{"id":"W6958479792","doi":"10.6084/m9.figshare.26600293.v1","title":"Additional file 2 of MetaPro: a scalable and reproducible data processing and analysis pipeline for metatranscriptomic investigation of microbial communities","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Pipeline (software); Subspecies; Annotation; Sample (material); Leuconostoc; Scalability","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003365627,0.002496095,0.002002189,0.003203088,0.001605345,0.002649296,0.004216861,0.001760146,0.6638069],"category_scores_gemma":[0.01513332,0.001282164,0.001840439,0.004496123,0.0006565934,0.002580681,0.002506618,0.002358217,0.1796055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001108253,"about_ca_system_score_gemma":0.002798118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004273419,"about_ca_topic_score_gemma":0.007889957,"domain_scores_codex":[0.998439,0.0001635725,0.0002180943,0.0005293773,0.0004161951,0.0002337756],"domain_scores_gemma":[0.9923643,0.004239845,0.0006291157,0.001025376,0.001230172,0.0005112032],"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":[0.001005453,0.0001499559,0.003583841,0.004487522,0.0001547632,0.0001679367,0.0001580228,0.001066182,0.00451834,0.0009917443,0.9711138,0.01260241],"study_design_scores_gemma":[0.004760216,0.0005437602,0.02442553,0.002169591,0.0003917986,0.0007216142,0.0004987553,0.00905655,0.01937016,0.01209335,0.9254748,0.0004937872],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.0003002681,0.00001995285,0.002128265,0.00006340888,0.00004920776,0.000107947,0.9918067,0.004951342,0.0005728848],"genre_scores_gemma":[0.005044497,0.00005998588,0.01597722,0.0003852717,0.00007780405,0.001328934,0.9672812,0.007189504,0.002655653],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.6638069,"threshold_uncertainty_score":0.4795386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05768414043885957,"score_gpt":0.2667832536324539,"score_spread":0.2090991131935943,"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."}}