Detect network interactions with confounder control

Trang Lê

@trang1618

Rocky Mountain Bioinformatics Conference, 2019

y_i = \beta_0 + \beta_a a_i + \epsilon_i
d_{ij}(y) = \beta_0 + \beta_a d_{ij}(a) + \epsilon_{ij}

projected distances

nearest neighbors

attributes

d_{ij}(y) = \beta_0 + \beta_a d_{ij}(a) + \epsilon_{ij}
M_a \sim d_{ij}(a|y_i \neq y_j)
H_a \sim d_{ij}(a|y_i = y_j)

discrete outcome

e.g., y \in \{0, 1\}
Supports regularization  No No Yes
m = 200
p = 1000

10% functionally interacting

 NPDR 0.05 adjusted cutoffs

Genes most highly associated with sex are eliminated by adjustment
but remain in non-adjusted set.

Acknowledgement

Brett McKinney

Bryan Dawkins

Jason Moore

Ryan Urbanowicz

devtools::install_github('insilico/npdr')

Detect network interactions while controling for confounders

By Trang Le

Detect network interactions while controling for confounders

Presentation on 2019-12-06 at Rocky Mountain Bioinformatics Conference

  • 298
Loading comments...

More from Trang Le