{"id":"W4399734222","doi":"10.1186/s13059-024-03304-9","title":"Beyond benchmarking and towards predictive models of dataset-specific single-cell RNA-seq pipeline performance","year":2024,"lang":"en","type":"article","venue":"Genome biology","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"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; Machine learning; Cluster analysis; Normalization (sociology); Pipeline transport; Artificial intelligence; Data mining; Predictive modelling; Range (aeronautics); Set (abstract data type); 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":[],"consensus_categories":[],"category_scores_codex":[0.0001840255,0.000196465,0.0002231905,0.00008290124,0.00005789958,0.00002157625,0.0001905169,0.000226677,0.00003185467],"category_scores_gemma":[0.000005279309,0.0001766992,0.00005964246,0.00009309201,0.0002204487,0.00001003842,0.0001322128,0.000128695,0.000004272814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001832451,"about_ca_system_score_gemma":0.0000654661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002485071,"about_ca_topic_score_gemma":0.000007202254,"domain_scores_codex":[0.998814,0.00004428599,0.0002938192,0.0005045542,0.00006678143,0.0002765706],"domain_scores_gemma":[0.9995191,0.0000164305,0.00005739518,0.0002799325,0.0000537955,0.00007333824],"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":[0.0001309556,0.00006534591,0.0002602453,0.0001082362,0.00004435262,0.000002953922,0.0001369129,0.000274099,0.9795068,0.0001271085,0.0005901546,0.01875287],"study_design_scores_gemma":[0.001664652,0.004393181,0.001066442,0.00008908525,0.0001378436,0.00008394795,0.0001330844,0.03118314,0.6623128,0.001549197,0.2963746,0.00101205],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9440873,0.02278834,0.02649978,0.00006313544,0.000653932,0.0002054824,0.001932464,0.00002502068,0.003744539],"genre_scores_gemma":[0.9908417,0.003870135,0.001230738,0.00009754626,0.0004812766,0.000009794788,0.003290982,0.0000261582,0.0001516346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.317194,"threshold_uncertainty_score":0.7205583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02194880880511308,"score_gpt":0.2261055599729756,"score_spread":0.2041567511678626,"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."}}