{"id":"W4320913459","doi":"10.1101/2023.02.13.528380","title":"Orthogonal outlier detection and dimension estimation for improved MDS embedding of biological datasets","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Outlier; Dimensionality reduction; Multidimensional scaling; Nonlinear dimensionality reduction; Anomaly detection; Embedding; Pattern recognition (psychology); Computer science; Dimension (graph theory); Curse of dimensionality; Clustering high-dimensional data; Artificial intelligence; Robust statistics; Data point; Data mining; Mathematics; Machine learning; Cluster analysis; Combinatorics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006534171,0.0003231452,0.0003366731,0.0001286743,0.0001165428,0.00005732461,0.0002130629,0.000612364,0.00000239988],"category_scores_gemma":[0.0008750429,0.00031536,0.000100739,0.0001123894,0.000103163,0.00001004507,0.0005965129,0.000289709,0.00000353099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003216343,"about_ca_system_score_gemma":0.0001121539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001094551,"about_ca_topic_score_gemma":0.000002577743,"domain_scores_codex":[0.9984547,0.00007121381,0.0004915958,0.000576221,0.0001257787,0.0002804115],"domain_scores_gemma":[0.9985204,0.00005337342,0.0004821199,0.0006272281,0.000214415,0.0001024619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009806734,0.00003320007,0.001529048,0.0003968951,0.00009430574,7.325e-7,0.000003908204,0.001141881,0.9964824,0.00005776691,0.0001281,0.00003367672],"study_design_scores_gemma":[0.001089962,0.000584028,0.04218252,0.0002616286,0.0001561663,1.005771e-7,0.000004903302,0.2550622,0.6956006,0.00001071986,0.00415023,0.0008969034],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8894928,0.0001842025,0.107578,0.00005041319,0.0005571914,0.0007781931,0.001253554,0.0001043826,0.000001286284],"genre_scores_gemma":[0.9481749,0.0001393249,0.05121478,0.00005338597,0.0001808123,0.0001158717,0.00005519763,0.00006329601,0.000002441866],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3008818,"threshold_uncertainty_score":0.9999298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01651000590205291,"score_gpt":0.2668083678826167,"score_spread":0.2502983619805638,"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."}}