{"id":"W6920825341","doi":"10.6084/m9.figshare.26600290.v1","title":"Additional file 1 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); Scalability; Chord (peer-to-peer); Diagram; Scalable Vector Graphics","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":[0.003395705,0.002143535,0.001656976,0.002967004,0.001558676,0.002491707,0.003896941,0.001579191,0.6704841],"category_scores_gemma":[0.01885062,0.001201045,0.001702716,0.004173033,0.0006547487,0.002466106,0.002504115,0.002135182,0.1812863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001169735,"about_ca_system_score_gemma":0.00291422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003885453,"about_ca_topic_score_gemma":0.008096318,"domain_scores_codex":[0.9984803,0.000180316,0.0002045066,0.0005092751,0.0004088013,0.0002169046],"domain_scores_gemma":[0.9910584,0.005377969,0.0006679613,0.001242385,0.001131479,0.0005218228],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008336364,0.0001098193,0.003558026,0.003779781,0.0001448475,0.0001531679,0.000148454,0.001029081,0.003332473,0.001106107,0.9735823,0.01222227],"study_design_scores_gemma":[0.004898222,0.0005042509,0.02580437,0.001788955,0.000383185,0.0007949771,0.0004558298,0.008377971,0.0161511,0.0134054,0.9269791,0.0004567831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0003250162,0.00002085032,0.00261227,0.00007274057,0.00005034274,0.00009995478,0.9904386,0.005743614,0.0006366511],"genre_scores_gemma":[0.006328977,0.00006523481,0.01915231,0.0004216443,0.00009591741,0.001333744,0.9611155,0.008450123,0.003036663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6704841,"threshold_uncertainty_score":0.4700145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05956878720666798,"score_gpt":0.2673059779747815,"score_spread":0.2077371907681135,"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."}}