{"id":"https://openalex.org/W7225834284","doi":"https://doi.org/10.64898/2026.11.10.765632","title":"RNA Small-Molecule Binding-Site Prediction by Integrating RNA Language Models and Structural Geometry","display_name":"RNA Small-Molecule Binding-Site Prediction by Integrating RNA Language Models and Structural Geometry","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225834284","doi":"https://doi.org/10.64898/2026.11.10.765632"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.10.765632","doi":"https://doi.org/10.64898/2026.11.10.765632","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.10.765632","pdf_url":null,"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://doi.org/10.64898/2026.11.10.765632","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101864214","display_name":"Nandita Sharma","orcid":"https://orcid.org/0000-0003-2191-8462","observed_orcids":["https://orcid.org/0000-0003-2191-8462"]},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Nandita Sharma","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur, India;"],"raw_orcid":"https://orcid.org/0000-0003-2191-8462","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur, India;","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069306071","display_name":"Pralay Mitra","orcid":"https://orcid.org/0000-0003-4119-3788","observed_orcids":["https://orcid.org/0000-0003-4119-3788"]},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pralay Mitra","raw_affiliation_strings":["IIT Kharagpur: Indian Institute of Technology Kharagpur"],"raw_orcid":"https://orcid.org/0000-0003-4119-3788","affiliations":[{"raw_affiliation_string":"IIT Kharagpur: Indian Institute of Technology Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101864214"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.86080002784729,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.86080002784729,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.10909999907016754,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10432","display_name":"DNA and Nucleic Acid Chemistry","score":0.0044999998062849045,"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":[],"concepts":[{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.6604999899864197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.593500018119812},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5139999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512499988079071},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C509619924","wikidata":"https://www.wikidata.org/wiki/Q17130757","display_name":"Structural complexity","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C41282012","wikidata":"https://www.wikidata.org/wiki/Q3928341","display_name":"RNA-binding protein","level":4,"score":0.387800008058548},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C126142528","wikidata":"https://www.wikidata.org/wiki/Q3771876","display_name":"Nucleic acid structure","level":4,"score":0.3774000108242035},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3562000095844269},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3050999939441681},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.3003999888896942},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C132677234","wikidata":"https://www.wikidata.org/wiki/Q3273544","display_name":"Structural motif","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2824000120162964},{"id":"https://openalex.org/C69131567","wikidata":"https://www.wikidata.org/wiki/Q2068215","display_name":"Structural bioinformatics","level":3,"score":0.2800000011920929},{"id":"https://openalex.org/C107824862","wikidata":"https://www.wikidata.org/wiki/Q616005","display_name":"Binding site","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.10.765632","doi":"https://doi.org/10.64898/2026.11.10.765632","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.10.765632","pdf_url":null,"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:10.64898/2026.11.10.765632","doi":"https://doi.org/10.64898/2026.11.10.765632","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.10.765632","pdf_url":null,"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"RNAs":[0],"are":[1,214],"emerging":[2],"as":[3],"promising":[4],"therapeutic":[5,19],"targets,":[6],"and":[7,14,35,46,101,113,115,122,136,139,149,176,261],"small-molecule":[8,25],"binding":[9,26,79,229,259],"can":[10],"modulate":[11],"their":[12,206],"structure":[13],"function,":[15],"creating":[16],"opportunities":[17],"for":[18,31,57,73],"development.":[20],"Accurate":[21],"identification":[22],"of":[23,44,50,76,86,119,162,169,248,269],"RNA":[24,45,93,108,201,224],"sites":[27,230],"is":[28,131,279],"therefore":[29],"important":[30],"understanding":[32],"RNA-ligand":[33,53,250],"interactions":[34],"facilitating":[36],"RNA-targeted":[37],"drug":[38],"discovery.":[39],"However,":[40],"the":[41,47,87,117,134,153,157,163,181,255,267],"structural":[42,100,212,225],"complexity":[43],"limited":[48],"availability":[49],"experimentally":[51],"characterized":[52],"complexes":[54,251],"pose":[55],"challenges":[56],"computational":[58],"binding-site":[59],"prediction.":[60],"In":[61],"this":[62],"study,":[63],"we":[64],"propose":[65],"RSMBind,":[66],"a":[67],"graph":[68],"attention-based":[69],"deep":[70],"learning":[71],"framework":[72],"nucleotide-level":[74],"prediction":[75,221],"RNA-small":[77],"molecule":[78],"sites.":[80],"The":[81,129,276],"model":[82,95,130,203],"integrates":[83],"geometric":[84,123],"descriptors":[85],"local":[88],"three-dimensional":[89],"environment":[90],"with":[91,166,227],"pretrained":[92,107,200],"language":[94,109,202],"embeddings":[96],"to":[97],"capture":[98],"complementary":[99],"sequence":[102,120],"information.":[103],"We":[104],"investigate":[105],"three":[106,161],"models":[110],"RNA-BERT,":[111],"ERNIE-RNA":[112],"RNA-FM":[114],"assess":[116],"contributions":[118],"representations":[121],"features":[124,213],"through":[125],"feature-level":[126],"ablation":[127],"experiments.":[128],"developed":[132],"using":[133,198],"TR60":[135],"HARIBOSS":[137],"datasets":[138],"evaluated":[140],"on":[141,160,171,174,178,190],"four":[142,164],"independent":[143],"benchmark":[144],"datasets:":[145],"RB9,":[146,172],"TE18,":[147],"TL12":[148,175],"JL10.":[150],"RSMBind":[151,193],"achieves":[152],"highest":[154],"MCC":[155],"among":[156],"compared":[158],"methods":[159],"benchmarks,":[165],"relative":[167],"improvements":[168],"17.1%":[170],"7.2%":[173],"16.0%":[177],"JL10":[179],"over":[180],"best":[182],"previously":[183],"reported":[184],"results,":[185],"while":[186],"achieving":[187],"competitive":[188],"performance":[189,222],"TE18.":[191],"Furthermore,":[192],"retains":[194],"predictive":[195],"capability":[196],"when":[197,209],"only":[199],"embeddings,":[204],"highlighting":[205,266],"potential":[207],"utility":[208],"explicit":[210],"tertiary":[211],"unavailable.":[215],"Structural":[216],"analysis":[217],"indicates":[218],"differences":[219],"in":[220,272],"across":[223],"regions,":[226],"loop-associated":[228],"generally":[231],"being":[232],"captured":[233],"more":[234],"effectively":[235],"than":[236],"those":[237],"embedded":[238],"within":[239],"stem":[240],"regions.":[241],"Additionally,":[242],"100":[243],"ns":[244],"molecular":[245],"dynamics":[246,271],"simulations":[247],"selected":[249],"provide":[252],"insights":[253],"into":[254],"relationship":[256],"between":[257],"predicted":[258],"probabilities":[260],"dynamic":[262],"ligand":[263],"proximity,":[264],"further":[265],"role":[268],"conformational":[270],"evaluating":[273],"structure-based":[274],"predictions.":[275],"source":[277],"code":[278],"available":[280],"at":[281],"[":[282],"https://github.com/sharma-nandita/RSMBind].":[283]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}