more tools + readme

.Rhistory

-flog.info('Plotting 2 ...')
-pf2 <- plotErrors(errF, nominalQ=TRUE)
-pr2 <- plotErrors(errR, nominalQ=TRUE)
-print("plotOK")
-ggsave(paste(out,'/err_plot_f.png',sep=''), plot=pf2)
-ggsave(paste(out,'/err_plot_f.png',sep=''), plot=pr2)
-flog.info('Done.')
-}
-setwd("~/Repository/LRF/00_erifa_bak/ranomaly_test")
 amplicon = "16S"
 path = "~/Repository/LRF/00_erifa_bak/ranomaly_test/reads"
 out = "./dada2_out/"
@@ -510,3 +501,12 @@ devtools::load_all("~/Repository/LRF/ranomaly")
 ? `assign_taxo
 è
 ? assign_taxo
+library(phyloseq)
+dat(GlobalPatterns)
+data(GlobalPatterns)
+rank(GlobalPatterns)
+ranknames(GlobalPatterns)
+rank_names(GlobalPatterns)
+library(ranomaly)
+library(ranomaly)
+setwd("/home/erifa/Repository/LRF/00_erifa_bak/ranomaly_test")

NAMESPACE

 # Generated by roxygen2: do not edit by hand
 
+export(ASVenn_fun)
 export(aggregate_fun)
 export(assign_taxo_fun)
 export(bars_fun)
+export(csv2phyloseq_fun)
 export(dada2_fun)
 export(decontam_fun)
 export(deseq2_fun)
@@ -14,8 +16,10 @@ export(generate_tree_fun)
 export(idTaxa_assign)
 export(metacoder_fun)
 export(metagenomeseq_fun)
+export(phy2cyto_fun)
 export(phy2tsv_fun)
 export(split_table_fun)
+export(update_metadata_fun)
 import(Biostrings)
 import(DECIPHER)
 import(DESeq2)
@@ -27,6 +31,7 @@ import(digest)
 import(futile.logger)
 import(ggplot2)
 import(ggpubr)
+import(glue)
 import(grid)
 import(gridExtra)
 import(metacoder)

