{"id":"W4379791907","doi":"10.1002/advs.202205442","title":"Reliable Identification and Interpretation of Single‐Cell Molecular Heterogeneity and Transcriptional Regulation using Dynamic Ensemble Pruning","year":2023,"lang":"en","type":"article","venue":"Advanced Science","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Fundamental Research Funds for the Central Universities; People's Government of Jilin Province; National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Pruning; Interpretability; Artificial intelligence; Identification (biology); Data mining; Hierarchical clustering; Autoencoder; Heuristic; Machine learning; Pattern recognition (psychology); Artificial neural network; Biology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001208836,0.0007877042,0.0009742211,0.0008005591,0.0004746513,0.0007210486,0.0009598177,0.000621999,0.0005219628],"category_scores_gemma":[0.001975155,0.000335291,0.000757547,0.0006522736,0.0005164342,0.0008704906,0.00112754,0.000915005,0.0001933348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005441832,"about_ca_system_score_gemma":0.0006593513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00217675,"about_ca_topic_score_gemma":0.00414538,"domain_scores_codex":[0.9995485,0.00008435176,0.00002524156,0.0001579448,0.0001261005,0.00005782085],"domain_scores_gemma":[0.9991949,0.0003393726,0.0001009684,0.0001450201,0.0001791405,0.00004058447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001829149,0.00008912239,0.008427002,0.0001484923,0.0001564214,0.000334234,0.000329494,0.5921203,0.1780795,0.01216714,0.001794019,0.2061713],"study_design_scores_gemma":[0.000003299248,0.0000178125,0.001868662,0.000006256681,0.00001453862,0.00004283008,0.00002654462,0.9824936,0.01072195,0.004153087,0.0006395496,0.00001186375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04844053,0.0001783306,0.9501482,0.00005808067,0.00001533852,0.00002320867,0.00008693508,0.0003431385,0.0007060635],"genre_scores_gemma":[0.5763239,0.0003413136,0.4205405,0.00009801092,0.00003478448,0.0001673636,0.0008284217,0.0002022128,0.001463512],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00217675,"threshold_uncertainty_score":0.006393015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01320188711269348,"score_gpt":0.2621363465243286,"score_spread":0.2489344594116351,"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."}}