{"id":"W3200833013","doi":"10.26434/chemrxiv.9914378.v1","title":"A Diversified Machine Learning Strategy for Predicting and Understanding Molecular Melting Points","year":2019,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; Canadian Institute for Advanced Research","funders":"Argonne National Laboratory; Office of Science; U.S. Department of Energy","keywords":"Autoencoder; Computer science; Molecular graph; Cluster analysis; Embedding; Graph; Machine learning; Artificial intelligence; Artificial neural network; Unsupervised learning; Quantum chemical; Gaussian; Data mining; Theoretical computer science; Molecule; Chemistry; Computational chemistry","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00108712,0.0002964112,0.0003599403,0.0001691322,0.0002101806,0.0004556857,0.000666166,0.0001788756,0.000003867798],"category_scores_gemma":[0.0003938577,0.0003287183,0.0001497646,0.0001546987,0.0000430728,0.000257738,0.002132362,0.0006239632,0.000002876299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002167071,"about_ca_system_score_gemma":0.0001769954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002898974,"about_ca_topic_score_gemma":0.000001438889,"domain_scores_codex":[0.9979802,0.0001649316,0.0003085634,0.0008864362,0.000314657,0.0003451786],"domain_scores_gemma":[0.9982278,0.0008720739,0.0003190221,0.0003936548,0.00008765501,0.00009980778],"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":[0.00003937997,0.00004428593,0.006215923,0.001133987,0.0002878944,0.00002967825,0.001873239,0.892263,0.002067975,0.08921679,0.0000458639,0.006781987],"study_design_scores_gemma":[0.0004730439,0.00004072098,0.0003792043,0.0002042887,0.00003140739,0.000007703287,0.0001457591,0.9277014,0.001732285,0.06892972,0.00003468055,0.0003197628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1319954,0.0004018138,0.8651921,0.0003100549,0.0004004066,0.0004622679,0.000004731271,0.0001712766,0.001061915],"genre_scores_gemma":[0.9095154,0.00001620514,0.09018543,0.00006570879,0.00006713509,0.00002224557,0.00003805039,0.00002951928,0.00006033745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7775199,"threshold_uncertainty_score":0.9999165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0899894111836564,"score_gpt":0.3186088813011674,"score_spread":0.228619470117511,"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."}}