{"id":"W4394745991","doi":"10.1093/bioinformatics/btae182","title":"Pacybara: accurate long-read sequencing for barcoded mutagenized allelic libraries","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Barcode; Identification (biology); Biology; Genetics; Computational biology; Identifier; DNA sequencing; Computer science; Gene; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0001167525,0.0001810817,0.0001434349,0.00004153831,0.0001109479,0.0002484534,0.0001953555,0.0001245941,0.0000321037],"category_scores_gemma":[0.00009114181,0.0001510847,0.0001746862,0.0000810539,0.00005682206,0.0000230311,0.0001065271,0.00006847161,0.00004572844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001941116,"about_ca_system_score_gemma":0.0003171313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006229709,"about_ca_topic_score_gemma":0.00001016109,"domain_scores_codex":[0.9991266,0.00001118453,0.0003115713,0.0001769699,0.00009045284,0.0002832307],"domain_scores_gemma":[0.9994686,0.00003047495,0.00005854849,0.0002737895,0.0000595556,0.0001089892],"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":[0.00178941,0.000419894,0.001256685,0.01174734,0.004170876,0.0003677502,0.01382684,0.004927854,0.4315339,0.03248059,0.2269939,0.270485],"study_design_scores_gemma":[0.003103159,0.0009831985,0.0006700741,0.0004265963,0.000400331,0.0002830541,0.003332332,0.1695711,0.1553001,0.003384717,0.6604547,0.002090685],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8778651,0.01213585,0.1019096,0.0007725779,0.001292985,0.001308863,0.000890665,0.0002467656,0.003577485],"genre_scores_gemma":[0.9743758,0.0007674485,0.01983204,0.0008391057,0.00047962,0.00009153974,0.001495934,0.00005978122,0.002058754],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4334608,"threshold_uncertainty_score":0.6161054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02109216297062837,"score_gpt":0.2625775321882256,"score_spread":0.2414853692175972,"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."}}