Skip to content

Commit 0c1dbe8

Browse files
author
holger
committed
first commit, no databases included
0 parents  commit 0c1dbe8

File tree

6,305 files changed

+1456462
-0
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

6,305 files changed

+1456462
-0
lines changed

.gitignore

+1
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+

BLOSUM62.txt

+34
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,34 @@
1+
# Matrix made by matblas from blosum62.iij
2+
# * column uses minimum score
3+
# BLOSUM Clustered Scoring Matrix in 1/2 Bit Units
4+
# Blocks Database = /data/blocks_5.0/blocks.dat
5+
# Cluster Percentage: >= 62
6+
# Entropy = 0.6979, Expected = -0.5209
7+
8+
GAP -12 -2
9+
10+
A R N D C Q E G H I L K M F P S T W Y V B Z X *
11+
A 4 -1 -2 -2 0 -1 -1 0 -2 -1 -1 -1 -1 -2 -1 1 0 -3 -2 0 -2 -1 0 -4
12+
R -1 5 0 -2 -3 1 0 -2 0 -3 -2 2 -1 -3 -2 -1 -1 -3 -2 -3 -1 0 -1 -4
13+
N -2 0 6 1 -3 0 0 0 1 -3 -3 0 -2 -3 -2 1 0 -4 -2 -3 3 0 -1 -4
14+
D -2 -2 1 6 -3 0 2 -1 -1 -3 -4 -1 -3 -3 -1 0 -1 -4 -3 -3 4 1 -1 -4
15+
C 0 -3 -3 -3 9 -3 -4 -3 -3 -1 -1 -3 -1 -2 -3 -1 -1 -2 -2 -1 -3 -3 -2 -4
16+
Q -1 1 0 0 -3 5 2 -2 0 -3 -2 1 0 -3 -1 0 -1 -2 -1 -2 0 3 -1 -4
17+
E -1 0 0 2 -4 2 5 -2 0 -3 -3 1 -2 -3 -1 0 -1 -3 -2 -2 1 4 -1 -4
18+
G 0 -2 0 -1 -3 -2 -2 6 -2 -4 -4 -2 -3 -3 -2 0 -2 -2 -3 -3 -1 -2 -1 -4
19+
H -2 0 1 -1 -3 0 0 -2 8 -3 -3 -1 -2 -1 -2 -1 -2 -2 2 -3 0 0 -1 -4
20+
I -1 -3 -3 -3 -1 -3 -3 -4 -3 4 2 -3 1 0 -3 -2 -1 -3 -1 3 -3 -3 -1 -4
21+
L -1 -2 -3 -4 -1 -2 -3 -4 -3 2 4 -2 2 0 -3 -2 -1 -2 -1 1 -4 -3 -1 -4
22+
K -1 2 0 -1 -3 1 1 -2 -1 -3 -2 5 -1 -3 -1 0 -1 -3 -2 -2 0 1 -1 -4
23+
M -1 -1 -2 -3 -1 0 -2 -3 -2 1 2 -1 5 0 -2 -1 -1 -1 -1 1 -3 -1 -1 -4
24+
F -2 -3 -3 -3 -2 -3 -3 -3 -1 0 0 -3 0 6 -4 -2 -2 1 3 -1 -3 -3 -1 -4
25+
P -1 -2 -2 -1 -3 -1 -1 -2 -2 -3 -3 -1 -2 -4 7 -1 -1 -4 -3 -2 -2 -1 -2 -4
26+
S 1 -1 1 0 -1 0 0 0 -1 -2 -2 0 -1 -2 -1 4 1 -3 -2 -2 0 0 0 -4
27+
T 0 -1 0 -1 -1 -1 -1 -2 -2 -1 -1 -1 -1 -2 -1 1 5 -2 -2 0 -1 -1 0 -4
28+
W -3 -3 -4 -4 -2 -2 -3 -2 -2 -3 -2 -3 -1 1 -4 -3 -2 11 2 -3 -4 -3 -2 -4
29+
Y -2 -2 -2 -3 -2 -1 -2 -3 2 -1 -1 -2 -1 3 -3 -2 -2 2 7 -1 -3 -2 -1 -4
30+
V 0 -3 -3 -3 -1 -2 -2 -3 -3 3 1 -2 1 -1 -2 -2 0 -3 -1 4 -3 -2 -1 -4
31+
B -2 -1 3 4 -3 0 1 -1 0 -3 -4 0 -3 -3 -2 0 -1 -4 -3 -3 4 1 -1 -4
32+
Z -1 0 0 1 -3 3 4 -2 0 -3 -3 1 -1 -3 -1 0 -1 -3 -2 -2 1 4 -1 -4
33+
X 0 -1 -1 -1 -2 -1 -1 -1 -1 -1 -1 -1 -1 -1 -2 0 0 -2 -1 -1 -1 -1 -1 -4
34+
* -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 1

