{"id":"W4318014921","doi":"10.1016/j.csbj.2023.01.028","title":"ProtInteract: A deep learning framework for predicting protein–protein interactions","year":2023,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"ENCODE; Computer science; Autoencoder; Leverage (statistics); Protein sequencing; Computational biology; Protein–protein interaction; Artificial intelligence; Convolutional neural network; Support vector machine; Deep learning; Sequence (biology); Protein structure; Machine learning; Peptide sequence; Pattern recognition (psychology); Biology; Genetics; Biochemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.0001471763,0.0001713943,0.0001502311,0.0001630769,0.0005999499,0.00008134876,0.0001703054,0.0002798073,0.00001132331],"category_scores_gemma":[0.0004910071,0.0001477118,0.00009111268,0.000172104,0.0001369665,0.00001552744,0.0001429092,0.0006167155,0.000003221684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001889341,"about_ca_system_score_gemma":0.00004730547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001402427,"about_ca_topic_score_gemma":0.000003046577,"domain_scores_codex":[0.9989835,0.00004075662,0.0002756455,0.0002940518,0.000113845,0.0002922245],"domain_scores_gemma":[0.9994423,0.00004367814,0.0001979058,0.0000949472,0.0001448725,0.00007632722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006875513,0.00002559536,0.006206977,0.0001560156,0.0004869048,0.00003920627,0.0003889492,0.0213924,0.6270576,0.05701814,0.0002263006,0.2863143],"study_design_scores_gemma":[0.001542409,0.001283789,0.01151433,0.0002472895,0.00004295422,0.002530555,0.0005695362,0.1396723,0.05067214,0.7828635,0.008366197,0.0006950278],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7771174,0.0001632296,0.2202346,0.001794378,0.0001798205,0.0004011504,0.00001339566,0.000079092,0.00001691445],"genre_scores_gemma":[0.9488589,0.00001795858,0.05030071,0.00007425375,0.0003713463,0.00006611194,0.0001182385,0.00001987663,0.000172589],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7258453,"threshold_uncertainty_score":0.6023514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007673851637078225,"score_gpt":0.2717939282163605,"score_spread":0.2641200765792823,"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."}}