{"id":"W3172130576","doi":"10.1093/sysbio/syab044","title":"A New Pipeline for Removing Paralogs in Target Enrichment Data","year":2021,"lang":"en","type":"article","venue":"Systematic Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; University of Calgary","funders":"","keywords":"Biology; Phylogenetic tree; Pipeline (software); Phylogenomics; Evolutionary biology; Computational biology; Divergence (linguistics); Tree (set theory); Sequence (biology); Phylogenetics; Genetics; Gene; Computer science; Clade; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004534168,0.000137673,0.0003731206,0.00002835557,0.00003725255,0.00001246491,0.0003099449,0.0001325592,0.00000814145],"category_scores_gemma":[0.0004528271,0.0001166903,0.00005740358,0.00006231378,0.00002250346,5.340619e-7,0.0004791702,0.00004253501,0.000004217372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000115416,"about_ca_system_score_gemma":0.0001479816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003238048,"about_ca_topic_score_gemma":0.0001500048,"domain_scores_codex":[0.998675,0.0001355674,0.0004293795,0.0004733572,0.00003739122,0.0002492809],"domain_scores_gemma":[0.9989346,0.00006083539,0.0001141238,0.0007750261,0.00006562134,0.0000497627],"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":[0.00006400942,0.00009952579,0.02236778,0.005712365,0.000288097,0.00001040227,0.0002652754,0.0001499601,0.963736,0.002302581,0.004160213,0.0008438103],"study_design_scores_gemma":[0.03177947,0.003730714,0.03275909,0.009027372,0.001474433,0.001185268,0.01017741,0.05458526,0.5768471,0.1313023,0.1394976,0.007634006],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6207932,0.05491204,0.3177366,0.001660881,0.001390152,0.002387397,0.0003189012,0.00001360913,0.0007872505],"genre_scores_gemma":[0.9707299,0.000128138,0.02777051,0.0002717968,0.0002200671,0.00007408501,0.000400413,0.00001287015,0.000392221],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3868889,"threshold_uncertainty_score":0.4758494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03497564237824111,"score_gpt":0.2969124139618574,"score_spread":0.2619367715836162,"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."}}