Repository 'prot_scriber'
hg clone https://toolshed.g2.bx.psu.edu/repos/iuc/prot_scriber

Changeset 3:863ab6ebcafc (2024-05-18)
Previous changeset 2:4d4df9779b7b (2022-09-20) Next changeset 4:f05dfa43240f (2024-08-19)
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/prot-scriber commit bac22f562727babce8e0f456c82408c3063a683d
modified:
prot-scriber.xml
test-data/8_Proteins_prot-scriber.out
b
diff -r 4d4df9779b7b -r 863ab6ebcafc prot-scriber.xml
--- a/prot-scriber.xml Tue Sep 20 09:45:46 2022 +0000
+++ b/prot-scriber.xml Sat May 18 20:36:38 2024 +0000
[
b'@@ -1,15 +1,15 @@\n <tool id="prot_scriber" name="prot-scriber" version="@TOOL_VERSION@" profile="21.05">\n-  <description>Protein annotation of short human readable descriptions</description>\n-  <macros>\n-    <token name="@TOOL_VERSION@">0.1.4</token>\n-  </macros>\n-  <requirements>\n-    <requirement type="package" version="@TOOL_VERSION@">prot-scriber</requirement>\n-  </requirements>\n-  <stdio>\n-    <regex match="panicked" level="fatal" source="stderr" />\n-  </stdio>\n-  <command>\n+    <description>Protein annotation of short human readable descriptions</description>\n+    <macros>\n+        <token name="@TOOL_VERSION@">0.1.5</token>\n+    </macros>\n+    <requirements>\n+        <requirement type="package" version="@TOOL_VERSION@">prot-scriber</requirement>\n+    </requirements>\n+    <stdio>\n+        <regex match="panicked" level="fatal" source="stderr"/>\n+    </stdio>\n+    <command>\n     <![CDATA[\'prot-scriber\'\n     #if str($input_config.input_config_selector) == "basic"\n       #for $sst in $input_config.seq_sim_table\n@@ -75,117 +75,103 @@\n     -o \'$output\'\n     ]]>\n   </command>\n-  <inputs>\n-    <conditional name="input_config">\n-      <param type="select" name="input_config_selector" label="Choose input configuration options">\n-        <option value="basic" selected="true">Basic</option>\n-        <option value="advanced">Advanced</option>\n-      </param>\n-      <when value="basic">\n-        <param type="data" multiple="true" name="seq_sim_table" argument="-s" format="tabular" label="Sequence similarity search results in tabular format (-s)" help="Files in which to find sequence similarity search results in tabular format (SSST). Use e.g. Blast or Diamond to produce them.\n-        Required columns are: \'qacc sacc stitle\' (Blast) or \'qseqid sseqid stitle\' (Diamond)." /> \n-      </when>\n-      <when value="advanced">\n-        <repeat name="advanced_input_repeat" title="Sequence similarity table" min="1" default="1">\n-          <param type="data" name="seq_sim_table" argument="-s" format="tabular" label="Sequence similarity search result in tabular format (-s)" help="File in which to find sequence similarity search results in tabular format (SSST). Use e.g. Blast or Diamond to produce them.\n-          Required columns are: \'qacc sacc stitle\' (Blast) or \'qseqid sseqid stitle\' (Diamond)." /> \n-          <param type="text" optional="true" name="field_separator" argument="-p" label="Field separator (-p)" help="Field-Separator of the (-s) sequence similarity table. The default value is the \'TAB\' character. Set to \'default\' to use the hard coded default">\n-            <sanitizer>\n-              <valid initial="default">\n-                <add preset="string.printable" />\n-              </valid>\n-            </sanitizer>\n-          </param>\n-          <param type="text" optional="true" name="header" argument="-e" label="Header of the sequence similarity tables (-e)" help="Header of the (-s) sequence similarity table. Separated by space (\' \') the names of the\n-            in order of appearance in the respective table. Required and default columns are \'qacc sacc stitle\'. Set to \'default\' to use the hard coded default" />\n-          <param type="data" optional="true" name="blacklist_regexs" argument="-b" format="tabular" label="Blacklist Regexs (-b)" help="A file with regular expressions, one per line. Any match to any of these\n-            regular expressions causes sequence similarity search result descriptions (\'stitle\' in Blast terminology) to be discarded from the prot-scriber annotation process. Set to \'default\' to use the hard coded default" />\n-          <param type="data" optional="true" name="capture_replace_pairs" argument="-c" format="tabular" label="Capture replace pairs (-c)" help="A file with pairs of lines. Within each pair the first line is a regular expressions\n-            defining one or more capture groups. The second line of a pair is the string used to replace the match in the regular expression with. Set to \'default\' to'..b'ault" />\n-        <param name="header" value="qacc sacc stitle" />\n-      </repeat>\n-      <repeat name="advanced_input_repeat">\n-        <param name="seq_sim_table" value="8_Proteins_vs_Trembl_blastp.txt" />\n-        <param