{"id":"W3173187119","doi":"10.1186/s12859-021-04267-5","title":"Pheniqs 2.0: accurate, high-performance Bayesian decoding and confidence estimation for combinatorial barcode indexing","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; New York University Abu Dhabi; New York University","keywords":"Barcode; Computer science; Decoding methods; Probabilistic logic; Benchmark (surveying); Data mining; Algorithm; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001395886,0.0001411757,0.0001531216,0.0000206112,0.0001940692,0.00007229337,0.00009691895,0.0001059443,0.0000027378],"category_scores_gemma":[0.000164605,0.0001419279,0.00003741781,0.00006111422,0.00005506667,0.000006645237,0.0001271071,0.00004868148,0.000001982134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001098129,"about_ca_system_score_gemma":0.0001199834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003165557,"about_ca_topic_score_gemma":0.0000120442,"domain_scores_codex":[0.9992296,0.00001421179,0.0002995044,0.0001590123,0.00008534479,0.0002123191],"domain_scores_gemma":[0.9994375,0.00004902008,0.0001199633,0.0001984015,0.0001362146,0.00005896672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00118331,0.0004336293,0.08475633,0.006821495,0.00110241,0.000007862302,0.005755998,0.07101467,0.5757601,0.07622306,0.006666555,0.1702746],"study_design_scores_gemma":[0.002696528,0.0003796554,0.009718436,0.00009607351,0.00007594144,0.00004610053,0.0007160339,0.7455002,0.2328732,0.002992205,0.00427844,0.0006271375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6957377,0.0004425317,0.3026395,0.00004149324,0.0004418817,0.0002434074,0.00003700721,0.00000713618,0.0004094301],"genre_scores_gemma":[0.8373924,0.0003359244,0.1618778,0.0001052906,0.000118524,0.00002580793,0.00008460895,0.00001178086,0.00004787713],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6744855,"threshold_uncertainty_score":0.5787653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.016237025944968,"score_gpt":0.251207369551136,"score_spread":0.234970343606168,"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."}}