{"id":"W3035506638","doi":"10.21203/rs.3.rs-120780/v1","title":"AMPlify: attentive deep learning model for discovery of novel antimicrobial peptides effective against WHO priority pathogens","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; BC Cancer Agency; University of Victoria; Canada's Michael Smith Genome Sciences Centre","funders":"National Institutes of Health; British Columbia Centre for Disease Control; Genome British Columbia; Genome Canada","keywords":"Antimicrobial; Drug discovery; Antimicrobial peptides; Computational biology; Deep learning; Computer science; Artificial intelligence; Chemistry; Biology; Data science; Microbiology; Bioinformatics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001362734,0.0004180371,0.0006203706,0.0001851086,0.0002840684,0.0001653572,0.0006673657,0.0006940094,0.000001460128],"category_scores_gemma":[0.003036994,0.0004165014,0.0004659073,0.0001739918,0.000321238,0.00001463464,0.002574007,0.001956671,0.000004578482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001109576,"about_ca_system_score_gemma":0.000463173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004182296,"about_ca_topic_score_gemma":0.00003524112,"domain_scores_codex":[0.9969454,0.0003901927,0.000534773,0.0008385385,0.0006022916,0.000688822],"domain_scores_gemma":[0.9975666,0.000265988,0.0004077257,0.0006665959,0.0009378192,0.0001552954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001048538,0.0003739676,0.009073558,0.008772915,0.0005910262,0.000005210874,0.002937898,0.240514,0.7302511,0.0003042199,0.001154962,0.004972669],"study_design_scores_gemma":[0.001691517,0.0009820481,0.003796914,0.001115978,0.00007391087,0.000003835975,0.0005811735,0.9430929,0.04631865,0.0001684667,0.001416417,0.0007582009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6629773,0.0002262038,0.3318633,0.000152121,0.0001084272,0.002612403,0.001473174,0.00003307738,0.0005539032],"genre_scores_gemma":[0.9804084,0.0004896366,0.01449305,0.00006275816,0.0003820455,0.0002698153,0.003356365,0.00009782727,0.0004401425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.702579,"threshold_uncertainty_score":0.9998287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03668465973951013,"score_gpt":0.3608503029405614,"score_spread":0.3241656432010512,"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."}}