{"id":"W4412146709","doi":"10.1039/d5dd00107b","title":"Chemical language models can generate biomolecules atom-by-atom","year":2025,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"","keywords":"Biomolecule; Atom (system on chip); Chemistry; Computer science; Nanotechnology; Materials science; Parallel computing","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":[0.0003919539,0.0005250511,0.0004205037,0.0004166969,0.0002569927,0.0008129702,0.0008722986,0.0008948841,0.003050235],"category_scores_gemma":[0.002123506,0.0002912462,0.0009282173,0.0003723848,0.0004910874,0.001758585,0.0005243566,0.001148752,0.001168451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006072191,"about_ca_system_score_gemma":0.0006608051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009974712,"about_ca_topic_score_gemma":0.002036366,"domain_scores_codex":[0.9998491,0.0000454944,0.000007839305,0.00003859064,0.00004322367,0.00001569403],"domain_scores_gemma":[0.9994459,0.0003237364,0.0000558932,0.00009254016,0.00006087673,0.00002108475],"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":[0.0001775495,0.000191742,0.00127487,0.0003589484,0.0001391445,0.0002342008,0.0001382735,0.6809502,0.028053,0.1801035,0.007050158,0.1013284],"study_design_scores_gemma":[0.00001812477,0.00003755317,0.00005498029,0.00001228564,0.00002039496,0.00003606029,0.00001557458,0.9389221,0.00527726,0.05150989,0.004084939,0.00001093698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06255345,0.0007813625,0.9163474,0.001558895,0.0002968713,0.0001390759,0.0009833404,0.003259432,0.01408009],"genre_scores_gemma":[0.6722752,0.001234289,0.3167701,0.0007380129,0.0001063662,0.0003341709,0.001571029,0.0006354161,0.00633541],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003050235,"threshold_uncertainty_score":0.01020408,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005876280322459212,"score_gpt":0.2430713952140933,"score_spread":0.2371951148916341,"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."}}