/var/lib/mobyle/programs/compseq.xml is in mobyle-programs 5.1.2-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 | <?xml version="1.0" encoding="ISO-8859-1"?>
<!-- XML Authors: Corinne Maufrais and Nicolas Joly, -->
<!-- 'Biological Software and Databases' Group, Institut Pasteur, Paris. -->
<!-- Distributed under LGPLv2 License. Please refer to the COPYING.LIB document. -->
<program>
<head>
<name>compseq</name>
<package>
<name>EMBOSS</name>
<version>6.3.1</version>
<doc>
<title>EMBOSS</title>
<description>
<text lang="en">European Molecular Biology Open Software Suite</text>
</description>
<authors>Rice,P. Longden,I. and Bleasby, A.</authors>
<reference>EMBOSS: The European Molecular Biology Open Software Suite (2000) Rice,P. Longden,I. and Bleasby, A. Trends in Genetics 16, (6) pp276--277</reference>
<sourcelink>http://emboss.sourceforge.net/download</sourcelink>
<homepagelink>http://emboss.sourceforge.net</homepagelink>
</doc>
</package>
<doc>
<title>compseq</title>
<description>
<text lang="en">Calculate the composition of unique words in sequences</text>
</description>
<doclink>http://bioweb2.pasteur.fr/docs/EMBOSS/compseq.html</doclink>
<doclink>http://emboss.sourceforge.net/docs/themes</doclink>
</doc>
<category>sequence:nucleic:composition</category>
<category>sequence:protein:composition</category>
<command>compseq</command>
</head>
<parameters>
<paragraph>
<name>e_input</name>
<prompt lang="en">Input section</prompt>
<parameters>
<parameter issimple="1" ismandatory="1">
<name>e_sequence</name>
<prompt lang="en">sequence option</prompt>
<type>
<datatype>
<class>Sequence</class>
</datatype>
<dataFormat>EMBL</dataFormat>
<dataFormat>FASTA</dataFormat>
<dataFormat>GCG</dataFormat>
<dataFormat>GENBANK</dataFormat>
<dataFormat>NBRF</dataFormat>
<dataFormat>CODATA</dataFormat>
<dataFormat>RAW</dataFormat>
<dataFormat>SWISSPROT</dataFormat>
<dataFormat>GFF</dataFormat>
<card>1,n</card>
</type>
<format>
<code proglang="python">("", " -sequence=" + str(value))[value is not None]</code>
</format>
<argpos>1</argpos>
</parameter>
<parameter>
<name>e_infile</name>
<prompt lang="en">Program compseq output file (optional)</prompt>
<type>
<datatype>
<class>CompseqReport</class>
<superclass>Report</superclass>
</datatype>
</type>
<format>
<code proglang="python">("", " -infile=" + str(value))[value is not None]</code>
</format>
<argpos>2</argpos>
<comment>
<text lang="en">This is a file previously produced by 'compseq' that can be used to set the expected frequencies of words in this analysis.
The word size in the current run must be the same as the one in this results file. Obviously, you should use a file produced from protein sequences if you are counting protein sequence word frequencies, and you must use one made from nucleotide frequencies if you are analysing a nucleotide sequence.</text>
</comment>
</parameter>
</parameters>
</paragraph>
<paragraph>
<name>e_required</name>
<prompt lang="en">Required section</prompt>
<parameters>
<parameter issimple="1" ismandatory="1">
<name>e_word</name>
<prompt lang="en">Word size to consider (e.g. 2=dimer) (value greater than or equal to 1)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<vdef>
<value>2</value>
</vdef>
<format>
<code proglang="python">("", " -word=" + str(value))[value is not None and value!=vdef]</code>
</format>
<ctrl>
<message>
<text lang="en">Value greater than or equal to 1 is required</text>
</message>
<code proglang="python">value >= 1</code>
</ctrl>
<argpos>3</argpos>
<comment>
<text lang="en">This is the size of word (n-mer) to count.
