{"id":"W4365508859","doi":"10.12688/f1000research.125579.1","title":"Cell-type classification of cancer single-cell RNA-seq data using the Subsemble ensemble-based machine learning classifier","year":2023,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Children’s Health Research Institute; Ontario Institute for Cancer Research; Lawson Health Research Institute; Western University","funders":"Ontario Institute for Cancer Research; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Children's Health Research Institute","keywords":"Artificial intelligence; Classifier (UML); Machine learning; Computer science; Support vector machine; Ensemble learning; Pattern recognition (psychology); Computational biology; Biology","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":[0.001257867,0.0003849724,0.0003930491,0.000186022,0.00028339,0.0001426455,0.001977445,0.0006343225,0.00007940548],"category_scores_gemma":[0.0002337187,0.0003253137,0.0001746799,0.0003940221,0.0002993748,0.000008142087,0.001506777,0.001292709,0.00001944026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001010054,"about_ca_system_score_gemma":0.001218954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003702651,"about_ca_topic_score_gemma":0.001026484,"domain_scores_codex":[0.9964373,0.0005439023,0.0005699754,0.001096357,0.0007389754,0.0006134565],"domain_scores_gemma":[0.9966961,0.0001630308,0.0003443432,0.002110194,0.0005456132,0.0001407654],"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":[0.0003504905,0.0002335458,0.01078705,0.0004929202,0.00008451503,0.000005170219,0.00006228722,0.01746399,0.9663924,0.000005423853,0.00283147,0.001290755],"study_design_scores_gemma":[0.0008542374,0.0002544637,0.0009210223,0.0001714436,0.0001343577,0.0000011945,0.0001314779,0.2366688,0.7451618,0.0000482578,0.01518343,0.0004694335],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9749057,0.007438394,0.0124421,0.0007577108,0.001237996,0.001031772,0.0005933747,0.00007727138,0.001515656],"genre_scores_gemma":[0.9873192,0.001760455,0.001047354,0.00006530272,0.0005279171,0.00004567947,0.003859239,0.0001790629,0.00519584],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2212305,"threshold_uncertainty_score":0.9999199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2663156725883557,"score_gpt":0.3755532099323227,"score_spread":0.109237537343967,"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."}}