{"id":"W3206711231","doi":"10.48550/arxiv.2110.07728","title":"Pre-training Molecular Graph Representation with 3D Geometry","year":2021,"lang":"en","type":"preprint","venue":"NPARC","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":154,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Molecular graph; Discriminative model; Computer science; Graph; Representation (politics); Consistency (knowledge bases); Theoretical computer science; Encoder; Training set; Artificial intelligence; Machine learning; Topology (electrical circuits); Mathematics; Combinatorics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006263735,0.001298896,0.001436157,0.00130586,0.0004989792,0.0009381768,0.002734455,0.002123736,0.005455604],"category_scores_gemma":[0.00410829,0.0007379351,0.001392377,0.001535895,0.001024036,0.002353979,0.0016977,0.002746755,0.00270801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009960519,"about_ca_system_score_gemma":0.001334607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003503973,"about_ca_topic_score_gemma":0.006826123,"domain_scores_codex":[0.9992913,0.000179028,0.00002398914,0.0002633952,0.0001759339,0.0000664043],"domain_scores_gemma":[0.9983243,0.0007247232,0.0001455711,0.0005094302,0.0002104745,0.00008540569],"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":[0.0002694069,0.0003610949,0.0022491,0.0005326468,0.0001165508,0.0002592139,0.00009182046,0.4729345,0.01634609,0.01792541,0.02807522,0.4608389],"study_design_scores_gemma":[0.00001470698,0.00006696624,0.0001950419,0.00001228233,0.00001237373,0.00005676098,0.00001820492,0.9829275,0.003674287,0.01091715,0.002096104,0.000008749104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04665663,0.001024712,0.9356585,0.0009344291,0.0001650165,0.0001698756,0.001429062,0.009952237,0.004009512],"genre_scores_gemma":[0.5360529,0.0009997413,0.4449762,0.001039328,0.0001509544,0.0003809661,0.009846193,0.0008345388,0.005719143],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005455604,"threshold_uncertainty_score":0.01825082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03343152167548662,"score_gpt":0.3201977049787594,"score_spread":0.2867661833032727,"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."}}