Merge branch 'master' into 'assign2'

# Conflicts:
#   R/assign_taxo_fun.R

DESCRIPTION

@@ -22,9 +22,13 @@ Imports:
   vctrs,
   biomformat,
   Biostrings,
+  Biobase,
+  BiocGenerics,
+  gtools,
   ShortRead,
   dada2,
   decontam,
+  dplyr,
   microbiome,
   DESeq2,
   metagenomeSeq,
@@ -33,11 +37,11 @@ Imports:
   pairwiseAdonis,
   phyloseq,
   psadd,
-  DESeq2,
   VennDiagram,
   digest,
   futile.logger,
   ggplot2,
+  glue,
   grid,
   gridExtra,
   vegan,
@@ -48,9 +52,14 @@ Imports:
   taxa,
   rmarkdown,
   ranacapa,
+  reshape2,
+  doParallel,
+  foreach,
   DECIPHER,
   mixOmics,
-  venn
+  venn,
+  htmlwidgets,
+  scales
 Remotes:
   github::omegahat/XML,
   bioc::3.10/biomformat,
@@ -61,11 +70,11 @@ Remotes:
   bioc::3.10/metagenomeSeq,
   bioc::3.10/phyloseq,
   bioc::3.10/microbiome,
-  bioc::3.10/DESeq2,
   bioc::3.10/DECIPHER,
   bioc::3.10/mixOmics,
   github::pmartinezarbizu/pairwiseAdonis/pairwiseAdonis,
   github::cpauvert/psadd,
   github::gauravsk/ranacapa,
   github::grunwaldlab/metacoder,
-  github::mixOmicsTeam/mixOmics
+  github::mixOmicsTeam/mixOmics,
+  github::mikelove/DESeq2

R/ASVenn_fun.R

@@ -134,18 +134,13 @@ ASVenn_fun <- function(data = data, output = "./ASVenn/", rank = "ASV",
     # write.table(TT, paste(output,"/otu_table_sp_",LOC,".csv",sep=""), sep="\t", quote=FALSE, col.names=NA)
 
   }
-  # print(names(TFtax))
-  # print(TFdata)
-  print(str(TFtax))
-  # stop()
+
   ## Venn diag
   flog.info('Defining unique taxa ...')
   alltax <- do.call(rbind, TFtax)
   alltax <- alltax[!duplicated(alltax[,1]),]
   row.names(alltax)=alltax[,1]
-  # print(alltax)
-  # stop()
-  # print(alltax)
+
   flog.info('Plotting ...')
 
   # Specific use to screen taxonomic composition of shared taxa...
@@ -158,6 +153,7 @@ ASVenn_fun <- function(data = data, output = "./ASVenn/", rank = "ASV",
     TF2 <- list(env1, others1)
     names(TF2) <- c(krona, "others")
     #Venn 2
+    # pdf(NULL)
     venn.plot <- venn.diagram(TF2, filename = NULL, col = "black",
                               fill = rainbow(length(TF2)), alpha = 0.50,
                               cex = 1.5, cat.col = 1, lty = "blank",
@@ -193,7 +189,7 @@ ASVenn_fun <- function(data = data, output = "./ASVenn/", rank = "ASV",
 
 
   TFbak <- TF <- sapply(TFtax, row.names, simplify = FALSE)
-  names(TFbak) = names(TF) = level1
+  names(TFbak) = names(TF) = lvls
   # print( length(unique(unlist(TF))) )
 
   if(length(lvls)>5){
@@ -238,10 +234,10 @@ ASVenn_fun <- function(data = data, output = "./ASVenn/", rank = "ASV",
 #'
 #' @param TF list containing vectors to plot.
 #' @param mode = 1: length(TF)<=5, mode = 2 5<length(TF)<7
-#' @param TITRE
-#' @param output
-#' @param refseq1
-#' @param alltax
+#' @param TITRE Plot title.
+#' @param output Output path.
+#' @param refseq1 Reference sequences.
+#' @param alltax Taxonomy table.
 #'
 #'
 #' @return Exports a venn diagram with corresponding tabulated file.
@@ -253,7 +249,8 @@ ASVenn_fun <- function(data = data, output = "./ASVenn/", rank = "ASV",
 
