{"id":"W3112351343","doi":"10.1088/2632-2153/ac09d6","title":"Deep molecular dreaming: inverse machine learning for de-novo molecular design and interpretability with surjective representations","year":2021,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto","funders":"Office of Naval Research; Tata Steel","keywords":"Chemical space; Artificial intelligence; Computer science; Machine learning; Interpretability; Cheminformatics; Representation (politics); Property (philosophy); Generative model; Generative grammar; Chemistry; Drug discovery; Biology; Computational chemistry; Bioinformatics","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":[0.001586761,0.0007028955,0.0009711274,0.0007091917,0.000320196,0.001570037,0.001769157,0.001326673,0.003334429],"category_scores_gemma":[0.005245901,0.000502146,0.0009467734,0.0005761289,0.001251975,0.001987833,0.001862459,0.002758782,0.0005737695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001166848,"about_ca_system_score_gemma":0.0008868635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001514711,"about_ca_topic_score_gemma":0.002325876,"domain_scores_codex":[0.9994375,0.0002266944,0.00002930854,0.0001262229,0.0001373056,0.00004293417],"domain_scores_gemma":[0.99823,0.001067946,0.0001140145,0.0003336272,0.0001775267,0.00007686544],"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":[0.0001264756,0.0001336638,0.001226638,0.0002442842,0.00009315501,0.00008984263,0.0001243162,0.7852718,0.004043441,0.07762067,0.003288776,0.1277369],"study_design_scores_gemma":[0.000005834238,0.00001561232,0.00003809644,0.000008799948,0.000002757253,0.000005264912,0.000005117216,0.9779812,0.000600824,0.02083402,0.0004995851,0.000002939859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04263147,0.0008845627,0.9494314,0.0008325971,0.00006167517,0.00005734965,0.0001668196,0.001501896,0.004432257],"genre_scores_gemma":[0.6288204,0.0004505253,0.3647337,0.0005704039,0.00007589174,0.0001771613,0.0007363094,0.0003122837,0.004123403],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003334429,"threshold_uncertainty_score":0.01115477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01320056893517005,"score_gpt":0.2976142649902339,"score_spread":0.2844136960550638,"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."}}