{"id":"W4411622822","doi":"10.1093/gigascience/giaf070","title":"Extraction of biological terms using large language models enhances the usability of metadata in the BioSample database","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; National Bioscience Database Center; Japan Society for the Promotion of Science; Japan Science and Technology Corporation","keywords":"Metadata; Computer science; Data curation; Information retrieval; World Wide Web; Usability; Data science; Database","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001239464,0.0000552692,0.00009485755,0.00002353765,0.00005837882,0.000010569,0.0005059103,0.00005669285,0.000003499638],"category_scores_gemma":[0.0005410722,0.00002673485,0.00003624936,0.0002531036,0.0005781371,0.00001038901,0.000164014,0.00006637669,9.788256e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003790303,"about_ca_system_score_gemma":0.00004997982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001922744,"about_ca_topic_score_gemma":0.0001098403,"domain_scores_codex":[0.999256,0.0001310047,0.0001710418,0.0001998795,0.0001105418,0.0001315913],"domain_scores_gemma":[0.999393,0.0001106502,0.0000697146,0.0003955987,0.00002042108,0.00001054391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001526401,0.00007604763,0.00185499,0.00001216943,0.000004604813,4.78624e-7,0.0001770475,0.00002117528,0.9947298,0.0005415593,0.0000405939,0.002526226],"study_design_scores_gemma":[0.0002479203,0.0001399076,0.0172205,0.00004443509,0.00001653644,0.00000695208,0.003977141,0.004552159,0.9702548,0.001255144,0.002184979,0.00009950782],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9632863,0.0006989368,0.03550633,0.0001766842,0.00005857906,0.00008187763,0.00006415181,0.000002508528,0.0001246207],"genre_scores_gemma":[0.9973066,0.00006961569,0.002447346,0.0001258667,0.00001201883,0.000004720274,0.00001736015,8.754824e-7,0.00001554539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03402035,"threshold_uncertainty_score":0.213017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0670437112549849,"score_gpt":0.3748008608905625,"score_spread":0.3077571496355777,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}