{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00001992183,0.0001153572,0.000188992,0.00001116123,0.0001056755,0.00004559778,0.0001398849,0.00007114791,0.9408866],"category_scores_gemma":[0.0008304901,0.00005785541,0.00008630991,0.0003550829,0.00001282764,0.0000844524,0.000130719,0.0000738536,0.00004474109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000114348,"about_ca_system_score_gemma":0.00003497598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005710298,"about_ca_topic_score_gemma":0.0001457134,"domain_scores_codex":[0.9991611,0.00003755726,0.0001421048,0.0003342894,0.0001745827,0.0001503735],"domain_scores_gemma":[0.9984763,0.001180722,0.0001084994,0.00006028115,0.00009004587,0.00008411194],"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":[0.000004299804,0.00001154306,0.00002127571,0.00001673826,0.00009624707,0.00002315359,0.00002312161,0.000003295238,0.1299574,2.798526e-7,0.860393,0.00944961],"study_design_scores_gemma":[0.0003257041,0.0000705284,0.03466019,0.003627586,0.0005672736,0.00009531981,0.002874559,0.07366354,0.7482337,0.000473026,0.133649,0.001759546],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01669262,0.0001230728,1.010151e-7,0.0000669471,0.000003392868,0.00004309148,0.9825597,0.00001576067,0.0004953588],"genre_scores_gemma":[0.05234113,0.000005207752,0.001895529,0.00008414029,0.00007673561,0.00006280946,0.9452469,8.045945e-7,0.0002867713],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9408419,"threshold_uncertainty_score":0.2359275,"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."}}