{"id":"W4407009368","doi":"10.1038/s41467-025-56273-3","title":"STICI: Split-Transformer with integrated convolutions for genotype imputation","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Army Research Laboratory; National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health; National Science Foundation","keywords":"Imputation (statistics); Genotype; Computer science; Computational biology; Biology; Genetics; Missing data; Gene; Machine learning","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":[0.0000904972,0.00009208629,0.00007628861,0.00007521918,0.0002493432,0.00002219324,0.0003738455,0.0002174116,0.000005892681],"category_scores_gemma":[0.00008452484,0.00007762716,0.00004572945,0.0002550754,0.00007900662,0.000004633079,0.00002590362,0.000203756,0.000002079487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002885737,"about_ca_system_score_gemma":0.0002311994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001125389,"about_ca_topic_score_gemma":0.0003778206,"domain_scores_codex":[0.999459,0.00004446198,0.0001473007,0.000182866,0.00005530925,0.0001110369],"domain_scores_gemma":[0.9987139,0.00003547072,0.000054842,0.0007962175,0.000368292,0.00003131641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004540794,0.0002907581,0.004009938,0.00005496114,0.000237453,9.654191e-8,0.0001337833,0.0002210856,0.7866456,0.1444671,0.04594455,0.01754065],"study_design_scores_gemma":[0.001034124,0.0001402642,0.01813216,0.00005581848,0.0001009821,0.000002709656,0.0004287586,0.001138279,0.07151345,0.0007129148,0.9065291,0.0002114448],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1034936,0.01719213,0.8437356,0.01411962,0.0005418615,0.002133389,0.0003558635,0.0001305283,0.01829745],"genre_scores_gemma":[0.9809579,0.0004039381,0.01493717,0.0004691662,0.00002617211,0.0002843634,0.001539588,0.00001106499,0.001370693],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8774642,"threshold_uncertainty_score":0.3165544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01160398433577059,"score_gpt":0.3147372058458723,"score_spread":0.3031332215101017,"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."}}