{"id":"https://openalex.org/W4413206447","doi":"https://doi.org/10.3389/fbinf.2025.1657841","title":"Sequence-based prioritization of i-Motif candidates in the human genome","display_name":"Sequence-based prioritization of i-Motif candidates in the human genome","publication_year":2025,"publication_date":"2025-08-12","ids":{"openalex":"https://openalex.org/W4413206447","doi":"https://doi.org/10.3389/fbinf.2025.1657841","pmid":"https://pubmed.ncbi.nlm.nih.gov/40873684"},"language":"en","primary_location":{"id":"doi:10.3389/fbinf.2025.1657841","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1657841","pdf_url":null,"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://doi.org/10.3389/fbinf.2025.1657841","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114289739","display_name":"Veronica Remori","orcid":null},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Veronica Remori","raw_affiliation_strings":["Department of Science and High Technology, University of Insubria, Como, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Science and High Technology, University of Insubria, Como, Italy","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119303507","display_name":"Michela Prest","orcid":null},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michela Prest","raw_affiliation_strings":["Department of Science and High Technology, University of Insubria, Como, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Science and High Technology, University of Insubria, Como, Italy","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049786321","display_name":"Mauro Fasano","orcid":"https://orcid.org/0000-0003-0628-5871"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]},{"id":"https://openalex.org/I4210127623","display_name":"Ospedale di Circolo di Busto Arsizio","ror":"https://ror.org/03af1ns45","country_code":"IT","type":"healthcare","lineage":["https://openalex.org/I4210127623"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Mauro Fasano","raw_affiliation_strings":["Center of Neuroscience Research, University of Insubria, Busto Arsizio, Italy","Department of Science and High Technology, University of Insubria, Como, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Neuroscience Research, University of Insubria, Busto Arsizio, Italy","institution_ids":["https://openalex.org/I115752224","https://openalex.org/I4210127623"]},{"raw_affiliation_string":"Department of Science and High Technology, University of Insubria, Como, Italy","institution_ids":["https://openalex.org/I115752224"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049786321"],"corresponding_institution_ids":["https://openalex.org/I115752224","https://openalex.org/I4210127623"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":2125,"currency":"USD","value_usd":2125},"fwci":0.8087,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71717858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"1657841","last_page":"1657841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10432","display_name":"DNA and Nucleic Acid Chemistry","score":0.9277999997138977,"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/T10432","display_name":"DNA and Nucleic Acid Chemistry","score":0.9277999997138977,"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":0.03449999913573265,"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":0.008100000210106373,"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/computational-biology","display_name":"Computational biology","score":0.6521702408790588},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.6048151850700378},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5571926832199097},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.5067165493965149},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.42034628987312317},{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.4187324345111847},{"id":"https://openalex.org/keywords/gene-annotation","display_name":"Gene Annotation","score":0.4124421179294586},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4046528935432434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39302393794059753},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.33411040902137756},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.32000789046287537},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.3180907368659973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27482324838638306}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6521702408790588},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.6048151850700378},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5571926832199097},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.5067165493965149},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.42034628987312317},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.4187324345111847},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.4124421179294586},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4046528935432434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39302393794059753},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.33411040902137756},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.32000789046287537},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3180907368659973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27482324838638306}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/fbinf.2025.1657841","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1657841","pdf_url":null,"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:40873684","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40873684","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:doaj.org/article:0ae5047ff2554649a10e4423287ea39b","is_oa":true,"landing_page_url":"https://doaj.org/article/0ae5047ff2554649a10e4423287ea39b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Bioinformatics, Vol 