R/ASVenn_fun.R

+#' ASVenn
+#'
+#'
+#' @param dada_res Results of dada2_fun()
+#' @param output Output directory
+#' @param rank Taxonomic rank name, or 'ASV' for ASV level.
+#' @param column1 Factor to test.
+#' @param subset Subset sample, please provide as c(FACTOR,LEVEL).
+#' @param lvls Vector list levels of factor to print in venn diagram (max. 5).
+#' @param krona Krona of exclusive ASV or shared with informed level and others. Must be among levels of column1 argument.
+#' @param shared shared [TRUE] or exclusive [FALSE] mode.
+#'
+#'
+#' @return Export a venn diagram with corresponding tabulated file.
+#'
+#' @import glue
+#' @export
+
+
+
+ASVenn_fun <- function(data = data, output = "./ASVenn/", rank = "ASV",
+                            column1 = NULL, subset = "", lvls = "", krona = "",
+                            shared = TRUE){
+
+  invisible(flog.threshold(futile.logger::ERROR, name = "VennDiagramLogger"))
+
+  if(!dir.exists(output)){
+    dir.create(output, recursive=TRUE)
+  }
+
+
+  #Check phyloseq object named data
+  if(!any(ls()=="data")){
+    for(i in ls()){
+      fun <- paste("cLS <- class(",i,")")
+      eval(parse(text=fun))
+      # print(c(i,cLS))
+      if(cLS == "phyloseq"){
+        fun <- paste("data = ", i)
+        eval(parse(text=fun))
+      }
+    }
+  }
+
+
+  if (is.null(column1)){
+    print_help(opt_parser)
+    flog.info("You must provide a factor:")
+    print(names(sample_data(data)))
+    quit()
+  }
+
+  #Subset data
+  if(subset!=""){
+    flog.info('Subset phyloseq object ...')
+    args1 <- unlist(strsplit(subset,","))
+    fun <- paste("data <- subset_samples(data, ",args1[1]," %in% '",args1[2],"')",sep="")
+    eval(parse(text=fun))
+    TITRE=paste(column1, args1[1], args1[2], sep="-")
+  }else{
+    TITRE=paste(column1)
+  }
+
+
+  #Nombre d'espèce par matrice
+  flog.info('Parsing factor ...')
+  level1 <- na.omit(levels(as.factor(sample_data(data)[,column1]@.Data[[1]])) )
+  TFdata <- list()
+  TFtax <- list()
+  if(!is.null(refseq(data, errorIfNULL=FALSE))){
+    refseq1 <- as.data.frame(refseq(data)); names(refseq1)="seq"
+  }else{flog.info('No Tree ...')}
+  databak <- data
+  for(i in 1:length(level1)){
+    databak -> data
+    LOC=as.character(level1[i])
+    print(LOC)
+    fun <- paste("data <- subset_samples(data, ",column1," %in% '",LOC,"')",sep="")
+    eval(parse(text=fun))
+    if(rank=="ASV"){
+      print("ASV")
+      sp_data = data
+      sp_data <- prune_taxa(taxa_sums(sp_data) > 0, sp_data)
+    }else{
+      print(rank)
+      sp_data <- tax_glom(data, rank)
+      sp_data <- prune_taxa(taxa_sums(sp_data) > 0, sp_data)
+      cat(LOC,ntaxa(sp_data)," ", rank, " \n")
+    }
+
+    ttable <- sp_data@tax_table@.Data
+    otable <- as.data.frame(otu_table(sp_data))
+    # print(nrow(ttable))
+
+    if(!any(rownames(ttable) == rownames(otable))){flog.info("Different order in otu table and tax table");quit()}
+
+    TT = cbind(otable,ttable)
+    TFdata[[i]] <- TT
+    TFtax[[i]] <- cbind(row.names(TT), as.character(apply(TT[,colnames(ttable)], 1, paste, collapse=";") ) ) #c("Kingdom","Phylum","Class","Order","Family","Genus","Species")
+    row.names(TFtax[[i]]) = TFtax[[i]][,1]
+    # write.table(TT, paste(output,"/otu_table_sp_",LOC,".csv",sep=""), sep="\t", quote=FALSE, col.names=NA)
+
+  }
+
+
+  ## Venn diag
+  flog.info('Defining unique taxa ...')
+  alltax <- do.call(rbind, TFtax)
+  alltax <- alltax[!duplicated(alltax[,1]),]
+  row.names(alltax)=alltax[,1]
+
+
+  flog.info('Plotting ...')
+  VENNFUN <- function(mode = 1){
+    if(mode==1){
+      venn.plot <- venn.diagram(TF, filename = NULL, col = "black",
+                                fill = rainbow(length(TF)), alpha = 0.50,
+                                cex = 1.5, cat.col = 1, lty = "blank",
+                                cat.cex = 1.8, cat.fontface = "bold",
+                                margin = 0.1, main=TITRE, main.cex=2.5,
+                                fontfamily ="Arial",main.fontfamily="Arial",cat.fontfamily="Arial") #cat.dist = 0.09,
+      png(paste(output,'/',TITRE,'_venndiag.png',sep=''), width=20, height=20, units="cm", res=200)
+      grid.draw(venn.plot)
+      invisible(dev.off())
