{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009435409,0.0004571477,0.0005804755,0.001614974,0.0002336267,0.001233394,0.0008888613,0.001315821,0.002745104],"category_scores_gemma":[0.001818832,0.0002163233,0.000351314,0.001687798,0.001195658,0.00376711,0.0007366082,0.002200639,0.001395339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008631709,"about_ca_system_score_gemma":0.0009172768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006907449,"about_ca_topic_score_gemma":0.0006212075,"domain_scores_codex":[0.9996574,0.0001034365,0.00003007816,0.00005614332,0.0001269421,0.00002602842],"domain_scores_gemma":[0.9993044,0.0004630156,0.00004644865,0.00004425189,0.000115513,0.00002626708],"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":[0.00003557774,0.00003770984,0.000112947,0.00394584,0.00003875206,0.0000834977,0.0001336391,0.00154314,0.001033202,0.1921604,0.02187956,0.7789958],"study_design_scores_gemma":[0.000008841495,0.00004593012,0.0002386868,0.001941046,0.0000276281,0.0004704356,0.00006079636,0.0008844936,0.001121767,0.07044863,0.9247293,0.00002242155],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004352715,0.9884623,0.003376715,0.001993752,0.0003615313,0.000005443166,0.00003316792,0.00004146682,0.005290417],"genre_scores_gemma":[0.008755,0.9825941,0.004250497,0.001128105,0.0005878137,0.00002678996,0.0001030754,0.0000206032,0.002533996],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.002745104,"threshold_uncertainty_score":0.009183228,"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."}}