{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006779303,0.001532401,0.001129774,0.003234701,0.001663531,0.002141508,0.002046913,0.001050647,0.005575093],"category_scores_gemma":[0.02638311,0.0008947733,0.002222116,0.002377288,0.0006171297,0.002761598,0.002278059,0.002010845,0.002544288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006505127,"about_ca_system_score_gemma":0.003192523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003008893,"about_ca_topic_score_gemma":0.009530962,"domain_scores_codex":[0.9971066,0.001064408,0.0002628597,0.0008759308,0.0005579499,0.0001323225],"domain_scores_gemma":[0.994258,0.003282397,0.0005074433,0.001087272,0.0006544871,0.0002104147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009805785,0.0004431537,0.02858151,0.002352548,0.002505892,0.0006607758,0.001852167,0.06286762,0.04693712,0.03209912,0.1101739,0.7105457],"study_design_scores_gemma":[0.0006499177,0.000465291,0.01834253,0.0004178711,0.0007964951,0.001477494,0.0006240426,0.6802777,0.03792845,0.08651704,0.1722603,0.0002427405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01728633,0.000671056,0.9521218,0.000325631,0.0001855448,0.0004396272,0.005984412,0.02136888,0.001616708],"genre_scores_gemma":[0.03342939,0.0002160215,0.9491727,0.0002188428,0.00006475597,0.0008941725,0.01110318,0.003210328,0.001690589],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006779303,"threshold_uncertainty_score":0.03585279,"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."}}