{"id":"W4394054680","doi":"10.5281/zenodo.7855544","title":"Genomic language model predicts protein co-regulation and function","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Function (biology); Computational biology; Biology; Genetics; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007724296,0.003562964,0.001162458,0.002392828,0.0007791233,0.00161002,0.003073351,0.002948667,0.01954729],"category_scores_gemma":[0.003537098,0.0006610382,0.002921996,0.002509179,0.0004758806,0.001020052,0.00090085,0.001930996,0.01745075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00185853,"about_ca_system_score_gemma":0.00197419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03131425,"about_ca_topic_score_gemma":0.05574327,"domain_scores_codex":[0.9993187,0.0001146814,0.00004067882,0.0003129437,0.0001177941,0.00009518302],"domain_scores_gemma":[0.9990113,0.0004620773,0.00007653331,0.0002032559,0.0001534853,0.00009323251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006603544,0.0002251442,0.006726475,0.001496569,0.00036913,0.0002603979,0.00004226899,0.01454268,0.001653706,0.0023097,0.9617651,0.009948444],"study_design_scores_gemma":[0.004125681,0.0003731376,0.03138068,0.0008010157,0.00106819,0.001555746,0.000277536,0.2017062,0.008611398,0.02771425,0.7221212,0.000264973],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.006573231,0.0004004054,0.001442072,0.0004088814,0.0000708548,0.00004636258,0.9864245,0.003299776,0.001333992],"genre_scores_gemma":[0.007446705,0.000107336,0.00203113,0.000138275,0.00001049976,0.0001013751,0.9894053,0.0001160555,0.0006432671],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03131425,"threshold_uncertainty_score":0.0653922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647956416855299,"score_gpt":0.2308846116420065,"score_spread":0.2144050474734535,"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."}}