name="field_separator" value="default" />\n-        <param name="header" value="qacc sacc stitle" />\n-      </repeat>\n-      <output name="output" file="8_Proteins_prot-scriber.out" sort="true" />\n-    </test>\n-    <test>\n-      <param name="input_config_selector" value="advanced" />\n-      <repeat name="advanced_input_repeat">\n-        <param name="seq_sim_table" value="8_Proteins_vs_Swissprot_blastp.txt" />\n-        <param name="blacklist_regexs" value="blacklist_stitle_regexs.txt" />\n-      </repeat>\n-      <repeat name="advanced_input_repeat">\n-        <param name="seq_sim_table" value="8_Proteins_vs_Trembl_blastp.txt" />\n-        <param name="blacklist_regexs" value="blacklist_stitle_regexs.txt" />\n-      </repeat>\n-      <param name="description_split_regex" value="([~_\\-/|;,\'\\\'\':.\\s]+)" />\n-      <param name="center_inverse_word_information_content_at_quantile" value="50" />\n-      <output name="output" file="8_Proteins_prot-scriber.out" sort="true" />\n-    </test>\n-  </tests>\n-  <help>\n+        <param name="exclude_not_annotated_queries" argument="-x" type="boolean" optional="true" label="Exclude not annotated query sequences (-x)" help="Use this option to exclude results from the output table that could not be annotated."/>\n+    </inputs>\n+    <outputs>\n+        <data format="tabular" name="output"/>\n+    </outputs>\n+    <tests>\n+        <test>\n+            <param name="input_config_selector" value="basic"/>\n+            <param name="seq_sim_table" value="8_Proteins_vs_Swissprot_blastp.txt,8_Proteins_vs_Trembl_blastp.txt"/>\n+            <output name="output" file="8_Proteins_prot-scriber.out" sort="true"/>\n+        </test>\n+        <test>\n+            <param name="input_config_selector" value="advanced"/>\n+            <repeat name="advanced_input_repeat">\n+                <param name="seq_sim_table" value="8_Proteins_vs_Swissprot_blastp.txt"/>\n+                <param name="field_separator" value="default"/>\n+                <param name="header" value="qacc sacc stitle"/>\n+            </repeat>\n+            <repeat name="advanced_input_repeat">\n+                <param name="seq_sim_table" value="8_Proteins_vs_Trembl_blastp.txt"/>\n+                <param name="field_separator" value="default"/>\n+                <param name="header" value="qacc sacc stitle"/>\n+            </repeat>\n+            <output name="output" file="8_Proteins_prot-scriber.out" sort="true"/>\n+        </test>\n+        <test>\n+            <param name="input_config_selector" value="advanced"/>\n+            <repeat name="advanced_input_repeat">\n+                <param name="seq_sim_table" value="8_Proteins_vs_Swissprot_blastp.txt"/>\n+                <param name="blacklist_regexs" value="blacklist_stitle_regexs.txt"/>\n+            </repeat>\n+            <repeat name="advanced_input_repeat">\n+                <param name="seq_sim_table" value="8_Proteins_vs_Trembl_blastp.txt"/>\n+                <param name="blacklist_regexs" value="blacklist_stitle_regexs.txt"/>\n+            </repeat>\n+            <param name="description_split_regex" value="([~_\\-/|;,\'\\\'\':.\\s]+)"/>\n+            <param name="center_inverse_word_information_content_at_quantile" value="50"/>\n+            <output name="output" file="8_Proteins_prot-scriber.out" sort="true"/>\n+        </test>\n+    </tests>\n+    <help>\n     <![CDATA[\n \n **What it does**\n@@ -343,4 +329,15 @@\n \n     ]]>\n   </help>\n+    <citations>\n+        <citation type="bibtex">\n+            @misc{githubprot-scriber,\n+            author = {Asis Hallab},\n+            year = {2024},\n+            title = {prot-scriber},\n+            publisher = {Github},\n+            journal = {Github repository},\n+            url = {https://github.com/usadellab/prot-scriber},\n+        }</citation>\n+    </citations>\n </tool>\n'
b
diff -r 4d4df9779b7b -r 863ab6ebcafc test-data/8_Proteins_prot-scriber.out
--- a/test-data/8_Proteins_prot-scriber.out Tue Sep 20 09:45:46 2022 +0000
+++ b/test-data/8_Proteins_prot-scriber.out Sat May 18 20:36:38 2024 +0000
b
@@ -1,12 +1,12 @@
 Annotee-Identifier Human-Readable-Description
 Soltu.DM.01G022510.1 sucrose nonfermenting protein x2
-Soltu.DM.02G020600.1 arath protein strubbelig receptor family
+Soltu.DM.02G020600.1 protein strubbelig receptor family
 Soltu.DM.10G003150.1 sh and domain containing protein
 Soltu.DM.04G035790.1 phosphatidylinositol phosphatidylcholine transfer protein sfh
 Soltu.DM.02G015700.1 lrr receptor serine threonine protein kinase
 Soltu.DM.03G026010.1 arm repeat protein interacting with
-Soltu.DM.07G016620.1 capch gdsl esterase lipase
+Soltu.DM.07G016620.1 gdsl esterase lipase
 Soltu.DM.S001650.1 germin protein member
 Soltu.DM.03G011280.1 increased dna methylation
-Soltu.DM.01G045390.1 gosmu hva protein
+Soltu.DM.01G045390.1 hva protein
 Soltu.DM.09G022410.3 unknown protein