derive.network.features {SIMMS}

Derive univariate features from pathway-derived networks

Description

This function fits Cox model to features as well as interaction between features. The coefficients of features are subsequently used to compute impact score of each of the pathway-derived networks.

Usage

derive.network.features(
  data.directory = ".",
  output.directory = ".",
  data.types = c("mRNA"),
  data.types.ordinal = c("cna"),
  centre.data = "median",
  feature.selection.fun = "calculate.network.coefficients",
  feature.selection.datasets = NULL,
  feature.selection.p.thresholds = c(0.05),
  truncate.survival = 100,
  networks.database = "default",
  subset = NULL,
  ...
)

Arguments

data.directory

Path to the directory containing datasets as specified by feature.selection.datasets

output.directory

Path to the output folder where intermediate and results files will be saved

data.types

A vector of molecular datatypes to load. Defaults to c('mRNA')

data.types.ordinal

A vector of molecular datatypes to be treated as ordinal. Defaults to c('cna')

centre.data

A character string specifying the centre value to be used for scaling data. Valid values are: 'median', 'mean', or a user defined numeric threshold e.g. '0.3' when modelling methylation beta values. This value is used for both scaling as well as for dichotomising data for estimating univariate betas from Cox model. Defaults to 'median'

feature.selection.fun

Name of the function to be used to estimate network coefficients. Defaults to 'calculate.network.coefficients'

feature.selection.datasets

A vector containing names of training datasets to be used to compute cox statistics

feature.selection.p.thresholds

A vector containing P values to be used as threshold for including features into overall impact score of a network

truncate.survival

A numeric value specifying survival truncation in years. Defaults to 100 years which effectively means no truncation

networks.database

Name of the pathway networks database. Default to NCI PID/Reactome/Biocarta i-e "default"

subset

A list with a Field and Entry component specifying a subset of patients to be selected from each dataset whose annotation Field matches Entry

...

other params to be passed on to user-defined method for estimating coefficients of network features

Value

The output files are stored under data.directory/output/

Author(s)

Syed Haider

Examples

options("warn" = -1);

# get data directory 
data.directory <- get.program.defaults(networks.database = "test")[["test.data.dir"]];

# initialise params
output.directory <- tempdir();
data.types <- c("mRNA");
feature.selection.datasets <- c("Breastdata1");
feature.selection.p.thresholds <- c(0.05);

# estimate network coefficients for all the subnet features
derive.network.features(
  data.directory = data.directory,
  output.directory = output.directory,
  data.types = data.types,
  feature.selection.fun = "calculate.network.coefficients",
  feature.selection.datasets = feature.selection.datasets,
  feature.selection.p.thresholds = feature.selection.p.thresholds,
  networks.database = "test"
  );