{"id":"W4390656815","doi":"10.1101/2024.01.02.572650","title":"Beyond benchmarking: towards predictive models of dataset-specific single-cell RNA-seq pipeline performance","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Lunenfeld-Tanenbaum Research Institute; Ontario Institute for Cancer Research; University of Toronto","funders":"Canadian Institutes of Health Research; University of Toronto; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Pipeline (software); Benchmarking; Computer science; Normalization (sociology); Cluster analysis; Pipeline transport; Machine learning; Data mining; Artificial intelligence; Range (aeronautics); Set (abstract data type); Predictive modelling; Engineering","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":[0.0005003594,0.0007804772,0.0006957021,0.0002406802,0.0001129402,0.0001440968,0.0008950218,0.0009211719,0.00003043231],"category_scores_gemma":[0.00003124433,0.0008268752,0.0002775896,0.0003226606,0.000269246,0.00002031506,0.001027144,0.0008844539,0.00001893634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001337089,"about_ca_system_score_gemma":0.0006859151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005478921,"about_ca_topic_score_gemma":0.000003484448,"domain_scores_codex":[0.9964104,0.00009787727,0.0008677683,0.001511094,0.0004922059,0.0006206225],"domain_scores_gemma":[0.9971222,0.00001855357,0.0004193679,0.001675549,0.0004999956,0.0002643661],"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":[0.0002098061,0.0004041292,0.0002288456,0.001045955,0.0001764389,0.00001925299,0.0000173955,0.002355509,0.9906251,0.00007343408,0.004807777,0.00003637279],"study_design_scores_gemma":[0.0006418731,0.0004281613,0.000400386,0.0004089695,0.0002013568,6.129463e-8,0.000003621065,0.01232464,0.9725101,0.00001343636,0.01216879,0.0008986028],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9645421,0.009905099,0.01173837,0.00007147104,0.002872579,0.0008091027,0.009539698,0.0001385886,0.0003829675],"genre_scores_gemma":[0.991035,0.002621732,0.004436745,0.0001226743,0.001352716,0.00008496664,0.0001139259,0.0002040628,0.00002814556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02649291,"threshold_uncertainty_score":0.9994182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01940723924096349,"score_gpt":0.2092493754798289,"score_spread":0.1898421362388654,"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."}}