{"id":"W4392584688","doi":"10.1016/j.xgen.2024.100522","title":"Revealing the grammar of small RNA secretion using interpretable machine learning","year":2024,"lang":"en","type":"article","venue":"Cell Genomics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McGill University; McGill Genome Centre","funders":"University of California, San Francisco","keywords":"RNA; Computational biology; Secretion; Biology; Non-coding RNA; Interactome; Artificial intelligence; Computer science; Genetics; Gene; Biochemistry","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":[0.0003658995,0.00009537214,0.00009136984,0.0000248899,0.00007253217,0.00003563649,0.0001488374,0.00008871928,0.00002055753],"category_scores_gemma":[0.0000260819,0.00007517269,0.00008748254,0.00005181642,0.00002740954,0.000001888643,0.00008883598,0.0001029528,0.00000577765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001659256,"about_ca_system_score_gemma":0.00004795259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004600354,"about_ca_topic_score_gemma":0.000005688122,"domain_scores_codex":[0.9993982,0.00007233759,0.0001611306,0.0001867719,0.00004633553,0.0001352224],"domain_scores_gemma":[0.9996817,0.00001982559,0.00006055188,0.0001884244,0.00002365894,0.00002581128],"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":[0.00002003518,0.000005076379,0.00002077407,0.00006237624,0.0000223351,0.000001288996,0.0001401066,0.002224308,0.9922086,0.00008370254,0.00001324089,0.005198156],"study_design_scores_gemma":[0.00005219425,0.00006369847,0.000002124066,0.00003641872,0.0000317175,0.000009792067,0.0000813435,0.02487474,0.948809,0.0002224372,0.02572317,0.00009338519],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8712577,0.008885354,0.1182375,0.00002948335,0.0002557549,0.0001319132,0.000007351232,0.00001252695,0.001182471],"genre_scores_gemma":[0.9920286,0.0007187453,0.005898482,0.00004166483,0.0001652108,0.000004374224,0.00003403203,0.00002997919,0.001078927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1207709,"threshold_uncertainty_score":0.3065453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01448239665668937,"score_gpt":0.2199959484210489,"score_spread":0.2055135517643595,"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."}}