Predicting temporal lobe volume on MRI from genotypes using L¹-L² regularized regression

Abstract

Penalized or sparse regression methods are gaining increasing attention in imaging genomics, as they can select optimal regressors from a large set of predictors whose individual effects are small or mostly zero. We applied a multivariate approach, based on L1-L2-regularized regression (elastic net) to predict a magnetic resonance imaging (MRI) tensor-based morphometry-derived measure of temporal lobe volume from a genome-wide scan in 740 Alzheimer’s Disease Neuroimaging Initiative (ADNI) subjects. We tuned the elastic net model’s parameters using internal crossvalidation and evaluated the model on independent test sets. Compared to 100,000 permutations performed with randomized imaging measures, the predictions were found to be statistically significant (p ~ 0.001). The rs9933137 variant in the RBFOX1 gene was a highly contributory genotype, along with rs10845840 in GRIN2B and rs2456930, discovered previously in a univariate genomewide search.

A Review of Feature Reduction Techniques in Neuroimaging

“…Second, the LASSO is able to cope with situations where there are a large number of predictor variables (voxels) and fewer observations (subjects) as is the case in majority of neuroimaging studies (Bunea et al 2011). Previous applications of feature selection using LASSO in neuroimaging machine learning tasks include: AD classification (Casanova et al 2011; Kohannim et al 2012b; Rao et al 2011; Vounou et al 2011; Yan et al 2012), prediction of video stimulus scores in fMRI (Carroll et al 2009), ASD classification (Duchesnay et al 2011), prediction of brain characteristics using genetic data (Kohannim et al 2012a; Kohannim et al 2012b), prediction of pain stimuli in fMRI (Rish et al 2010) and Gender classification (Casanova et al 2012). …”

“…$$\sum _{i=1}^N{\left(y_i-\sum _j{x}_{ij}{\beta }_j\right)}^2+{\lambda }_1\sum _{j=1}^P\mid {\beta }_j\mid +{\lambda }_2\sum _{j=1}^P{\beta }_j^2$$ Contrary to LASSO, the Elastic Net requires definition of two user-defined model regularization parameters ( λ 1 and λ 2 ), which control the degree of penalization. The L 1 penalty ${\sum }_{j=1}^P{\beta }_j^2$ promotes sparsity in the solution, resulting in few features with non-zero weights, whilst L 2 penalty encourages stability in the solution and acts as a bound on the number of features selected (Bunea et al 2011; Kohannim et al 2012a; Ogutu et al 2012; Zou and Hastie, 2005). These parameters are often selected using an objective parameter grid-search process which evaluates a ‘range’ of parameters in two-dimensions (grid-search) and parameters giving the best performance selected.…”

Orchestration of Neurodevelopmental Programs by RBFOX1

“…Wang et al, 2009) as well as a diverse array of other human conditions including Alzheimer disease (Kohannim et al, 2012), bipolar disorder (Le-Niculescu et al, 2009), attention-deficit hyperactivity disorder (Elia et al, 2010), schizoaffective disorder (Hamshere et al, 2009), obesity (Ma et al, 2010), and refractive error (Stambolian et al, 2013). It is unclear whether these SNPs may, in some cases, co-segregate with other rare sequence or structural variants directly influencing RBFOX1 expression or regulation.…”

Longitudinal Relationships Among Activity in Attention Redirection Neural Circuitry and Symptom Severity in Youth

“…This class of statistical techniques has been used in genetic studies (19-23), and in clinical research, including fMRI (24-26). These techniques minimize risk of inflating model error or overfitting, by minimizing the model's mean squared error through cross validation.…”