{"id":"W4281858631","doi":"10.1101/2022.06.03.494701","title":"Metagenomics vs. total RNA sequencing: most accurate data-processing tools, microbial identification accuracy, and implications for freshwater assessments","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Canada First Research Excellence Fund; University of Guelph","keywords":"Metagenomics; Identification (biology); Computational biology; Biology; Workflow; Deep sequencing; RNA-Seq; Microbial population biology; Computer science; Ecology; Genetics; Genome; Gene; Transcriptome; Database","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01556432,0.001365533,0.001229957,0.001531879,0.0007228853,0.004112772,0.001030497,0.001379326,0.001053608],"category_scores_gemma":[0.02590914,0.0004890602,0.0008219194,0.001434084,0.001094708,0.002934295,0.001477269,0.001568663,0.0006862682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001004479,"about_ca_system_score_gemma":0.001280747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001776535,"about_ca_topic_score_gemma":0.002225077,"domain_scores_codex":[0.989111,0.004166912,0.0008264618,0.002085991,0.003144976,0.0006646807],"domain_scores_gemma":[0.9867959,0.006133629,0.001757067,0.001284569,0.003643079,0.0003857525],"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":[0.00239641,0.0003670483,0.09935997,0.002023658,0.0005670829,0.0003249893,0.0006709422,0.015478,0.632883,0.003941805,0.003469361,0.2385179],"study_design_scores_gemma":[0.00006323151,0.000719503,0.09462479,0.0007207192,0.0005866817,0.000398052,0.001125013,0.06433063,0.8081529,0.01475386,0.0142429,0.0002816626],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6668974,0.01995883,0.2953766,0.005634085,0.0007913511,0.0003191897,0.004178422,0.001846026,0.004998077],"genre_scores_gemma":[0.796523,0.00344045,0.1944541,0.000881612,0.0001676627,0.0001623141,0.002637723,0.000620094,0.001112954],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01556432,"threshold_uncertainty_score":0.082313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05890559125931814,"score_gpt":0.2949368002865261,"score_spread":0.2360312090272079,"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."}}