+
+      ov <- calculate.overlap(TF)
+      print(sapply(ov, length))
+
+      flog.info('Calculating lists ...')
+      uniqTax = TABf = unique(do.call(c,TF))
+      for (j in 1:length(TF)){
+        TABtest = TF[[j]]
+        TABtest_filt=rep(0, length(uniqTax))
+        for (i in 1:length(uniqTax)) {
+          featureI = uniqTax[i]
+          res=grep( paste('^',featureI,'$', sep="" ) , TABtest)
+          if(length(res)>0){TABtest_filt[i]=length(res)
+          }
+        }
+        TABf=cbind.data.frame( TABtest_filt, TABf )
+        names(TABf)[1] = names(TF)[j]
+      }
+      if(exists("refseq1")){
+        TABf <- cbind(TABf,alltax[as.character(TABf$TABf),2], refseq1[as.character(TABf$TABf),])
+        names(TABf) <- c(rev(names(TF)), "ASV", "taxonomy", "seq")
+      }else{
+        TABf <- cbind(TABf,alltax[as.character(TABf$TABf),2])
+        names(TABf) <- c(rev(names(TF)), "ASV", "taxonomy")
+      }
+
+      write.table(TABf, paste(output,"/",TITRE,"_venn_table.csv",sep=""), sep="\t", quote=FALSE, row.names=FALSE)
+    } else if(mode == 2){
+      png(paste(output,'/',TITRE,'_venndiag.png',sep=''), width=20, height=20, units="cm", res=200)
+      venn.plot <- venn::venn(TF , zcol=rainbow(length(TF)))
+      #venn::venn(TF[c("LI","LA","EA","FI","TR","AI")] , zcol=rainbow(length(TF[c("LI","LA","EA","FI","TR","AI")])))
+      #venn::venn(TF[c("FI", "TR")] , zcol=rainbow(length(TF[c("FI", "TR")])))
+      dev.off()
+      ENVS = names(TF)
+      Tabf <- NULL; Tab1 <- NULL
+      for(i in ENVS){
+        tt = c(i, ENVS[ENVS != i])
+        print(tt)
+        yy = Reduce(setdiff, TF[tt])
+        print(length(yy))
+        Tab1 <- cbind(rep(i, length(yy)), alltax[yy,])
+        Tabf <- rbind(Tabf, Tab1)
+      }
+      yy <- Reduce(intersect, TF)
+      Core <- cbind(rep("core", length(yy)), alltax[yy,])
+      Tabf <- rbind(Core, Tabf)
+      write.table(Tabf, paste(output,"/",TITRE,"_venn_table.csv",sep=""), sep="\t", quote=FALSE, row.names=FALSE)
+    }
+  }
+
+  # Specific use to screen taxonomic composition of shared taxa...
+  if(krona != ""){
+    TF <- TFbak
+    flog.info('Krona ...')
+    env1 <- TF[[krona]]
+    others1 <- unique( unlist( TF[level1[level1!=krona]] ) )
+
+    TF2 <- list(env1, others1)
+    names(TF2) <- c(krona, "others")
+    #Venn 2
+    venn.plot <- venn.diagram(TF2, filename = NULL, col = "black",
+                              fill = rainbow(length(TF2)), alpha = 0.50,
+                              cex = 1.5, cat.col = 1, lty = "blank",
+                              cat.cex = 1.8, cat.fontface = "bold",
+                              margin = 0.1, main=TITRE, main.cex=2.5,
+                              fontfamily ="Arial",main.fontfamily="Arial",cat.fontfamily="Arial") #cat.dist = 0.09,
+    venn_tab=paste(output,"/",TITRE,"_",krona, "_kronaVenn.png", sep="")
+    png(venn_tab, width=20, height=20, units="cm", res=200)
+    grid.draw(venn.plot)
+    invisible(dev.off())
+
+    #Krona
+    if(shared==TRUE){
+      L1 = intersect(env1, others1)
+    }else{
+      L1 = setdiff(env1, others1)
+    }
+
+    subtaxdata=prune_taxa(L1,data)
+    ttable <- as.data.frame(subtaxdata@tax_table@.Data)
+    fttable = cbind.data.frame(rep(1,nrow(ttable)),ttable)
+    fttable$ASV = row.names(fttable)
+    dir.create("00test")
+    flog.info('Write Krona table ...')
+    krona_tab=paste(output,"/",TITRE,"_",krona, "_krona.txt", sep="")
+    write.table(fttable, krona_tab, col.names=FALSE, row.names=FALSE, quote=FALSE, sep="\t")
+
+    flog.info('Generate Krona html ...')
+    output <- paste(output,"/",TITRE,"_",krona, "_krona.html", sep = "")
+    system(paste("ktImportText", krona_tab, "-o", output, sep = " "))
+    # browseURL(output)
+  }
+
+
+
+  TFbak <- TF <- sapply(TFtax, row.names)
+  names(TFbak) = names(TF) = level1
+
+  if(length(level1)>5){
+    flog.info('Too much levels (max. 5) ...')
+    if(lvls == ""){
+      flog.info('Selecting 5 first levels ...')
+      # TF <- TF[c(1:5)]
+      VENNFUN(mode=2)
+    }else{
+      flog.info(glue('Selecting {lvls} ...'))
+      LVLs <- unlist(strsplit(lvls,","))
+      TF <- TF[LVLs]
+    }
+  } else {
+    VENNFUN()
+  }
+
+  flog.info('Done ...')
+
+}

