DeepBipolar: Identifying genomic mutations for bipolar disorder via deep learning
Open Access
- 23 May 2017
- journal article
- research article
- Published by Wiley in Human Mutation
- Vol. 38 (9) , 1217-1224
Abstract
Bipolar disorder, also known as manic depression, is a brain disorder that affects the brain structure of a patient. It results in extreme mood swings, severe states of depression, and overexcitement simultaneously. It is estimated that roughly 3% of the population of the United States (about 5.3 million adults) suffers from bipolar disorder. Recent research efforts like the Twin studies have demonstrated a high heritability factor for the disorder, making genomics a viable alternative for detecting and treating bipolar disorder, in addition to the conventional lengthy and costly postsymptom clinical diagnosis. Motivated by this study, leveraging several emerging deep learning algorithms, we design an end‐to‐end deep learning architecture (called DeepBipolar) to predict bipolar disorder based on limited genomic data. DeepBipolar adopts the Deep Convolutional Neural Network (DCNN) architecture that automatically extracts features from genotype information to predict the bipolar phenotype. We participated in the Critical Assessment of Genome Interpretation (CAGI) bipolar disorder challenge and DeepBipolar was considered the most successful by the independent assessor. In this work, we thoroughly evaluate the performance of DeepBipolar and analyze the type of signals we believe could have affected the classifier in distinguishing the case samples from the control set.Keywords
Funding Information
- National Institutes of Health (U41 HG007446, R13 HG006650, and R01GM110240))
This publication has 24 references indexed in Scilit:
- Genetic relationship between five psychiatric disorders estimated from genome-wide SNPsNature Genetics, 2013
- Genetics of bipolar disorderThe Lancet, 2013
- Large-scale genome-wide association analysis of bipolar disorder identifies a new susceptibility locus near ODZ4Nature Genetics, 2011
- Finding the missing heritability of complex diseasesNature, 2009
- Genomewide Association Studies: History, Rationale, and Prospects for Psychiatric DisordersAmerican Journal of Psychiatry, 2009
- Common and rare variants in multifactorial susceptibility to common diseasesNature Genetics, 2008
- Lifetime and 12-Month Prevalence of Bipolar Spectrum Disorder in the National Comorbidity Survey ReplicationArchives of General Psychiatry, 2007
- The psychosocial context of bipolar disorder: Environmental, cognitive, and developmental risk factorsClinical Psychology Review, 2005
- A review of the evidence from family, twin and adoption studies for a genetic contribution to adult psychiatric disordersInternational Review of Psychiatry, 2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998