Repository 'ncbi_blast_plus'
hg clone https://toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus

Changeset 34:b6893f57f8d8 (2024-02-22)
Previous changeset 33:d999e774072a (2023-11-19) Next changeset 35:cbf3f518b668 (2024-02-22)
Commit message:
planemo upload for repository https://github.com/peterjc/galaxy_blast/tree/master/tools/ncbi_blast_plus commit 028e3e806ba6df913403a2a083a354dfa713755f
modified:
test-data/three_human_mRNA.fasta.gz
test-data/tool_data_table_conf.xml.test
tool-data/tool_data_table_conf.xml.sample
tools/ncbi_blast_plus/README.rst
tools/ncbi_blast_plus/ncbi_macros.xml
tools/ncbi_blast_plus/ncbi_makeblastdb.xml
b
diff -r d999e774072a -r b6893f57f8d8 test-data/three_human_mRNA.fasta.gz
b
Binary file test-data/three_human_mRNA.fasta.gz has changed
b
diff -r d999e774072a -r b6893f57f8d8 test-data/tool_data_table_conf.xml.test
--- a/test-data/tool_data_table_conf.xml.test Sun Nov 19 22:57:39 2023 +0000
+++ b/test-data/tool_data_table_conf.xml.test Thu Feb 22 14:47:01 2024 +0000
b
@@ -12,4 +12,8 @@
         <columns>value, name, path</columns>
         <file path="${__HERE__}/blastdb_d.loc" />
     </table>
+    <table name="all_fasta" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="${__HERE__}/all_fasta.loc" />
+    </table>
 </tables>
b
diff -r d999e774072a -r b6893f57f8d8 tool-data/tool_data_table_conf.xml.sample
--- a/tool-data/tool_data_table_conf.xml.sample Sun Nov 19 22:57:39 2023 +0000
+++ b/tool-data/tool_data_table_conf.xml.sample Thu Feb 22 14:47:01 2024 +0000
b
@@ -11,4 +11,8 @@
         <columns>value, name, path</columns>
         <file path="tool-data/blastdb_d.loc" />
     </table>
+    <table name="all_fasta" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/all_fasta.loc.sample" />
+    </table>
 </tables>
b
diff -r d999e774072a -r b6893f57f8d8 tools/ncbi_blast_plus/README.rst
--- a/tools/ncbi_blast_plus/README.rst Sun Nov 19 22:57:39 2023 +0000
+++ b/tools/ncbi_blast_plus/README.rst Thu Feb 22 14:47:01 2024 +0000
b
@@ -136,6 +136,10 @@
 ============== ===============================================================
 Version        Changes
 -------------- ---------------------------------------------------------------
+2.14.1+galaxy2 - Add usage of genome FASTA files on the Galaxy server with
+                 ``makeblastdb`` (contribution from Wolfgang Maier and
+                 Elischa Berger)
+2.14.1+galaxy1 - Fix for get_species_taxids
 2.14.1+galaxy0 - Updated for NCBI BLAST+ 2.14.1 release.
 2.10.1+galaxy3 - Silenced ``deltablast`` warning about using ``-num_threads``
                  with ``--subject`` (i.e. FASTA file from your history).
b
diff -r d999e774072a -r b6893f57f8d8 tools/ncbi_blast_plus/ncbi_macros.xml
--- a/tools/ncbi_blast_plus/ncbi_macros.xml Sun Nov 19 22:57:39 2023 +0000
+++ b/tools/ncbi_blast_plus/ncbi_macros.xml Thu Feb 22 14:47:01 2024 +0000
b
@@ -1,6 +1,6 @@
 <macros>
     <token name="@TOOL_VERSION@">2.14.1</token>
-    <token name="@VERSION_SUFFIX@">1</token>
+    <token name="@VERSION_SUFFIX@">2</token>
     <token name="@PROFILE@">16.10</token>
     <xml name="parallelism">
         <!-- If job splitting is enabled, break up the query file into parts -->
b
diff -r d999e774072a -r b6893f57f8d8 tools/ncbi_blast_plus/ncbi_makeblastdb.xml
--- a/tools/ncbi_blast_plus/ncbi_makeblastdb.xml Sun Nov 19 22:57:39 2023 +0000
+++ b/tools/ncbi_blast_plus/ncbi_makeblastdb.xml Thu Feb 22 14:47:01 2024 +0000
[
b'@@ -8,21 +8,36 @@\n         <requirement type="package" version="3.9">python</requirement>\n     </expand>\n     <command detect_errors="aggressive" strict="true"><![CDATA[\n+#set $inputs = []\n+#set $input_compression = []\n+#for r in $input.selection:\n+    #if $input.type == "protein":\n+        #silent $inputs.append($r.input_file)\n+        #silent $input_compression.append($r.input_file.is_of_type(\'fasta.gz\'))\n+    #elif $r.nuc_choice.source == "history":\n+        #silent $inputs.append($r.nuc_choice.input_file)\n+        #silent $input_compression.append($r.nuc_choice.input_file.is_of_type(\'fasta.gz\'))\n+    #else:\n+        #silent $inputs.append($r.nuc_choice.input_file.fields.path)\n+        #silent $input_compression.append(False)\n+    #end if\n+#end for\n+\n python $__tool_directory__/check_no_duplicates.py\n ##First check for duplicates (since BLAST+ 2.2.28 fails to do so)\n ##and abort (via the ampersand ampersand trick) if any are found.\n-#for i in $input_file#\'${i}\' #end for#\n+#for i in $inputs#\'$i\' #end for#\n &&\n ##makeblastdb does not like input redirects of the sort\n ##makeblastdb -in <(gunzip -c gzipped_fasta_file)\n ##therefore we\'re cramming everything\n ##into a single cat command below\n cat\n-#for i in $input_file:\n-    #if $i.is_of_type(\'fasta.gz\') and $i.ext != "fasta":\n-        <(gunzip -c ${i})\n+#for i, is_gzipped in zip($inputs, $input_compression):\n+    #if $is_gzipped:\n+        <(gunzip -c \'$i\')\n     #else:\n-        ${i}\n+        \'$i\'\n     #end if\n #end for\n | makeblastdb -out \'${os.path.join($outfile.files_path, "blastdb")}\'\n@@ -36,7 +51,12 @@\n ##Would default to being based on the cryptic Galaxy filenames, which is unhelpful\n -title \'BLAST Database\'\n #end if\n--dbtype $dbtype\n+-dbtype\n+#if $input.type == "protein":\n+    prot\n+#else:\n+    nucl\n+#end if\n ## --------------------------------------------------------------------\n ## Masking\n ## --------------------------------------------------------------------\n@@ -60,15 +80,39 @@\n > \'$outfile\'\n     ]]></command>\n     <inputs>\n-        <param argument="-dbtype" type="select" display="radio" label="Molecule type of input">\n-            <option value="prot">protein</option>\n-            <option value="nucl">nucleotide</option>\n-        </param>\n-        <!