LICENCE

+675
Large diffs are not rendered by default.

bin/configure

+205
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,205 @@
1+
#!/bin/bash
2+
error=0;
3+
####### FUNCTIONS #########
4+
function usage
5+
{
6+
echo "usage: configure [[[-p ] [-n]] | [-h]]"
7+
echo "choose flag -p or --protein_only if you want to run hamstr only on protein sequence data"
8+
echo "choose flag -n or --noublast if you want to run hamstr without the -ublast option"
9+
}
10+
11+
12+
## parsing command line option
13+
while [ "$1" != "" ]; do
14+
case $1 in
15+
-p | --protein_only ) protonly=1
16+
;;
17+
-n | --noublast ) noublast=1
18+
;;
19+
-h | --help ) usage
20+
exit
21+
;;
22+
* ) usage
23+
exit 1
24+
esac
25+
shift
26+
done
27+
################# USER SETTINGS ###############
28+
sedprog='sed';
29+
grepprog='grep';
30+
###############################################
31+
#### testing the user settings ################
32+
sedpath=`which $sedprog 2>&1 |grep -v '\bno\b'`
33+
greppath=`which $grepprog 2>&1 |grep -v '\bno\b'`
34+
if [ ! $sedpath ]
35+
then
36+
echo "$sedprog could not be found. Please update the configure script";
37+
exit;
38+
fi
39+
if [ ! $greppath ]
40+
then
41+
echo "$grepprog could not be found. Please update the configure script";
42+
exit;
43+
fi
44+
##############################################
45+
########### update the sed and grep commands in the perl scripts
46+
$sedprog -i -e "s/\(my \$sedprog = '\).*/\1$sedprog';/" hamstr.pl;
47+
$sedprog -i -e "s/\(my \$grepprog = '\).*/\1$grepprog';/" hamstr.pl;
48+
$sedprog -i -e "s/\(my \$sedprog = '\).*/\1$sedprog';/" oneSeq.pl;
49+
$sedprog -i -e "s/\(my \$grepprog = '\).*/\1$grepprog';/" oneSeq.pl;
50+
#############################################
51+
## localize the perl installation
52+
echo "Updating paths"
53+
path2perl=`which perl`
54+
echo " updating path to perl: $path2perl"
55+
$sedprog -i -e "s|\#\!.*|\#\!$path2perl|g" hamstr.pl;
56+
$sedprog -i -e "s|\#\!.*|\#\!$path2perl|g" nentferner.pl;
57+
$sedprog -i -e "s|\#\!.*|\#\!$path2perl|g" translate.pl;
58+
$sedprog -i -e "s|\#\!.*|\#\!$path2perl|g" oneSeq.pl;
59+
$sedprog -i -e "s|\#\!.*|\#\!$path2perl|g" multifasta2oneSeq.pl;
60+
61+
## get the path to the perl modules
62+
path2dir=`pwd |$sedprog -e 's/\(.*\)\/.*/\1/'`;
63+
64+
echo " updating path to lib: $path2dir"
65+
$sedprog -i -e "s|use lib.*lib\(.*\)|use lib '$path2dir/lib\1|" hamstr.pl
66+
$sedprog -i -e "s|use lib.*|use lib '$path2dir/lib';|" nentferner.pl
67+
$sedprog -i -e "s|use lib.*|use lib '$path2dir/lib';|g" translate.pl
68+
$sedprog -i -e "s|use lib.*|use lib '$path2dir/lib';|g" oneSeq.pl
69+
70+
## update the default paths to core_ortholog and blast_dir
71+
echo " updating default path to blast_dir and core_orthologs: $path2bin"
72+
$sedprog -i -e "s|\(my \$path = \).*|\1 '$path2dir';|g" hamstr.pl
73+
74+
75+
## checking dependencies
76+
echo "Checking dependencies"
77+
blastallpath=`which blastall 2>&1 |grep -v '\bno\b'`
78+
echo " checking blastall"
79+
if [ $blastallpath ]
80+
then
81+
echo " succeeded" #do nothing as this is default for hamstr
82+
else
83+
echo " blastall is not installed or not in the default path."
84+
echo " checking for blastp"
85+
blastpluspath=`which blastp 2>&1 |grep -v '\bno\b'`
86+
if [ $blastpluspath ]
87+
then
88+
echo " succeeded"
89+
$sedprog -i -e 's/^\(my $blast_prog .*blastall\)/\#\1/' hamstr.pl;
90+
$sedprog -i -e 's/^\(my $blast_prog .*blastall\)/\#\1/' oneSeq.pl;
91+
92+
$sedprog -i -e 's/\#\(my $blast_prog .*blastp\)/\1/' hamstr.pl;
93+
$sedprog -i -e 's/\#\(my $blast_prog .*blastp\)/\1/' oneSeq.pl;
94+
else " FATAL: No blast program was found. Please install!"
95+
error=1;
96+
fi
97+
fi
98+
## Check for ublast
99+
if [ $noublast ]
100+
then
101+
