Skip to main content
. 2020 Jul 22;10:1257. doi: 10.3389/fonc.2020.01257

Figure 3.

Figure 3

The prognosis-associated AS events were screened by LASSO regression analysis for all AS types combined and for each of the 7 AS types separately. Left panel (A–H) The coefficients are plotted against log(λ). A vertical line is shown at the value selected using 10-fold cross-validation, where the optimal λ results in ten features with nonzero coefficients. Right panel (A–H): Optimal parameter (λ) selection in the LASSO model used 10-fold cross-validation via minimum criteria. The partial likelihood deviance (binomial deviance) curve is plotted vs. log(λ). Dotted vertical lines are shown at the optimal values selected using two different criteria: the minimum and 1 standard error of the minimum.