R/csv2phyloseq_fun.R

+#' Create Phyloseq object from external datas.
+#'
+#'
+#' @param otutable Tabulated ASVtable file path.
+#' @param taxtable Tabulated taxonomy table file path.
+#' @param seq Tabulated sequence file path.
+#' @param metadata Tabulated metadata file path.
+#' @param output Output directory
+#' @param returnval Boolean to return values in console or not.
+#'
+#' @return Return a taxonomy table with multiple ancestor checking and incongruence checking when 2 databases are used.
+#'
+#' @export
+
+
+
+csv2phyloseq_fun <- function(otutable = NULL, taxtable = NULL, seq = NULL, metadata = NULL, output = "./csv2phyloseq/", returnval = TRUE){
+
+  flog.info("Input...")
+  flog.info("...OTUtable...")
+  otable <- read.table(otutable, sep="\t", h=TRUE)
+  row.names(otable)=otable[,1]
+  flog.info("...TAXtable...")
+  ttable <- as.matrix(read.table(taxtable, sep="\t", h=TRUE, stringsAsFactors=FALSE))
+  row.names(ttable)=ttable[,1]
+  flog.info("...Metadatas...")
+  mtable <- read.table(metadata, sep="\t", h=TRUE)
+  row.names(mtable)=mtable[,1]
+  flog.info("...Sequences...")
+  stable <- read.table(seq, sep="\t", h=TRUE)
+  sequences1 = DNAStringSet(stable[,-1])
+  names(sequences1)=stable[,1]
+  save.image("debug.rdata")
+
+
+
+  flog.info('Generating tree...')
+  sequences <- sequences1
+  # names(sequences) <- sapply(sequences,digest,algo='md5')
+  flog.info('Aligning sequences...')
+  alignment <- AlignSeqs(DNAStringSet(sequences),anchor=NA,processors=NULL)
+  flog.info('Creating distance matrices...')
+  phang.align <- phyDat(as(alignment, "matrix"), type="DNA")
+  dm <- dist.ml(phang.align)
+  flog.info('Neigbour joining...')
+  treeNJ <- NJ(dm) # Note, tip order != sequence order
+  fit = pml(treeNJ, data=phang.align)
+
+  flog.info('GTR...')
+  fitGTR <- update(fit, k=4, inv=0.2)
+  # fitGTR <- optim.pml(fitGTR, model="GTR", optInv=TRUE, optGamma=TRUE, rearrangement = "stochastic", control = pml.control(epsilon = 1e-08, maxit = 10,trace = 0))
+  # detach("package:phangorn", unload=TRUE)
+  flog.info('Done.')
+  tree <- fitGTR$tree
+
+  data <- phyloseq(otu_table(otable[,-1], taxa_are_rows=TRUE), sample_data(mtable), tax_table(ttable[,-1]), sequences1, tree) # phy_tree(tree),
+
+  if(!dir.exists(output)){
+    flog.info('Creating output directory...')
+    dir.create(output)
+    flog.info('Done.')
+  }
+  flog.info('Saving R objects.')
+  save(data, file=paste(output,'/phyloseq_object.Rdata',sep=''))
+
+  if(returnval){return(data)}
+
+  flog.info('Finish.')
+
+}

