{"id":"W4306179830","doi":"10.1016/j.patter.2022.100588","title":"SELFIES and the future of molecular string representations","year":2022,"lang":"en","type":"review","venue":"Patterns","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":267,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"National Institute of General Medical Sciences; European Research Council; Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme; National Centre of Competence in Research Robotics; University of Toronto; Horizon 2020; Amazon Web Services; Universität Wien; Office of Science; Austrian Science Fund; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Consejo Nacional de Ciencia y Tecnología; National Science Foundation; Deutsche Forschungsgemeinschaft; Fundação de Amparo à Pesquisa do Estado de São Paulo; U.S. Department of Energy; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Cheminformatics; Computer science; String (physics); Artificial intelligence; Interpretability; Context (archaeology); Popularity; Representation (politics); Perspective (graphical); Data science; Cognitive science; Chemistry; Computational chemistry; Physics; Theoretical physics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001124717,0.0001985754,0.0007386023,0.00007800089,0.0001908042,0.0001197535,0.0007198886,0.00005646863,0.002330702],"category_scores_gemma":[0.0001358643,0.0001225243,0.0001447468,0.0001717457,0.0001885694,0.00006546239,0.00059712,0.0002329431,0.00001833878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002187288,"about_ca_system_score_gemma":0.00006131861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001490278,"about_ca_topic_score_gemma":0.000007698321,"domain_scores_codex":[0.9977567,0.000860378,0.0004458947,0.0003773277,0.0003745743,0.0001851014],"domain_scores_gemma":[0.9984539,0.0004535643,0.0004836939,0.0005555746,0.0000185507,0.00003478446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003351972,0.00008827032,0.0004383088,0.04216727,0.0001487775,0.0001061894,0.00404444,0.0005349186,0.001976817,0.02384263,0.000591083,0.9260278],"study_design_scores_gemma":[0.0002405319,0.00002387769,0.00004266504,0.00106769,0.000303263,0.00008969293,0.0002583573,0.00003799014,0.0002071897,0.0003395916,0.9971101,0.0002790379],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002200361,0.9955239,0.000419598,0.0001041674,0.0008321166,0.0004623456,0.0001349635,0.00004172361,0.0002808729],"genre_scores_gemma":[0.0005717718,0.9985197,0.0004502006,0.00003539548,0.0001434463,0.0001427156,0.00002276009,0.00002403494,0.00009004601],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.996519,"threshold_uncertainty_score":0.9985813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02486925247903319,"score_gpt":0.3301125758047184,"score_spread":0.3052433233256852,"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."}}