{"id":"W4391390112","doi":"10.1093/bioinformatics/btae034","title":"GeNLP: a web tool for NLP-based exploration and prediction of microbial gene function","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Azrieli Foundation; Israel Science Foundation","keywords":"Computer science; MIT License; Context (archaeology); Function (biology); License; Source code; Interface (matter); Semantics (computer science); World Wide Web; Artificial intelligence; Web application; Natural language processing; Programming language; Biology; Genetics","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":[0.0002695362,0.0001296488,0.00011096,0.00009732095,0.00006223588,0.00006085253,0.00006624616,0.0001515409,0.000006818615],"category_scores_gemma":[0.00009371231,0.0001195666,0.00007337843,0.00008992758,0.00004968166,0.00003294927,0.00003706018,0.00006629655,0.000006843504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001447122,"about_ca_system_score_gemma":0.000115429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001173977,"about_ca_topic_score_gemma":0.000002095732,"domain_scores_codex":[0.9992108,0.00001374239,0.0004193936,0.0001079441,0.0001109016,0.0001371925],"domain_scores_gemma":[0.9995472,0.00002284305,0.0001170444,0.0001853579,0.00009312544,0.00003438297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000596433,0.0001012791,0.001164125,0.004998316,0.0002839943,5.861673e-7,0.001221034,0.005857409,0.8824775,0.001358665,0.03549124,0.0664494],"study_design_scores_gemma":[0.0008447273,0.000891924,0.0002795705,0.00007747868,0.00009072254,0.00001437166,0.0001067062,0.8192417,0.07720463,0.0000871953,0.1009683,0.0001927283],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2478262,0.0003429921,0.749429,0.0001642534,0.0006222232,0.0006534818,0.0004447045,0.00008115333,0.0004359432],"genre_scores_gemma":[0.8807448,0.0002163214,0.1151965,0.0003283118,0.0004412277,0.00008452115,0.002634506,0.00004032227,0.0003134954],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8133843,"threshold_uncertainty_score":0.4875785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01115480356403785,"score_gpt":0.2332521643204552,"score_spread":0.2220973607564174,"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."}}