{"id":"W4384626667","doi":"10.1093/gbe/evad129","title":"A Machine Learning Framework Identifies Plastid-Encoded Proteins Harboring C3 and C4 Distinguishing Sequence Information","year":2023,"lang":"en","type":"article","venue":"Genome Biology and Evolution","topic":"Photosynthetic Processes and Mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Plastid; Genome; Clade; Convergent evolution; Phylogenetics; Computational biology; Evolutionary biology; Gene; Genetics; Chloroplast","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002676745,0.0001083556,0.00009946452,0.00005342236,0.0002854034,0.00003644113,0.0000695543,0.0001783753,0.000003497206],"category_scores_gemma":[0.0005091825,0.000101978,0.00001935548,0.0001062492,0.00008092137,0.0000205736,0.0001487667,0.000134538,0.000009232773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001353651,"about_ca_system_score_gemma":0.00002926696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008125455,"about_ca_topic_score_gemma":0.00001611034,"domain_scores_codex":[0.9993399,0.0000380503,0.0001464213,0.0002120514,0.00004423541,0.00021937],"domain_scores_gemma":[0.9997117,0.00001892589,0.00008393018,0.0000898363,0.00004397526,0.00005163767],"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":[0.00004491774,0.000004548479,0.00480301,0.0000652126,0.00001777884,9.225627e-7,0.0002510442,0.00006837244,0.9917015,0.001893964,0.000003663192,0.001145051],"study_design_scores_gemma":[0.002903135,0.003021697,0.1397755,0.0006409034,0.0002064994,0.0003736613,0.003369863,0.03834527,0.6279643,0.1062227,0.07445981,0.00271663],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9555254,0.0006760796,0.04321569,0.00007679026,0.0001527375,0.0001439126,0.00003274931,0.00005629172,0.0001203435],"genre_scores_gemma":[0.9980815,0.0008790633,0.0005244529,0.00003657179,0.000107919,0.00003686075,0.000257355,0.000006814202,0.00006947669],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3637372,"threshold_uncertainty_score":0.4158544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01085697419772201,"score_gpt":0.2472168135216643,"score_spread":0.2363598393239423,"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."}}