{"id":"W3204459403","doi":"10.1101/2021.09.29.462289","title":"Assessing sequence-based protein-protein interaction predictors for use in therapeutic peptide engineering","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"In silico; Context (archaeology); Computational biology; Protein engineering; Computer science; Peptide; Similarity (geometry); Task (project management); Protein sequencing; Machine learning; Artificial intelligence; Biology; Peptide sequence; Engineering; Biochemistry; Systems engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001740982,0.0007775924,0.0007843606,0.001185015,0.000210249,0.0009163465,0.0003328003,0.0008919201,0.001596219],"category_scores_gemma":[0.004525202,0.000182589,0.0004004177,0.0007920869,0.0002824248,0.0007669941,0.0005754349,0.0008673225,0.0007850646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003404005,"about_ca_system_score_gemma":0.0007044842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008548223,"about_ca_topic_score_gemma":0.0008490147,"domain_scores_codex":[0.999204,0.0002807432,0.00003696099,0.0001273045,0.0002867118,0.00006440439],"domain_scores_gemma":[0.9975281,0.001554334,0.0003465496,0.0001234756,0.0003050788,0.00014243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001480348,0.001082155,0.04750775,0.0008199234,0.000467692,0.0002731151,0.00005878829,0.6827072,0.07842242,0.004531449,0.008809947,0.1738392],"study_design_scores_gemma":[0.0000250934,0.0002696827,0.003753671,0.00002153573,0.00004068595,0.00007677634,0.00002017069,0.9689885,0.02376623,0.001911066,0.001110085,0.00001650012],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8216972,0.004246017,0.1615885,0.0009498594,0.0001004583,0.0001049146,0.002802945,0.00357621,0.004933821],"genre_scores_gemma":[0.9462548,0.0007603141,0.04873153,0.0001642859,0.00004159951,0.00006756047,0.00280337,0.0001191358,0.001057242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001740982,"threshold_uncertainty_score":0.009207249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03218796958434669,"score_gpt":0.2472060376458143,"score_spread":0.2150180680614676,"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."}}