{"id":"W2892884209","doi":"10.1038/s41598-018-32834-z","title":"Pattern to Knowledge: Deep Knowledge-Directed Machine Learning for Residue-Residue Interaction Prediction","year":2018,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminative model; Computer science; Residue (chemistry); Deep learning; Artificial intelligence; Construct (python library); Machine learning; Computational biology; Bioinformatics; Biology; Biochemistry","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003420666,0.0002382833,0.0002440085,0.0006376077,0.0008724261,0.0008740473,0.0005254335,0.00008409467,0.00005699663],"category_scores_gemma":[0.001384261,0.0002364801,0.0001363841,0.001612678,0.0001328811,0.0008858488,0.0004931266,0.0002101884,0.0002053809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002310982,"about_ca_system_score_gemma":0.0003096197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006301019,"about_ca_topic_score_gemma":0.0007297227,"domain_scores_codex":[0.9965199,0.0003671038,0.0007150161,0.001451522,0.000479572,0.0004668659],"domain_scores_gemma":[0.9968191,0.0004294496,0.0003433984,0.0009820882,0.00119328,0.0002327271],"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":[0.00008860532,0.0005819267,0.007818668,0.0001464073,0.0001014309,0.00007646236,0.01290056,0.02247879,0.0199317,0.0008470631,0.07241254,0.8626158],"study_design_scores_gemma":[0.0002134179,0.0002213742,0.009302999,0.0001046628,0.00001787103,0.0001814179,0.00004125122,0.8218721,0.03619976,0.008223998,0.1233069,0.0003142575],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07131223,0.0001554696,0.8992536,0.0002870934,0.02383954,0.0006990365,0.000003729591,0.000691477,0.00375779],"genre_scores_gemma":[0.9467887,0.000001077091,0.0457854,0.00004927117,0.0007803328,0.0001414246,0.00009981356,0.00003499475,0.006318931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8754765,"threshold_uncertainty_score":0.9643376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0267575839912762,"score_gpt":0.3304733810031875,"score_spread":0.3037157970119113,"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."}}