{"id":"W4404607640","doi":"10.1093/bioinformatics/btae701","title":"Sparse Neighbor Joining: rapid phylogenetic inference using a sparse distance matrix","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Vetenskapsrådet","keywords":"Distance matrix; Python (programming language); Computer science; Sparse matrix; Distance matrices in phylogeny; Phylogenetic tree; Inference; Computation; Matrix (chemical analysis); Set (abstract data type); Tree (set theory); Algorithm; Theoretical computer science; Data mining; Combinatorics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001720654,0.0002806445,0.0002247263,0.00008022985,0.0001301061,0.0001407522,0.0002501943,0.0001422949,0.000027723],"category_scores_gemma":[0.00006740726,0.0002530804,0.0001332229,0.0001879837,0.0001191969,0.000004183316,0.0002246333,0.0001084138,0.00006574015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002743122,"about_ca_system_score_gemma":0.0001806062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008481519,"about_ca_topic_score_gemma":0.000009494375,"domain_scores_codex":[0.9986752,0.00002298808,0.000453219,0.0002772137,0.0001705862,0.0004007797],"domain_scores_gemma":[0.9992318,0.00002892689,0.0001038139,0.0004455385,0.00007493351,0.0001149449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001992324,0.000208208,0.01213273,0.001674677,0.001074516,0.00006002254,0.00357848,0.008027098,0.8821164,0.006721631,0.01159123,0.07261579],"study_design_scores_gemma":[0.001315778,0.0009604467,0.005018626,0.0004052443,0.0003322067,0.0001894929,0.001185615,0.2674621,0.06868645,0.001029641,0.6513681,0.002046277],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9334868,0.01855364,0.04205439,0.0001184292,0.001054295,0.0004299178,0.0001987599,0.00004123308,0.004062604],"genre_scores_gemma":[0.9761104,0.001565074,0.02136079,0.0001917222,0.0003200356,0.00001607719,0.0000466879,0.00003685428,0.0003523897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.81343,"threshold_uncertainty_score":0.9999921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03048351482630215,"score_gpt":0.2807530257646901,"score_spread":0.250269510938388,"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."}}