wrapper_fast_multinom: Wrapper for the function fast_multinom

In MultinomialMutations/MultinomialMutations: Fast multinomial regression for large cancer mutation datasets

Description

The function wrapper_fast_multinom estimates the regression coefficients of a multinomial logistic model with fast_multinom. This wrapper was used in our analysis in Bertl et al. (2007) (see References). The function wrapper_fast_multinom_binom uses a binomial model instead.

Usage

wrapper_fast_multinom(model.index, mi, datafolder, modelfile, resultsfolder,
  startfile, contrasts = "all_sum", nested_samples = T, VC = T,
  loglik = T)

wrapper_fast_multinom_binom(model.index, mi, datafolder, modelfile,
  resultsfolder, startfile, contrasts = "all_sum", nested_samples = T,
  VC = T, loglik = T)

Arguments

model.index	integer. Number of the model in the model matrix.
mi	integer. Number of multiple imputation replicate of the data set.
datafolder	character. Folder, where the data is saved. See data(cancermutations) for an example. The filename is paste0("imp", mi, ".txt"), where mi is the multiple imputation replicate.
modelfile	character. File that contains the models in the form of a matrix (see examples).
resultsfolder	character. Where to save the results?
startfile	character. File that contains starting values for the parameter estimation.
contrasts	character. What contrasts should be set for the variables cancer_type, genomicSeg and sample_id. Default: 'all_sum'. All other settings will use the default contrasts, i. e. treatment contrasts.
nested_samples	Logical. Should the contrasts be defined such that the samples are nested within the cancer types? Default: T
VC	Logical. Should the VC matrix be computed? Default: T
loglik	Logical. Should the log-likelihood be computed? Default: T

Details

A dataset similar to the example data set cancermutations is read. The dummy variables strong, Cgi, simple_repeat, DNase1_peak, expression_dummy are changed to factors, optionally, sum contrasts are set to cancer_type, genomicSeg and sample_id, and nested contrasts are set to create a nesting of sample_id in cancer_type.

Then, the multinomial regression model indexed by model.index is obtained from a model file and estimated with the function fast_multinom.

The scripts that were used to run this function and that show all settings used in Bertl et al. (2007) are available in this package in the folder inst/Bertl_et_al_2017. The pre-processed data can be downloaded from figshare.

Value

There is no output. The estimates are saved along with (potential) warning messages.

Author(s)

Johanna Bertl

References

Bertl, J.; Guo, Q.; Rasmussen, M. J.; Besenbacher, S; Nielsen, M. M.; Hornshøj, H.; Pedersen, J. S. & Hobolth, A. A Site Specific Model And Analysis Of The Neutral Somatic Mutation Rate In Whole-Genome Cancer Data. bioRxiv, 2017. doi: https://doi.org/10.1101/122879 http://www.biorxiv.org/content/early/2017/06/21/122879

See Also

fast_multinom

MultinomialMutations/MultinomialMutations documentation built on May 22, 2019, 4:39 p.m.