{"id":"W4318828595","doi":"10.26434/chemrxiv-2022-m3900-v2","title":"Latent Spaces for Antimicrobial Peptide Design","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Antimicrobial Peptides and Activities","field":"Immunology and Microbiology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Canada Research Chairs; Compute Canada","keywords":"Interpretability; Computer science; Benchmark (surveying); Artificial intelligence; Machine learning; Generative model; Generative grammar; Chemical space; Construct (python library); Pipeline (software); Drug discovery; Biology; Bioinformatics; Geography","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":[0.001298174,0.0007724801,0.000717042,0.0007768662,0.0002884873,0.001071544,0.0008007361,0.001064892,0.003030568],"category_scores_gemma":[0.003789246,0.0004667179,0.001018238,0.0005762362,0.0009565213,0.001343896,0.001138001,0.00182894,0.0007482208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001060162,"about_ca_system_score_gemma":0.0007501059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001767769,"about_ca_topic_score_gemma":0.002205249,"domain_scores_codex":[0.9994442,0.0002808562,0.00002743252,0.00009523073,0.0001075163,0.00004487883],"domain_scores_gemma":[0.9984182,0.00114579,0.0001509305,0.000120059,0.0001136044,0.00005153079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000746607,0.00003990655,0.0008312668,0.0001418145,0.00006136317,0.00003792298,0.00004444618,0.8736884,0.002920098,0.06870013,0.001277419,0.05218259],"study_design_scores_gemma":[0.000006521627,0.00002518817,0.00006729233,0.00001552288,0.000006578,0.00001010272,0.000005267783,0.9657835,0.0007363973,0.03211344,0.001223447,0.000006663859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01208565,0.001808531,0.9827802,0.0005398639,0.0000554907,0.00003134881,0.0002077656,0.0004835028,0.002007729],"genre_scores_gemma":[0.6207276,0.003194503,0.3669331,0.0005479367,0.000198078,0.0004841289,0.001121853,0.0003014534,0.006491349],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003030568,"threshold_uncertainty_score":0.01013827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05724908168096823,"score_gpt":0.264637694123144,"score_spread":0.2073886124421758,"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."}}