|
0
|
1 OSRA: Optical Structure Recognition Application
|
|
|
2
|
|
|
3 OSRA is a utility designed to convert graphical representations of chemical
|
|
|
4 structures, as they appear in journal articles, patent documents, textbooks,
|
|
|
5 trade magazines etc., into SMILES (Simplified Molecular Input Line Entry
|
|
|
6 Specification - see http://en.wikipedia.org/wiki/SMILES) or
|
|
|
7 SD files - a computer recognizable molecular structure format.
|
|
|
8 OSRA can read a document in any of the over 90 graphical formats parseable by
|
|
|
9 ImageMagick - including GIF, JPEG, PNG, TIFF, PDF, PS etc., and generate
|
|
|
10 the SMILES or SDF representation of the molecular structure images encountered
|
|
|
11 within that document.
|
|
|
12
|
|
|
13 Note that any software designed for optical recognition is unlikely to be
|
|
|
14 perfect, and the output produced might, and probably will, contain errors,
|
|
|
15 so curation by a human knowledgeable in chemical structures is highly recommended.
|
|
|
16
|
|
|
17 http://cactus.nci.nih.gov/osra/
|
|
|
18
|
|
|
19
|
|
|
20 The wrapper comes with an automatic installation of all dependencies through the
|
|
|
21 galaxy toolshed. If you do not want to use that feature you can compile OSRA with
|
|
|
22 the following instructions.
|
|
|
23
|
|
|
24
|
|
|
25 ########################################
|
|
|
26 # #
|
|
|
27 # OSRA Setup #
|
|
|
28 # currently a small patch is requiered #
|
|
|
29 # #
|
|
|
30 ########################################
|
|
|
31
|
|
|
32 Save the following file to 'osra-1.4.0-configure.patch' and store it next
|
|
|
33 to that script below.
|
|
|
34
|
|
|
35 -------------------------------------------------------
|
|
|
36 --- configure 2013-03-18 18:14:00.888605219 +0100
|
|
|
37 +++ configure_ori 2013-03-18 18:13:48.396605759 +0100
|
|
|
38 @@ -4178,7 +4178,8 @@
|
|
|
39
|
|
|
40 # Check whether --with-tclap-include was given.
|
|
|
41 if test "${with_tclap_include+set}" = set; then :
|
|
|
42 - withval=$with_tclap_include;
|
|
|
43 + withval=$with_tclap_include;
|
|
|
44 + CPPFLAGS="-I${withval} ${CPPFLAGS}"
|
|
|
45 else
|
|
|
46 with_tclap_include="auto"
|
|
|
47 fi
|
|
|
48 -------------------------------------------------------
|
|
|
49
|
|
|
50 #!/usr/bin/bash
|
|
|
51 #osra installation
|
|
|
52
|
|
|
53 cdir=`pwd`
|
|
|
54
|
|
|
55 wget http://sourceforge.net/projects/graphicsmagick/files/graphicsmagick/1.3.18/GraphicsMagick-1.3.18.tar.gz
|
|
|
56 tar xfvz GraphicsMagick-1.3.18.tar.gz
|
|
|
57 cd GraphicsMagick-1.3.18
|
|
|
58 ./configure --prefix=`pwd`/build --enable-shared=yes
|
|
|
59 make
|
|
|
60 make install
|
|
|
61 cd ..
|
|
|
62
|
|
|
63 export PATH=$PATH:/home/bag/projects/osra/GraphicsMagick-1.3.18/build/bin/
|
|
|
64
|
|
|
65 wget http://potrace.sourceforge.net/download/potrace-1.11.tar.gz
|
|
|
66 tar xfvz potrace-1.11.tar.gz
|
|
|
67 cd potrace-1.11
|
|
|
68 ./configure --with-libpotrace --prefix=`pwd`/build
|
|
|
69 make
|
|
|
70 make install
|
|
|
71 cd ..
|
|
|
72
|
|
|
73 wget http://downloads.sourceforge.net/project/osra/gocr-patched/gocr-0.50pre-patched.tgz
|
|
|
74 tar xfvz gocr-0.50pre-patched.tgz
|
|
|
75 cd gocr-0.50pre-patched
|
|
|
76 ./configure --prefix=`pwd`/build
|
|
|
77 make libs
|
|
|
78 make all install
|
|
|
79 cd ..
|
|
|
80
|
|
|
81 wget http://downloads.sourceforge.net/project/tclap/tclap-1.2.1.tar.gz
|
|
|
82 tar xfvz tclap-1.2.1.tar.gz
|
|
|
83 cd tclap-1.2.1
|
|
|
84 ./configure --prefix=`pwd`/build
|
|
|
85 make
|
|
|
86 make install
|
|
|
87 cd ..
