{"id":"https://openalex.org/W7125932917","doi":"https://doi.org/10.1093/bioinformatics/btag048","title":"How negative sampling shapes the performance of transcription factor binding site prediction models","display_name":"How negative sampling shapes the performance of transcription factor binding site prediction models","publication_year":2026,"publication_date":"2026-01-23","ids":{"openalex":"https://openalex.org/W7125932917","doi":"https://doi.org/10.1093/bioinformatics/btag048","pmid":"https://pubmed.ncbi.nlm.nih.gov/41601205"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag048","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag048","pdf_url":null,"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://doi.org/10.1093/bioinformatics/btag048","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121012841","display_name":"Natan Tourne","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Natan Tourne","raw_affiliation_strings":["Department of Data Analysis and Mathematical Modelling, Ghent University , Ghent 9000,"],"affiliations":[{"raw_affiliation_string":"Department of Data Analysis and Mathematical Modelling, Ghent University , Ghent 9000,","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052622361","display_name":"Gaetan De Waele","orcid":"https://orcid.org/0000-0003-0367-9699"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Gaetan De Waele","raw_affiliation_strings":["Department of Data Analysis and Mathematical Modelling, Ghent University , Ghent 9000,"],"affiliations":[{"raw_affiliation_string":"Department of Data Analysis and Mathematical Modelling, Ghent University , Ghent 9000,","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031701521","display_name":"Vanessa Vermeirssen","orcid":"https://orcid.org/0000-0002-1975-0712"},"institutions":[{"id":"https://openalex.org/I12607205","display_name":"University College Ghent","ror":"https://ror.org/00rs45z86","country_code":"BE","type":"education","lineage":["https://openalex.org/I12607205"]},{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I4210118715","display_name":"Cancer Research Institute Ghent","ror":"https://ror.org/02afm7029","country_code":"BE","type":"facility","lineage":["https://openalex.org/I4210118715"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Vanessa Vermeirssen","raw_affiliation_strings":["Department of Biomedical Molecular Biology, Ghent University , Ghent 9000,","Department of Biomolecular Medicine, Ghent University , Ghent 9000,","Lab for Computational Biology, Integromics and Gene Regulation (CBIGR), Cancer Research Institute Ghent (CRIG) , Ghent 9000,"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Molecular Biology, Ghent University , Ghent 9000,","institution_ids":["https://openalex.org/I32597200","https://openalex.org/I12607205","https://openalex.org/I2801227569"]},{"raw_affiliation_string":"Department of Biomolecular Medicine, Ghent University , Ghent 9000,","institution_ids":["https://openalex.org/I12607205","https://openalex.org/I32597200","https://openalex.org/I2801227569"]},{"raw_affiliation_string":"Lab for Computational Biology, Integromics and Gene Regulation (CBIGR), Cancer Research Institute Ghent (CRIG) , Ghent 9000,","institution_ids":["https://openalex.org/I4210118715"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028945060","display_name":"Willem Waegeman","orcid":"https://orcid.org/0000-0002-5950-3003"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Willem Waegeman","raw_affiliation_strings":["Department of Data Analysis and Mathematical Modelling, Ghent University , Ghent 9000,"],"affiliations":[{"raw_affiliation_string":"Department of Data Analysis and Mathematical Modelling, Ghent University , Ghent 9000,","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5121012841"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24546227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9836999773979187,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9836999773979187,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.007000000216066837,"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":0.0020000000949949026,"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/sampling","display_name":"Sampling (signal processing)","score":0.5184000134468079},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4731000065803528},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4458000063896179},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.4284000098705292},{"id":"https://openalex.org/keywords/dna-binding-site","display_name":"DNA binding site","score":0.3668999969959259},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3578000068664551},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.33649998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5842000246047974},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5184000134468079},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4731000065803528},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.46399998664855957},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.4284000098705292},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4122999906539917},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.3668999969959259},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33390000462532043},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C107824862","wikidata":"https://www.wikidata.org/wiki/Q616005","display_name":"Binding site","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C2984391234","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential sampling","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2581999897956848},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25450000166893005}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000081204","descriptor_name":"Chromatin Immunoprecipitation Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000081204","descriptor_name":"Chromatin Immunoprecipitation Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000081204","descriptor_name":"Chromatin Immunoprecipitation Sequencing","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btag048","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag048","pdf_url":null,"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:41601205","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41601205","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:archive.ugent.be:01KJFQKQMBZ42ZMAQ0RSWJDC2X","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01KJFQKQMBZ42ZMAQ0RSWJDC2X","pdf_url":"https://biblio.ugent.be/publication/01KJFQKQMBZ42ZMAQ0RSWJDC2X/file/01KJFR9PHSSJAY7X7R87BGM743.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISSN: 1367-4811","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pubmedcentral.nih.gov:12910371","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12910371/","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag048","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag048","pdf_url":null,"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":[],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W42318800","https://openalex.org/W1019830208","https://openalex.org/W1587004646","https://openalex.org/W1907835050","https://openalex.org/W1974800873","https://openalex.org/W1990893875","https://openalex.org/W2027057997","https://openalex.org/W2029201460","https://openalex.org/W2061834804","https://openalex.org/W2098412979","https://openalex.org/W2099848965","https://openalex.org/W2107665411","https://openalex.org/W2114850508","https://openalex.org/W2122097157","https://openalex.org/W2127184995","https://openalex.org/W2158266834","https://openalex.org/W2160378721","https://openalex.org/W2198606573","https://openalex.org/W2259938310","https://openalex.org/W2336509392","https://openalex.org/W2338148720","https://openalex.org/W2589838901","https://openalex.org/W2744579364","https://openalex.org/W2779662045","https://openalex.org/W2789652838","https://openalex.org/W2896262061","https://openalex.org/W2926285546","https://openalex.org/W2951410692","https://openalex.org/W2988126442","https://openalex.org/W3097592152","https://openalex.org/W3112390879","https://openalex.org/W3130819465","https://openalex.org/W3180669414","https://openalex.org/W3203588026","https://openalex.org/W3215596355","https://openalex.org/W4220872625","https://openalex.org/W4283766509","https://openalex.org/W4292723044","https://openalex.org/W4318669110","https://openalex.org/W4387735261","https://openalex.org/W4396617739","https://openalex.org/W4396834536"],"related_works":[],"abstract_inverted_index":{"The":[0],"code":[1],"used":[2],"in":[3],"this":[4],"study":[5],"is":[6],"available":[7],"at":[8],"https://github.com/NatanTourne/TFBS-negatives":[9],"(DOI:":[10],"10.5281/zenodo.18007567).":[11]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-29T00:00:00"}