 VENNFUN <- function(TF = TF, mode = 1, TITRE = TITRE, output = "./", refseq1 = NULL, alltax=NULL){
   if(mode==1){
-    venn::venn(TF, zcol = rainbow(7), ilcs = 2, sncs = 2) #, col=rainbow(7)
+    # pdf(NULL)
+    venn::venn(TF, zcol = rainbow(7), ilcs = 2, sncs = 2, ggplot = FALSE) #, col=rainbow(7)
     venn.plot <- recordPlot()
     invisible(dev.off())
 
@@ -298,8 +295,8 @@ VENNFUN <- function(TF = TF, mode = 1, TITRE = TITRE, output = "./", refseq1 = N
       write.table(TABf, paste(output,"/",TITRE,"_venn_table.csv",sep=""), sep="\t", quote=FALSE, row.names=FALSE)
     }
   } else if(mode == 2){ # more than 5 environments
-
-    venn.plot <- venn::venn(TF, zcol = rainbow(7), ilcs = 2, sncs = 2) #, col=rainbow(7)
+    # pdf(NULL)
+    venn.plot <- venn::venn(TF, zcol = rainbow(7), ilcs = 2, sncs = 2, ggplot = FALSE) #, col=rainbow(7)
     venn.plot <- recordPlot()
     invisible(dev.off())
 

R/aggregate_fun.R

@@ -12,6 +12,7 @@
 #' @param verbose Verbose level. (1: quiet, 3: verbal)
 #' @param rank Taxonomy rank to merge features that have same taxonomy at a certain taxonomic rank (among rank_names(data), or 'ASV' for no glom)
 #' @param comp Comparison to test. Comma separated and comparisons are informed with a tilde (A~C,A~B,B~C). If empty, test all combination.
+#' @param returnval Boolean for function to return values.
 #'
 #' @return Export final CSV files, barplot with top significant ASV and Venn Digramm.
 #'

R/assign_taxo_fun.R

@@ -8,6 +8,7 @@
 #' @param verbose Verbose level. (1: quiet, 3: verbal)
 #' @param confidence Bootstrap threshold 0...100
 #' @param returnval Boolean to return values in console or not.
+#' @param ncpu Number of cpus to use.
 #'
 #'
 #' @return Return a taxonomy table with multiple ancestor checking and incongruence checking when 2 databases are used.
@@ -22,7 +23,7 @@
 
 
 
-assign_taxo_fun <- function(dada_res = dada_res,  output = "./idtaxa/", id_db = "/PathToDB/UNITE_idtaxa.Rdata", confidence = 50, verbose = 1, returnval = TRUE){
+assign_taxo_fun <- function(dada_res = dada_res,  output = "./idtaxa/", id_db = "/PathToDB/UNITE_idtaxa.Rdata", confidence = 50, verbose = 1, returnval = TRUE, ncpu=NULL){
 
 
   if(verbose == 3){

R/bars_fun.R

@@ -41,6 +41,7 @@ rarefaction <- function(data = data, col = NULL, step = 100, ggplotly = TRUE){
 #' @param Fact1 Variable used to change X axis tick labels and color (when split = FALSE)
 #' @param split if TRUE make a facet_wrap like grouped by Ord1 (default FALSE)
 #' @param relative Plot relative (TRUE, default) or raw abundance plot (FALSE)
+#' @param outfile Output html file.
 #'
 #' @return Returns barplots in an interactive plotly community plot
 #'

R/core_soft.R

@@ -7,6 +7,7 @@
 #' @param group Choose which level of the factor, if NULL generate a list for each level.
 #' @param freq frequence threshold of microbiome::core_members function
 #' @param prev prevalence threshold of microbiome::core_members function
+#' @param rank Taxonomy rank.
 #'
 #' @importFrom microbiome transform core_members
 #'