R/phy2cyto_fun.R

+#' Export files for cytoscape.
+#'
+#'
+#' @param data output from decontam or generate_phyloseq
+#' @param output Output directory
+#' @param column1 Factor to test.
+#' @param repl Replicates column.
+#' @param verbose Verbose level. (1: quiet, 3: verbal)
+#'
+#' @return Export files ready to use with Cytoscape
+#'
+#' @references https://cytoscape.org/
+#'
+#' @export
+
+
+
+phy2cyto_fun <- function(data = data, output = "./cytoscape/", column1 = NULL, repl = NULL, verbose = 1){
+
+  if(!dir.exists(output)){
+    dir.create(output, recursive=TRUE)
+  }
+
+
+  data1 <- data
+  otab = as.data.frame(otu_table(data1))
+  sdat <- sdata <- as.data.frame(as.matrix(sample_data(data1)))
+  fact <- levels(as.factor(sdata[,column1]))
+  # repl <- "temps"
+
+
+  if(is.null(repl)){
+    flog.info('No replicates, performing links ...')
+    #Test1 VUE globale sans tenir compte des réplicats
+    # Interaction table
+    sif_tab=NULL
+    for(env in fact ){
+      flog.debug(print(env))
+      eval(parse(text=glue("tt <- subset_samples(data1, {column1} %in% '{env}')") ))   ###
+      flog.debug(print(nsamples(tt)))
+
+      #ASV present dans au moins 3 échantillons, autre filtre sur abondance?
+      tt2 = prune_taxa( apply(otu_table(tt), 1, function(x){length(which(x>0))>3}), tt)
+      flog.debug(print(ntaxa(tt2)))
+      #Effectif des asv dans la table < 20
+      otab2 <- as.data.frame(otu_table(tt2))
+      otab2[otab2<20] = 0
+      otu_table(tt2) = otu_table(otab2, taxa_are_rows=TRUE)
+      tt2 <- prune_taxa(taxa_sums(tt2) > 0, tt2)
+
+      tabf = cbind(taxa_names(tt2), rep(glue("type_{env}"), ntaxa(tt2)), rep(env, ntaxa(tt2)))
+      sif_tab = rbind(sif_tab, tabf)
+    }
+    flog.info('Output ...')
+    write.table(as.data.frame(sif_tab), glue("{output}/sif_tab1.tsv"), sep="\t", row.names=FALSE, col.names=TRUE, quote=FALSE)
+
+    # Node table
+    src = unique(sif_tab[,3])
+    trgt = sif_tab[,1]
+    freq = taxa_sums(data1) / sum(taxa_sums(data1))
+
+    node_table=cbind.data.frame(c(src, trgt), c(rep("source", length(src)), rep("cible", length(trgt))), c(rep(NA, length(src)), freq[trgt]) )
+    names(node_table)=c("names","attribute", "freq")
+    node_table[node_table$attribute=="source","freq"] = 0.75*max(na.omit(node_table$freq))
+
+    node_table$tax = "source"
+    node_table[node_table$attribute == "cible","tax"] = tax_table(data1)[as.character(node_table[node_table$attribute == "cible",1]),"Phylum"]
+
+
+    write.table(as.data.frame(node_table), glue("{output}/node_tab1.tsv"), sep="\t", row.names=FALSE, col.names=TRUE, quote=FALSE)
+
+  }else{
+    flog.info('Replicates, performing links ...')
+    sif_tab = NULL
+    for(asv in taxa_names(data1)){
+      # print(asv)
+      notu = otab[asv,]