|
|
|
88
|
|
|
89 wget http://mirror.checkdomain.de/gnu/ocrad/ocrad-0.21.tar.gz
|
|
|
90 tar xfvz ocrad-0.21.tar.gz
|
|
|
91 cd ocrad-0.21
|
|
|
92 ./configure --prefix=`pwd`/build
|
|
|
93 make
|
|
|
94 make install
|
|
|
95 cd ..
|
|
|
96
|
|
|
97 wget http://downloads.sourceforge.net/project/openbabel/openbabel/2.3.2/openbabel-2.3.2.tar.gz
|
|
|
98 tar xfvz openbabel-2.3.2.tar.gz
|
|
|
99 cd openbabel-2.3.2
|
|
|
100 mkdir build
|
|
|
101 cd build
|
|
|
102 cmake .. -DCMAKE_INSTALL_PREFIX=`pwd`/install/
|
|
|
103 make
|
|
|
104 make install
|
|
|
105 cd ../..
|
|
|
106
|
|
|
107 #wget http://tesseract-ocr.googlecode.com/files/tesseract-ocr-3.02.02.tar.gz
|
|
|
108 #tar xfvz tesseract-ocr-3.02.02.tar.gz
|
|
|
109 #cd tesseract-ocr
|
|
|
110 #./configure --prefix=`pwd`/build
|
|
|
111 #make
|
|
|
112 #make install
|
|
|
113 #cd ..
|
|
|
114
|
|
|
115
|
|
|
116 wget https://launchpad.net/cuneiform-linux/1.1/1.1/+download/cuneiform-linux-1.1.0.tar.bz2
|
|
|
117 tar xfvj cuneiform-linux-1.1.0.tar.bz2
|
|
|
118 cd cuneiform-linux-1.1.0
|
|
|
119 mkdir build
|
|
|
120 cd build
|
|
|
121 cmake .. -DCMAKE_INSTALL_PREFIX=`pwd`/install/
|
|
|
122 make
|
|
|
123 make install
|
|
|
124 cd ../..
|
|
|
125
|
|
|
126
|
|
|
127 wget http://downloads.sourceforge.net/project/osra/osra/1.4.0/osra-1.4.0.tgz
|
|
|
128 tar xfvz osra-1.4.0.tgz
|
|
|
129 patch osra-1.4.0/configure < osra-1.4.0-configure.patch
|
|
|
130 cd osra-1.4.0
|
|
|
131
|
|
|
132 ./configure --with-tclap-include=$cdir/tclap-1.2.1/build/include/ \
|
|
|
133 --with-potrace-include=$cdir/potrace-1.11/build/include/ \
|
|
|
134 --with-potrace-lib=$cdir/potrace-1.11/build/lib/ \
|
|
|
135 --with-gocr-include=$cdir/gocr-0.50pre-patched/build/include/gocr/ \
|
|
|
136 --with-gocr-lib=$cdir/gocr-0.50pre-patched/build/lib/ \
|
|
|
137 --with-ocrad-include=$cdir/ocrad-0.21/build/include/ \
|
|
|
138 --with-ocrad-lib=$cdir/ocrad-0.21/build/lib/ \
|
|
|
139 --with-cuneiform-include=$cdir/cuneiform-linux-1.1.0/build/install/include/ \
|
|
|
140 --with-cuneiform \
|
|
|
141 --with-cuneiform-lib=$cdir/cuneiform-linux-1.1.0/build/install/lib/ \
|
|
|
142 --with-openbabel-include=$cdir/openbabel-2.3.2/build/install/include/openbabel-2.0/ \
|
|
|
143 --with-openbabel-lib=$cdir/openbabel-2.3.2/build/install/lib/ \
|
|
|
144 --with-graphicsmagick-lib=$cdir/GraphicsMagick-1.3.18/build/lib/ \
|
|
|
145 --with-graphicsmagick-include=$cdir/GraphicsMagick-1.3.18/build/include/GraphicsMagick/ \
|
|
|
146 --prefix=`pwd`/bin/
|
|
|
147 #--enable-static-linking --disable-graphicsmagick-config
|
|
|
148 make
|
|
|
149 make install
|
|
|
150
|
|
|
151 export LD_LIBRARY_PATH=$cdir/GraphicsMagick-1.3.18/build/lib/:$cdir/GraphicsMagick-1.3.18/build/lib:$cdir/potrace-1.11/build/lib/
|
|
|
152 ./bin/bin/osra
|
|
|
153
|
|
|
154
|
|
|
155 #--with-tesseract-include=$cdir/tclap-1.2.1/build/include/
|
|
|
156 #--with-tesseract
|
|
|
157 #--with-tesseract-lib
|
|
|
158
|
|
|
159
|
|
|
160
|
|
|
161
|
|
|
162
|
|
|
163
|
|
|
164
|
|
|
165
|