R/csv2phyloseq_fun.R

@@ -5,6 +5,7 @@
 #' @param taxtable Tabulated taxonomy table file path.
 #' @param seq Tabulated sequence file path.
 #' @param metadata Tabulated metadata file path.
+#' @param generateTree Boolean to generate the phylogenetic tree.
 #' @param output Output directory
 #' @param returnval Boolean to return values in console or not.
 #'

R/dada2_fun.R

@@ -5,7 +5,7 @@
 #' @param amplicon Choose amplipcon "16S" or "ITS"
 #' @param path Read files folder path
 #' @param outpath output .Rdata file name
-#' @param pool option for dada function (FALSE, TRUE or "pseudo"), default is "pseudo". See ? dada.
+#' @param dadapool option for dada function (FALSE, TRUE or "pseudo"), default is "pseudo". See ? dada.
 #' @param f_trunclen Forward read tuncate length (only for paired end 16S)
 #' @param r_trunclen Reverse read tuncate length (only for paired end 16S)
 #' @param f_primer Forward primer sequence (only for ITS)
@@ -31,9 +31,19 @@
 #' @import futile.logger
 #' @import digest
 #' @import phyloseq
+#' @import stringr
 #' @export
 
 
+
+get.sample.name <- function(fname){
+  # res <- stringr::str_match(basename(fname), "^(.*)_R[12]\\.fastq\\.gz$")
+  # tt <- res[1,2]
+  tt <- strsplit(basename(fname), "_")[[1]][1]
+
+  return(tt)
+}
+
 # DADA2 function
 
 dada2_fun <- function(amplicon = "16S", path = "", outpath = "./dada2_out/", f_trunclen = 240, r_trunclen = 240, dadapool = "pseudo",
@@ -70,8 +80,8 @@ dada2_fun <- function(amplicon = "16S", path = "", outpath = "./dada2_out/", f_t
     }
 
     flog.debug("File list...")
-    flog.debug(fnFs)
-    flog.debug(fnRs)
+    flog.debug(length(fnFs))
+    flog.debug(length(fnRs))
     flog.info('Done.')
 
     if(amplicon=="ITS"){
@@ -104,11 +114,11 @@ dada2_fun <- function(amplicon = "16S", path = "", outpath = "./dada2_out/", f_t
       # print(fnRs.filtN)
 
       flog.info('filterAndTrim...')
-      # if(! dir.exists(paste(path,'/filtN',sep=''))){
-      filterAndTrim(fwd = fnFs, filt = fnFs.filtN, rev = fnRs, filt.rev = fnRs.filtN, maxN = 0, multithread = TRUE, verbose=TRUE, rm.phix = TRUE, compress=compress)
-      # }else{
-      #   flog.info('Filtered files exist, skipping...')
-      # }
+      if(! dir.exists(paste(path,'/filtN',sep=''))){
+        filterAndTrim(fwd = fnFs, filt = fnFs.filtN, rev = fnRs, filt.rev = fnRs.filtN, maxN = 0, multithread = TRUE, verbose=TRUE, rm.phix = TRUE, compress=compress)
+      }else{
+        flog.info('Filtered files exist, skipping...')
+      }
 
       flog.info('Done.')
 
@@ -174,7 +184,8 @@ dada2_fun <- function(amplicon = "16S", path = "", outpath = "./dada2_out/", f_t
       cutRs <- sort(list.files(path.cut, pattern = "_R2.fastq", full.names = TRUE))
 
       # Extract sample names, assuming filenames have format:
-      get.sample.name <- function(fname) strsplit(basename(fname), "_")[[1]][1]
+
+      # get.sample.name <- function(fname) strsplit(basename(fname), "_")[[1]][1]
       sample.names <- unname(sapply(cutFs, get.sample.name))
       #head(sample.names)
 
@@ -189,6 +200,15 @@ dada2_fun <- function(amplicon = "16S", path = "", outpath = "./dada2_out/", f_t
       names(filtFs) <- sample.names
       names(filtRs) <- sample.names
 