+      nsamples = names(notu)[notu>20]  #nombre d'occurence de l'otu
+      if(length(nsamples) == 1){flog.debug(print(asv))}
+
+      sdat2 = sdat[nsamples,]
+      rep1 = table(as.character(sdat[nsamples,repl]))
+      reps = names(rep1)   #[which(rep1>1)]
+      # if(max(rep1[which(rep1>1)]) == 1){print(asv)}
+
+      # si aucun partage 1 seul environnement
+      if(length(rep1)==1){
+        if(rep1==1){
+          flog.debug(glue("{asv} exclusif 1 seul réplicat 1 env"))
+          src <- as.character(unique(sdat2[,column1]))
+          LINKS = c(asv, glue("type_{src}"), src)
+        }else{
+          rep=names(rep1)
+          sdat3 = sdat2[sdat2$exploit_saison==rep,]
+          srcs = as.character(unique(sdat3[,column1]))
+          LINKS = cbind(rep(asv, length(srcs)), glue("type_{srcs}"), srcs)
+        }
+      } else{
+        #sinon partage et création 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
+          if(length(srcs)>1){
+            link = cbind(rep(asv, length(srcs)), glue("type_{srcs}"), srcs)
+            # print(glue("{rep} {srcs} envs"))
+            # print(link)
+            LINKS = rbind(LINKS, link)
+          }
+        }
+      }
+      sif_tab = rbind(sif_tab, LINKS)
+
+    }
+    save.image("debug.rdata")
+    flog.info('Output ...')
+    # LINK table output
+    #Compte le nombre d'occurence de chaque lien (environnement - ASV)
+    tt=apply(sif_tab, 1, paste, collapse="-")
+    # Unique + counts de chaque lien
+    sif_tabF = cbind(unique(sif_tab), table(tt), names(table(tt)) )
+    colnames(sif_tabF) = c("asv", "type", "srcs", "nb_lien", "rownames")
+
+    length(unique(sif_tabF[,1]))
+    length(taxa_names(data1))
+
+    sif_tabF <- as.data.frame(sif_tabF)
+
+    # Metriques links
+    #nombres de liens pour chaque OTU
+    table(sif_tabF[,"asv"])
+    table(sif_tabF[,"srcs"])
+
+
+    write.table(as.data.frame(sif_tabF), glue("{output}/sif_tab2.tsv"), sep="\t", row.names=FALSE, col.names=TRUE, quote=FALSE)
+
+    # Node table output
+    src = unique(sif_tabF[,3])
+    trgt = sif_tabF[,1]
+    freq = taxa_sums(data1) / sum(taxa_sums(data1))
+
+    # Taille des noeud en fonction de la frequence, noeud "groupe" 0.75 de la freq max.
+    node_table=cbind.data.frame(c(src, trgt), c(rep("source", length(src)), rep("cible", length(trgt))), c(rep(NA, length(src)), freq[trgt]) )
+    names(node_table)=c("names","attribute", "freq")
+
+    node_table[node_table$attribute=="source","freq"] = 0.75*max(na.omit(node_table$freq))
+
+    node_table$tax = "source"
+    node_table[node_table$attribute == "cible","tax"] = tax_table(data1)[as.character(node_table[node_table$attribute == "cible",1]),"Phylum"]
+
+    write.table(as.data.frame(node_table), glue("{output}/node_tab2.tsv"), sep="\t", row.names=FALSE, col.names=TRUE, quote=FALSE)
+
+  }
+
+
+}

