{"id":"W4403012771","doi":"10.1186/s13326-024-00319-w","title":"MeSH2Matrix: combining MeSH keywords and machine learning for biomedical relation classification based on PubMed","year":2024,"lang":"en","type":"article","venue":"Journal of Biomedical Semantics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Craig Newmark Philanthropies; Université de Sousse; Wikimedia Foundation; University of Dayton","keywords":"Computer science; Relation (database); Machine learning; Artificial intelligence; Data science; Information retrieval; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001462706,0.0001664531,0.0002739383,0.000269293,0.0001097249,0.00007102334,0.0001678727,0.0004078518,0.00001320786],"category_scores_gemma":[0.001560782,0.000121633,0.0001547798,0.0002482811,0.0003548429,0.000007524403,0.00004653001,0.0004324751,0.000002274886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003364025,"about_ca_system_score_gemma":0.0001527535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001385871,"about_ca_topic_score_gemma":6.011401e-7,"domain_scores_codex":[0.9982916,0.0001085495,0.0005630461,0.00026315,0.0004858103,0.0002878412],"domain_scores_gemma":[0.9989454,0.0003280388,0.0002164144,0.0001243282,0.0001004686,0.000285409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001182777,0.0007974679,0.003479275,0.0008973172,0.0005915464,0.0001500441,0.0003587793,0.00005331829,0.09916537,0.002386386,0.03328344,0.8576543],"study_design_scores_gemma":[0.002806063,0.004575591,0.005586104,0.0005576383,0.0002459215,0.0002078986,0.0002436574,0.1806463,0.002245132,0.0005745336,0.801934,0.0003772326],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2811708,0.008634362,0.6728935,0.03205745,0.003923554,0.0006043983,0.00005858791,0.000139676,0.0005176679],"genre_scores_gemma":[0.9915389,0.0005003825,0.006634432,0.000240961,0.0007389421,0.00001073955,0.0001501783,0.00002581532,0.0001596652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.857277,"threshold_uncertainty_score":0.496005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02942215229220309,"score_gpt":0.2881921641784086,"score_spread":0.2587700118862056,"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."}}