{"id":"W6958327492","doi":"10.6084/m9.figshare.14623466.v1","title":"Additional file 1 of Profile hidden Markov model sequence analysis can help remove putative pseudogenes from DNA barcoding and metabarcoding datasets","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Seed and Plant Biochemistry","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"DNA barcoding; Pseudogene; Hidden Markov model; Sequence (biology); Sequence analysis; Markov chain","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":[0.001904918,0.001662326,0.001535597,0.003163717,0.001444856,0.001929291,0.002857562,0.001632548,0.775875],"category_scores_gemma":[0.0115824,0.0008714304,0.001232565,0.004495223,0.0004369573,0.002528134,0.001767954,0.001733954,0.2814456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001019993,"about_ca_system_score_gemma":0.001696394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005196413,"about_ca_topic_score_gemma":0.01080975,"domain_scores_codex":[0.9992791,0.0001188857,0.00008256235,0.000239487,0.0001526654,0.0001272796],"domain_scores_gemma":[0.9921733,0.005595905,0.000374873,0.000683205,0.0008666404,0.0003061163],"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":[0.0002563313,0.0000833602,0.001589639,0.001746997,0.00005101406,0.00007579147,0.00007925589,0.0006834064,0.000945457,0.001163144,0.9855695,0.007756114],"study_design_scores_gemma":[0.001592601,0.0001688073,0.01284269,0.001075676,0.0001704623,0.0003952168,0.0003085437,0.004222795,0.004676889,0.01245473,0.961905,0.0001865094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001765698,0.00001501603,0.0009721675,0.00005339403,0.00002779286,0.00003055273,0.9964033,0.001489204,0.0008318574],"genre_scores_gemma":[0.002814273,0.00006177805,0.005862398,0.0002257595,0.00003886818,0.0003829881,0.9850655,0.002789773,0.002758707],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.775875,"threshold_uncertainty_score":0.3196871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0520281364726817,"score_gpt":0.2365371487466741,"score_spread":0.1845090122739924,"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."}}