This function generates counts, FPKM and TPM tables from rnaseqCounts outuputs.

sample2experiment(
  sample.folders,
  covariates,
  batch = NULL,
  bio.type = c("protein_coding", "unitary_pseudogene", "unprocessed_pseudogene",
    "processed_pseudogene", "transcribed_unprocessed_pseudogene", "processed_transcript",
    "antisense", "transcribed_unitary_pseudogene", "polymorphic_pseudogene", "lincRNA",
    "sense_intronic", "transcribed_processed_pseudogene", "sense_overlapping",
    "IG_V_pseudogene", "pseudogene", "TR_V_gene", "3prime_overlapping_ncRNA",
    "IG_V_gene", "bidirectional_promoter_lncRNA", "snRNA", "miRNA", "misc_RNA", "snoRNA",
    "rRNA", "IG_C_gene", "IG_J_gene", 
     "TR_J_gene", "TR_C_gene", "TR_V_pseudogene",
    "TR_J_pseudogene", "IG_D_gene", "ribozyme", "IG_C_pseudogene", "TR_D_gene", "TEC",
    "IG_J_pseudogene", "scRNA", "scaRNA", "vaultRNA", "sRNA", "macro_lncRNA",
    "non_coding", "IG_pseudogene"),
  output.prefix = "."
)

Arguments

sample.folders,

a character string indicating the paths of rnaseqCouts output folders

covariates,

a character string indicating the covariates associated to each sample. Covariates are required for differnetial expression analysis

batch,

a character string indicating the batch associated to each sample

bio.type,

a character string indicating the ensemb bio.type. Options: "protein_coding","unitary_pseudogene","unprocessed_pseudogene","processed_pseudogene", "transcribed_unprocessed_pseudogene","processed_transcript","antisense","transcribed_unitary_pseudogene","polymorphic_pseudogene","lincRNA","sense_intronic","transcribed_processed_pseudogene","sense_overlapping","IG_V_pseudogene","pseudogene","TR_V_gene","3prime_overlapping_ncRNA","IG_V_gene","bidirectional_promoter_lncRNA","snRNA","miRNA","misc_RNA","snoRNA","rRNA","IG_C_gene","IG_J_gene","TR_J_gene","TR_C_gene","TR_V_pseudogene","TR_J_pseudogene","IG_D_gene","ribozyme","IG_C_pseudogene","TR_D_gene","TEC","IG_J_pseudogene","scRNA","scaRNA","vaultRNA","sRNA","macro_lncRNA","non_coding","IG_pseudogene"

output.prefix,

a character value indicating the output folder path

Value

Returns counts, fpkm, tpm data frames for gene and isoforms, save data frames in experiment.tables.Rda, in counts.txt, log2fpkm.txt and in log2TPM

Author

Raffaele Calogero

Examples

if (FALSE) {
  system("wget http://130.192.119.59/public/test.samples2experiment.zip")
  unzip("test.samples2experiment.zip")
  setwd("test.samples2experiment")
  library(docker4seq)
  sample2experiment(sample.folders=c("./e1g","./e2g","./e3g",
                 "./p1g", "./p2g", "./p3g"),
                 covariates=c("Cov.1","Cov.1","Cov.1",
                 "Cov.2","Cov.2","Cov.2"),
                 bio.type="protein_coding", output.prefix=".")
}