{"id":"W4205469791","doi":"10.1101/2022.01.12.475995","title":"GNN-SubNet: disease subnetwork detection with explainable Graph Neural Networks","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Austrian Science Fund; European Commission","keywords":"Subnetwork; Subnet; Interpretability; Computer science; Python (programming language); Machine learning; Artificial intelligence; Graph; Computational biology; Theoretical computer science; Biology; Computer network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007564743,0.001132434,0.0006275735,0.001715021,0.0002947075,0.0007519288,0.001333592,0.001248745,0.005683055],"category_scores_gemma":[0.003311225,0.000461028,0.001098021,0.0007104266,0.0003805914,0.0008519925,0.001148685,0.001077351,0.001014345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008594884,"about_ca_system_score_gemma":0.0009473302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007021424,"about_ca_topic_score_gemma":0.01068762,"domain_scores_codex":[0.9997359,0.0000814728,0.00001242241,0.00009374976,0.00004768405,0.00002882558],"domain_scores_gemma":[0.9993646,0.0003338307,0.00007164908,0.0001110293,0.00007135667,0.00004757951],"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":[0.000447877,0.0001968372,0.009604504,0.0004629657,0.0005393514,0.000505702,0.0001277407,0.6389017,0.005303578,0.01900442,0.04237672,0.2825286],"study_design_scores_gemma":[0.00002148317,0.00001176217,0.00037747,0.00001224359,0.00001682473,0.00003823869,0.000005823865,0.9843374,0.0008333837,0.01269344,0.001645808,0.000006114299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03750619,0.0006323472,0.9278923,0.001154026,0.0001694808,0.0001607202,0.0060617,0.02448277,0.001940538],"genre_scores_gemma":[0.490893,0.0004228829,0.4867322,0.000606861,0.0001331614,0.0003551877,0.01495084,0.001313287,0.004592597],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007021424,"threshold_uncertainty_score":0.01901174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005944423756176822,"score_gpt":0.1864367240737987,"score_spread":0.1804923003176219,"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."}}