{"id":"W2741011090","doi":"10.1111/eva.12524","title":"Applications of random forest feature selection for fine‐scale genetic population assignment","year":2017,"lang":"en","type":"article","venue":"Evolutionary Applications","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":134,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland; Fisheries and Oceans Canada; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Atlantic Canada Opportunities Agency","keywords":"Random forest; Selection (genetic algorithm); Biology; Oncorhynchus; Population; Salmo; SNP; Statistics; Artificial intelligence; Single-nucleotide polymorphism; Computer science; Mathematics; Genetics; Fishery; Fish <Actinopterygii>; Genotype","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007478666,0.0001235991,0.000122089,0.00003509186,0.0006222886,0.00001821402,0.0002953474,0.0001451035,0.00001375741],"category_scores_gemma":[0.00002471133,0.0001305819,0.0001019892,0.00005569539,0.0001101977,0.000007338605,0.00005755021,0.00005675185,0.000006373325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002285355,"about_ca_system_score_gemma":0.0000638319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000374329,"about_ca_topic_score_gemma":0.0001245648,"domain_scores_codex":[0.9991727,0.00002067579,0.0002135575,0.0003247992,0.0001122498,0.0001559818],"domain_scores_gemma":[0.9989347,0.0000224707,0.0002360941,0.0005924396,0.0001533064,0.00006095938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00069432,0.001411792,0.5998257,0.0003100465,0.0003417389,4.280614e-8,0.00009914964,0.04183652,0.1216373,0.1000267,0.04029714,0.09351952],"study_design_scores_gemma":[0.0009539613,0.0001628603,0.8661138,0.000007530273,0.0000675228,0.000007205844,0.00001331071,0.0006405889,0.002694977,0.02137019,0.1077808,0.0001872053],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04292915,0.000542204,0.9531854,0.0003373529,0.00006315993,0.001864042,0.0001783651,0.00001863114,0.0008816856],"genre_scores_gemma":[0.8589449,0.00002200768,0.1351853,0.00002044813,0.0004844248,0.003107942,0.000674503,0.00001783677,0.00154263],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8180001,"threshold_uncertainty_score":0.5324977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006527567886376638,"score_gpt":0.2509173471517909,"score_spread":0.2443897792654143,"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."}}