{"id":"W2023937877","doi":"10.1007/s10822-004-5319-9","title":"Locally Linear Embedding for dimensionality reduction in QSAR","year":2004,"lang":"en","type":"article","venue":"Journal of Computer-Aided Molecular Design","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal; AstraZeneca (Canada); Université de Montréal","funders":"","keywords":"Dimensionality reduction; Quantitative structure–activity relationship; Embedding; Curse of dimensionality; Feature selection; Representation (politics); Reduction (mathematics); Computer science; Artificial intelligence; Nonlinear dimensionality reduction; Pattern recognition (psychology); Mathematics; Data mining; 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":[0.001197514,0.0008351917,0.001526298,0.0007262878,0.000451176,0.0008040242,0.00103974,0.0009371864,0.002256517],"category_scores_gemma":[0.004598868,0.0005333628,0.001028169,0.0008763144,0.0008151804,0.001772132,0.001517142,0.001969886,0.0007674617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005339976,"about_ca_system_score_gemma":0.0008169413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003129131,"about_ca_topic_score_gemma":0.002431985,"domain_scores_codex":[0.9989451,0.0005971498,0.00006285802,0.0001129669,0.0002168702,0.0000651252],"domain_scores_gemma":[0.9978693,0.001330707,0.0001186247,0.0003527938,0.000275598,0.00005302585],"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":[0.0002319273,0.0001955519,0.0006080067,0.000285589,0.0001073764,0.00005859921,0.0001353851,0.6736038,0.005995485,0.03220306,0.005118215,0.281457],"study_design_scores_gemma":[0.00000602302,0.0000361675,0.00007444373,0.000004520745,0.000006316719,0.000007640579,0.000008913323,0.9910156,0.0005911405,0.007819328,0.0004225059,0.000007415397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02014706,0.001015718,0.9767864,0.0003285256,0.00005333728,0.00005039451,0.000196676,0.000626855,0.0007950055],"genre_scores_gemma":[0.5214073,0.001441523,0.4692712,0.0002344937,0.000174051,0.0004576946,0.001415043,0.0003395266,0.00525914],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003129131,"threshold_uncertainty_score":0.007548809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03451273211108479,"score_gpt":0.3313538552061729,"score_spread":0.2968411230950881,"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."}}