{"id":"W2971405760","doi":"10.1093/bioinformatics/btz699","title":"Protein–protein interaction site prediction through combining local and global features with deep neural networks","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":296,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; Central South University; Virginia Commonwealth University","keywords":"Computer science; Convolutional neural network; Sequence (biology); Artificial intelligence; Deep learning; Artificial neural network; Source code; Code (set theory); Protein sequencing; Sliding window protocol; Machine learning; Peptide sequence; Window (computing); Biology","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":[0.0005781298,0.001696653,0.001200142,0.001304341,0.0003948191,0.0008674353,0.001570502,0.001078154,0.004188485],"category_scores_gemma":[0.001447447,0.0005650438,0.001112911,0.001221803,0.0004712885,0.001627011,0.001468673,0.001969265,0.002309793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008027167,"about_ca_system_score_gemma":0.0008903141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005100264,"about_ca_topic_score_gemma":0.007416299,"domain_scores_codex":[0.9995492,0.00005437512,0.0000236083,0.000178896,0.0001315584,0.00006233413],"domain_scores_gemma":[0.9996186,0.0001019596,0.00007216679,0.000049499,0.00009640733,0.00006125528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009281622,0.0006558078,0.01656187,0.001387276,0.0006550044,0.0007394903,0.0001057043,0.409487,0.06116423,0.0105471,0.06434027,0.4334281],"study_design_scores_gemma":[0.00002356513,0.00003804869,0.001167622,0.00002215644,0.00004642284,0.00005831731,0.000009761027,0.9843653,0.005607471,0.006543742,0.00209981,0.00001772815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1899636,0.009304972,0.7492157,0.002102822,0.0003572399,0.0002212461,0.01341076,0.02396571,0.01145805],"genre_scores_gemma":[0.7400098,0.003464169,0.2105037,0.001146891,0.0002691321,0.0003615298,0.03378724,0.0008612549,0.009596449],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005100264,"threshold_uncertainty_score":0.01401186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004727256528390456,"score_gpt":0.2081237899887306,"score_spread":0.2033965334603402,"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."}}