VALORATE: Fast and accurate log-rank test in balanced and unbalanced comparisons of survival curves and cancer genomics
- Additional Document Info
- View All
© The Author 2017. Published by Oxford University Press. All rights reserved.The association of genomic alterations to outcomes in cancer is affected by a problem of unbalanced groups generated by the low frequency of alterations. For this, an R package (VALORATE) that estimates the null distribution and the P-value of the log-rank based on a recent reformulation is presented. For a given number of alterations that define the size of survival groups, the log-rank density is estimated by a weighted sum of conditional distributions depending on a co-occurrence term of mutations and events. The estimations are accurately accelerated by sampling across co-occurrences allowing the analysis of large genomic datasets in few minutes. In conclusion, the proposed VALORATE R package is a valuable tool for survival analysis. Availability and Implementation: The R package is available in CRAN at https://cran.r-project.org and in http://bioinformatica.mty.itesm.mx/valorateR.