example_code.txt

######		Computational approach to discriminate human and mouse sequences	######
######				in patient-derived tumour xenografts			######
######												######
######					Supplementary file 1					######
######		Set of commands to implement an ICRG-based alignment pipeline		######
##############################################################################################

#!/bin/bash

### MERGE TWO GENOMES (FASTA FORMAT)

# specify genome path
GENOME_A=path/to/genome_a
GENOME_B=path/to/genome_b

# generate a copy of genome_b with modified chromosome names
cp "$GENOME_B" "$GENOME_B"_edited
sed -i 's/chr/m.chr/g' "$GENOME_B"_edited

# combine the two fasta files
cat "$GENOME_A" "$GENOME_B"_edited > path/to/ICRG



### EXTRACT THE NUMBER OF READS (MAPQ>0) MAPPED TO GENOME_A AND GENOME_B (WES DATA)
READCOUNT=$(echo  $(samtools view -F 4 -q 1 path/to/ICRG_aligned.bam | grep -v $'\t''m.chr' | wc -l) \
	$(samtools view -F 4 -q 1 path/to/ICRG_aligned.bam | grep $'\t''m.chr' | wc -l))
echo $READCOUNT > path/to/stats_file.txt



### SUBSET READS MAPPED TO GENOME_A
samtools view -h path/to/ICRG_aligned.bam \
| grep -v $'\t''m.chr' \
| grep -v 'SN:m.chr' \
| samtools view -b - > path/to/genome_a_only.bam



### EXTRACT THE NUMBER OF READS MAPPED (PRIMARY ALIGNMENT) TO GENOME_A AND GENOME_B (RNA-SEQ DATA)
READCOUNT=$(echo  $(samtools view -F 260 path/to/ICRG_aligned.bam | grep -v $'\t''m.chr' | wc -l) \
	$(samtools view -F 260 path/to/ICRG_aligned.bam | grep $'\t''m.chr' | wc -l))
echo $READCOUNT > path/to/stats_file.txt