{"id":"W3185496276","doi":"10.1101/gr.268599.120","title":"Sequence-based correction of barcode bias in massively parallel reporter assays","year":2021,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute; National Institutes of Health; School of Medicine, New York University; York University","keywords":"Biology; Reporter gene; Regulatory sequence; Computational biology; Gene; Massively parallel; Sequence (biology); Identification (biology); Upstream (networking); DNA sequencing; Genetics; Barcode; Regulation of gene expression; Gene expression; Computer science; Parallel computing","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":[0.0008228317,0.00009159801,0.0001458442,0.0001166488,0.0000560567,0.00002472542,0.0001706703,0.0001426867,0.00006660823],"category_scores_gemma":[0.0003008031,0.00009585055,0.00007247231,0.0002960617,0.00009940652,0.000002188226,0.0001422809,0.000178672,0.000009329844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006973225,"about_ca_system_score_gemma":0.0006426923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008124368,"about_ca_topic_score_gemma":0.0002555908,"domain_scores_codex":[0.9985014,0.0002298992,0.0002997621,0.0003543916,0.0002813423,0.0003332061],"domain_scores_gemma":[0.9990138,0.00003752929,0.00007672251,0.0004370929,0.0003652397,0.00006964739],"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":[0.00004688757,0.00008717842,0.007432781,0.00004102304,0.0000189746,0.00007797693,0.00004172888,0.004898027,0.9858562,0.00004069516,0.0002968766,0.00116168],"study_design_scores_gemma":[0.002633568,0.001028008,0.102207,0.0001268878,0.00001852033,0.0001663997,0.00126138,0.03770333,0.8142257,0.001528004,0.03834071,0.0007605671],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931494,0.0003958189,0.001595262,0.0002110734,0.0001016283,0.0001547782,0.00002491565,0.000003824477,0.004363313],"genre_scores_gemma":[0.9951274,0.0002400127,0.002317583,0.00003665887,0.00006208947,0.00002921217,0.0002702906,0.00001873744,0.001897991],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1716305,"threshold_uncertainty_score":0.3908672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1055845955324764,"score_gpt":0.3535575530803973,"score_spread":0.2479729575479209,"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."}}