{"id":"W4396515244","doi":"10.1089/cmb.2024.0483","title":"On Minimizers and Convolutional Filters: Theoretical Connections and Applications to Genome Analysis","year":2024,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Convolutional neural network; Categorical variable; Computer science; Pooling; Sequence (biology); Initialization; Hash function; Pattern recognition (psychology); Artificial intelligence; Mathematics; Algorithm; Biology; Machine learning; Genetics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002105014,0.00007443074,0.00012845,0.0002362236,0.00005747982,0.00003016844,0.00006360676,0.00006689366,0.00004350026],"category_scores_gemma":[0.0001078448,0.00006080547,0.00006819033,0.0001582812,0.0001748302,0.000003756056,0.00004036876,0.0001074502,0.000005836162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001160914,"about_ca_system_score_gemma":0.00005612588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.804894e-7,"about_ca_topic_score_gemma":6.097591e-7,"domain_scores_codex":[0.9994354,0.00005095922,0.0002415733,0.0001201164,0.00007137779,0.00008061587],"domain_scores_gemma":[0.9994412,0.0002415144,0.00006760917,0.00005392318,0.0001103886,0.00008533295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001771893,0.00005641644,0.002175095,0.00003355227,0.001395363,0.000003342721,0.0001610284,0.1298986,0.006295225,0.8551042,0.001115746,0.003584245],"study_design_scores_gemma":[0.002618771,0.006929037,0.1009489,0.00009325361,0.001558546,0.002070193,0.0004373578,0.1967422,0.0005296413,0.3717105,0.3152528,0.001108871],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.403716,0.0006136377,0.5928514,0.002128375,0.00009087423,0.00009807022,0.00008552252,0.000007652567,0.0004084643],"genre_scores_gemma":[0.985846,0.00004098137,0.01315367,0.000624894,0.0001677943,0.000005527108,0.0001282978,0.000004877078,0.00002797237],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.58213,"threshold_uncertainty_score":0.2479575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00539845112460039,"score_gpt":0.2879018184740523,"score_spread":0.2825033673494519,"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."}}