pipeline.bpipe

SCRIPT = "~/projects_backup/INCSeq"
//ALIGNER = "graphmap"
ALIGNER = "blastn"
READ_NUM = 1000
LINE_NUM = READ_NUM * 2

set_global_var = {
  doc title: "Set global branch variables"
  branch.PREFIX = branch.name
}

split_fasta = {
  doc title: "Split the fasta files"
  desc: """
        Split the fasta file into multiple chunks
  """
  output.dir = "tmp_split"
  produce("*.fasta"){
    exec "split -l ${LINE_NUM} -d -a 8 $input tmp_split/read.split_"
    exec """	
    	 for file in tmp_split/read.split_*; do mv "$file" "${file}.fasta"; done
    	 """
  }
}


consensus = {
  doc title: "Consensus construction"
  output.dir = "tmp_consensus"
  transform (".fasta") to (".inc-seq.fa", ".inc-seq.log"){
    exec "${SCRIPT}/inc-seq.py -i $input.fasta  -o $output1 -a ${ALIGNER} --copy_num_thre 4 --length_difference_threshold 0.5  2> $output2", "main"
  }
}

merge_fasta = {
  doc title: "Merge fasta"
  desc:"""
      Merge all the consensus fasta files
  """
  produce ("${PREFIX}.inc-seq.fasta",
	   "${PREFIX}.inc-seq.log"){
    multi "cat tmp_consensus/*.inc-seq.fa  > $output1",
          "cat tmp_consensus/*.log > $output2"
  }
}


run { "%.fa" * [set_global_var + split_fasta + "read.split_%" * [ consensus ] + merge_fasta ]}