{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T18:41:16Z","timestamp":1773859276542,"version":"3.50.1"},"reference-count":28,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ascpt.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Clin Pharma and Therapeutics"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:p>\n                    Multiple imputation is well\u2010established for handling missing data, yet its use in high\u2010dimensional genetic datasets remains limited. Using pharmacokinetic tuberculosis simulations and SNP data (1000 Genomes Project), we compared machine learning (ML) and traditional approaches (e.g., mean imputation and complete\u2010case analysis) for imputation and covariate selection. We developed a multiple imputation framework incorporating genotype probabilities, imputation uncertainty (INFO score), and missingness percentages. Dimensionality reduction enabled scalable random forest and penalized regression for covariate selection. In simulations, only multiple imputation achieved adequate coverage (percentage of 95% confidence intervals containing the true value) exceeding a 90% nominal threshold. For example, on the imputation server, coverage improved from 0% with single imputation to up to 94% under 10% missingness. Applied to clinical warfarin datasets (War\u2010PATH,\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u2009548; IWPC,\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u2009316) and the UK Biobank (\n                    <jats:italic>n<\/jats:italic>\n                    \u2009=\u2009500, 1000), multiple imputation recovered known pharmacogenomic associations (\n                    <jats:italic>CYP2C9<\/jats:italic>\n                    <jats:italic>*8\/*9\/*<\/jats:italic>\n                    <jats:italic>11; VKORC1 \u20101639G&gt;A<\/jats:italic>\n                    ), reduced false\u2010positives, and detected signals missed by single imputation (e.g., genome\u2010wide significant rs4697699,\n                    <jats:italic>SLC2A9<\/jats:italic>\n                    locus). Computational costs were modest, adding only ~1.25\u2009minutes for 10 imputations to the 22.7\u2009minutes required by single imputation on the Michigan Imputation Server. For SNP selection, penalized regression performed best in the high\u2010effect scenario (F1\u2009=\u20090.897\u2009\u00b1\u20090.091), while GWAS followed by random forest performed best in the low\u2010effect scenario (F1\u2009=\u20090.657\u2009\u00b1\u20090.110). These findings show that multiple imputation improves reliability and discovery in high\u2010dimensional pharmacogenomics, with ML offering promising but inconsistent benefits during SNP selection. However, generalizability beyond the studied datasets and computational scalability to larger biobank\u2010scale analyses remain important limitations that warrant further investigation.\n                  <\/jats:p>","DOI":"10.1002\/cpt.70171","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T01:31:13Z","timestamp":1766021473000},"page":"964-978","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Genotype Imputation in High\u2010Dimensional Pharmacogenomics Using Multiple Imputation: Evaluation with Machine Learning Approaches"],"prefix":"10.1002","volume":"119","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1196-1822","authenticated-orcid":false,"given":"Innocent G.","family":"Asiimwe","sequence":"first","affiliation":[{"name":"Department of Health Data Science, Institute of Population Health Sciences University of Liverpool  Liverpool UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2033-6188","authenticated-orcid":false,"given":"Tao","family":"You","sequence":"additional","affiliation":[{"name":"Department of Pharmacology and Therapeutics, Institute of Systems, Molecular and Integrative Biology University of Liverpool  Liverpool UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8028-4282","authenticated-orcid":false,"given":"Daniel F.","family":"Carr","sequence":"additional","affiliation":[{"name":"Department of Pharmacology and Therapeutics, Institute of Systems, Molecular and Integrative Biology University of Liverpool  Liverpool UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7534-7266","authenticated-orcid":false,"given":"Munir","family":"Pirmohamed","sequence":"additional","affiliation":[{"name":"Department of Pharmacology and Therapeutics, Institute of Systems, Molecular and Integrative Biology University of Liverpool  Liverpool UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3819-490X","authenticated-orcid":false,"given":"Geraint","family":"Davies","sequence":"additional","affiliation":[{"name":"Department of Clinical Infection, Microbiology &amp; Immunology, Institute of Infection, Veterinary &amp; Ecological Sciences University of Liverpool  Liverpool UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6977-9337","authenticated-orcid":false,"given":"Andrea L.","family":"Jorgensen","sequence":"additional","affiliation":[{"name":"Department of Health Data Science, Institute of Population Health Sciences University of Liverpool  Liverpool UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"name":"the UNITE4TB Consortium","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,12,17]]},"reference":[{"key":"e_1_2_13_1_1","doi-asserted-by":"publisher","DOI":"10.1093\/jssam\/smab038"},{"key":"e_1_2_13_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10928-021-09757-w"},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.1208\/s12248-024-00934-6"},{"key":"e_1_2_13_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/cts.13379"},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.5588\/ijtld.21.0515"},{"key":"e_1_2_13_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/ng.3656"},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature15393"},{"key":"e_1_2_13_8_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr330"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.1201\/9780429492259"},{"key":"e_1_2_13_10_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v045.i03"},{"key":"e_1_2_13_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/psp4.12874"},{"key":"e_1_2_13_12_1","doi-asserted-by":"publisher","DOI":"10.1208\/s12248-013-9526-y"},{"key":"e_1_2_13_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/psp4.12611"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/psp4.70039"},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0187624"},{"key":"e_1_2_13_16_1","unstructured":"Lixoft SAS aSPc.lixoftConnectors: R connectors for Lixoft Suite (@Lixoft). R package version 2024.1(2024)."},{"key":"e_1_2_13_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4067"},{"key":"e_1_2_13_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316696"},{"key":"e_1_2_13_19_1","unstructured":"Ding Z. Tian J. Wang Z. Zhao J.&Li S.Data imputation using large language model to accelerate recommender system.arXiv2407.10078 1\u20137 (2024)."},{"key":"e_1_2_13_20_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2022.967082"},{"key":"e_1_2_13_21_1","doi-asserted-by":"publisher","DOI":"10.1182\/bloodadvances.2024014227"},{"key":"e_1_2_13_22_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa0809329"},{"key":"e_1_2_13_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.3229"},{"key":"e_1_2_13_24_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v028.i05"},{"key":"e_1_2_13_25_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13742-015-0047-8"},{"key":"e_1_2_13_26_1","first-page":"Unit1.19","article-title":"Quality control procedures for genome\u2010wide association studies","volume":"1","author":"Turner S.","year":"2011","journal-title":"Curr. Protoc. Hum. Genet."},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1003344"},{"key":"e_1_2_13_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2006.01.009"}],"container-title":["Clinical Pharmacology &amp; Therapeutics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpt.70171","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cpt.70171","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpt.70171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T11:42:51Z","timestamp":1773834171000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/10.1002\/cpt.70171"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1002\/cpt.70171"],"URL":"https:\/\/doi.org\/10.1002\/cpt.70171","archive":["Portico"],"relation":{},"ISSN":["0009-9236","1532-6535"],"issn-type":[{"value":"0009-9236","type":"print"},{"value":"1532-6535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2025-08-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}