{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001080603,0.00008734728,0.00007064061,0.00003011825,0.0007397391,0.00002041901,0.0004524472,0.00006861086,0.000007277807],"category_scores_gemma":[0.00002255108,0.00009587113,0.00005355168,0.000122945,0.0000463661,9.938673e-7,0.0008563192,0.0003569725,7.461937e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002940744,"about_ca_system_score_gemma":0.00005824306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001591875,"about_ca_topic_score_gemma":0.0001056221,"domain_scores_codex":[0.9994535,0.00006738712,0.0001115183,0.0001656886,0.00007267909,0.000129154],"domain_scores_gemma":[0.9992372,0.000009067172,0.00006559774,0.0006090101,0.00005775368,0.00002136696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002039419,0.00003203909,0.0007900088,0.00000270667,0.00003635768,3.142732e-7,0.0001658268,0.0003873087,0.9941237,0.00004784135,0.0003509599,0.004042542],"study_design_scores_gemma":[0.001851129,0.0003466861,0.03126793,0.0000217793,0.0003188393,0.0002687525,0.004330664,0.01198439,0.1388745,0.0001401487,0.8093042,0.00129095],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8999033,0.09879679,0.0002668797,0.0001759622,0.0003106319,0.0001181415,0.00003150405,0.000008338498,0.0003884657],"genre_scores_gemma":[0.9916247,0.0001440349,0.00734114,0.0004231414,0.0001328826,0.00002705017,0.0001718068,0.00001783048,0.000117391],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8552492,"threshold_uncertainty_score":0.568955,"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."}}