{"id":"W2918710707","doi":"10.1093/bioinformatics/btz155","title":"Enhancing the prediction of disease–gene associations with multimodal deep learning","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Wuhan Institute of Technology; China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Deep learning; Disease; Artificial intelligence; Computational biology; Machine learning; Biology; Medicine; Internal medicine","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":[0.001237795,0.0009686379,0.0006386879,0.0009386373,0.0002554566,0.0005922768,0.001154298,0.000989091,0.002120539],"category_scores_gemma":[0.003459791,0.0002846723,0.0006911508,0.0006630952,0.0003987299,0.0008390073,0.001195253,0.001300482,0.0006900274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007423784,"about_ca_system_score_gemma":0.0008934912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006223067,"about_ca_topic_score_gemma":0.007649275,"domain_scores_codex":[0.9996684,0.00009043168,0.0000175774,0.0001015065,0.00007845423,0.00004375134],"domain_scores_gemma":[0.999218,0.0003958688,0.00009587323,0.00008994577,0.0001325282,0.00006770169],"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":[0.0008144429,0.0006083815,0.04892707,0.0003568128,0.0004227201,0.0004768979,0.0001366501,0.5274026,0.01547343,0.003359858,0.01247876,0.3895423],"study_design_scores_gemma":[0.00001501279,0.00002942832,0.001518646,0.00001613599,0.0000271837,0.00004484738,0.00001034871,0.9920967,0.002292222,0.003463923,0.0004776315,0.000007954066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2626458,0.003364982,0.7181473,0.002060147,0.0001296063,0.0001051438,0.003599897,0.007240976,0.00270621],"genre_scores_gemma":[0.8864533,0.0005510484,0.1064086,0.0005889236,0.00006386996,0.0001183038,0.003833968,0.00009607915,0.001885995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006223067,"threshold_uncertainty_score":0.01237369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004619670751991929,"score_gpt":0.1969937966343857,"score_spread":0.1923741258823937,"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."}}