{"id":"W4406859606","doi":"10.1101/2025.01.24.634804","title":"Refining sequence-to-activity models by increasing model resolution","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Chromatin; Computational biology; Computer science; Sequence (biology); Gene regulatory network; Artificial intelligence; Sequence motif; Biology; Genetics; Gene; Gene expression","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":[0.001768681,0.001571991,0.00120676,0.0006795967,0.0003804434,0.00123375,0.001450528,0.001922151,0.002330233],"category_scores_gemma":[0.007196002,0.0007691383,0.001716544,0.0004641044,0.0007037923,0.001796006,0.001125778,0.003813083,0.0007452715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001076857,"about_ca_system_score_gemma":0.001230658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007696543,"about_ca_topic_score_gemma":0.008963847,"domain_scores_codex":[0.9994463,0.0002119091,0.00003068186,0.0001887464,0.0000741204,0.00004815403],"domain_scores_gemma":[0.9969553,0.002407635,0.0001537838,0.000238356,0.0001463973,0.00009847953],"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":[0.00006235958,0.0000415082,0.001153085,0.0000287118,0.00004816808,0.00003956863,0.00002318864,0.9878297,0.002069212,0.001714805,0.0003333572,0.006656356],"study_design_scores_gemma":[0.000003948522,0.000006816386,0.0000638334,0.000002416357,0.000004148946,0.000004051127,0.000002173172,0.9977111,0.0003060522,0.00179579,0.00009702689,0.000002668501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2173761,0.0007139324,0.7732279,0.00134993,0.00009840483,0.00009858593,0.001089321,0.002282046,0.003763771],"genre_scores_gemma":[0.8978271,0.0003282053,0.09656454,0.0005426308,0.00006589549,0.0002648501,0.001595424,0.0003430097,0.002468331],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007696543,"threshold_uncertainty_score":0.01530349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02914561722415017,"score_gpt":0.2431225174466088,"score_spread":0.2139769002224586,"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."}}