{"id":"W3187466590","doi":"10.1371/journal.pcbi.1009224","title":"Evaluation and comparison of multi-omics data integration methods for cancer subtyping","year":2021,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":120,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; Microsoft Research Asia; Microsoft Research; Xidian University; National Natural Science Foundation of China; Guizhou Institute of Technology","keywords":"Subtyping; Omics; Computer science; Data integration; Robustness (evolution); Benchmarking; Data mining; Cluster analysis; Data type; Intuition; Data science; Computational biology; Bioinformatics; Machine learning; Biology; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.000531773,0.00007188969,0.0001454835,0.00002227278,0.00004841822,0.00000962663,0.0001004591,0.0001082505,0.000006758717],"category_scores_gemma":[0.0002711842,0.00006950474,0.00002360194,0.00004082268,0.0000539538,0.000004471633,0.0001332594,0.00004416392,2.822504e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001118128,"about_ca_system_score_gemma":0.0001732274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005711328,"about_ca_topic_score_gemma":0.00005113726,"domain_scores_codex":[0.9992695,0.000127023,0.000257494,0.0002120594,0.00004713783,0.0000867884],"domain_scores_gemma":[0.99909,0.0001048059,0.0001416096,0.0001614771,0.0004791844,0.00002293429],"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":[0.00005818509,0.0001177883,0.002320091,0.00005072489,0.0002772119,3.055658e-8,0.0001753336,0.01425433,0.3412458,0.002588411,0.0003091064,0.638603],"study_design_scores_gemma":[0.0005222047,0.00006584256,0.0007186789,0.00001059374,0.00006971369,0.000001885178,0.00007655844,0.9624481,0.02965128,0.004906589,0.00144684,0.00008166652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07164486,0.00470058,0.9228812,0.0001884703,0.0001449539,0.0002257598,0.0001819591,0.00000337816,0.00002887008],"genre_scores_gemma":[0.6037856,0.00009827592,0.3903572,0.0001236916,0.00008160799,0.00002522304,0.005513877,0.00000622957,0.000008366374],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9481938,"threshold_uncertainty_score":0.2834321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1439021341484414,"score_gpt":0.4496101568553616,"score_spread":0.3057080227069202,"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."}}