{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001572109,0.0008051482,0.0004971022,0.001288421,0.000487932,0.001025613,0.001018469,0.00134846,0.002143192],"category_scores_gemma":[0.007219484,0.0005728075,0.0008314367,0.001092018,0.00263479,0.003087582,0.00140003,0.002289128,0.0003785015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001853707,"about_ca_system_score_gemma":0.0006303987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004387116,"about_ca_topic_score_gemma":0.003310315,"domain_scores_codex":[0.9995701,0.0001584727,0.00002573716,0.0001133494,0.000087326,0.00004503618],"domain_scores_gemma":[0.9978022,0.001576593,0.0001701539,0.0001958216,0.0001987262,0.00005651971],"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":[0.00003198031,0.00002305921,0.001042825,0.00009740258,0.00003305203,0.00008451732,0.0001123071,0.1381402,0.001900049,0.8165976,0.00141432,0.04052261],"study_design_scores_gemma":[0.000004551973,0.00001785124,0.000362587,0.00002329969,0.000006552317,0.00004309445,0.00001356948,0.4897137,0.0006569813,0.507648,0.001495839,0.00001406121],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0167822,0.001180874,0.976232,0.001245836,0.00004707046,0.00001327111,0.0000602859,0.0001536205,0.004284916],"genre_scores_gemma":[0.5394247,0.004822101,0.4416083,0.0009758351,0.0004901678,0.0002287351,0.0002969428,0.0003497467,0.01180339],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004387116,"threshold_uncertainty_score":0.01344961,"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."}}