1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
|
#!/bin/sh
#
# Downloads sequence for the GRCh37 release 75 version of H. sapiens (human) from
# Ensembl.
#
# Note that Ensembl's GRCh37 build has three categories of compressed fasta
# files:
#
# The base files, named ??.fa.gz
#
# By default, this script builds and index for just the base files,
# since alignments to those sequences are the most useful. To change
# which categories are built by this script, edit the CHRS_TO_INDEX
# variable below.
#
ENSEMBL_RELEASE=75
ENSEMBL_GRCh37_BASE=ftp://ftp.ensembl.org/pub/release-${ENSEMBL_RELEASE}/fasta/homo_sapiens/dna
get() {
file=$1
if ! wget --version >/dev/null 2>/dev/null ; then
if ! curl --version >/dev/null 2>/dev/null ; then
echo "Please install wget or curl somewhere in your PATH"
exit 1
fi
curl -o `basename $1` $1
return $?
else
wget $1
return $?
fi
}
HISAT2_BUILD_EXE=./hisat2-build
if [ ! -x "$HISAT2_BUILD_EXE" ] ; then
if ! which hisat2-build ; then
echo "Could not find hisat2-build in current directory or in PATH"
exit 1
else
HISAT2_BUILD_EXE=`which hisat2-build`
fi
fi
rm -f genome.fa
F=Homo_sapiens.GRCh37.${ENSEMBL_RELEASE}.dna.primary_assembly.fa
if [ ! -f $F ] ; then
get ${ENSEMBL_GRCh37_BASE}/$F.gz || (echo "Error getting $F" && exit 1)
gunzip $F.gz || (echo "Error unzipping $F" && exit 1)
mv $F genome.fa
fi
CMD="${HISAT2_BUILD_EXE} genome.fa genome"
echo Running $CMD
if $CMD ; then
echo "genome index built; you may remove fasta files"
else
echo "Index building failed; see error message"
fi
|
