{"id":"W2771761215","doi":"10.1186/s12859-019-2916-0","title":"A multivariate Poisson-log normal mixture model for clustering transcriptome sequencing data","year":2019,"lang":"en","type":"preprint","venue":"BMC Bioinformatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Cluster analysis; Mixture model; Overdispersion; Markov chain Monte Carlo; Computer science; Multivariate statistics; Expectation–maximization algorithm; Context (archaeology); Poisson distribution; Count data; Data mining; Mathematics; Statistics; Biology; Artificial intelligence; Machine learning; Bayesian probability","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001900454,0.0006867708,0.0008601139,0.0002843667,0.0001999478,0.0007493717,0.005640457,0.0008111536,0.000002890828],"category_scores_gemma":[0.0001437433,0.0006177741,0.0003258239,0.0002058573,0.00005084407,0.00179201,0.004693283,0.0009795094,0.00002204266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001911731,"about_ca_system_score_gemma":0.001236244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004376829,"about_ca_topic_score_gemma":0.00004809812,"domain_scores_codex":[0.9964255,0.00009627538,0.001185022,0.0009019066,0.0005214958,0.0008697613],"domain_scores_gemma":[0.9943815,0.0002195368,0.0006704928,0.004276733,0.0002139434,0.000237763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001293792,0.0001219032,0.00002574707,0.01496027,0.000350585,0.000008203289,0.0358384,0.806761,0.0006531903,0.02563735,0.006349297,0.1091646],"study_design_scores_gemma":[0.0007851018,0.00003580175,0.000007149933,0.0003936354,0.00008050828,0.00002809346,0.00004573756,0.9872828,0.00006433005,0.01000346,0.0004857765,0.0007876818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004650167,0.0002085917,0.9931704,0.0002520675,0.002006643,0.001746493,0.0009964986,0.0003411076,0.001231666],"genre_scores_gemma":[0.002961421,0.00004230287,0.9947747,0.0007555441,0.0002090815,0.00007713256,0.0004865963,0.00005697077,0.0006362276],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1805217,"threshold_uncertainty_score":0.9997395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1182697790224262,"score_gpt":0.3252396361446816,"score_spread":0.2069698571222554,"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."}}