{"id":"W4280539381","doi":"10.1101/2022.04.21.489097","title":"scTagger: Fast and accurate matching of cellular barcodes across short- and long-reads of single-cell RNA-seq experiments","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Computational biology; Computer science; RNA-Seq; RNA splicing; Single cell sequencing; Matching (statistics); Barcode; Biology; RNA; Transcriptome; Genetics; Gene; Mutation; Gene expression; Exome sequencing","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"],"consensus_categories":[],"category_scores_codex":[0.0004257897,0.0005309984,0.0006519607,0.0001034557,0.0001642893,0.00009858614,0.0004522773,0.0004580146,0.00002388661],"category_scores_gemma":[0.00003739231,0.0005974401,0.0001599805,0.0001462495,0.0003164405,0.00001566053,0.0009762759,0.0003848483,5.321134e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004528203,"about_ca_system_score_gemma":0.0001767071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008432235,"about_ca_topic_score_gemma":0.000005072578,"domain_scores_codex":[0.9974753,0.0001359049,0.0006681079,0.0009575067,0.0003059395,0.0004572613],"domain_scores_gemma":[0.9983181,0.00002558105,0.0004005865,0.0008441086,0.0002141697,0.0001974064],"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":[0.0001192865,0.0002951106,0.01360008,0.0007512983,0.0001483069,0.00001656768,0.00008083452,0.0001232339,0.984824,0.00001843193,0.00001190776,0.00001092183],"study_design_scores_gemma":[0.0006202789,0.0002289423,0.005342484,0.0001668569,0.00008151614,5.677388e-8,0.00004490382,0.00008957731,0.992559,0.000001300772,0.0003110057,0.0005540992],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9872091,0.007891436,0.003499269,0.00001420812,0.0004296271,0.0004166841,0.0004919562,0.00003427704,0.00001340227],"genre_scores_gemma":[0.9968898,0.0009166006,0.001809833,0.00005407109,0.0001377659,0.00005249717,0.000005700419,0.0001215161,0.00001222217],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009680654,"threshold_uncertainty_score":0.9996477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02023091442322058,"score_gpt":0.2428344089887061,"score_spread":0.2226034945654855,"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."}}