{"id":"https://openalex.org/W7216422159","doi":"https://doi.org/10.64898/2026.09.28.754914","title":"AntiCapt: Fine-Tuned Nucleotide Language Models for Predicting and Designing Anticancer Aptamers","display_name":"AntiCapt: Fine-Tuned Nucleotide Language Models for Predicting and Designing Anticancer Aptamers","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7216422159","doi":"https://doi.org/10.64898/2026.09.28.754914"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.28.754914","doi":"https://doi.org/10.64898/2026.09.28.754914","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.754914","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/02/2026.09.28.754914.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/02/2026.09.28.754914.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058212884","display_name":"Nisha Bajiya","orcid":"https://orcid.org/0000-0002-5075-5386","observed_orcids":["https://orcid.org/0000-0002-5075-5386"]},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nisha Bajiya","raw_affiliation_strings":["Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi-110020, India"],"raw_orcid":"https://orcid.org/0000-0002-5075-5386","affiliations":[{"raw_affiliation_string":"Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi-110020, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105068075","display_name":"Naman Kumar Mehta","orcid":"https://orcid.org/0009-0009-0244-2826","observed_orcids":["https://orcid.org/0009-0009-0244-2826"]},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Naman Kumar Mehta","raw_affiliation_strings":["Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi-110020, India"],"raw_orcid":"https://orcid.org/0009-0009-0244-2826","affiliations":[{"raw_affiliation_string":"Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi-110020, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051938893","display_name":"Gajendra P. S. Raghava","orcid":"https://orcid.org/0000-0002-8902-2876","observed_orcids":["https://orcid.org/0000-0002-8902-2876"]},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Gajendra P. S. Raghava","raw_affiliation_strings":["Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi-110020, India"],"raw_orcid":"https://orcid.org/0000-0002-8902-2876","affiliations":[{"raw_affiliation_string":"Department of Computational Biology, Indraprastha Institute of Information Technology, New Delhi-110020, India","institution_ids":["https://openalex.org/I119939252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051938893"],"corresponding_institution_ids":["https://openalex.org/I119939252"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.4180000126361847,"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":0.4180000126361847,"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/T10207","display_name":"Advanced biosensing and bioanalysis techniques","score":0.16539999842643738,"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":0.11219999939203262,"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/aptamer-design","display_name":"aptamer design","score":0.8420000076293945},{"id":"https://openalex.org/keywords/single-stranded-dna","display_name":"single-stranded DNA","score":0.7680000066757202},{"id":"https://openalex.org/keywords/sequence-descriptors","display_name":"sequence descriptors","score":0.6240000128746033},{"id":"https://openalex.org/keywords/autocorrelation-features","display_name":"autocorrelation features","score":0.8259999752044678},{"id":"https://openalex.org/keywords/structural-features","display_name":"structural features","score":0.6660000085830688},{"id":"https://openalex.org/keywords/molecular-descriptors","display_name":"molecular descriptors","score":0.7049999833106995},{"id":"https://openalex.org/keywords/web-server","display_name":"web server","score":0.5329999923706055}],"concepts":[{"id":"https://openalex.org/C128972844","wikidata":"https://www.wikidata.org/wiki/Q418722","display_name":"Aptamer","level":2,"score":0.9690999984741211},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6309000253677368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5515000224113464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5311999917030334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45820000767707825},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.3465999960899353},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3375000059604645},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C3019813237","wikidata":"https://www.wikidata.org/wiki/Q65089264","display_name":"Model validation","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C2983331546","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer therapy","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.28.754914","doi":"https://doi.org/10.64898/2026.09.28.754914","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.754914","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/02/2026.09.28.754914.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.28.754914","doi":"https://doi.org/10.64898/2026.09.28.754914","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.754914","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/02/2026.09.28.754914.