The goal of Colossus is to provide an open-source means of performing survival analysis on big data with complex risk formula. Colossus is designed to perform Cox Proportional Hazard regressions and Poisson regressions on datasets loaded as data.tables or data.frames. The risk models allowed are sums or products of linear, log-linear, or several other radiation dose response formula highlighted in the vignettes. Additional plotting capabilities are available.
By default a fully portable version of the code is compiled, which does not support OpenMP on every system. Note that Colossus requires OpenMP support to perform parallel calculations. The environment variable “R_COLOSSUS_NOT_CRAN” is checked to determine if OpenMP should be disabled for linux compiling with clang. The number of cores is set to 1 if the environment variable is empty, the operating system is detected as linux, and the default compiler or R compiler is clang. Colossus testing checks for the “NOT_CRAN” variable to determine if additional tests should be run. Setting “NOT_CRAN” to “false” will disable the longer tests. Currently OpenMP support is not configured for linux compiling with clang and MacOS systems.
Example
This is a basic example which shows you how to solve a common problem:
library(data.table)
library(parallel)
library(Colossus)
## basic example code reproduced from the starting-description vignette
df <- data.table(
"UserID" = c(112, 114, 213, 214, 115, 116, 117),
"Starting_Age" = c(18, 20, 18, 19, 21, 20, 18),
"Ending_Age" = c(30, 45, 57, 47, 36, 60, 55),
"Cancer_Status" = c(0, 0, 1, 0, 1, 0, 0),
"a" = c(0, 1, 1, 0, 1, 0, 1),
"b" = c(1, 1.1, 2.1, 2, 0.1, 1, 0.2),
"c" = c(10, 11, 10, 11, 12, 9, 11),
"d" = c(0, 0, 0, 1, 1, 1, 1)
)
# For the interval case
time1 <- "Starting_Age"
time2 <- "Ending_Age"
event <- "Cancer_Status"
names <- c("a", "b", "c", "d")
term_n <- c(0, 1, 1, 2)
tform <- c("loglin", "lin", "lin", "plin")
modelform <- "M"
fir <- 0
a_n <- c(0.1, 0.1, 0.1, 0.1)
keep_constant <- c(0, 0, 0, 0)
der_iden <- 0
control <- list(
"lr" = 0.75, "maxiter" = 100, "halfmax" = 5, "epsilon" = 1e-9,
"dbeta_max" = 0.5, "deriv_epsilon" = 1e-9, "abs_max" = 1.0,
"change_all" = TRUE, "dose_abs_max" = 100.0, "verbose" = FALSE,
"ties" = "breslow", "double_step" = 1
)
e <- RunCoxRegression(df, time1, time2, event, names, term_n, tform, keep_constant, a_n, modelform, fir, der_iden, control)
Interpret_Output(e)
#> |-------------------------------------------------------------------|
#> Final Results
#> Covariate Subterm Term Number Central Estimate Standard Deviation
#> <char> <char> <int> <num> <num>
#> 1: a loglin 0 41.26157 NaN
#> 2: b lin 1 98.72266 NaN
#> 3: c lin 1 96.82311 177.9643
#> 4: d plin 2 101.10000 0.0000
#>
#> Cox Model Used
#> -2*Log-Likelihood: 1.35, AIC: 9.35
#> Iterations run: 100
#> maximum step size: 1.00e+00, maximum first derivative: 1.92e-04
#> Analysis did not converge, check convergence criteria or run further
#> |-------------------------------------------------------------------|