echo " omitting check for usearch. Option --noublast has been chosen";
102+
echo " updating hamstr.pl script"
103+
$sedprog -i -e 's/my $runublast = [0,1];/my $runublast = 0;/' hamstr.pl;
104+
else
105+
echo " checking ublast"
106+
usearchpath=`which usearch 2>&1 |grep -v '\bno\b'`
107+
if [ $usearchpath ]
108+
then
109+
echo " succeeded" #do nothing as this is default for hamstr
110+
$sedprog -i -e 's/my $runublast = [0,1];/my $runublast = 1;/' hamstr.pl;
111+
else
112+
echo " FATAL: usearch was not found and configure was run without the --noublast option"
113+
error=1;
114+
fi
115+
fi
116+
## Check for genewise
117+
if [ $protonly ]
118+
then
119+
echo " ommitting check for genewise. Option --protein_only has been chosen";
120+
echo " updating hamstr.pl script"
121+
$sedprog -i -e 's/$check_genewise = [0,1];/$check_genewise = 0;/' hamstr.pl;
122+
123+
else
124+
echo " checking genewise"
125+
$sedprog -i -e 's/$check_genewise = [0,1];/$check_genewise = 1;/' hamstr.pl;
126+
genewisepath=`which genewise 2>&1 |$grepprog -v '\bno\b'`
127+
if [ $genewisepath ]
128+
then
129+
echo " succeeded"
130+
echo " checking environmental variable WISECONFIGDIR"
131+
wisecfg=`echo $WISECONFIGDIR |$grepprog '/'`
132+
if [ $wisecfg ]
133+
then
134+
echo " succeeded: $wisecfg"
135+
else
136+
echo " FATAL: Please set the environmental variable WISECONFIGDIR according to the installation instructions of genewise. If you want to run HaMStR on protein data only, run configure --protein_only";
137+
error=1;
138+
fi
139+
140+
else
141+
echo " FATAL: genewise has not been installed properly. If you want to run HaMStR on protein data only, run configure --protein_only";
142+
error=1;
143+
fi
144+
fi
145+
## Checking for environmental variable ONESEQDIR
146+
echo "Checking environmental variable ONESEQDIR"
147+
oneseqcfg=`echo $ONESEQDIR`
148+
if [ $oneseqcfg ]
149+
then
150+
echo " succeeded: $oneseqcfg"
151+
else
152+
echo "FATAL: Please set the environmental variable ONSEQDIR to point at the directory containing the oneseq files and directory"
153+
error=1;
154+
fi
155+
## Checking for hmmsearch
156+
echo " checking for hmmsearch"
157+
hmmsearchpath=`which hmmsearch 2>&1 |grep -v '\bno\b'`
158+
if [ $hmmsearchpath ]
159+
then
160+
echo " succeeded: $hmmsearchpath"
161+
else
162+
echo " FATAL: Please install the hmmer3 package"
163+
error=1;
164+
fi
165+
## Checking for clustalw2
166+
echo " checking for clustalw2";
167+
clustalpath=`which clustalw2 2>&1 |grep -v '\bno\b'`
168+
if [ $clustalpath ]
169+
then
170+
echo " succeeded: $clustalpath"
171+
else
172+
echo " checking for clustalw"
173+
clustalpath=`which clustalw 2>&1 |grep -v '\bno\b'`
174+
if [ $clustalpath ]
175+
then
176+
echo " succeeded: $clustalpath";
177+
echo " updating hamstrscript";
178+
$sedprog -i -e 's/clustalw2/clustalw/g' hamstr.pl;
179+
else
180+
echo " FATAL: Please install clustalw2"
181+
error=1;
182+
fi
183+
fi
184+
## Checking for Mafft
185+
echo " checking for mafft-linsi";
186+
mafftpath=`which mafft-linsi 2>&1 |grep -v '\bno\b'`
187+
if [ $mafftpath ]
188+
then
189+
echo " succeeded: $mafftpath"
190+
else
191+
echo " FATAL: Please install mafft"
192+
error=1;
193+
fi
194+
### wrap up
195+
if [ $error == 1 ]
196+
then
197+
echo "Configuration of HaMStR failed. Please see the error messages above."
198+
else
199+
echo "Generating symbolic link hamstr -> hamstr.pl"
200+
ln -s -f ./hamstr.pl ./hamstr
201+
echo "All tests succeeded, HaMStR should be ready to run";
202+
$sedprog -i -e 's/my $configure = .*/my $configure = 1;/' hamstr.pl;
203+
$sedprog -i -e 's/my $configure = .*/my $configure = 1;/' oneSeq.pl;
204+
$sedprog -i -e 's/my $configure = .*/my $configure = 1;/' multifasta2oneSeq.pl;
205+
fi;

0 commit comments

Comments
 (0)