{"id":"W3022126255","doi":"10.1101/2020.05.06.058180","title":"Cancer phylogenetic tree inference at scale from 1000s of single cell genomes","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; University of British Columbia","funders":"","keywords":"Phylogenetic tree; Inference; Scalability; Phylogenetic network; Markov chain Monte Carlo; Tree (set theory); Computational biology; Computer science; Bayesian inference; Genome; Bayesian probability; Markov chain; Biology; Evolutionary biology; Theoretical computer science; Artificial intelligence; Machine learning; Mathematics; Genetics; Gene","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":[0.0001017937,0.0005671156,0.0006532563,0.00007024007,0.0001047959,0.00004692344,0.0006849151,0.0005016223,0.00004870252],"category_scores_gemma":[0.00004930064,0.0006202175,0.0002330204,0.0001547145,0.0002014192,0.000001242076,0.001588157,0.0002328994,0.00002044006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009694336,"about_ca_system_score_gemma":0.0004205818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001980046,"about_ca_topic_score_gemma":0.00008800802,"domain_scores_codex":[0.997532,0.00008550665,0.0005319521,0.001167534,0.0002406169,0.000442462],"domain_scores_gemma":[0.9978011,0.0000310266,0.0004858491,0.001127259,0.0003272216,0.0002275323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005332072,0.0001059418,0.05087653,0.0001672549,0.0002508156,0.000004070819,0.00002231035,0.0002199344,0.9480363,0.000003751886,0.0002495688,0.00001024691],"study_design_scores_gemma":[0.0004018192,0.0001377947,0.1237312,0.00006649028,0.0001578493,3.154726e-9,0.00000355866,0.00004086941,0.8673155,0.000003837029,0.00756742,0.0005736615],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9697398,0.02728016,0.0002300485,0.0001154361,0.0006006105,0.0004103961,0.001554779,0.00002035608,0.00004844717],"genre_scores_gemma":[0.9908945,0.004798052,0.003198139,0.0001815184,0.0006572015,0.0001345063,0.000003578504,0.0001149754,0.00001756228],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08072072,"threshold_uncertainty_score":0.9996249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01643681847927837,"score_gpt":0.2171507836919584,"score_spread":0.20071396521268,"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."}}