H-MAGMA, inheriting a shaky statistical foundation, yields excess false positives.

Abstract

All data used in the manuscript are available at https://github.com/ryurko/HMAGMA-comment. Supplementary Fig. 1. Comparison of covariance approximations for two-sided tests (green-solid) versus Brown's one-sided approximation described in MAGMA paper (red-dashed) and the code implemented in MAGMA with r2 (cyan-dashed). Supplementary Fig. 2. Comparison of the type 1 error rate control, plus/minus two standard errors, at target a = 0:05 (denoted by dashed red line) by gene-level method for seven example genes of different sizes. Supplementary Fig. 3. Comparison of multiple testing family-wise error rate (FWER), plus/minus two standard errors, at target a = 0:05 (denoted with dashed red line) by gene-level method. Supplementary Fig. 4. a, Comparison of the proportion of simulations with zero to six false positives for each method, excluding MAGMA: paper, using the Bonferroni correction at target a = 0:05 (plus/minus two standard errors). Supplementary Fig. 5. Comparison of gene-set analysis type 1 error, plus/minus two-standard errors, at target a = 0:05 (denoted with dashed red line) by gene-level method for each considered gene-set analysis method (from left to right) MAGMA: gene-set, Fisher's combination test, and Stouffer's z-test. Supplementary Table 1. Comparison of number of BH discoveries (union across adult and fetal Hi-C data annotations) with H-MAGMA versus corrected Monte Carlo based approach. Supplementary Fig. 6. Comparison of null histograms by gene-set analysis method (columns) and methods for computing gene-level p-values (rows) for gene-sets of size G = 45 genes. Red dashed lines indicate expected 2.5% and 97.5% quantiles for uniform p-values across 200,000 simulations. Supplementary Fig. 7. Comparison of distributions for MAGMA gene-set analysis standardized test statistic by methods for computing gene-level p-values. Red density curve displays the expected t(G 1) distribution, with the red vertical dashed line denoting the center at zero. Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.