{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003324413,0.001190688,0.001458423,0.001118022,0.0006406097,0.001202889,0.003349804,0.001486542,0.006411092],"category_scores_gemma":[0.007745877,0.0008439199,0.002448265,0.001763548,0.0006849823,0.001599693,0.002506293,0.002918151,0.003607617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009667119,"about_ca_system_score_gemma":0.002604918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008345433,"about_ca_topic_score_gemma":0.01346448,"domain_scores_codex":[0.9989586,0.0003152328,0.00006909191,0.0002677804,0.0002563489,0.0001329449],"domain_scores_gemma":[0.9984958,0.0006268104,0.0001133003,0.0003678061,0.0002739718,0.0001222878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001234459,0.0003226874,0.01065728,0.0002609311,0.0007757986,0.0005618221,0.0002771523,0.2981491,0.01071328,0.02799389,0.03670134,0.6123524],"study_design_scores_gemma":[0.00004056286,0.00004769742,0.0005725276,0.00001041627,0.00003494167,0.0001298253,0.0000136859,0.9794973,0.002484726,0.01416891,0.002978493,0.00002084593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004071149,0.0001251618,0.988929,0.0001385766,0.00005023107,0.00004896047,0.0005569464,0.005534776,0.0005452846],"genre_scores_gemma":[0.1658268,0.0003179341,0.8186511,0.0007361418,0.0001531009,0.0003607731,0.007717135,0.001433622,0.004803366],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008345433,"threshold_uncertainty_score":0.0214473,"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."}}