{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001726266,0.0008601221,0.0008113991,0.00161652,0.0003896783,0.0008366789,0.001451665,0.001068244,0.0007092779],"category_scores_gemma":[0.004619744,0.0005294578,0.0009556363,0.0009988724,0.001275438,0.002457603,0.00162652,0.002032305,0.0002800577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008551035,"about_ca_system_score_gemma":0.0007503966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001382255,"about_ca_topic_score_gemma":0.001788195,"domain_scores_codex":[0.9994622,0.0001809714,0.00003147773,0.0001660589,0.0001299964,0.00002940613],"domain_scores_gemma":[0.9984416,0.0006809201,0.0002229649,0.0004064213,0.0001796999,0.00006838916],"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":[0.00006181012,0.00006877934,0.002274734,0.00007226218,0.00009883683,0.00005458705,0.00008720141,0.9028787,0.008423377,0.02624704,0.0005335418,0.05919907],"study_design_scores_gemma":[0.000002277526,0.00001260367,0.0001554215,0.000003338334,0.000004044346,0.000008262513,0.000003869217,0.9836662,0.001110852,0.0148324,0.0001963273,0.000004432836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02720553,0.0001765175,0.9713895,0.0001980552,0.000009231054,0.00002692765,0.00009978156,0.0003908194,0.0005036158],"genre_scores_gemma":[0.6351685,0.0004251169,0.3619603,0.0002122502,0.00005435646,0.000178888,0.0005885374,0.0001480309,0.001264066],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001726266,"threshold_uncertainty_score":0.009129524,"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."}}