{"id":"W4213235856","doi":"10.1093/bioinformatics/btac100","title":"Pre-training graph neural networks for link prediction in biomedical networks","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Research (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Initialization; Graph; Artificial intelligence; Convolutional neural network; Machine learning; Artificial neural network; Node (physics); Encoder; Deep learning; Data mining; Theoretical computer science","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":[0.0009021749,0.002012434,0.000872139,0.001228344,0.0004217671,0.000517285,0.001677324,0.001403805,0.002258268],"category_scores_gemma":[0.003641569,0.0005629295,0.0009252179,0.001103959,0.0006602882,0.001763213,0.0009597816,0.002100283,0.0009032566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00118971,"about_ca_system_score_gemma":0.001199527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01181245,"about_ca_topic_score_gemma":0.0175537,"domain_scores_codex":[0.9995313,0.00009251039,0.00002723136,0.0001911176,0.000094378,0.00006352231],"domain_scores_gemma":[0.998778,0.0006254133,0.0001379486,0.0001517807,0.0002483552,0.00005839252],"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":[0.0001496506,0.0001698616,0.003043496,0.0001755126,0.00007630297,0.0001469756,0.0000423854,0.7924318,0.004666144,0.002033453,0.004741629,0.1923227],"study_design_scores_gemma":[0.000004939363,0.0000234407,0.0002390188,0.000007728006,0.00001023324,0.00001356307,0.000005388909,0.9960548,0.001603376,0.00169199,0.0003415945,0.000003985647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1400842,0.002790928,0.8388703,0.000959174,0.0002015233,0.0002287634,0.001638086,0.01078935,0.00443767],"genre_scores_gemma":[0.7922683,0.001125668,0.1945223,0.0006043484,0.0001068087,0.0002782039,0.006417997,0.0002957548,0.004380614],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01181245,"threshold_uncertainty_score":0.02348739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.012200227654295,"score_gpt":0.2334871319472515,"score_spread":0.2212869042929565,"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."}}