{"id":"W2979255327","doi":"10.1101/786236","title":"Structure-Based Protein Function Prediction using Graph Convolutional Networks","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Protein function prediction; Convolutional neural network; Graph; Function (biology); Protein structure prediction; Pattern recognition (psychology); Deep learning; Sequence (biology); Protein structure","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0002553123,0.0005852622,0.0003908423,0.00017785,0.0001866235,0.0001221032,0.0003707299,0.001347478,0.00002475578],"category_scores_gemma":[0.00006779695,0.0006374369,0.0002281625,0.0002461929,0.0001411887,0.00001306588,0.0003147119,0.0007132129,0.000004395764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001591858,"about_ca_system_score_gemma":0.0008535469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003109753,"about_ca_topic_score_gemma":0.000003903623,"domain_scores_codex":[0.9974195,0.0001438207,0.0004607433,0.001115432,0.0003519805,0.0005085609],"domain_scores_gemma":[0.9977116,0.000008311157,0.0004550352,0.001178809,0.000474924,0.000171304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001867051,0.0000350844,0.005749601,0.0001752077,0.0001808077,0.00000324924,3.614504e-7,0.07608792,0.9172066,0.0002682005,0.000104819,0.00000140558],"study_design_scores_gemma":[0.002261596,0.0004950172,0.07752657,0.0005739313,0.0004575712,1.35847e-7,0.000001391684,0.1438945,0.7690712,0.00007415686,0.003552605,0.002091323],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6895644,0.001132594,0.3058589,0.00001762318,0.001660597,0.001056765,0.0006014293,0.0001045357,0.000003209743],"genre_scores_gemma":[0.9917873,0.00002689566,0.006291495,0.0002106912,0.001419871,0.0001040678,0.00003016512,0.0001243811,0.00000515601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3022229,"threshold_uncertainty_score":0.999949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006971699041107137,"score_gpt":0.1951996761301314,"score_spread":0.1882279770890243,"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."}}