{"id":"W4361989906","doi":"10.1039/d3dd00012e","title":"Group SELFIES: a robust fragment-based molecular string representation","year":2023,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Resources Canada; University of Toronto; Canada Foundation for Innovation; Intel Labs; Government of Ontario; Intel Corporation","keywords":"Robustness (evolution); Computer science; Representation (politics); Fragment (logic); Generative model; Generative grammar; Theoretical computer science; Artificial intelligence; Chemistry; Algorithm; Biochemistry; Gene","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":[0.0009171116,0.0006665007,0.0009198866,0.001742053,0.0005183633,0.001233923,0.002702683,0.001718035,0.007092942],"category_scores_gemma":[0.003361578,0.0004096682,0.001136397,0.001733752,0.001074115,0.00280438,0.001963013,0.001567067,0.002369919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006168495,"about_ca_system_score_gemma":0.000889476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001817429,"about_ca_topic_score_gemma":0.001880417,"domain_scores_codex":[0.9992707,0.0001536588,0.00004076705,0.0001495757,0.0003213143,0.0000640208],"domain_scores_gemma":[0.9989402,0.0003316303,0.0001400116,0.0003985237,0.0001275404,0.00006212138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009190516,0.0002168064,0.0009852196,0.0002930147,0.0001606057,0.0004194757,0.0002598241,0.2784447,0.03036377,0.1550961,0.02224009,0.5106013],"study_design_scores_gemma":[0.000068007,0.0001564088,0.0001669578,0.0000265937,0.00004792105,0.0001459111,0.00002725282,0.9099129,0.01297514,0.06219663,0.01422658,0.00004971571],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01230782,0.0003519632,0.9769045,0.0002179703,0.0001101367,0.00008018334,0.0007884466,0.006379673,0.002859429],"genre_scores_gemma":[0.3698848,0.0008308155,0.6109728,0.0006366742,0.0002106537,0.0003509567,0.004300378,0.001825405,0.01098755],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007092942,"threshold_uncertainty_score":0.02372831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02997225018932947,"score_gpt":0.2860760604838954,"score_spread":0.2561038102945659,"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."}}