Adipose gene expression prior to weight loss can differentiate and weakly predict dietary responders

Abstract

Background: The ability to identify obese individuals who will successfully lose weight in response to dietary intervention will revolutionize disease management. Therefore, we asked whether it is possible to identify subjects who will lose weight during dietary intervention using only a single gene expression snapshot.

Methodology/principal findings: The present study involved 54 female subjects from the Nutrient-Gene Interactions in Human Obesity-Implications for Dietary Guidelines (NUGENOB) trial to determine whether subcutaneous adipose tissue gene expression could be used to predict weight loss prior to the 10-week consumption of a low-fat hypocaloric diet. Using several statistical tests revealed that the gene expression profiles of responders (8-12 kgs weight loss) could always be differentiated from non-responders (<4 kgs weight loss). We also assessed whether this differentiation was sufficient for prediction. Using a bottom-up (i.e. black-box) approach, standard class prediction algorithms were able to predict dietary responders with up to 61.1%+/-8.1% accuracy. Using a top-down approach (i.e. using differentially expressed genes to build a classifier) improved prediction accuracy to 80.9%+/-2.2%.

Conclusion: Adipose gene expression profiling prior to the consumption of a low-fat diet is able to differentiate responders from non-responders as well as serve as a weak predictor of subjects destined to lose weight. While the degree of prediction accuracy currently achieved with a gene expression snapshot is perhaps insufficient for clinical use, this work reveals that the comprehensive molecular signature of adipose tissue paves the way for the future of personalized nutrition.

Figure 1. Weight loss curves during the 10 week hypocaloric diet.

The two groups were defined as responders (i.e. subjects losing between 8–12 kgs) and non-responders (i.e. subjects losing less than 4 kgs). Weight was measured in at least 43 subjects at each weekly time point. Error bars represent the 95% confidence intervals (equal to 1.96 * standard deviation).

Figure 2. Distribution of the mean gene expression levels in responders and non-responders, computed from microarray measurements normalized with respect to the standard Gaussian distribution.

Each spot represents the mean expression for a single gene. Dotted lines indicate the 95% confidence interval of the means (equal to 1.96 * standard deviation).

Figure 3. A. Differentiating populations by PLS-DA.

Global gene expression analysis in sub-cutaneous tissue reveals a separation trend between dietary responders (black squares) and non-responders (red circles); however, there is a significant overlap between the two populations (R² = 0.547 and Q² = −0.096). B. ALL patients (black squares) can be clearly separated from AML patients (red circles), apart from a single patient (identified by the green circle) (R² = 0.795 and Q² = 0.622). R² explains the cumulative variation of the first two components and Q² indicates the variation explained by the model according to cross validation. Only a Q²>0.5 indicates a good model.