{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002437124,0.0001993971,0.0001834893,0.0002919329,0.0001004847,0.001741221,0.0006782938,0.0000485682,0.000004236257],"category_scores_gemma":[0.0002337618,0.0002065085,0.0001808184,0.001507788,0.00004570788,0.004296132,0.0004598897,0.0001136236,0.0001610074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008615111,"about_ca_system_score_gemma":0.0001134857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001366693,"about_ca_topic_score_gemma":0.000001377278,"domain_scores_codex":[0.9979518,0.00008689006,0.0003080272,0.0006196414,0.0006634379,0.0003702134],"domain_scores_gemma":[0.9986603,0.0004993134,0.0001022032,0.0005871371,0.00005473976,0.00009634197],"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":[0.00002250934,0.0001496846,0.00187034,0.00004591966,0.00005625145,0.0002046383,0.000228713,0.798867,0.001495802,0.1709372,0.001159219,0.02496274],"study_design_scores_gemma":[0.001030123,0.0001229937,0.01976131,0.0001079226,0.00001350449,0.00001191579,0.0002570507,0.9009454,0.006859804,0.06926323,0.0009068716,0.0007199321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3314061,0.00002377289,0.6655,0.0003073231,0.000270231,0.0001510193,0.00003045356,0.0003883564,0.001922715],"genre_scores_gemma":[0.9871529,0.000003344943,0.01195417,0.0002856937,0.00005304853,0.00004334317,0.0002168284,0.00002460653,0.0002660104],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6557469,"threshold_uncertainty_score":0.9992951,"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."}}