The effects of sample size on omics study: from the perspective of robustness and diagnostic accuracy

In the design of a specific omics study, sample size is an essential consideration that represents the balance among investigation ability, financial requirements and ethical issues. And it was reported critical to increase robustness and diagnostic accuracy. In this study, two metabolomics datasets were used to conduct analysis to understand the effects of sample size on omics study and strengthen the importance of it. Overlap and AUC were applied to measure the robustness and diagnostic accuracy respectively. The results showed the positive correlation between sample size and robustness, sample size and diagnostic accuracy. Moreover, the effects of sample size vary in datasets and indexes. So, for a specific dataset, sample size should be determined according to its purpose.