Pharmacogenomics-Driven Prediction of Antidepressant Treatment Outcomes: A Machine-Learning Approach With Multi-trial Replication

• Type of Material: Article
• Authors: ARjun P. Athreya, University of Illinois; Drew Neavin, Mayo Clinic; Tania Carrillo-Roa, Max Planck Institute of Psychiatry; Michelle Skime, Mayo Clinic; Joanna Biernacka, Mayo Clinic; Mark A. Frye, Mayo Clinic; A. John Rush, Duke University; Liewei Wang, Mayo Clinic; Elisabeth Binder, Emory University; Ravishankar K. Iyer, University of Illinois; Richard M. Weinshilboum, Mayo Clinic; William V. Bobo, Mayo Clinic
• Language: English
• Date: 2019-10-01
• Publisher: WILEY
• Publication Version: Final Published Version
• Copyright Statement: © 2019 The Authors Clinical Pharmacology & Therapeutics published by Wiley Periodicals, Inc. on behalf of American Society for Clinical Pharmacology and Therapeutics
• License: Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1002/cpt.1482
• Title of Journal or Parent Work: CLINICAL PHARMACOLOGY & THERAPEUTICS
• Volume: 106
• Issue: 4
• Start Page: 855
• End Page: 865
• Grant/Funding Information: This material is based upon work partially supported by a Mayo Clinic and Illinois Alliance Fellowship for Technology‐Based Healthcare Research; a CompGen Fellowship; an IBM Faculty Award; the National Science Foundation under grant CNS 13‐37732; the National Institutes of Health under grants U19 GM61388, R01 GM28157, RC2 GM092729, R24 GM078233, RC2 GM092729, and T32 GM072474; and the Mayo Clinic Center for Individualized Medicine.
• Keywords: Pharmacology & Pharmacy; POLYMORPHISMS; SEROTONIN REUPTAKE INHIBITORS; GENE; CYTOCHROME-P450 ENZYMES; CITALOPRAM; STAR-ASTERISK-D; DEPRESSIVE SYMPTOMS; GENDER-DIFFERENCES; Science & Technology; PREDICTABILITY; SEX-DIFFERENCES; Life Sciences & Biomedicine
• Research Categories: Health Sciences, Pharmacology; Biology, Genetics

Abstract

We set out to determine whether machine learning–based algorithms that included functionally validated pharmacogenomic biomarkers joined with clinical measures could predict selective serotonin reuptake inhibitor (SSRI) remission/response in patients with major depressive disorder (MDD). We studied 1,030 white outpatients with MDD treated with citalopram/escitalopram in the Mayo Clinic Pharmacogenomics Research Network Antidepressant Medication Pharmacogenomic Study (PGRN-AMPS; n = 398), Sequenced Treatment Alternatives to Relieve Depression (STAR*D; n = 467), and International SSRI Pharmacogenomics Consortium (ISPC; n = 165) trials. A genomewide association study for PGRN-AMPS plasma metabolites associated with SSRI response (serotonin) and baseline MDD severity (kynurenine) identified single nucleotide polymorphisms (SNPs) in DEFB1, ERICH3, AHR, and TSPAN5 that we tested as predictors. Supervised machine-learning methods trained using SNPs and total baseline depression scores predicted remission and response at 8 weeks with area under the receiver operating curve (AUC) > 0.7 (P < 0.04) in PGRN-AMPS patients, with comparable prediction accuracies > 69% (P ≤ 0.07) in STAR*D and ISPC. These results demonstrate that machine learning can achieve accurate and, importantly, replicable prediction of SSRI therapy response using total baseline depression severity combined with pharmacogenomic biomarkers.