{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003917444,0.001397307,0.001371212,0.003278209,0.0006812733,0.001826191,0.001319514,0.0009835702,0.001031418],"category_scores_gemma":[0.01947903,0.0005745881,0.00131773,0.002819689,0.001527131,0.00179177,0.00326036,0.002222709,0.0007805686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008088898,"about_ca_system_score_gemma":0.001444246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001638525,"about_ca_topic_score_gemma":0.001694104,"domain_scores_codex":[0.9963163,0.001287001,0.0003023124,0.0007169071,0.001213019,0.0001646129],"domain_scores_gemma":[0.9911726,0.003286202,0.001187859,0.002137436,0.001925465,0.0002904177],"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":[0.0005546189,0.0001948794,0.008165773,0.0005911857,0.000423567,0.0002909668,0.0007024076,0.4718012,0.03822952,0.05960904,0.009802205,0.4096345],"study_design_scores_gemma":[0.00001178951,0.00002956672,0.0006558707,0.00001893299,0.000009208276,0.00005785533,0.00004719304,0.9736613,0.005895326,0.0176063,0.001980566,0.00002607038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01439905,0.000159592,0.9840977,0.0001448751,0.00004181142,0.0000347679,0.0002373153,0.0007108561,0.0001740638],"genre_scores_gemma":[0.1646417,0.0002562996,0.8319237,0.00006422381,0.00006749058,0.0001957549,0.001798998,0.0003261557,0.0007255824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003917444,"threshold_uncertainty_score":0.02071768,"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."}}