{"id":"https://openalex.org/W7127402757","doi":"https://doi.org/10.3389/fbinf.2026.1740722","title":"GPXplore: an intelligent computational framework for precise gene promoter extraction","display_name":"GPXplore: an intelligent computational framework for precise gene promoter extraction","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7127402757","doi":"https://doi.org/10.3389/fbinf.2026.1740722","pmid":"https://pubmed.ncbi.nlm.nih.gov/41710172"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2026.1740722","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2026.1740722","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2026.1740722/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2026.1740722/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064955955","display_name":"Shruti Godara","orcid":"https://orcid.org/0009-0009-1072-7290"},"institutions":[{"id":"https://openalex.org/I100681346","display_name":"Forest Institute","ror":"https://ror.org/04fves619","country_code":"US","type":"education","lineage":["https://openalex.org/I100681346"]},{"id":"https://openalex.org/I1141210","display_name":"Indian Agricultural Statistics Research Institute","ror":"https://ror.org/03kkevc75","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1141210","https://openalex.org/I179420787"]}],"countries":["IN","US"],"is_corresponding":true,"raw_author_name":"Shruti Godara","raw_affiliation_strings":["ICAR-Indian Agricultural Statistics Research Institute","ICFRE-Forest Research Institute"],"affiliations":[{"raw_affiliation_string":"ICAR-Indian Agricultural Statistics Research Institute","institution_ids":["https://openalex.org/I1141210"]},{"raw_affiliation_string":"ICFRE-Forest Research Institute","institution_ids":["https://openalex.org/I100681346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006025220","display_name":"Samarth Godara","orcid":null},"institutions":[{"id":"https://openalex.org/I100681346","display_name":"Forest Institute","ror":"https://ror.org/04fves619","country_code":"US","type":"education","lineage":["https://openalex.org/I100681346"]},{"id":"https://openalex.org/I1141210","display_name":"Indian Agricultural Statistics Research Institute","ror":"https://ror.org/03kkevc75","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1141210","https://openalex.org/I179420787"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Samarth Godara","raw_affiliation_strings":["ICAR-Indian Agricultural Statistics Research Institute","ICFRE-Forest Research Institute"],"affiliations":[{"raw_affiliation_string":"ICAR-Indian Agricultural Statistics Research Institute","institution_ids":["https://openalex.org/I1141210"]},{"raw_affiliation_string":"ICFRE-Forest Research Institute","institution_ids":["https://openalex.org/I100681346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123481123","display_name":"Shbana Begam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091233","display_name":"National Research Centre on Plant Biotechnology","ror":"https://ror.org/00cq3cz72","country_code":"IN","type":"facility","lineage":["https://openalex.org/I179420787","https://openalex.org/I4210091233"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shbana Begam","raw_affiliation_strings":["ICAR-National Institute for Plant Biotechnology"],"affiliations":[{"raw_affiliation_string":"ICAR-National Institute for Plant Biotechnology","institution_ids":["https://openalex.org/I4210091233"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065098967","display_name":"Anil Kumar Singh","orcid":"https://orcid.org/0000-0002-3569-5207"},"institutions":[{"id":"https://openalex.org/I4210091233","display_name":"National Research Centre on Plant Biotechnology","ror":"https://ror.org/00cq3cz72","country_code":"IN","type":"facility","lineage":["https://openalex.org/I179420787","https://openalex.org/I4210091233"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anil Kumar Singh","raw_affiliation_strings":["ICAR-National Institute for Plant Biotechnology"],"affiliations":[{"raw_affiliation_string":"ICAR-National Institute for Plant Biotechnology","institution_ids":["https://openalex.org/I4210091233"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064955955"],"corresponding_institution_ids":["https://openalex.org/I100681346","https://openalex.org/I1141210"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":14.8753,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97352287,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"6","issue":null,"first_page":"1740722","last_page":"1740722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.20100000500679016,"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":0.20100000500679016,"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/T10878","display_name":"CRISPR and Genetic Engineering","score":0.12489999830722809,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.08669999986886978,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/promoter","display_name":"Promoter","score":0.5515000224113464},{"id":"https://openalex.org/keywords/upstream","display_name":"Upstream (networking)","score":0.541100025177002},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.482699990272522},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4749000072479248},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.46149998903274536},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.40290001034736633},{"id":"https://openalex.org/keywords/gene-prediction","display_name":"Gene prediction","score":0.3684999942779541},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.3540000021457672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6230000257492065},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.5515000224113464},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5422000288963318},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41029998660087585},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.3684999942779541},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3215000033378601},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3073999881744385},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3005000054836273},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3389/fbinf.2026.1740722","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2026.1740722","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2026.1740722/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41710172","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41710172","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":"Frontiers in bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12909496","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12909496/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"Front Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2026.1740722","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2026.1740722","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2026.1740722/pdf","source":{"id":"https://openalex.org/S4210219554","display_name":"Frontiers in Bioinformatics","issn_l":"2673-7647","issn":["2673-7647"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1288741607","display_name":null,"funder_award_id":"ICAR-IASRI","funder_id":"https://openalex.org/F4320320769","funder_display_name":"Indian Council of Agricultural Research"}],"funders":[{"id":"https://openalex.org/F4320320769","display_name":"Indian Council of Agricultural Research","ror":"https://ror.org/04fw54a43"},{"id":"https://openalex.org/F4320336714","display_name":"ICAR-Indian Agricultural Statistics Research Institute","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127402757.pdf","grobid_xml":"https://content.openalex.org/works/W7127402757.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2001157929","https://openalex.org/W2035908878","https://openalex.org/W2052250375","https://openalex.org/W2100651362","https://openalex.org/W2102619694","https://openalex.org/W2131478115","https://openalex.org/W2141292707","https://openalex.org/W2141454371","https://openalex.org/W2142678031","https://openalex.org/W2157009395","https://openalex.org/W2169202776","https://openalex.org/W2886541918","https://openalex.org/W2979343233","https://openalex.org/W4243357985","https://openalex.org/W4281254649","https://openalex.org/W4387997265"],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"and":[1,22,34,50,73,83,90,115,119,124,139,145],"precise":[2,49],"extraction":[3,52,78],"of":[4,53,157],"gene":[5,12,18,54,88],"promoter":[6,77,162],"regions":[7],"is":[8,107,120],"vital":[9],"for":[10,47,152],"understanding":[11],"regulation,":[13],"with":[14,122],"broad":[15],"implications":[16],"in":[17,31,75,109,164],"editing,":[19],"functional":[20],"genomics,":[21],"disease":[23],"research.":[24],"However,":[25],"existing":[26],"tools":[27],"often":[28],"fall":[29],"short":[30],"scalability,":[32],"usability":[33],"performance.":[35],"To":[36],"address":[37],"these":[38],"limitations,":[39],"we":[40],"present":[41],"\"GPXplore,\"":[42],"a":[43,113,149],"computational":[44,158],"tool":[45,106],"designed":[46],"the":[48],"user-friendly":[51],"promoters":[55],"from":[56],"genomic":[57,134],"data.":[58],"It":[59],"leverages":[60],"vectorized":[61],"data":[62,68],"processing":[63,69],"techniques":[64],"to":[65,87,96],"significantly":[66],"reduce":[67],"time,":[70],"enhancing":[71],"speed":[72],"efficiency":[74],"large-scale":[76],"tasks.":[79],"GPXplore":[80,127,147],"retrieves":[81],"upstream":[82],"downstream":[84],"sequences":[85],"relative":[86],"loci":[89],"supports":[91],"customizable":[92],"parameters,":[93],"enabling":[94],"users":[95],"define":[97],"region":[98],"lengths":[99],"based":[100],"on":[101],"specific":[102],"research":[103],"needs.":[104],"The":[105],"implemented":[108],"Python,":[110],"features":[111],"both":[112],"command-line":[114],"graphical":[116],"user":[117],"interface,":[118],"compatible":[121],"Windows":[123],"Ubuntu":[125],"platforms.":[126],"was":[128],"rigorously":[129],"validated":[130],"using":[131],"eight":[132],"diverse":[133],"datasets,":[135],"demonstrating":[136],"high":[137],"accuracy":[138],"reliability.":[140],"By":[141],"combining":[142],"automation,":[143],"flexibility,":[144],"accessibility,":[146],"provides":[148],"robust":[150],"solution":[151],"researchers":[153],"across":[154],"varying":[155],"levels":[156],"expertise,":[159],"facilitating":[160],"high-throughput":[161],"analysis":[163],"modern":[165],"genomics.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-02-04T00:00:00"}
