{"id":"W4298006192","doi":"10.1038/s41467-022-33397-4","title":"Deciphering microbial gene function using natural language processing","year":2022,"lang":"en","type":"article","venue":"Nature Communications","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Azrieli Foundation; Israel Science Foundation","keywords":"Function (biology); Computational biology; Natural (archaeology); Computer science; Gene; Biology; Genetics; Paleontology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000885499,0.0007369288,0.0004281666,0.001657521,0.0004198044,0.00134718,0.0006483396,0.0008152424,0.0009085092],"category_scores_gemma":[0.003953007,0.0002123076,0.0008995715,0.001032943,0.0008322365,0.002009817,0.0006775948,0.001118235,0.0007619555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006706278,"about_ca_system_score_gemma":0.000969044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002539045,"about_ca_topic_score_gemma":0.002782675,"domain_scores_codex":[0.9995376,0.000136483,0.00003537932,0.0001438686,0.0001151552,0.00003156814],"domain_scores_gemma":[0.9984306,0.001104368,0.000157542,0.0001436643,0.0001322463,0.00003160055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005493721,0.0004994701,0.02404001,0.001167409,0.0002261312,0.001038238,0.0007094387,0.2256792,0.160968,0.04904718,0.007441632,0.528634],"study_design_scores_gemma":[0.00001365947,0.00006556547,0.002124995,0.00005519134,0.00002873125,0.0002215263,0.0002071037,0.8846729,0.02096931,0.08608357,0.005522449,0.00003512641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.13666,0.001477778,0.8486124,0.002255594,0.000103228,0.0001023481,0.003835332,0.00416967,0.002783661],"genre_scores_gemma":[0.5298353,0.001384848,0.4607374,0.0006527294,0.0001153105,0.0001581879,0.006039793,0.0002012297,0.000875071],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002539045,"threshold_uncertainty_score":0.005048513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01421903207619403,"score_gpt":0.2776656968467657,"score_spread":0.2634466647705717,"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."}}