+      flog.debug(length(cutFs))
+      print(head(cutFs))
+      flog.debug(length(filtFs))
+      print(head(filtFs))
+      flog.debug(length(cutRs))
+      print(head(cutRs))
+      flog.debug(length(filtRs))
+      print(head(filtRs))
+
       out <- filterAndTrim(cutFs, filtFs, cutRs, filtRs, maxN = 0, maxEE = c(2, 2),
       truncQ = 2, minLen = 50, compress = FALSE, multithread = TRUE)  # on windows, set multithread = FALSE
       #head(out)
@@ -209,7 +229,9 @@ dada2_fun <- function(amplicon = "16S", path = "", outpath = "./dada2_out/", f_t
       flog.debug(length(fnFs))
       flog.debug(length(fnRs))
 
-      sample.names <- sapply(strsplit(basename(fnFs), "_"), `[`, 1)
+      sample.names <- unname(sapply(fnFs, get.sample.name))
+      flog.debug(head(sample.names))
+      # sample.names <- sapply(strsplit(basename(fnFs), "_"), `[`, 1)
 
       if(compress){
         filtFs <- file.path(path, "filtered", paste0(sample.names, "_F_filt.fastq.gz"))

R/export_to_stamp_fun.R

@@ -4,7 +4,7 @@
 #'
 #' @param data a phyloseq object (output from decontam or generate_phyloseq)
 #' @param output Output directory
-#' @param correc If TRUE, correct metadata to replace most common special characters (eg. é -> e), save the new file in meta_stampOK.tsv.
+#' @param correc If TRUE, correct metadata to replace most common special characters, save the new file in meta_stampOK.tsv.
 #'
 #' @return Export 2 text files ready to use with STAMP.
 #'

R/generate_phyloseq_fun.R

@@ -3,7 +3,7 @@
 #'
 #'
 #' @param dada_res Results of dada2_fun()
-#' @param taxtable Results of assign_taxo_fun()
+#' @param tax.table Results of assign_taxo_fun()
 #' @param tree Results of generate_tree_fun()
 #' @param metadata Path of metadata file (tab separated with header)
 #' @param output Output directory

R/generate_tree_fun.R

@@ -3,7 +3,9 @@
 #'
 #'
 #' @param dada_res Results of dada2_fun()
-#' @param output Output directory
+#' @param output Output directory.
+#' @param psobj Phyloseq object with sequences.
+#' @param verbose Verbosity level.
 #' @param returnval Boolean to return values in console or not.
 #'
 #' @return Return a formatted tree object ready to use in phyloseq.

R/idtaxaDB_formatting_functions.R

@@ -137,8 +137,8 @@ check_tax_fun <- function(taxtable = taxtable, output = NULL, rank = 7, verbose=
 #' @param taxtable data.frame
 #' @param seqs path to fasta file or readDNAStringSet
 #' @param prunedb maximum number of sequences per unique taxa.
-#' @param outputDIR
-#' @output
+#' @param outputDIR Output directory.
+
 
 #' @return List with taxonomy table and corresponding sequences.
 #'

R/idtaxa_assign_fun.R

@@ -6,6 +6,7 @@
 #' @param dna A ‘DNAStringSet’ of unaligned sequences.
 #' @param asv_names sequences IDs in same order.
 #' @param confidence Bootstrap threshold 0...100
+#' @param ncpu Number of cpu to use
 #'
 #' @return return taxonomic assignment of given sequences.
 #' @import futile.logger
@@ -14,10 +15,10 @@
 #' @export
 
 
-idTaxa_assign = function(db_file, dna, asv_names, confidence){
+idTaxa_assign = function(db_file, dna, asv_names, confidence, ncpu = NULLS){
   flog.info(paste('Using database ',db_file,sep=''))
   toto <- load(db_file)
-  ids <- IdTaxa(dna, trainingSet, strand="both", processors=NULL, verbose=TRUE)
+  ids <- IdTaxa(dna, trainingSet, strand="both", processors=ncpu, verbose=TRUE)
   names(ids) <- asv_names
   flog.info("Confidence filtering...")
   IDCONF = as.numeric(confidence)

