Mercurial > repos > iuc > prot_scriber

comparison prot-scriber.xml @ 2:c32f98757c4d draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/prot-scriber commit cbc2e768addc5b6697cdc4ed9b57bc7889a57fe9
author iuc
date Tue, 20 Sep 2022 09:45:13 +0000
parents a830e9f84593
children ed4a6c9786c8
comparison
equal deleted inserted replaced
1:a830e9f84593 2:c32f98757c4d
1 <tool id="prot_scriber" name="prot-scriber" version="@TOOL_VERSION@" profile="21.05"> 1 <tool id="prot_scriber" name="prot-scriber" version="@TOOL_VERSION@" profile="21.05">
2 <description>Protein annotation of short human readable descriptions</description> 2 <description>Protein annotation of short human readable descriptions</description>
3 <macros> 3 <macros>
4 <token name="@TOOL_VERSION@">0.1.3</token> 4 <token name="@TOOL_VERSION@">0.1.4</token>
5 </macros> 5 </macros>
6 <requirements> 6 <requirements>
7 <requirement type="package" version="@TOOL_VERSION@">prot-scriber</requirement> 7 <requirement type="package" version="@TOOL_VERSION@">prot-scriber</requirement>
8 </requirements> 8 </requirements>
9 <stdio> 9 <stdio>
18 #else if str($input_config.input_config_selector) == "advanced" 18 #else if str($input_config.input_config_selector) == "advanced"
19 #for $ssr in $input_config.advanced_input_repeat 19 #for $ssr in $input_config.advanced_input_repeat
20 -s '$ssr.seq_sim_table' 20 -s '$ssr.seq_sim_table'
21 #if $ssr.header 21 #if $ssr.header
22 -e '$ssr.header' 22 -e '$ssr.header'
23 #else
24 -e 'default'
23 #end if 25 #end if
24 #if $ssr.field_separator 26 #if $ssr.field_separator
25 -p '$ssr.field_separator' 27 -p '$ssr.field_separator'
28 #else
29 -p 'default'
26 #end if 30 #end if
27 #if $ssr.blacklist_regexs 31 #if $ssr.blacklist_regexs
28 -b '$ssr.blacklist_regexs' 32 -b '$ssr.blacklist_regexs'
33 #else
34 -b 'default'
29 #end if 35 #end if
30 #if $ssr.capture_replace_pairs 36 #if $ssr.capture_replace_pairs
31 -c '$ssr.capture_replace_pairs' 37 -c '$ssr.capture_replace_pairs'
38 #else
39 -c 'default'
32 #end if 40 #end if
33 #if $ssr.filter_regexs 41 #if $ssr.filter_regexs
34 -l '$ssr.filter_regexs' 42 -l '$ssr.filter_regexs'
43 #else
44 -l 'default'
35 #end if 45 #end if
36 #end for 46 #end for
37 #if $input_config.expert_options.non_informative_words_regexs 47 #if $input_config.expert_options.non_informative_words_regexs
38 -w '$input_config.expert_options.non_informative_words_regexs' 48 -w '$input_config.expert_options.non_informative_words_regexs'
39 #end if 49 #end if
40 #if $input_config.expert_options.description_split_regex 50 #if $input_config.expert_options.description_split_regex
41 -r "$input_config.expert_options.description_split_regex" 51 -r '$input_config.expert_options.description_split_regex'
42 #end if 52 #end if
43 #if $input_config.expert_options.center_inverse_word_information_content_at_quantile 53 #if $input_config.expert_options.center_inverse_word_information_content_at_quantile
44 -q $input_config.expert_options.center_inverse_word_information_content_at_quantile 54 -q $input_config.expert_options.center_inverse_word_information_content_at_quantile
45 #end if 55 #end if
56 #if $input_config.expert_options.polish_capture_replace_pairs
57 -d '$input_config.expert_options.polish_capture_replace_pairs'
58 #end if
46 #end if 59 #end if
47 #if $seq_family.seq_families 60 #if $seq_family.seq_families
48 -f '$seq_families' 61 -f '$seq_families'
49 #end if 62 #end if
50 #if $seq_family.annotate_non_family_queries 63 #if $seq_family.annotate_non_family_queries
51 -a 64 -a
52 #end if 65 #end if
53 #if $seq_family.seq_family_gene_ids_separator 66 #if $seq_family.seq_family_gene_ids_separator
54 -g "$seq_family_gene_ids_separator" 67 -g '$seq_family_gene_ids_separator'
55 #end if 68 #end if
56 #if $seq_family.seq_family_id_genes_separator 69 #if $seq_family.seq_family_id_genes_separator
57 -i '$seq_family_id_genes_separator' 70 -i '$seq_family_id_genes_separator'
71 #end if
72 #if $exclude_not_annotated_queries
73 -x
58 #end if 74 #end if
59 -o '$output' 75 -o '$output'
60 ]]> 76 ]]>
61 </command> 77 </command>
62 <inputs> 78 <inputs>
100 </valid> 116 </valid>
101 </sanitizer> 117 </sanitizer>
102 </param> 118 </param>
103 <param type="integer" optional="true" name="center_inverse_word_information_content_at_quantile" argument="-q" label="Center inverse word-information-content at quantile (-q)" help="The quantile (percentile) to be subtracted from calculated inverse word information 119 <param type="integer" optional="true" name="center_inverse_word_information_content_at_quantile" argument="-q" label="Center inverse word-information-content at quantile (-q)" help="The quantile (percentile) to be subtracted from calculated inverse word information
104 content to center these values. Value between 0 and 1." /> 120 content to center these values. Value between 0 and 1." />
121 <param type="data" optional="true" name="polish_capture_replace_pairs" argument="-d" label="Polishing capture replace pairs (-d)" help="A file with pairs of lines. Defines pairs of regex / replace
