predict_with_rmtlr {easier} | R Documentation |
Obtains predictions of immune response for individual quantitative descriptors by using a cancer-specific model learned with Regularized Multi-Task Linear Regression algorithm (RMTLR).
predict_with_rmtlr( view_name, view_info, view_data, opt_model_cancer_view_spec, opt_xtrain_stats_cancer_view_spec, verbose = TRUE )
view_name |
character string containing the name of the input view. |
view_info |
character string informing about the family of the input data. |
view_data |
list containing the data for each input view. |
opt_model_cancer_view_spec |
cancer-view-specific model
feature parameters learned during training. These are available
from easierData package through |
opt_xtrain_stats_cancer_view_spec |
cancer-view-specific
features mean and standard deviation of the training set. These
are available from easierData package through
|
verbose |
logical flag indicating whether to display messages about the process. |
A list of predictions, one for each task, in a matrix format (rows = samples; columns = [runs).
## Not run: # using a SummarizedExperiment object library(SummarizedExperiment) # Using example exemplary dataset (Mariathasan et al., Nature, 2018) # from easierData. Original processed data is available from # IMvigor210CoreBiologies package. library("easierData") dataset_mariathasan <- easierData::get_Mariathasan2018_PDL1_treatment() RNA_tpm <- assays(dataset_mariathasan)[["tpm"]] cancer_type <- metadata(dataset_mariathasan)[["cancertype"]] # Select a subset of patients to reduce vignette building time. pat_subset <- c( "SAM76a431ba6ce1", "SAMd3bd67996035", "SAMd3601288319e", "SAMba1a34b5a060", "SAM18a4dabbc557" ) RNA_tpm <- RNA_tpm[, colnames(RNA_tpm) %in% pat_subset] # Computation of TF activity (Garcia-Alonso et al., Genome Res, 2019) tf_activities <- compute_TF_activity( RNA_tpm = RNA_tpm ) view_name <- "tfs" view_info <- c(tfs = "gaussian") view_data <- list(tfs = as.data.frame(tf_activities)) # Retrieve internal data opt_models <- suppressMessages(easierData::get_opt_models()) opt_xtrain_stats <- suppressMessages(easierData::get_opt_xtrain_stats()) opt_model_cancer_view_spec <- lapply(view_name, function(X) { return(opt_models[[cancer_type]][[X]]) }) names(opt_model_cancer_view_spec) <- view_name opt_xtrain_stats_cancer_view_spec <- lapply(view_name, function(X) { return(opt_xtrain_stats[[cancer_type]][[X]]) }) names(opt_xtrain_stats_cancer_view_spec) <- view_name # Predict using rmtlr prediction_view <- predict_with_rmtlr( view_name = view_name, view_info = view_info, view_data = view_data, opt_model_cancer_view_spec = opt_model_cancer_view_spec, opt_xtrain_stats_cancer_view_spec = opt_xtrain_stats_cancer_view_spec ) ## End(Not run)