{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003060964,0.001067959,0.001371542,0.001647713,0.0007071104,0.001071158,0.0009756074,0.001226316,0.001012608],"category_scores_gemma":[0.004731563,0.000267045,0.001686402,0.000642831,0.000298123,0.0008195915,0.0007222638,0.001337344,0.00107101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007559299,"about_ca_system_score_gemma":0.0008921734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006371303,"about_ca_topic_score_gemma":0.008617422,"domain_scores_codex":[0.9988599,0.0002220505,0.00008696329,0.0003913509,0.0003070792,0.0001326774],"domain_scores_gemma":[0.998009,0.0005981814,0.000118346,0.0003333359,0.000840576,0.0001005547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001348297,0.0007725561,0.09504373,0.0003478942,0.001389204,0.0004559266,0.0005515126,0.1915193,0.0865353,0.00142311,0.0258814,0.5947318],"study_design_scores_gemma":[0.0000238389,0.0002801056,0.01270615,0.00003286682,0.0001423565,0.0001714135,0.0001205443,0.9537544,0.02855658,0.001134328,0.003013587,0.00006379894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6191229,0.002604891,0.3563521,0.0007617312,0.0006961652,0.0004284054,0.007166009,0.009204994,0.003662826],"genre_scores_gemma":[0.7623631,0.0004762043,0.2163063,0.0004911597,0.0001507196,0.0004838852,0.01581327,0.0003355866,0.003579895],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006371303,"threshold_uncertainty_score":0.01618814,"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."}}