Dataset Information

Relative power and sample size analysis on gene expression profiling data.

ABSTRACT:

Background

With the increasing number of expression profiling technologies, researchers today are confronted with choosing the technology that has sufficient power with minimal sample size, in order to reduce cost and time. These depend on data variability, partly determined by sample type, preparation and processing. Objective measures that help experimental design, given own pilot data, are thus fundamental.

Results

Relative power and sample size analysis were performed on two distinct data sets. The first set consisted of Affymetrix array data derived from a nutrigenomics experiment in which weak, intermediate and strong PPARalpha agonists were administered to wild-type and PPARalpha-null mice. Our analysis confirms the hierarchy of PPARalpha-activating compounds previously reported and the general idea that larger effect sizes positively contribute to the average power of the experiment. A simulation experiment was performed that mimicked the effect sizes seen in the first data set. The relative power was predicted but the estimates were slightly conservative. The second, more challenging, data set describes a microarray platform comparison study using hippocampal deltaC-doublecortin-like kinase transgenic mice that were compared to wild-type mice, which was combined with results from Solexa/Illumina deep sequencing runs. As expected, the choice of technology greatly influences the performance of the experiment. Solexa/Illumina deep sequencing has the highest overall power followed by the microarray platforms Agilent and Affymetrix. Interestingly, Solexa/Illumina deep sequencing displays comparable power across all intensity ranges, in contrast with microarray platforms that have decreased power in the low intensity range due to background noise. This means that deep sequencing technology is especially more powerful in detecting differences in the low intensity range, compared to microarray platforms.

Conclusion

Power and sample size analysis based on pilot data give valuable information on the performance of the experiment and can thereby guide further decisions on experimental design. Solexa/Illumina deep sequencing is the technology of choice if interest lies in genes expressed in the low-intensity range. Researchers can get guidance on experimental design using our approach on their own pilot data implemented as a BioConductor package, SSPA http://bioconductor.org/packages/release/bioc/html/SSPA.html.

SUBMITTER: van Iterson M

PROVIDER: S-EPMC2759969 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundBefore conducting a microarray experiment, one important issue that needs to be determined is the number of arrays required in order to have adequate power to identify differentially expressed genes. This paper discusses some crucial issues in the problem formulation, parameter specifications, and approaches that are commonly proposed for sample size estimation in microarray experiments. Common methods for sample size estimation are formulated as the minimum sample size necessary to achieve a specified sensitivity (proportion of detected truly differentially expressed genes) on average at a specified false discovery rate (FDR) level and specified expected proportion (pi1) of the true differentially expression genes in the array. Unfortunately, the probability of detecting the specified sensitivity in such a formulation can be low. We formulate the sample size problem as the number of arrays needed to achieve a specified sensitivity with 95% probability at the specified significance level. A permutation method using a small pilot dataset to estimate sample size is proposed. This method accounts for correlation and effect size heterogeneity among genes.ResultsA sample size estimate based on the common formulation, to achieve the desired sensitivity on average, can be calculated using a univariate method without taking the correlation among genes into consideration. This formulation of sample size problem is inadequate because the probability of detecting the specified sensitivity can be lower than 50%. On the other hand, the needed sample size calculated by the proposed permutation method will ensure detecting at least the desired sensitivity with 95% probability. The method is shown to perform well for a real example dataset using a small pilot dataset with 4-6 samples per group.ConclusionsWe recommend that the sample size problem should be formulated to detect a specified proportion of differentially expressed genes with 95% probability. This formulation ensures finding the desired proportion of true positives with high probability. The proposed permutation method takes the correlation structure and effect size heterogeneity into consideration and works well using only a small pilot dataset.