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.5683000087738037,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G5082420746","display_name":null,"funder_award_id":"BT/PR40158/BTIS/137/24/2021","funder_id":"https://openalex.org/F4320320717","funder_display_name":"Department of Biotechnology, Ministry of Science and Technology, India"}],"funders":[{"id":"https://openalex.org/F4320320717","display_name":"Department of Biotechnology, Ministry of Science and Technology, India","ror":"https://ror.org/03tjsyq23"},{"id":"https://openalex.org/F4320320721","display_name":"Council of Scientific and Industrial Research, India","ror":"https://ror.org/021wm7p51"},{"id":"https://openalex.org/F4320324473","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7216422159.pdf","grobid_xml":"https://content.openalex.org/works/W7216422159.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1825242443","https://openalex.org/W1972978214","https://openalex.org/W1986074268","https://openalex.org/W1995875735","https://openalex.org/W2043915025","https://openalex.org/W2069520341","https://openalex.org/W2070171305","https://openalex.org/W2086561953","https://openalex.org/W2086744970","https://openalex.org/W2102023232","https://openalex.org/W2110065044","https://openalex.org/W2118911320","https://openalex.org/W2127635589","https://openalex.org/W2135995702","https://openalex.org/W2333198304","https://openalex.org/W2791084028","https://openalex.org/W2795226762","https://openalex.org/W2800208425","https://openalex.org/W2805406480","https://openalex.org/W2980933109","https://openalex.org/W3048086963","https://openalex.org/W3110828293","https://openalex.org/W3127238141","https://openalex.org/W3138479300","https://openalex.org/W3163189192","https://openalex.org/W4200038759","https://openalex.org/W4292058855","https://openalex.org/W4292840778","https://openalex.org/W4309787426","https://openalex.org/W4386268786","https://openalex.org/W4386942017","https://openalex.org/W4388034696","https://openalex.org/W4389005410","https://openalex.org/W4389944751","https://openalex.org/W4391403465","https://openalex.org/W4393935425","https://openalex.org/W4400918715","https://openalex.org/W4401021139","https://openalex.org/W4403118713","https://openalex.org/W4404821554","https://openalex.org/W4405074077","https://openalex.org/W4405807431","https://openalex.org/W4408569178","https://openalex.org/W4408652367","https://openalex.org/W4409304082","https://openalex.org/W4409764905","https://openalex.org/W4410207434","https://openalex.org/W4414519458","https://openalex.org/W4416299893","https://openalex.org/W4416921397","https://openalex.org/W4416957632","https://openalex.org/W7160050920","https://openalex.org/W7165396081","https://openalex.org/W7167229446","https://openalex.org/W7170840807","https://openalex.org/W7212433081"],"related_works":["https://openalex.org/W2591635277","https://openalex.org/W3088799321","https://openalex.org/W4295532582","https://openalex.org/W6950396396","https://openalex.org/W4399075790","https://openalex.org/W1007490150","https://openalex.org/W4414740403","https://openalex.org/W3192914859","https://openalex.org/W2911197460","https://openalex.org/W7167229446"],"abstract_inverted_index":{"Abstract":[0],"Over":[1],"the":[2,80,105,146],"past":[3],"decade,":[4],"aptamers":[5,29,49,163,188],"have":[6],"emerged":[7],"as":[8,14],"promising":[9],"therapeutics,":[10],"with":[11,87,141,149],"cancer":[12],"therapeutics":[13],"a":[15,31,40,125,158,174,178],"major":[16],"research":[17],"area.":[18],"Existing":[19],"computational":[20,41],"methods,":[21],"however,":[22],"either":[23],"predict":[24],"aptamer-target":[25],"pairs":[26],"or":[27],"design":[28],"against":[30],"specific":[32],"target.":[33],"In":[34],"this":[35],"study,":[36],"we":[37,156],"present":[38],"AntiCapt,":[39,173],"method":[42],"for":[43,160,181],"identifying":[44],"single-stranded":[45],"DNA":[46],"(ssDNA)":[47],"anticancer":[48,162,187],"(ACAs)":[50],"using":[51,95,132],"sequence":[52],"descriptors":[53],"and":[54,67,83,100,134,177,184],"fine-tuned":[55,135,142],"nucleotide":[56],"language":[57],"models.":[58],"The":[59,167],"main":[60],"dataset":[61],"comprises":[62],"1,021":[63],"experimentally":[64],"validated":[65],"ACAs":[66],"an":[68,110,115,150],"equal":[69],"number":[70],"of":[71,112,128,153],"non-aptamer":[72],"sequences.":[73],"Comparative":[74],"analysis":[75],"revealed":[76],"distinct":[77],"patterns":[78],"in":[79],"nucleotide,":[81],"dinucleotide,":[82],"trinucleotide":[84],"compositions":[85],"associated":[86],"ACAs.":[88],"We":[89],"developed":[90,157],"machine":[91],"learning":[92],"(ML)":[93],"models":[94,123,131,169],"composition,":[96],"autocorrelation,":[97],"binary":[98],"profiles":[99],"structural":[101,121],"features.":[102],"Among":[103],"these,":[104],"best-performing":[106,168],"composition-based":[107],"model":[108,159],"achieved":[109,124],"AUC":[111,127,152],"0.93":[113],"on":[114],"independent":[116,151],"dataset,":[117],"while":[118],"chemical":[119],"descriptor-and":[120],"feature-based":[122],"maximum":[126],"0.89.":[129],"ML":[130],"pretrained":[133],"NLM":[136],"embeddings":[137,144],"were":[138,170],"also":[139],"developed,":[140],"HyenaDNA":[143],"achieving":[145],"highest":[147],"performance,":[148],"0.94.":[154],"Furthermore,":[155],"discriminating":[161],"from":[164],"general":[165],"aptamers.":[166],"integrated":[171],"into":[172],"web":[175],"server":[176],"standalone":[179],"tool":[180],"predicting,":[182],"designing,":[183],"genome-scale":[185],"scanning":[186],"(":[189],"https://webs.iiitd.edu.in/raghava/anticapt/":[190],").":[191]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-03T00:00:00"}