{"id":"W4406717052","doi":"10.1101/2025.01.19.633789","title":"Towards whole-genome inference of polygenic scores with fast and memory-efficient algorithms","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Inference; Algorithm; Computer science; Artificial intelligence; Computational biology; Biology","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":[0.003050162,0.001472581,0.001347327,0.001831916,0.0005975093,0.002302448,0.00312347,0.001191383,0.005372983],"category_scores_gemma":[0.01410115,0.00109486,0.001652889,0.002433684,0.001050189,0.001838873,0.002794676,0.002845456,0.002822888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105221,"about_ca_system_score_gemma":0.002792891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01697412,"about_ca_topic_score_gemma":0.01902322,"domain_scores_codex":[0.9985018,0.0005679097,0.00009197943,0.0004112486,0.0003328066,0.00009431596],"domain_scores_gemma":[0.9949911,0.00309136,0.0002490724,0.0008684911,0.0006314649,0.0001684553],"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":[0.0005226052,0.0002202972,0.008376413,0.0003258278,0.0004767569,0.0003011105,0.0002551565,0.666768,0.008511959,0.0426814,0.02178646,0.249774],"study_design_scores_gemma":[0.00007564621,0.00001370787,0.0004411942,0.00001236295,0.00001600715,0.00002192758,0.00001573975,0.9728854,0.000941405,0.02393381,0.001631409,0.00001135449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01294325,0.0003055759,0.9782268,0.000325175,0.00008280215,0.00005004361,0.0005633506,0.006601982,0.0009009698],"genre_scores_gemma":[0.07468834,0.0001537204,0.9205348,0.0002470845,0.0001139811,0.0001776393,0.001978444,0.0008793697,0.001226593],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01697412,"threshold_uncertainty_score":0.03375065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01119197926842277,"score_gpt":0.2364627982539334,"score_spread":0.2252708189855107,"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."}}