{"id":"W4385724762","doi":"10.3389/fbinf.2023.1211819","title":"Orthogonal outlier detection and dimension estimation for improved MDS embedding of biological datasets","year":2023,"lang":"en","type":"article","venue":"Frontiers in Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Dimensionality reduction; Multidimensional scaling; Outlier; Computer science; Nonlinear dimensionality reduction; Anomaly detection; Visualization; Pattern recognition (psychology); Embedding; Clustering high-dimensional data; Data mining; Dimension (graph theory); Data point; Artificial intelligence; Curse of dimensionality; Mathematics; Machine learning; Cluster analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.0003188602,0.00008980862,0.000147196,0.0001542543,0.00003880027,0.00001286985,0.00007166296,0.0001291487,6.407316e-7],"category_scores_gemma":[0.000181878,0.00008012464,0.00004542422,0.0001565473,0.00006026876,0.00001452215,0.00009287008,0.00004358185,5.868275e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001164808,"about_ca_system_score_gemma":0.00001193297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002634757,"about_ca_topic_score_gemma":0.000004901591,"domain_scores_codex":[0.9993764,0.00001477846,0.0002969,0.000123615,0.00005214925,0.0001361469],"domain_scores_gemma":[0.9996279,0.00001320337,0.0001225662,0.0001724471,0.00003709389,0.00002676466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003857556,0.00008712745,0.009899307,0.000337056,0.0001578922,0.000001234702,0.0003474207,0.001268837,0.638834,0.00003600946,0.03683956,0.3118058],"study_design_scores_gemma":[0.0004209653,0.0002266765,0.001125378,0.00001679947,0.0000231115,0.000002820949,0.0002313337,0.8446046,0.1495491,0.0002806289,0.003378189,0.0001404109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3202895,0.00008022501,0.6790397,0.00001707453,0.00007131392,0.0003273936,0.0000832639,0.00003099039,0.00006061158],"genre_scores_gemma":[0.5974871,0.000408644,0.3991305,0.00006815841,0.00002816222,0.00004089867,0.002792327,0.00001255896,0.00003166819],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8433357,"threshold_uncertainty_score":0.3267388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01024526259367467,"score_gpt":0.2778625048076531,"score_spread":0.2676172422139784,"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."}}