Yufeng Shen
@yshen.bsky.social
Computational genomics and human genetics. Associate Professor @ Columbia University
Lab: http://www.columbia.edu/~ys2411/
Lab: http://www.columbia.edu/~ys2411/
Right. With zeros, the point estimate of effect size is just too far off. Maybe you can use pseudo count to stabilize it, although how to do pseudo count depends on assumptions about priors
November 23, 2024 at 7:37 PM
Right. With zeros, the point estimate of effect size is just too far off. Maybe you can use pseudo count to stabilize it, although how to do pseudo count depends on assumptions about priors
Small sample size is a problem, but my hunch is normal approximation would underestimate the tail on the right side of the distribution, therefore stderr based meta analysis would deflate type I
November 23, 2024 at 4:55 PM
Small sample size is a problem, but my hunch is normal approximation would underestimate the tail on the right side of the distribution, therefore stderr based meta analysis would deflate type I
I highly recommend it as a generic method. In our analysis, it has the most consistent score scale across genes, even for genes under-represented in ClinVar or with somewhat weak MSA. A few other methods, like REVEL, gMVP (from us), and EVE, are better for certain genes but less inconsistent.
October 10, 2023 at 9:39 PM
I highly recommend it as a generic method. In our analysis, it has the most consistent score scale across genes, even for genes under-represented in ClinVar or with somewhat weak MSA. A few other methods, like REVEL, gMVP (from us), and EVE, are better for certain genes but less inconsistent.