{"id":"W3210203575","doi":"10.1101/2021.10.21.465343","title":"NAToRA, a relatedness-pruning method to minimize the loss of dataset size in genetic and omics analyses","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Ministério da Saúde; Ministério da Educação; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Pruning; Computer science; Heuristics; Metric (unit); Pipeline (software); Data mining; Software; Reduction (mathematics); Machine learning; Visualization; Artificial intelligence; Mathematics; Biology","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":[0.005626092,0.001206893,0.0009348539,0.003129052,0.001370211,0.001709217,0.001814075,0.0009439119,0.003717992],"category_scores_gemma":[0.01804787,0.000729696,0.001565969,0.002072356,0.0005538907,0.002415311,0.002093447,0.001454488,0.001666256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006127146,"about_ca_system_score_gemma":0.002329524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002640761,"about_ca_topic_score_gemma":0.008284979,"domain_scores_codex":[0.9979621,0.0007942496,0.0001528141,0.0005406089,0.00045461,0.00009561129],"domain_scores_gemma":[0.9953949,0.002503081,0.0004187762,0.0008573186,0.0006056344,0.0002203169],"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":[0.0009105845,0.0004163298,0.01925818,0.001478624,0.001533631,0.0005298668,0.001266595,0.08890147,0.05407324,0.03095517,0.06900891,0.7316673],"study_design_scores_gemma":[0.0003245387,0.0003055517,0.009312087,0.0002088735,0.000355748,0.0007576844,0.0003008357,0.8311318,0.03258478,0.05017669,0.07441977,0.0001217613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02198241,0.0006358402,0.9572858,0.0002982386,0.0001313756,0.0002326673,0.00258489,0.01540354,0.001445258],"genre_scores_gemma":[0.04510038,0.0001708189,0.9458163,0.0001512944,0.00005597932,0.0003915386,0.005068561,0.001845526,0.001399492],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005626092,"threshold_uncertainty_score":0.02975398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01750276940466674,"score_gpt":0.2734390846188721,"score_spread":0.2559363152142053,"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."}}