Thus if you want to count codon frequencies for a nucleotide sequence, you should enter 3 here.</text>
</comment>
</parameter>
</parameters>
</paragraph>
<paragraph>
<name>e_additional</name>
<prompt lang="en">Additional section</prompt>
<parameters>
<parameter>
<name>e_frame</name>
<prompt lang="en">Frame of word to look at (0=all frames) (value greater than or equal to 0)</prompt>
<type>
<datatype>
<class>Integer</class>
</datatype>
</type>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="python">("", " -frame=" + str(value))[value is not None and value!=vdef]</code>
</format>
<ctrl>
<message>
<text lang="en">Value greater than or equal to 0 is required</text>
</message>
<code proglang="python">value >= 0</code>
</ctrl>
<argpos>4</argpos>
<comment>
<text lang="en">The normal behaviour of 'compseq' is to count the frequencies of all words that occur by moving a window of length 'word' up by one each time.
This option allows you to move the window up by the length of the word each time, skipping over the intervening words.
You can count only those words that occur in a single frame of the word by setting this value to a number other than zero.
If you set it to 1 it will only count the words in frame 1, 2 will only count the words in frame 2 and so on.</text>
</comment>
</parameter>
<parameter>
<name>e_ignorebz</name>
<prompt lang="en">Ignore the amino acids b and z and just count them as 'other'</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<vdef>
<value>1</value>
</vdef>
<format>
<code proglang="python">(" -noignorebz", "")[ bool(value) ]</code>
</format>
<argpos>5</argpos>
<comment>
<text lang="en">The amino acid code B represents Asparagine or Aspartic acid and the code Z represents Glutamine or Glutamic acid.
These are not commonly used codes and you may wish not to count words containing them, just noting them in the count of 'Other' words.</text>
</comment>
</parameter>
<parameter>
<name>e_reverse</name>
<prompt lang="en">Count words in the forward and reverse sense</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="python">("", " -reverse")[ bool(value) ]</code>
</format>
<argpos>6</argpos>
<comment>
<text lang="en">Set this to be true if you also wish to also count words in the reverse complement of a nucleic sequence.</text>
</comment>
</parameter>
<parameter>
<name>e_calcfreq</name>
<prompt lang="en">Calculate expected frequency from sequence</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<vdef>
<value>0</value>
</vdef>
<format>
<code proglang="python">("", " -calcfreq")[ bool(value) ]</code>
</format>
<argpos>7</argpos>
<comment>
<text lang="en">If this is set true then the expected frequencies of words are calculated from the observed frequency of single bases or residues in the sequences.
If you are reporting a word size of 1 (single bases or residues) then there is no point in using this option because the calculated expected frequency will be equal to the observed frequency.
Calculating the expected frequencies like this will give an approximation of the expected frequencies that you might get by using an input file of frequencies produced by a previous run of this program. If an input file of expected word frequencies has been specified then the values from that file will be used instead of this calculation of expected frequency from the sequence, even if 'calcfreq' is set to be true.</text>
</comment>
</parameter>
</parameters>
</paragraph>
<paragraph>
<name>e_output</name>
<prompt lang="en">Output section</prompt>
<parameters>
<parameter>
<name>e_outfile</name>
<prompt lang="en">Name of the output file (e_outfile)</prompt>
<type>
<datatype>
<class>Filename</class>
</datatype>
</type>
<vdef>
<value>outfile.composition</value>
</vdef>
<format>
<code proglang="python">("" , " -outfile=" + str(value))[value is not None]</code>
</format>
<argpos>8</argpos>
<comment>
<text lang="en">This is the results file.</text>
</comment>
</parameter>
<parameter isout="1">
<name>e_outfile_out</name>
<prompt lang="en">outfile_out option</prompt>
<type>
<datatype>
<class>CompseqReport</class>
<superclass>Report</superclass>
</datatype>
</type>
<filenames>
<code proglang="python">e_outfile</code>
</filenames>
</parameter>
<parameter>
<name>e_zerocount</name>
<prompt lang="en">Display the words that have a frequency of zero</prompt>
<type>
<datatype>
<class>Boolean</class>
</datatype>
</type>
<vdef>
<value>1</value>
</vdef>
<format>
<code proglang="python">(" -nozerocount", "")[ bool(value) ]</code>
</format>
<argpos>9</argpos>
<comment>
<text lang="en">You can make the output results file much smaller if you do not display the words with a zero count.</text>
</comment>
</parameter>
</parameters>
</paragraph>
<parameter ishidden="1">
<name>auto</name>
<prompt lang="en">Turn off any prompting</prompt>
<type>
<datatype>
<class>String</class>
</datatype>
</type>
<format>
<code proglang="python">" -auto -stdout"</code>
</format>
<argpos>10</argpos>
</parameter>
</parameters>
</program>
|