5 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11187345","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12378704","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:irinsubria.uninsubria.it:11383/2198031","is_oa":false,"landing_page_url":"https://hdl.handle.net/11383/2198031","pdf_url":null,"source":{"id":"https://openalex.org/S4377196351","display_name":"IrInSubria (University of Insubria)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115752224","host_organization_name":"University of Insubria","host_organization_lineage":["https://openalex.org/I115752224"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.3389/fbinf.2025.1657841","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fbinf.2025.1657841","pdf_url":null,"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":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1748992454","https://openalex.org/W1911339904","https://openalex.org/W1972485143","https://openalex.org/W1990635146","https://openalex.org/W1998940503","https://openalex.org/W1999474945","https://openalex.org/W2052685738","https://openalex.org/W2073722866","https://openalex.org/W2078174377","https://openalex.org/W2091374137","https://openalex.org/W2105249891","https://openalex.org/W2127322768","https://openalex.org/W2137015675","https://openalex.org/W2327094479","https://openalex.org/W2520749639","https://openalex.org/W2886466753","https://openalex.org/W2907510538","https://openalex.org/W2988527199","https://openalex.org/W3026218946","https://openalex.org/W3042292144","https://openalex.org/W3046309832","https://openalex.org/W3124493020","https://openalex.org/W4214518018","https://openalex.org/W4311359473","https://openalex.org/W4323313749","https://openalex.org/W4327979800","https://openalex.org/W4361278744","https://openalex.org/W4383645997","https://openalex.org/W4385443629","https://openalex.org/W4388668653","https://openalex.org/W4389252922","https://openalex.org/W4395689111","https://openalex.org/W4399807935","https://openalex.org/W4402004890","https://openalex.org/W4404529890","https://openalex.org/W4404566191","https://openalex.org/W4406202875","https://openalex.org/W4406421300","https://openalex.org/W4407058761","https://openalex.org/W4409844514"],"related_works":["https://openalex.org/W2108491719","https://openalex.org/W2005244175","https://openalex.org/W1585743302","https://openalex.org/W2404565489","https://openalex.org/W2167996728","https://openalex.org/W1970582053","https://openalex.org/W2901823680","https://openalex.org/W2052483969","https://openalex.org/W2946410450","https://openalex.org/W2108984616"],"abstract_inverted_index":{"Introduction:":[0],"i-Motifs":[1],"(iMs)":[2],"are":[3],"cytosine-rich,":[4],"four-stranded":[5],"DNA":[6],"structures":[7],"with":[8,86,111],"emerging":[9],"roles":[10],"in":[11,127,193],"gene":[12,191],"regulation":[13],"and":[14,31,100,120,130,162,181],"genome":[15,69],"stability.":[16],"Despite":[17],"their":[18],"biological":[19],"relevance,":[20],"genome-wide":[21],"prediction":[22],"of":[23,148,185],"iM-forming":[24,113],"sequences":[25,108],"remains":[26],"limited":[27],"by":[28,82],"low":[29],"specificity":[30],"high":[32,153],"false-positive":[33],"rates,":[34],"leading":[35],"to":[36,166,189],"considerable":[37],"experimental":[38,179],"burden.":[39],"Method:":[40],"To":[41],"address":[42],"this,":[43],"we":[44],"developed":[45],"a":[46,56,74,152,160,174],"refined":[47],"computational":[48],"approach":[49],"that":[50],"prioritizes":[51],"high-confidence":[52],"iM":[53,171],"candidates":[54],"using":[55,73],"Position-Specific":[57],"Similarity":[58],"Matrix":[59],"(PSSM)":[60],"derived":[61],"from":[62],"multiple":[63],"sequence":[64,85,131],"alignments.":[65],"The":[66],"human":[67],"reference":[68],"(hg38)":[70],"was":[71,91],"scanned":[72],"custom":[75],"regular":[76],"expression":[77,192],"targeting":[78,187],"cytosine-rich":[79],"motifs,":[80],"followed":[81],"scoring":[83],"each":[84],"the":[87,146,149,182],"PSSM.":[88],"Statistical":[89],"significance":[90],"assessed":[92],"via":[93],"permutation":[94],"testing,":[95],"one-sided":[96],"t-tests,":[97],"Benjamini-Hochberg":[98],"correction,":[99],"Z-scores.":[101],"Results:":[102],"This":[103,157],"pipeline":[104],"identified":[105],"37,075":[106],"candidate":[107],"(15-46":[109],"nucleotides)":[110],"strong":[112],"potential.":[114],"Validation":[115],"against":[116],"experimentally":[117],"confirmed":[118],"iMs":[119,188],"known":[121],"G-quadruplexes":[122],"(G4s)":[123],"demonstrated":[124],"significant":[125],"differences":[126],"alignment":[128],"scores":[129],"similarity,":[132],"confirming":[133],"structural":[134],"specificity.":[135],"A":[136],"random":[137],"forest":[138],"classifier":[139],"trained":[140],"on":[141],"nucleotide":[142],"features":[143],"further":[144],"supported":[145],"distinctiveness":[147],"candidates,":[150],"achieving":[151],"classification":[154],"performance.":[155],"Conclusion:":[156],"work":[158],"presents":[159],"scalable":[161],"statistically":[163],"robust":[164],"method":[165],"enrich":[167],"for":[168,177],"biologically":[169],"relevant":[170],"sequences,":[172],"providing":[173],"valuable":[175],"resource":[176],"future":[178],"validation":[180],"rational":[183],"design":[184],"ligands":[186],"modulate":[190],"contexts":[194],"such":[195],"as":[196],"cancer.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}