{"id":"W4226247981","doi":"10.1016/j.csbj.2022.04.009","title":"NAToRA, a relatedness-pruning method to minimize the loss of dataset size in genetic and omics analyses","year":2022,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"National Institute of Neurological Disorders and Stroke; Ministério da Saúde; Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Universidade Federal de Minas Gerais; Ministério da Educação; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; National Research Council","keywords":"Metric (unit); Pruning; Data mining; Computer science; Heuristics; Pipeline (software); Software; Principal component analysis; Visualization; Reduction (mathematics); Machine learning; Artificial intelligence; Pattern recognition (psychology); Biology; Mathematics; Engineering","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":[0.0002457328,0.00009112447,0.0001383512,0.00008270706,0.0002367324,0.00002030495,0.0001896531,0.00009505644,0.000009064504],"category_scores_gemma":[0.00003832072,0.00006767777,0.00002608121,0.0001475235,0.0001335984,0.000003838981,0.0003568232,0.0003027858,1.262149e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001187657,"about_ca_system_score_gemma":0.00004679468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008695156,"about_ca_topic_score_gemma":0.000002704066,"domain_scores_codex":[0.9992871,0.00007597975,0.0002815115,0.0001393455,0.00008729862,0.0001287309],"domain_scores_gemma":[0.9996312,0.00006208532,0.0001392989,0.00009658223,0.0000298726,0.00004099252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008246449,0.00004644319,0.02086498,0.00005739663,0.0006211919,0.00008338621,0.0011653,0.737836,0.0957732,0.005211652,0.003424312,0.1340915],"study_design_scores_gemma":[0.006640808,0.001704024,0.3460662,0.0000623369,0.000237482,0.02140512,0.005901538,0.4157956,0.01036098,0.1728949,0.01753663,0.001394311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9711512,0.00144455,0.02511017,0.001941619,0.00007497308,0.00007897022,0.0001915741,0.000002492653,0.000004396013],"genre_scores_gemma":[0.940545,0.00009110352,0.05880583,0.0004254043,0.00002660669,0.000002845951,0.00009292393,0.000004595629,0.000005718956],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3252013,"threshold_uncertainty_score":0.275982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01300612834219888,"score_gpt":0.2952613242771608,"score_spread":0.282255195934962,"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."}}