{"id":"W4402355360","doi":"10.1101/2024.09.05.611300","title":"A scalable, multi-resolution consensus clustering approach for prioritising robust signals from high-throughput screens","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Health and Medical Research Council; Therapeutic Innovation Australia; BC Cancer Foundation; Peter MacCallum Cancer Centre; National Heart Foundation of Australia; Australian Cancer Research Foundation; U.S. Department of Defense; Australian Government; Ovarian Cancer Canada; Marshfield Clinic Research Foundation; Ovarian Cancer Research Foundation; Cancer Research Society","keywords":"Cluster analysis; Computer science; High dimensional; Clustering high-dimensional data; Pattern recognition (psychology); Artificial intelligence; Computational biology; Data mining; 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":[0.003043182,0.001354611,0.001489203,0.002454091,0.0008699085,0.001412225,0.002807092,0.001571599,0.002205541],"category_scores_gemma":[0.007233099,0.0006805842,0.001314479,0.001910421,0.0008489596,0.001068685,0.002041551,0.002062173,0.0009040319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001143547,"about_ca_system_score_gemma":0.002408499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00395333,"about_ca_topic_score_gemma":0.005746758,"domain_scores_codex":[0.9979341,0.000522323,0.000119606,0.0004928595,0.0007829419,0.0001482844],"domain_scores_gemma":[0.9961609,0.001526603,0.0004632805,0.0004924719,0.001045307,0.0003115935],"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":[0.0006119445,0.0003332034,0.002351317,0.0003901652,0.0004110372,0.0003461723,0.0001952808,0.6424256,0.1246405,0.01329932,0.007726531,0.2072689],"study_design_scores_gemma":[0.00002819376,0.00003486331,0.0002461125,0.000004860879,0.00001527281,0.00003104698,0.00002150896,0.9834163,0.01057516,0.004879188,0.0007244243,0.0000230592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008440221,0.00006643364,0.9891914,0.00008718956,0.00002116501,0.00006038131,0.0001362381,0.001677112,0.0003199131],"genre_scores_gemma":[0.1482315,0.00008983127,0.848838,0.0001474738,0.00004246665,0.00025549,0.0007464539,0.0005412598,0.001107589],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00395333,"threshold_uncertainty_score":0.01609403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02130968391016759,"score_gpt":0.2484881607808487,"score_spread":0.2271784768706812,"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."}}