Prediction of lithium response using genomic data

Stone W, Nunes A, Akiyama K, Akula N, Ardau R, Aubry JM, Backlund L, Bauer M, Bellivier F, Cervantes P, Chen HC, Chillotti C, Cruceanu C, Dayer A, Degenhardt F, Del Zompo M, Forstner AJ, Frye M, Fullerton JM, Grigoroiu-Serbanescu M, Grof P, Hashimoto R, Hou L, Jiménez E, Kato T, Kelsoe J, Kittel-Schneider S, Kuo PH, Kusumi I, Lavebratt C, Manchia M, Martinsson L, Mattheisen M, McMahon FJ, Millischer V, Mitchell PB, Nöthen MM, O’Donovan C, Ozaki N, Pisanu C, Reif A, Rietschel M, Rouleau G, Rybakowski J, Schalling M, Schofield PR, Schulze TG, Severino G, Squassina A, Veeh J, Vieta E, Trappenberg T, Alda M (2021)

Publication Type: Journal article

Publication year: 2021

Journal

Book Volume: 11

Article Number: 1155

Journal Issue: 1

DOI: 10.1038/s41598-020-80814-z

Abstract

Predicting lithium response prior to treatment could both expedite therapy and avoid exposure to side effects. Since lithium responsiveness may be heritable, its predictability based on genomic data is of interest. We thus evaluate the degree to which lithium response can be predicted with a machine learning (ML) approach using genomic data. Using the largest existing genomic dataset in the lithium response literature (n = 2210 across 14 international sites; 29% responders), we evaluated the degree to which lithium response could be predicted based on 47,465 genotyped single nucleotide polymorphisms using a supervised ML approach. Under appropriate cross-validation procedures, lithium response could be predicted to above-chance levels in two constituent sites (Halifax, Cohen’s kappa 0.15, 95% confidence interval, CI [0.07, 0.24]; and Würzburg, kappa 0.2 [0.1, 0.3]). Variants with shared importance in these models showed over-representation of postsynaptic membrane related genes. Lithium response was not predictable in the pooled dataset (kappa 0.02 [− 0.01, 0.04]), although non-trivial performance was achieved within a restricted dataset including only those patients followed prospectively (kappa 0.09 [0.04, 0.14]). Genomic classification of lithium response remains a promising but difficult task. Classification performance could potentially be improved by further harmonization of data collection procedures.

Involved external institutions

Università degli Studi di Cagliari Italy (IT) Karolinska Institute Sweden (SE) Julius-Maximilians-Universität Würzburg Germany (DE) National Institute of Mental Health Information Resource Center United States (USA) (US) Rheinische Friedrich-Wilhelms-Universität Bonn Germany (DE) Dalhousie University Canada (CA) Nagoya University / 名古屋大学 Japan (JP) Universitätsklinikum Frankfurt am Main (KGU) Germany (DE) Ruprecht-Karls-Universität Heidelberg Germany (DE) Montreal Neurological Institute and Hospital (MNI, The Neuro) Canada (CA) University of New South Wales (UNSW) Australia (AU) Klinikum der Universität München (LMU Klinikum) Germany (DE) Poznan University of Medical Sciences / Uniwersytet Medyczny im. Karola Marcinkowskiego w Poznaniu Poland (PL) Universitat de Barcelona (UB) / University of Barcelona Spain (ES) Technische Universität Berlin Germany (DE) Université Sorbonne Paris Cité France (FR) McGill University Canada (CA) National Taiwan University Hospital (NTUH) / 國立台灣大學醫學院附設醫院 Taiwan (TW) Dokkyo Medical University Japan (JP) Azienda Ospedaliera Universitaria di Cagliari Italy (IT) Max-Planck-Institut für Psychiatrie (Deutsche Forschungsanstalt für Psychiatrie) Germany (DE) University of Geneva / Université de Genève (UNIGE) Switzerland (CH) Universitätsklinikum Bonn Germany (DE) Mayo Clinic United States (USA) (US) Mood Disorders Ottawa Canada (CA) RIKEN Center for Brain Science (CBS) Japan (JP) National Taiwan University (NTU) Taiwan (TW)

How to cite

APA:

Stone, W., Nunes, A., Akiyama, K., Akula, N., Ardau, R., Aubry, J.M.,... Alda, M. (2021). Prediction of lithium response using genomic data. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-020-80814-z

MLA:

Stone, William, et al. "Prediction of lithium response using genomic data." Scientific Reports 11.1 (2021).

BibTeX: Download