explore_biomarkers {easier} | R Documentation |
Provides a good overview of the computed features
(biomarkers) including the corresponding weights from the
trained model. If patient_response
is provided,
this function shows statistically significant biomarkers
between responders (R) and non-responders (NR) patients.
explore_biomarkers( pathways = NULL, immunecells = NULL, tfs = NULL, lrpairs = NULL, ccpairs = NULL, cancer_type, patient_response = NULL, verbose = TRUE )
pathways |
numeric matrix with pathways activity
(rows = samples; columns = pathways). This is the
output from |
immunecells |
numeric matrix with immune cell quantification
(rows = samples; columns = cell types). This is the
output from |
tfs |
numeric matrix with transcription factors activity
(rows = samples; columns = transcription factors). This is the
output from |
lrpairs |
numeric matrix with ligand-receptor weights
(rows = samples; columns = ligand-receptor pairs). This is the
output from |
ccpairs |
numeric matrix with cell-cell scores
(rows = samples; columns = cell-cell pairs). This is the
output from |
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". |
patient_response |
character vector with two factors (Non-responders = NR, Responders = R). |
verbose |
logical flag indicating whether to display messages about the process. |
A combined plot for each type of quantitative descriptors, showing the original distribution of the features and the importance of these features for the trained models #'
Volcano plot displaying relevant biomarkers differentiating responders vs non-responders patients.
# 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 tf_activity <- compute_TF_activity( RNA_tpm = RNA_tpm ) # retrieve clinical response patient_ICBresponse <- colData(dataset_mariathasan)[["BOR"]] names(patient_ICBresponse) <- colData(dataset_mariathasan)[["pat_id"]] patient_ICBresponse <- patient_ICBresponse[names(patient_ICBresponse) %in% pat_subset] # Investigate possible biomarkers output_biomarkers <- explore_biomarkers( tfs = tf_activity, cancer_type = cancer_type, patient_response = patient_ICBresponse ) ## Not run: RNA_counts <- assays(dataset_mariathasan)[["counts"]] RNA_counts <- RNA_counts[, colnames(RNA_counts) %in% pat_subset] # Computation of cell fractions cell_fractions <- compute_cell_fractions(RNA_tpm = RNA_tpm) # Computation of pathway scores 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" ) # Investigate possible biomarkers output_biomarkers <- explore_biomarkers( pathways = pathway_activity, immunecells = cell_fractions, lrpairs = lrpair_weights, tfs = tf_activity, ccpairs = ccpair_scores, cancer_type = cancer_type, patient_response = patient_ICBresponse ) ## End(Not run)