R/phy2cyto_fun.R

@@ -97,12 +97,12 @@ phy2cyto_fun <- function(data = data, output = "./cytoscape/", column1 = NULL, r
           LINKS = cbind(rep(asv, length(srcs)), glue("type_{srcs}"), srcs)
         }
       } else{
-        #sinon partage et création d'un lien pour chaque environnement source.
+        #sinon partage et creation d'un lien pour chaque environnement source.
         LINKS = NULL
         for(rep in reps){
           sdat3 = sdat2[sdat2[,repl]==rep,]
           srcs = as.character(unique(sdat3[,column1]))
-          # Lien seulement si l'asv présent dans même sample à 2 environnements ou plus
+          # Lien seulement si l'asv present dans meme sample a 2 environnements ou plus
           if(length(srcs)>1){
             link = cbind(rep(asv, length(srcs)), glue("type_{srcs}"), srcs)
             # print(glue("{rep} {srcs} envs"))

R/subset_fastx.R

 #' subset_fastx
 #'
-#' Allows subset fastq or fasta files at a given threshold. This fonction can convert fastq to fasta.
+#' Allows subset fastq or fasta files at a given threshold. This function can convert fastq to fasta.
 #'
 #' @param path Path to the fastq files directory
 #' @param format fasta or fastq format are allowed.
@@ -36,7 +36,7 @@ subset_fastx <- function(path = NULL, format = "fastq", outformat = "fastq", out
       writeXStringSet(X, glue::glue("{output}/{L2[i]}.{outformat}"), format = outformat, compress=compress)
       return("Done")
     }
-    
+
     if(length(X)>nbseq){
       if(random){
         if(!is.null(seed)){set.seed(seed)}

README.md

@@ -59,4 +59,4 @@ Murali, Adithya, Aniruddha Bhargava, et Erik S. Wright. « IDTAXA: a novel appr
 GPL 3.0
 
 ## Copyright
-2021 INRA
+2021 INRAE

man/VENNFUN.Rd

@@ -18,7 +18,13 @@ VENNFUN(
 
 \item{mode}{= 1: length(TF)<=5, mode = 2 5<length(TF)<7}
 
-\item{alltax}{}
+\item{TITRE}{Plot title.}
+
+\item{output}{Output path.}
+
+\item{refseq1}{Reference sequences.}
+
+\item{alltax}{Taxonomy table.}
 }
 \value{
 Exports a venn diagram with corresponding tabulated file.

man/aggregate_fun.Rd

@@ -38,6 +38,8 @@ aggregate_fun(
 \item{rank}{Taxonomy rank to merge features that have same taxonomy at a certain taxonomic rank (among rank_names(data), or 'ASV' for no glom)}
 
 \item{comp}{Comparison to test. Comma separated and comparisons are informed with a tilde (A~C,A~B,B~C). If empty, test all combination.}
+
+\item{returnval}{Boolean for function to return values.}
 }
 \value{
 Export final CSV files, barplot with top significant ASV and Venn Digramm.

man/assign_taxo_fun.Rd

@@ -10,7 +10,8 @@ assign_taxo_fun(
   id_db = "/PathToDB/UNITE_idtaxa.Rdata",
   confidence = 50,
   verbose = 1,
-  returnval = TRUE
+  returnval = TRUE,
+  ncpu = NULL
 )
 }
 \arguments{
@@ -25,6 +26,8 @@ assign_taxo_fun(
 \item{verbose}{Verbose level. (1: quiet, 3: verbal)}
 
 \item{returnval}{Boolean to return values in console or not.}
+
+\item{ncpu}{Number of cpus to use.}
 }
 \value{
 Return a taxonomy table with multiple ancestor checking and incongruence checking when 2 databases are used.

man/bars_fun.Rd

@@ -29,6 +29,8 @@ bars_fun(
 \item{split}{if TRUE make a facet_wrap like grouped by Ord1 (default FALSE)}
 
 \item{relative}{Plot relative (TRUE, default) or raw abundance plot (FALSE)}
+
+\item{outfile}{Output html file.}
 }
 \value{
 Returns barplots in an interactive plotly community plot