{"id":"W4297991272","doi":"10.1371/journal.pone.0274260","title":"MetaWorks: A flexible, scalable bioinformatic pipeline for high-throughput multi-marker biodiversity assessments","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Government of Canada; Ontario Genomics; Genome Canada","keywords":"Computer science; Scalability; Pipeline (software); Workflow; Computational biology; Biology; Classifier (UML); Data science; Database; Artificial intelligence","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":[0.003949113,0.003824994,0.001586436,0.003076639,0.001577583,0.00358899,0.004883084,0.001653193,0.02245011],"category_scores_gemma":[0.004732314,0.002618302,0.003345677,0.002131969,0.0007291141,0.003346671,0.003950554,0.003958264,0.0184424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001424882,"about_ca_system_score_gemma":0.003179246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003185055,"about_ca_topic_score_gemma":0.004505494,"domain_scores_codex":[0.9979972,0.0002453007,0.0001810503,0.0007171223,0.0006598952,0.0001992716],"domain_scores_gemma":[0.9979977,0.0005765414,0.0002577816,0.0004650563,0.0004254293,0.0002773913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003640729,0.0003878798,0.00684379,0.002872072,0.001448827,0.001014058,0.001167161,0.01795385,0.17976,0.008046483,0.4974256,0.2794395],"study_design_scores_gemma":[0.001619025,0.0005735639,0.01383422,0.0005871984,0.0007283017,0.001240863,0.0003979708,0.2688753,0.2068416,0.04049942,0.463678,0.001124593],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.007490667,0.000576391,0.4493301,0.0004873105,0.000312739,0.0006537598,0.03960197,0.4964016,0.005145452],"genre_scores_gemma":[0.0460529,0.0007440573,0.7319373,0.001150876,0.0001869807,0.002649786,0.1344822,0.07339356,0.009402321],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02245011,"threshold_uncertainty_score":0.0751031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05554969787539162,"score_gpt":0.2388530373279584,"score_spread":0.1833033394525668,"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."}}