predict_immune_response: Compute predicted immune response

In olapuentesantana/easier: Estimate Systems Immune Response from RNA-seq data

Compute predicted immune response

Description

Calculates predictions of patients' immune response using the quantitative descriptors data as input features and the optimized model parameters derived from the trained models. These models are available from easierData package through easierData::get_opt_models().

Usage

predict_immune_response(
  pathways = NULL,
  immunecells = NULL,
  tfs = NULL,
  lrpairs = NULL,
  ccpairs = NULL,
  cancer_type,
  verbose = TRUE
)

Arguments

pathways	numeric matrix with pathways activity (rows = samples; columns = pathways).
immunecells	numeric matrix with immune cell quantification (rows = samples; columns = cell types).
tfs	numeric matrix with transcription factors activity (rows = samples; columns = transcription factors).
lrpairs	numeric matrix with ligand-receptor weights (rows = samples; columns = ligand-receptor pairs).
ccpairs	numeric matrix with cell-cell scores (rows = samples; columns = cell-cell pairs).
cancer_type	character string indicating which cancer-specific model should be used to compute the predictions. This should be available from the cancer-specific models. The following cancer types have a corresponding model available: "BLCA", "BRCA", "CESC", "CRC", "GBM", "HNSC", "KIRC", "KIRP", "LIHC", "LUAD", "LUSC", "NSCLC", "OV", "PAAD", "PRAD", "SKCM", "STAD", "THCA" and "UCEC".
verbose	logical flag indicating whether to display messages about the process.

Value

A list containing the predictions for each quantitative descriptor and for each task. Given that the model training was repeated 100 times with randomized-cross validation, a set of 100 predictions is returned.

Examples

# 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_activity <- compute_TF_activity(
  RNA_tpm = RNA_tpm
)

# Predict patients' immune response
predictions_immune_response <- predict_immune_response(
  tfs = tf_activity,
  cancer_type = cancer_type
)



RNA_counts <- assays(dataset_mariathasan)[["counts"]]
RNA_counts <- RNA_counts[, colnames(RNA_counts) %in% pat_subset]

# Computation of cell fractions (Finotello et al., Genome Med, 2019)
cell_fractions <- compute_cell_fractions(RNA_tpm = RNA_tpm)

# Computation of pathway scores (Holland et al., BBAGRM, 2019;
# Schubert et al., Nat Commun, 2018)
pathway_activity <- compute_pathway_activity(
  RNA_counts = RNA_counts,
  remove_sig_genes_immune_response = TRUE
)

# Computation of ligand-receptor pair weights
lrpair_weights <- compute_LR_pairs(
  RNA_tpm = RNA_tpm,
  cancer_type = "pancan"
)

# Computation of cell-cell interaction scores
ccpair_scores <- compute_CC_pairs(
  lrpairs = lrpair_weights,
  cancer_type = "pancan"
)

# Predict patients' immune response
predictions_immune_response <- predict_immune_response(
  pathways = pathway_activity,
  immunecells = cell_fractions,
  tfs = tf_activity,
  lrpairs = lrpair_weights,
  ccpairs = ccpair_scores,
  cancer_type = cancer_type
)

olapuentesantana/easier documentation built on Feb. 25, 2024, 3:39 p.m.