122 pairs for post polishing of annotation results. Set to 'none' or provide an empty file to supress polishing."/>
105 </section> 123 </section>
106 </when> 124 </when>
107 </conditional> 125 </conditional>
108 <section title="Sequence family annotation" name="seq_family"> 126 <section title="Sequence family annotation" name="seq_family">
109 <param type="data" optional="true" name="seq_families" argument="-f" format="tabular" label="Families of biological sequences (-f)" help="A file in which families of biological sequences are stored, one family per line. Each 127 <param type="data" optional="true" name="seq_families" argument="-f" format="tabular" label="Families of biological sequences (-f)" help="A file in which families of biological sequences are stored, one family per line. Each
125 <add preset="string.printable" /> 143 <add preset="string.printable" />
126 </valid> 144 </valid>
127 </sanitizer> 145 </sanitizer>
128 </param> 146 </param>
129 </section> 147 </section>
148 <param type="boolean" optional="true" name="exclude_not_annotated_queries" argument="-x" label="Exclude not annotated query sequences (-x)" help="Use this option to exclude results from the output table that could not be annotated."/>
130 </inputs> 149 </inputs>
131 <outputs> 150 <outputs>
132 <data format="tabular" name="output" /> 151 <data format="tabular" name="output" />
133 </outputs> 152 </outputs>
134 <tests> 153 <tests>
159 </repeat> 178 </repeat>
160 <repeat name="advanced_input_repeat"> 179 <repeat name="advanced_input_repeat">
161 <param name="seq_sim_table" value="8_Proteins_vs_Trembl_blastp.txt" /> 180 <param name="seq_sim_table" value="8_Proteins_vs_Trembl_blastp.txt" />
162 <param name="blacklist_regexs" value="blacklist_stitle_regexs.txt" /> 181 <param name="blacklist_regexs" value="blacklist_stitle_regexs.txt" />
163 </repeat> 182 </repeat>
164 <param name="description_split_regex" value="([~_\-/|;,':.\s]+)" /> 183 <param name="description_split_regex" value="([~_\-/|;,'\'':.\s]+)" />
165 <param name="center_inverse_word_information_content_at_quantile" value="50" /> 184 <param name="center_inverse_word_information_content_at_quantile" value="50" />
166 <output name="output" file="8_Proteins_prot-scriber.out" sort="true" /> 185 <output name="output" file="8_Proteins_prot-scriber.out" sort="true" />
167 </test> 186 </test>
168 </tests> 187 </tests>
169 <help> 188 <help>
289 -q, --center-inverse-word-information-content-at-quantile 308 -q, --center-inverse-word-information-content-at-quantile
290 The quantile (percentile) to be subtracted from calculated inverse word information 309 The quantile (percentile) to be subtracted from calculated inverse word information
291 content to center these values. Consequently, this must be a value between zero and one 310 content to center these values. Consequently, this must be a value between zero and one
292 or literal 50, which is interpreted as mean instead of a quantile. Default is 50, 311 or literal 50, which is interpreted as mean instead of a quantile. Default is 50,
293 implying centering at the mean. 312 implying centering at the mean.
313
314 -d, --polish-capture-replace-pairs
315 The last step of the process generating human readable descriptions (HRDs) for the
316 queries (proteins or sequence families) is to 'polish' the selected HRDs. Polishing is
317 done by iterative application of regular expressions (fancy-regex) and replace
318 instructions (capture-replace-pairs). If you do not want to use the default polishing
319 capture replace pairs specify a file in which pairs of lines are given. Of each pair the
320 first line hold a regular expression (fancy-regex syntax) and the second the replacement
321 instructions providing access to capture groups. Set to 'none' or provide an empty file,
322 if you want to suppress polishing. If you want to have a template file for your custom
323 polishing capture-replace-pairs please refer to
324 https://raw.githubusercontent.com/usadellab/prot-scriber/master/misc/polish_capture_replace_pairs.txt
294 325
295 ---- 326 ----
296 327
297 **Output** 328 **Output**
298 329
302 Soltu.DM.02G020600.1 arath strubbelig receptor family 333 Soltu.DM.02G020600.1 arath strubbelig receptor family
303 Soltu.DM.S001650.1 germin member 334 Soltu.DM.S001650.1 germin member
304 Soltu.DM.03G011280.1 increased dna methylation 335 Soltu.DM.03G011280.1 increased dna methylation
305 ... 336 ...
306 337
338 If you want to supress results from the output table that could not be annotated, i.e. 'unknown protein' or 'unknown sequence family' respectively use the '-x' parameter::
339
340 -x, --exclude-not-annotated-queries
341 Exclude results from the output table that could not be annotated, i.e. 'unknown
342 protein' or 'unknown sequence family', respectively.
343
307 ]]> 344 ]]>
308 </help> 345 </help>
309 </tool> 346 </tool>