{"id":"W2848983148","doi":"10.1186/s12920-018-0372-8","title":"Phenotype-driven gene prioritization for rare diseases using graph convolution on heterogeneous networks","year":2018,"lang":"en","type":"article","venue":"BMC Medical Genomics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Hospital for Sick Children; Tata Consultancy Services","keywords":"Prioritization; Human genetics; Phenotype; Computational biology; Biology; DNA microarray; Graph; Gene; Genetics; Convolution (computer science); Computer science; Bioinformatics; Gene expression; Theoretical computer science; Artificial intelligence; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001470172,0.001116188,0.0008704553,0.003250839,0.0006139468,0.0009379582,0.0008891972,0.0007929164,0.001571381],"category_scores_gemma":[0.005604626,0.0003789277,0.001445213,0.001703039,0.0004402645,0.001437875,0.001323429,0.0008915556,0.0003681898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001119672,"about_ca_system_score_gemma":0.001159638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01622111,"about_ca_topic_score_gemma":0.01964314,"domain_scores_codex":[0.9991727,0.0002748646,0.00004605001,0.0002711411,0.0001577372,0.00007739201],"domain_scores_gemma":[0.9972956,0.001801791,0.0002561224,0.0002793391,0.0002529268,0.0001143209],"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":[0.0005424939,0.000297774,0.03184377,0.0003381283,0.0004803219,0.0009264551,0.0003892654,0.6352261,0.02036234,0.0137031,0.005575656,0.2903146],"study_design_scores_gemma":[0.00001110987,0.00001960132,0.001369721,0.000006482987,0.00003205783,0.00008001852,0.00002408795,0.9882931,0.001606403,0.007900525,0.0006500963,0.000006793373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1126671,0.0005324872,0.8803708,0.000417004,0.00003966544,0.0001150999,0.001260845,0.003285018,0.001311999],"genre_scores_gemma":[0.6427674,0.0003936814,0.350513,0.0002717304,0.00007062325,0.0001138251,0.004026088,0.0001959975,0.001647586],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01622111,"threshold_uncertainty_score":0.03225338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01574462587150688,"score_gpt":0.2629914139861319,"score_spread":0.247246788114625,"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."}}