A short test to generate a test SAM file with a long read

generate_sam_test.py

import sys

base_seq = "ACGT"
seq = base_seq * int(int(sys.argv[1])/len(base_seq))
spacer_length = 10000
header = "@HD	VN:1.0\n@SQ	SN:Mock	LN:%s" % (len(seq) + spacer_length)

cigar_string = "%sM" % (len(seq))
genome_line = "62DJLAAXX_8:1:17056:1190	0	Mock	1	255	%s	*	0	0	%s	*	NM:i:0	MD:Z:30	NH:i:1" % (
    cigar_string, seq)

print("\n".join([header, genome_line]))

run.sh

for LEN in 400000 800000 1600000
do
    python generate_sam_test.py  ${LEN} > sam_test_${LEN}_nt.sam
    samtools view -bS sam_test_${LEN}_nt.sam > sam_test_${LEN}_nt.bam
    samtools sort sam_test_${LEN}_nt.bam sam_test_${LEN}_nt_sorted
    rm -f sam_test_${LEN}_nt.bam
    samtools index sam_test_${LEN}_nt_sorted.bam
done