Dataset Information

Comparison of Statistical Tests and Power Analysis for Phosphoproteomics Data.

ABSTRACT: Advances in protein tagging and mass spectrometry have enabled generation of large quantitative proteome and phosphoproteome data sets, for identifying differentially expressed targets in case-control studies. The power study of statistical tests is critical for designing strategies for effective target identification and control of experimental cost. Here, we develop a simulation framework to generate realistic phospho-peptide data with known changes between cases and controls. Using this framework, we quantify the performance of traditional t-tests, Bayesian tests, and the ranking-by-fold-change test. Bayesian tests, which share variance information among peptides, outperform the traditional t-tests. Although ranking-by-fold-change has similar power as the Bayesian tests, its type I error rate cannot be properly controlled without proper permutation analysis; therefore, simply relying on the ranking likely brings false positives. Two-sample Bayesian tests considering dependencies between intensity and variance are superior for data sets with complex variance. While increasing the sample size enhances the statistical tests' performance, balanced controls and cases are recommended over a one-side weighted group. Further, higher peptide standard deviations require higher fold changes to achieve the same statistical power. Together, these results highlight the importance of model-informed experimental design and principled statistical analyses when working with large-scale proteomics and phosphoproteomics data.

SUBMITTER: Ding LJ

PROVIDER: S-EPMC8042666 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Microarray technology has enabled the measurement of comprehensive transcriptomic information. However, each data entry may reflect trivial individual differences among samples and also contain technical noise. Therefore, the certainty of each observed difference should be confirmed at earlier steps of the analyses, and statistical tests are frequently used for this purpose. Since a microarray measures a huge number of genes and the results are processed simultaneously, concerns regarding problems of multiplicity have been raised to the tests. To deal with these problems, several methodologies have been proposed, making the tests very conservative. Indeed, arbitrary tuning of the test threshold has also been introduced to relax the test conditions. However, the appropriateness of the multiplicity problems as well as the compensation methods has not been confirmed. The appropriateness of the compensation methods was checked by means of coincidence of the premises of the methodologies with the observed characteristics found in real data of two typical platforms of microarray analysis. Normality was observed in within-group data variations, supporting applications of parametric tests. However, genes displayed their own tendencies in the magnitude of variations, and the distributions of P-values were rather complex and varied; these characteristics are inconsistent with the premises of the compensation methodologies. Additionally, the appropriateness of the proposed multiplicities is reconsidered. When we observed differences in the transcriptome, the family-wise error rate should not be considered, since analyses at higher levels would not be influenced by a few false positives among the huge numbers of true information. Likely, concerns for a false discovery rate are not suitable for the point null hypotheses on expression levels, since the rate of true null hypotheses should be rare in contradiction to the premise of the methodology. Although compensation methods have been recommended to deal with the problem of multiplicity, the compensations are actually inappropriate for many of the applications of transcriptome analyses. Compensations are not only unnecessary, but will increase the occurrence of false negative errors, and arbitrary adjustment of the threshold damages the objectivity of the tests. Rather, the results of parametric tests should be evaluated directly. This SuperSeries is composed of the SubSeries listed below.

Project description:IntroductionAlzheimer's disease (AD) is a complex disease influenced by genetics and environment. More than 75 susceptibility loci have been linked to late-onset AD, but most of these loci were discovered in genome-wide association studies (GWAS) exclusive to non-Hispanic White individuals. There are wide disparities in AD risk across racially stratified groups, and while these disparities are not due to genetic differences, underrepresentation in genetic research can further exacerbate and contribute to their persistence. We investigated the racial/ethnic representation of participants in United States (US)-based AD genetics and the statistical implications of current representation.MethodsWe compared racial/ethnic data of participants from array and sequencing studies in US AD genetics databases, including National Institute on Aging Genetics of Alzheimer's Disease Data Storage Site (NIAGADS) and NIAGADS Data Sharing Service (dssNIAGADS), to AD and related dementia (ADRD) prevalence and mortality. We then simulated the statistical power of these datasets to identify risk variants from non-White populations.ResultsThere is insufficient statistical power (probability <80%) to detect single nucleotide polymorphisms (SNPs) with low to moderate effect sizes (odds ratio [OR]<1.5) using array data from Black and Hispanic participants; studies of Asian participants are not powered to detect variants OR <= 2. Using available and projected sequencing data from Black and Hispanic participants, risk variants with OR = 1.2 are detectable at high allele frequencies. Sample sizes remain insufficiently powered to detect these variants in Asian populations.DiscussionAD genetics datasets are largely representative of US ADRD burden. However, there is a wide discrepancy between proportional representation and statistically meaningful representation. Most variation identified in GWAS of non-Hispanic White individuals have low to moderate effects. Comparable risk variants in non-White populations are not detectable given current sample sizes, which could lead to disparities in future studies and drug development. We urge AD genetics researchers and institutions to continue investing in recruiting diverse participants and use community-based participatory research practices.

Dataset Information

Comparison of Statistical Tests and Power Analysis for Phosphoproteomics Data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets