{"id":"W2793660201","doi":"10.1101/276345","title":"Imputing missing distances in molecular phylogenetics","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Distance matrix; Algorithm; Mathematics; Expectation–maximization algorithm; Least-squares function approximation; Imputation (statistics); Distance matrices in phylogeny; Function (biology); Computer science; Data mining; Maximum likelihood; Statistics; Combinatorics; Biology; Evolutionary biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04116251,0.001529576,0.003808492,0.00508859,0.00324205,0.004302935,0.005538857,0.00434516,0.00374057],"category_scores_gemma":[0.1576285,0.002076721,0.002907489,0.007816225,0.004289544,0.005301488,0.005782505,0.007978614,0.002232449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001774428,"about_ca_system_score_gemma":0.002388844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001994827,"about_ca_topic_score_gemma":0.002463482,"domain_scores_codex":[0.9689236,0.0220798,0.001167845,0.004216135,0.002858715,0.000753884],"domain_scores_gemma":[0.8851225,0.08903521,0.006719665,0.01281397,0.004672294,0.001636278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008882307,0.0003430632,0.05176859,0.002011483,0.002464027,0.002190183,0.00222497,0.3542142,0.01165064,0.1791288,0.01884698,0.3742689],"study_design_scores_gemma":[0.00008967292,0.0001249604,0.00512175,0.0003721411,0.0002134517,0.0009246626,0.0002639123,0.5425801,0.009717955,0.428153,0.0122224,0.0002160952],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008969842,0.0005961667,0.9881706,0.0005762334,0.0001854612,0.00002880985,0.0003532058,0.0007561119,0.000363533],"genre_scores_gemma":[0.1530709,0.000632133,0.8421499,0.0005041015,0.0002673305,0.0001692967,0.001478197,0.0007747922,0.0009533642],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04116251,"threshold_uncertainty_score":0.2176908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009732759988059446,"score_gpt":0.2223632810933747,"score_spread":0.2126305211053152,"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."}}