{"id":"W4388706662","doi":"10.1093/bioinformatics/btad679","title":"ReGeNNe: genetic pathway-based deep neural network using canonical correlation regularizer for disease prediction","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto; University Health Network","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Correlation; Machine learning; Robustness (evolution); Artificial neural network; Canonical correlation; Generalizability theory; Convolutional neural network; Novelty; Gene; Biology; Mathematics; Genetics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003153447,0.0002250676,0.0001760392,0.00006951897,0.0002706069,0.00007026874,0.0001891604,0.0002493619,0.00000702734],"category_scores_gemma":[0.00006132072,0.0002192609,0.0001790312,0.000245263,0.00007449877,0.00001634705,0.00009948715,0.0001055358,0.00002051695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000420021,"about_ca_system_score_gemma":0.0002205949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002844868,"about_ca_topic_score_gemma":0.00001095848,"domain_scores_codex":[0.9984644,0.00002791683,0.0006063923,0.0001967283,0.0001928894,0.0005116535],"domain_scores_gemma":[0.9989371,0.0000333586,0.0002387815,0.000460347,0.0001135508,0.0002168305],"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":[0.0002940505,0.00003189155,0.002822396,0.0002288971,0.00006764764,0.000002591525,0.00009142829,0.9651355,0.001424155,0.0003061047,0.01219583,0.01739958],"study_design_scores_gemma":[0.0008092952,0.0001500891,0.002153643,0.00002747289,0.00005964321,0.000006463761,0.00004051994,0.9822702,0.0001562634,0.0003295655,0.01374405,0.0002528324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.140334,0.0004066386,0.8559671,0.0001670789,0.001291965,0.001147798,0.0003291864,0.0001297447,0.0002265191],"genre_scores_gemma":[0.874511,0.0000970553,0.1139968,0.001341996,0.00207892,0.0001665582,0.007197904,0.0001101582,0.0004995713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7419703,"threshold_uncertainty_score":0.8941202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01467302902274496,"score_gpt":0.2301602004368411,"score_spread":0.2154871714140962,"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."}}