{"id":"W3142115687","doi":"10.1093/bib/bbab365","title":"Using molecular embeddings in QSAR modeling: does it make a difference?","year":2021,"lang":"en","type":"preprint","venue":"Briefings in Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Agencia Nacional de Promoción Científica y Tecnológica; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Quantitative structure–activity relationship; Embedding; Molecular descriptor; Computer science; Artificial intelligence; Similarity (geometry); Machine learning","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":[0.004255692,0.001147361,0.001357582,0.0008202615,0.0003082625,0.00233775,0.001263264,0.00198025,0.002412709],"category_scores_gemma":[0.01939961,0.00069826,0.0009308512,0.001613809,0.00181333,0.01037978,0.001788341,0.003318054,0.001397845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004276869,"about_ca_system_score_gemma":0.0006859655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008339138,"about_ca_topic_score_gemma":0.001148815,"domain_scores_codex":[0.9983183,0.0009109163,0.000111864,0.0002163655,0.0003558838,0.00008673356],"domain_scores_gemma":[0.9931838,0.004316038,0.0005492652,0.001167718,0.00065518,0.0001280392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003872057,0.0002239964,0.005151839,0.001239986,0.0003755534,0.0001410798,0.0002754672,0.2108703,0.006659266,0.1260792,0.0068631,0.641733],"study_design_scores_gemma":[0.00007807062,0.0005157848,0.001742232,0.0006303125,0.0001707006,0.0002704745,0.0002797472,0.71529,0.009133292,0.2470371,0.02472709,0.0001253704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04759128,0.02355721,0.9081843,0.01201995,0.0009192476,0.00008920582,0.0003952221,0.0009054622,0.006338032],"genre_scores_gemma":[0.5696496,0.03413509,0.3888747,0.002024067,0.0008054199,0.0001780927,0.0008143538,0.0005743065,0.002944379],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004255692,"threshold_uncertainty_score":0.02250654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05624475321727422,"score_gpt":0.3319905884313202,"score_spread":0.275745835214046,"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."}}