R/phy2tsv_fun.R

@@ -21,19 +21,6 @@ phy2tsv_fun <- function(data = data, output = "./tsv_table/", rank = "ASV"){
     dir.create(output, recursive=TRUE)
   }
 
-  #Check phyloseq object named data
-  flog.info('Check phyloseq object ...')
-  if(!any(ls()=="data")){
-    for(i in ls()){
-      fun <- paste("cLS <- class(",i,")")
-      eval(parse(text=fun))
-      # print(c(i,cLS))
-      if(cLS == "phyloseq"){
-        fun <- paste("data = ", i)
-        eval(parse(text=fun))
-      }
-    }
-  }
 
   flog.info('Generating table ...')
   stable <- as.data.frame(sample_data(data))

R/update_metadata_fun.R

+#' Update metadata
+#'
+#'
+#' @param data output from decontam or generate_phyloseq
+#' @param metadata Tabulated metadata file path.
+#' @param output Output directory
+#' @param returnval Boolean to return values in console or not.
+#'
+#' @return Return a phyloseq object with updated metadata.
+#'
+#' @export
+
+
+update_metadata_fun <- function(data = data, output = "./updated_physeq/", metadata = NULL, returnval = TRUE){
+
+  if (is.null(metadata)){
+    print_help(opt_parser)
+    stop("You must provide metadata file path.", call.=FALSE)
+  } else{
+    flog.info("Loading sample metadata..")
+    sampledata <- read.table(metadata, sep="\t",header=TRUE)
+    rownames(sampledata) <- sampledata$sample.id
+    sample.metadata <- sample_data(sampledata)
+    flog.info('Done.')
+  }
+
+  if(!dir.exists(output)){
+    flog.info('Creating output directory...')
+    dir.create(output)
+    flog.info('Done.')
+  }
+  print(sample.metadata)
+
+  sample_data(data) <- sample.metadata
+
+  save(data, file=paste(output,'/robjects.Rdata',sep=''))
+
+  if(returnval){data}
+
+}

README.Rmd

+---
+output: github_document
+---
+
+<!-- README.md is generated from README.Rmd. Please edit that file -->
+
+```{r, include = FALSE}
+knitr::opts_chunk$set(
+  collapse = TRUE,
+  comment = "#>",
+  fig.path = "man/figures/README-",
+  out.width = "100%"
+)
+```
+# rANOMALY
+
+<!-- badges: start -->
+[![Lifecycle: experimental](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://www.tidyverse.org/lifecycle/#experimental)
+<!-- badges: end -->
+
+rANOMALY is the R Package of the first version of ANOMALY (https://forgemia.inra.fr/umrf/anomaly)
+
+## Installation
+
+You can install the development version of rANOMALY from this repository with:
+
+``` r
+devtools::install_git("https://forgemia.inra.fr/umrf/ranomaly")
+```
+

README.md

+
+<!-- README.md is generated from README.Rmd. Please edit that file -->
+
+# rANOMALY
+
+<!-- badges: start -->
+
+[![Lifecycle:
+experimental](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://www.tidyverse.org/lifecycle/#experimental)
+<!-- badges: end -->
+
+rANOMALY is the R Package of the first version of ANOMALY
+(<https://forgemia.inra.fr/umrf/anomaly>)
+
+## Installation
+
+You can install the development version of rANOMALY from this repository
+with:
+
+``` r
+devtools::install_git("https://forgemia.inra.fr/umrf/ranomaly")
+```

man/ASVenn_fun.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/ASVenn_fun.R
+\name{ASVenn_fun}
+\alias{ASVenn_fun}
+\title{ASVenn}
+\usage{
+ASVenn_fun(
+  data = data,
+  output = "./ASVenn/",
+  rank = "ASV",
+  column1 = NULL,
+  subset = "",
+  lvls = "",
+  krona = "",
+  shared = TRUE
+)
+}
+\arguments{
+\item{output}{Output directory}
+
+\item{rank}{Taxonomic rank name, or 'ASV' for ASV level.}
+
+\item{column1}{Factor to test.}
+
+\item{subset}{Subset sample, please provide as c(FACTOR,LEVEL).}
+
+\item{lvls}{Vector list levels of factor to print in venn diagram (max. 5).}
+
+\item{krona}{Krona of exclusive ASV or shared with informed level and others. Must be among levels of column1 argument.}
+
+\item{shared}{shared [TRUE] or exclusive [FALSE] mode.}
+
+\item{dada_res}{Results of dada2_fun()}
+}
+\value{
+Export a venn diagram with corresponding tabulated file.
+}
+\description{
+ASVenn
+}

