{"doi":"10.1093/database/baaf006","title":"LitSumm: large language models for literature summarization of noncoding RNAs","abstract":"<jats:title>Abstract</jats:title>\n               <jats:p>Curation of literature in life sciences is a growing challenge. The continued increase in the rate of publication, coupled with the relatively fixed number of curators worldwide, presents a major challenge to developers of biomedical knowledgebases. Very few knowledgebases have resources to scale to the whole relevant literature and all have to prioritize their efforts.</jats:p>\n               <jats:p>In this work, we take a first step to alleviating the lack of curator time in RNA science by generating summaries of literature for noncoding RNAs using large language models (LLMs). We demonstrate that high-quality, factually accurate summaries with accurate references can be automatically generated from the literature using a commercial LLM and a chain of prompts and checks. Manual assessment was carried out for a subset of summaries, with the majority being rated extremely high quality.</jats:p>\n               <jats:p>We apply our tool to a selection of &amp;gt;4600 ncRNAs and make the generated summaries available via the RNAcentral resource. We conclude that automated literature summarization is feasible with the current generation of LLMs, provided that careful prompting and automated checking are applied.</jats:p>\n               <jats:p>Database URL: https://rnacentral.org/</jats:p>","journal":"Database","year":2025,"id":633510,"datarank":0.38474240361923057,"base_score":2.5649493574615367,"endowment":2.5649493574615367,"self_citation_contribution":0.38474240361923057,"citation_network_contribution":0.0,"self_endowment_contribution":0.38474240361923057,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":12,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":228791,"name":"Carlos Eduardo Ribas","orcid":"0000-0002-9572-273X","position":1,"is_corresponding":false},{"id":106794,"name":"Nancy Ontiveros‐Palacios","orcid":"0000-0001-8457-4455","position":2,"is_corresponding":false},{"id":57002,"name":"Sam Griffiths-Jones","orcid":"0000-0001-6043-807X","position":3,"is_corresponding":false},{"id":106800,"name":"Anton I. Petrov","orcid":"0000-0001-7279-2682","position":4,"is_corresponding":false},{"id":228792,"name":"Alex Bateman","orcid":"0000-0002-6982-4660","position":5,"is_corresponding":false},{"id":228790,"name":"Blake Sweeney","orcid":"0000-0002-6497-2883","position":6,"is_corresponding":false},{"id":40120,"name":"Andrew Green","orcid":"0000-0002-1077-7417","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"LitSumm: large language models for literature summarization of noncoding RNAs","abstract":"<jats:title>Abstract</jats:title>\n               <jats:p>Curation of literature in life sciences is a growing challenge. The continued increase in the rate of publication, coupled with the relatively fixed number of curators worldwide, presents a major challenge to developers of biomedical knowledgebases. Very few knowledgebases have resources to scale to the whole relevant literature and all have to prioritize their efforts.</jats:p>\n               <jats:p>In this work, we take a first step to alleviating the lack of curator time in RNA science by generating summaries of literature for noncoding RNAs using large language models (LLMs). We demonstrate that high-quality, factually accurate summaries with accurate references can be automatically generated from the literature using a commercial LLM and a chain of prompts and checks. Manual assessment was carried out for a subset of summaries, with the majority being rated extremely high quality.</jats:p>\n               <jats:p>We apply our tool to a selection of &amp;gt;4600 ncRNAs and make the generated summaries available via the RNAcentral resource. We conclude that automated literature summarization is feasible with the current generation of LLMs, provided that careful prompting and automated checking are applied.</jats:p>\n               <jats:p>Database URL: https://rnacentral.org/</jats:p>","is_dataset_classified":null,"base_score":2.5649493574615367,"endowment":2.5649493574615367,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"39908113","pmcid":"PMC11833236","openalex_id":"https://openalex.org/W4407236426","authors":[],"funders":[{"funder_name":"H2020 Marie Sklodowska-Curie Actions","grant_id":"945405","title":"Career Accelerator for Research Infrastructure Scientists"},{"funder_name":"Wellcome Trust","grant_id":"218302/Z/19/Z","title":null},{"funder_name":"Wellcome Trust","grant_id":"218302","title":"A comprehensive platform for the functional annotation of non-coding RNA genes and gene families"},{"funder_name":"Wellcome Trust","grant_id":"","title":null}],"total_grants":4,"fwci":14.4985,"citation_percentile":0.98682377,"influential_citations":0,"citation_trend":[{"year":2025,"count":8},{"year":2026,"count":4}],"oa_status":"gold","license":"cc-by","oa_locations":[{"url":"https://doi.org/10.1093/database/baaf006","host_type":"journal"},{"url":"https://doi.org/10.1093/database/baaf006","host_type":"publisher"},{"url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baaf006/61769336/baaf006.pdf","host_type":"publisher"},{"url":"https://pubmed.ncbi.nlm.nih.gov/39908113","host_type":"repository"},{"url":"https://pubmed.ncbi.nlm.nih.gov/40402769","host_type":"repository"},{"url":"https://research.manchester.ac.uk/en/publications/8bed735e-4c57-49b0-a918-2d78501ccf39","host_type":"repository"},{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11833236","host_type":"repository"},{"url":"https://www.scopus.com/pages/publications/85217974241","host_type":"repository"},{"url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11833236/pdf/baaf006.pdf","host_type":"repository"},{"url":"https://europepmc.org/articles/PMC11833236","host_type":"Europe_PMC"},{"url":"https://europepmc.org/articles/PMC11833236?pdf=render","host_type":"Europe_PMC"},{"url":"https://dx.doi.org/10.48550/arxiv.2311.03056","host_type":""},{"url":"http://dx.doi.org/10.1093/database/baaf006","host_type":""},{"url":"http://arxiv.org/abs/2311.03056","host_type":""},{"url":"https://doi.org/10.48550/arXiv.2311.03056","host_type":""}],"fields_of_study":["Natural Language Processing Techniques","Topic Modeling","RNA modifications and cancer","0206 medical engineering","02 engineering and technology"],"mesh_terms":["Large Language Models","Humans","Programming Languages","Software","RNA, Untranslated","Databases, Nucleic Acid","Data Curation"],"keywords":["Automatic summarization","Computer science","Long non-coding RNA","Natural language processing","Computational biology","Information retrieval","RNA","Biology","Genetics","Gene","Data Curation/methods","Genomics (q-bio.GN)","FOS: Computer and information sciences","RNA, Untranslated","Nucleic Acid","Computer Science - Artificial Intelligence","RNA, Untranslated/genetics","Untranslated/genetics","Databases","Large Language Models","Artificial Intelligence (cs.AI)","FOS: Biological sciences","Humans","Quantitative Biology - Genomics","Original Article","Programming Languages","Databases, Nucleic Acid","Data Curation","Software"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Responsible consumption and production"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-06T12:12:17.185913Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}