{"id":"W4282563525","doi":"10.1101/2022.06.08.495370","title":"Multi-objective Bayesian Optimization with Heuristic Objectives for Biomedical and Molecular Data Analysis Workflows","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research; Vector Institute; Lunenfeld-Tanenbaum Research Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Vector Institute","keywords":"Computer science; Bayesian optimization; Workflow; Multi-objective optimization; Heuristic; Set (abstract data type); Bayesian probability; Data mining; Gaussian process; A priori and a posteriori; Machine learning; Process (computing); Mathematical optimization; Artificial intelligence; Gaussian; Mathematics","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":[0.0004304886,0.0004862606,0.0005460674,0.0002883136,0.0002298024,0.0001424051,0.0006692715,0.0004282161,0.00002014337],"category_scores_gemma":[0.0002278767,0.0004969193,0.0001509518,0.000572362,0.0002124624,0.00001240233,0.0007179108,0.0003802668,3.617612e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007465253,"about_ca_system_score_gemma":0.0004539409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000645032,"about_ca_topic_score_gemma":0.00002006886,"domain_scores_codex":[0.9971323,0.0001670219,0.0003723426,0.001651721,0.0002746707,0.0004019633],"domain_scores_gemma":[0.9976513,0.00003863117,0.0002661894,0.001551327,0.0002671764,0.0002253082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006858813,0.0008036584,0.01570762,0.0004611394,0.004998173,0.00006047943,0.00003342228,0.03654704,0.9405331,0.00004271576,0.0001156314,0.00001114689],"study_design_scores_gemma":[0.00862478,0.002316859,0.04520369,0.0004169265,0.01075161,3.128295e-7,0.0000929116,0.6854396,0.2327393,0.000005445642,0.008891564,0.00551709],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1881068,0.001459323,0.8075328,0.00006578865,0.0002871666,0.0008664796,0.001612563,0.0000665003,0.000002654413],"genre_scores_gemma":[0.8444345,0.0002729036,0.1545119,0.0001200582,0.0001838452,0.0002516166,0.0001059347,0.0001149483,0.000004238772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7077938,"threshold_uncertainty_score":0.9997482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0142208353852261,"score_gpt":0.237382862733925,"score_spread":0.2231620273486989,"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."}}