa.":[130],"RESULTS:":[131],"Our":[132],"gradient":[134],"boosting":[135],"model,":[136,146],"which":[137],"uses":[138],"features":[139],"derived":[140],"language":[145],"outperforms":[147],"earlier":[149],"Perhaps":[151],"surprisingly,":[152],"so":[153],"does":[154],"baseline":[156],"nearest":[157],"neighbor":[158],"using":[160],"BLAST":[161],"percent":[162],"identity.":[163],"sensitivity":[167],"perturbations":[172],"regions":[175,178],"control":[177],"sequences.":[181],"The":[182,220,232,242],"successful":[183],"data-driven":[184],"learn":[186],"regions.":[191],"When":[192],"predicting":[193,214],"taxa,":[195],"are":[199],"highly":[200],"accurate":[201],"species":[203],"same":[206],"kingdom":[207],"can":[209,227,237,247],"information":[212],"when":[213],"kingdoms.":[216],"AVAILABILITY":[217],"AND":[218],"IMPLEMENTATION:":[219],"data":[221,244],"results":[223,246],"this":[225,235],"article":[226,236],"be":[228,238,249],"found":[229,239,250],"at":[230,240,251],"https://doi.org/10.5281/zenodo.5153906.":[231],"code":[233],"https://doi.org/10.5281/zenodo.5153683.":[241],"code,":[243],"also":[248],"https://github.com/AZaitzeff/tools_for_dna_binding_proteins.":[252]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-20T20:08:15.867695","created_date":"2025-10-10T00:00:00"}
