library(Biostrings)
library(dplyr)
homo.files <- list.files("orthologs.faa/")
info.files <- list.files("gene.info/")

#Define a string split function which splits by space character and returns first element
splitfun <- function(x){
  strsplit(x," ")[[1]][1]
}

#Define a simple function that will replace all spaces and illegal characters with underscores
spc.replc <- function(x){
  gsub(" ", "_", x, fixed = TRUE)
  gsub(",",".",x)
  gsub(";",".",x)
  gsub(":",".",x)
}


#define a funciton that will replace any annoying illegal punctuation
punct.replc <- function(x){
  gsub("([[:punct:]])|\\s+","_",x)
}

#define write fasta function
writeFasta<-function(data, filename){
  fastaLines = c()
  for (rowNum in 1:nrow(data)){
    fastaLines = c(fastaLines, as.character(paste(">", data[rowNum,"name"], sep = "")))
    fastaLines = c(fastaLines,as.character(data[rowNum,"seq"]))
  }
  fileConn<-file(filename)
  writeLines(fastaLines, fileConn)
  close(fileConn)
}

for (x in c(1:length(homo.files))) {
  iter <- readAAStringSet(paste("orthologs.faa/",homo.files[x],sep = ""))
  Gene.ID <- names(iter)
  Gene.ID <- unlist(lapply(Gene.ID, splitfun))
  seq <- paste(iter)
  fasta.df <- data.frame(Gene.ID, seq, stringsAsFactors = F)
  fasta.df$Gene.ID <- as.character(fasta.df$Gene.ID)
  info <- read.csv(paste("gene.info/",info.files[x],sep=""),header = T,sep = "\t")[c(1,5)]
  info$newname <- paste(info$Genome.Name,info$Gene.ID,sep=" ")
  #info$newname <- unlist(lapply(info$newname, spc.replc))
  info$newname <- unlist(lapply(info$newname, punct.replc))
  info$Gene.ID <- as.character(info$Gene.ID)
  fasta.df <- dplyr::left_join(fasta.df, info, by="Gene.ID" )
  fasta.df <- fasta.df[c(4,2)]
  colnames(fasta.df)[1] <- "name"
  writeFasta(fasta.df, paste("orthlogs.clean/",homo.files[x],sep = ""))
}

DCM.all <- readAAStringSet("cass.proteins/five.DCM.cassette.proteins.faa")
name.old <- names(DCM.all)
seq <- paste(DCM.all)
DCM.df <- data.frame(name.old, seq)
colnames(DCM.df)[1] <- "gene_oid"
DCM.info.all <- read.csv("cass.proteins/gene.info.IMG.all.csv",header = T,stringsAsFactors = F)[c(1,4,8)]
cass <- sort(unique(DCM.info.all$DCM.gene.name))

for (x in c(1:length(cass))) {
  info <- DCM.info.all[DCM.info.all$DCM.gene.name == cass[x],]
  info$newname <- paste(info$Genome.Name,info$gene_oid,sep=" ")
  #info$newname <- unlist(lapply(info$newname, spc.replc))
  info$newname <- unlist(lapply(info$newname, punct.replc))
  info$gene_oid <- as.character(info$gene_oid)
  fasta.df <- dplyr::left_join(info, DCM.df, by="gene_oid" )
  fasta.df <- fasta.df[c(4,5)]
  colnames(fasta.df)[1] <- "name"
  writeFasta(fasta.df, paste("DCM.cass.clean/",cass[x],".clean.faa",sep = ""))
}

DCM.files <- list.files("DCM.cass.clean/")
ortho.files <- list.files("orthlogs.clean/")

for (x in c(1:length(DCM.files))) {
  DCM <- readAAStringSet(paste("DCM.cass.clean/",DCM.files[x],sep = ""))
  name <- names(DCM)
  seq <- paste(DCM)
  DCM <- data.frame(name,seq)
  DCM$name <- as.character(DCM$name)
  ortho <- readAAStringSet(paste("orthlogs.clean/",ortho.files[x],sep=""))
  name <- names(ortho)
  seq <- paste(ortho)
  ortho <- data.frame(name,seq)
  ortho$name <- as.character(ortho$name)
  all.fa <- rbind(DCM,ortho)
  writeFasta(all.fa, paste("DCM.cass.with.ortho/",DCM.files[x],sep=""))
}