man/csv2phyloseq_fun.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/csv2phyloseq_fun.R
+\name{csv2phyloseq_fun}
+\alias{csv2phyloseq_fun}
+\title{Create Phyloseq object from external datas.}
+\usage{
+csv2phyloseq_fun(
+  otutable = NULL,
+  taxtable = NULL,
+  seq = NULL,
+  metadata = NULL,
+  output = "./csv2phyloseq/",
+  returnval = TRUE
+)
+}
+\arguments{
+\item{otutable}{Tabulated ASVtable file path.}
+
+\item{taxtable}{Tabulated taxonomy table file path.}
+
+\item{seq}{Tabulated sequence file path.}
+
+\item{metadata}{Tabulated metadata file path.}
+
+\item{output}{Output directory}
+
+\item{returnval}{Boolean to return values in console or not.}
+}
+\value{
+Return a taxonomy table with multiple ancestor checking and incongruence checking when 2 databases are used.
+}
+\description{
+Create Phyloseq object from external datas.
+}

man/phy2cyto_fun.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/phy2cyto_fun.R
+\name{phy2cyto_fun}
+\alias{phy2cyto_fun}
+\title{Export files for cytoscape.}
+\usage{
+phy2cyto_fun(
+  data = data,
+  output = "./cytoscape/",
+  column1 = NULL,
+  repl = NULL,
+  verbose = 1
+)
+}
+\arguments{
+\item{data}{output from decontam or generate_phyloseq}
+
+\item{output}{Output directory}
+
+\item{column1}{Factor to test.}
+
+\item{repl}{Replicates column.}
+
+\item{verbose}{Verbose level. (1: quiet, 3: verbal)}
+}
+\value{
+Export files ready to use with Cytoscape
+}
+\description{
+Export files for cytoscape.
+}
+\references{
+https://cytoscape.org/
+}

man/update_metadata_fun.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/update_metadata_fun.R
+\name{update_metadata_fun}
+\alias{update_metadata_fun}
+\title{Update metadata}
+\usage{
+update_metadata_fun(
+  data = data,
+  output = "./updated_physeq/",
+  metadata = NULL,
+  returnval = TRUE
+)
+}
+\arguments{
+\item{data}{output from decontam or generate_phyloseq}
+
+\item{output}{Output directory}
+
+\item{metadata}{Tabulated metadata file path.}
+
+\item{returnval}{Boolean to return values in console or not.}
+}
+\value{
+Return a phyloseq object with updated metadata.
+}
+\description{
+Update metadata
+}

scripts/00_Rscriptmode_anomaly.R

@@ -3,7 +3,7 @@
 #system.file("reads", "", package="ranomaly")  # Reads folder
 #system.file("", "sample-metadata.csv", package="ranomaly") # metadata
 
-#setwd("")
+setwd("/home/erifa/Repository/LRF/00_erifa_bak/ranomaly_test")
 
 dada_res = dada2_fun(path=system.file("reads", "", package="ranomaly"), compress=TRUE, plot=TRUE)
 
@@ -43,3 +43,17 @@ TABF = aggregate_fun(data = data, metacoder = "./metacoder/metacoder_temps_lot_G
                           column1 = "temps_lot", column2 = NULL, verbose = 1, rank = "Genus", comp = "T6_lot1~T6_lot3,T9_lot1~T9_lot3")
 head(TABF)
 
+
+
+#other TOOLS
+ASVenn_fun(data = data, output = "./ASVenn/", rank = "ASV",
+                            column1 = "temps", subset = "", lvls = "", krona = "",
+                            shared = TRUE)
+
+csv2phyloseq_fun(otutable = "00_csv2phyloseqtest/opticum_fro_otutable.csv", taxtable = "00_csv2phyloseqtest/opticum_fro_taxo.csv",
+                             seq = "00_csv2phyloseqtest/opticum_fro_seq.csv", metadata = "00_csv2phyloseqtest/opticum_fro_metadata.csv", output = "./00_csv2phyloseqtest/csv2phyloseq/")
+
+
+update_metadata_fun(data = data, output = "./updated_physeq/", metadata = "./sample-metadata_up1.csv", )
+
+phy2cyto_fun(data = data, output = "./cytoscape/", column1 = "Producteur_Lait", repl = NULL, verbose = 1)