{"id":"W4405441847","doi":"10.24124/2024/59584","title":"Transformer models for protein-guided drug compound generation: A comparison of amino acid sequences, pre-trained protein embeddings, SMILES, and SELFIES","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Drug; Transformer; Amino acid; Computational biology; Computer science; Chemistry; Pharmacology; Medicine; Biochemistry; Biology; Engineering; Electrical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001014683,0.0008455572,0.0005507502,0.000523048,0.0001649976,0.0005672451,0.001056004,0.0006136821,0.001835697],"category_scores_gemma":[0.002574235,0.0002825444,0.000700969,0.0003565603,0.0003437757,0.001276081,0.0007730445,0.001184741,0.0006886254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007934803,"about_ca_system_score_gemma":0.0009438553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002449425,"about_ca_topic_score_gemma":0.004654268,"domain_scores_codex":[0.9997503,0.00008995293,0.00001829411,0.00004670873,0.00006785129,0.00002686698],"domain_scores_gemma":[0.999044,0.0006033535,0.00007099932,0.0001180345,0.0001225811,0.00004109643],"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":[0.0003944825,0.0001828744,0.001914238,0.000170803,0.00008206026,0.00007214095,0.00005540864,0.8065748,0.005628807,0.007504754,0.001998254,0.1754213],"study_design_scores_gemma":[0.0000127382,0.0001318635,0.0001102601,0.000009822051,0.00001066509,0.00002070153,0.000009174808,0.9939128,0.003174047,0.001992455,0.0006104429,0.000005025227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3164895,0.002616758,0.6597292,0.001008698,0.0001685495,0.0002381681,0.0009359269,0.006549391,0.01226366],"genre_scores_gemma":[0.8148944,0.001718492,0.1752003,0.0003722372,0.00003753022,0.0002081967,0.002016782,0.0004115032,0.005140714],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002449425,"threshold_uncertainty_score":0.006141067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05199538215055109,"score_gpt":0.353723114106522,"score_spread":0.3017277319559709,"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."}}