-- TODO Allow merging of existing BLAST databases (conditional on the database type)?\n-             NOTE Double check the new database would be self contained first\n-        -->\n-        <!-- Note this is a mandatory parameter - default should be most recent FASTA file -->\n-        <param name="input_file" argument="-in" type="data" multiple="true" optional="false" format="fasta,fasta.gz" label="Input FASTA files(s)" help="One or more FASTA files" />\n+        <conditional name="input">\n+            <param argument="-dbtype" name="type" type="select" label="Molecule type of input">\n+                <option value="protein">protein</option>\n+                <option value="nucleotide">nucleotide</option>\n+            </param>\n+            <!-- TODO Allow merging of existing BLAST databases (conditional on the database type)?\n+                 NOTE Double check the new database would be self contained first\n+            -->\n+            <when value="protein">\n+                <repeat name="selection" title="Select input" min="1" default="1">\n+                    <!-- Note this is a mandatory parameter - default should be most recent FASTA file -->\n+                    <param name="input_file" argument="-in" type="data" format="fasta,fasta.gz" label="FASTA input" help="FASTA file with one or more sequences to add to the database" />\n+                </repeat>\n+            </when>\n+            <when value="nucleotide">\n+                <repeat name="selection" title="Select input" min="1" default="1">\n+                    <conditional name="nuc_choice">\n+                        <param name="source" type="select" label="Input is a">\n+                            <option value="history">Dataset in history</option>\n+               '..b'"parse_seqids" value="" />\n             <param name="hash_index" value="true" />\n@@ -132,8 +181,12 @@\n             </output>\n         </test>\n         <test>\n-            <param name="dbtype" value="prot" />\n-            <param name="input_file" value="four_human_proteins.fasta" ftype="fasta" />\n+            <conditional name="input">\n+                <param name="type" value="protein"/>\n+                <repeat name="selection">\n+                    <param name="input_file" value="four_human_proteins.fasta" ftype="fasta" />\n+                </repeat>\n+            </conditional>    \n             <param name="title" value="Just 4 human proteins" />\n             <param name="parse_seqids" value="" />\n             <param name="hash_index" value="true" />\n@@ -151,8 +204,12 @@\n             </output>\n         </test>\n         <test>\n-            <param name="dbtype" value="prot" />\n-            <param name="input_file" value="four_human_proteins.fasta" ftype="fasta" />\n+            <conditional name="input">\n+                <param name="type" value="protein"/>\n+                <repeat name="selection">\n+                    <param name="input_file" value="four_human_proteins.fasta" ftype="fasta" />\n+                </repeat>\n+            </conditional>                \n             <param name="title" value="Just 4 human proteins" />\n             <param name="parse_seqids" value="" />\n             <param name="hash_index" value="true" />\n@@ -169,8 +226,41 @@\n             </output>\n         </test>\n         <test>\n-            <param name="dbtype" value="nucl" />\n-            <param name="input_file" value="three_human_mRNA.fasta.gz" ftype="fasta.gz" />\n+            <conditional name="input">\n+                <param name="type" value="nucleotide"/>\n+                <repeat name="selection">\n+                    <conditional name="nuc_choice">\n+                        <param name="source" value="history"/>\n+                        <param name="input_file" value="three_human_mRNA.fasta.gz" ftype="fasta.gz" />\n+                    </conditional> \n+                </repeat>\n+            </conditional> \n+            <param name="title" value="Just 3 human mRNA sequences" />\n+            <param name="parse_seqids" value="" />\n+            <param name="hash_index" value="true" />\n+            <param name="taxselect" value="id" />\n+            <param name="taxid" value="9606" />\n+            <output name="outfile" compare="contains" file="three_human_mRNA.fasta.log.txt" ftype="blastdbn">\n+                <extra_files type="file" value="three_human_mRNA.fasta.nhr" name="blastdb.nhr" />\n+                <extra_files type="file" value="three_human_mRNA.fasta.nin" name="blastdb.nin" compare="sim_size" delta="8" />\n+                <extra_files type="file" value="three_human_mRNA.fasta.nsq" name="blastdb.nsq" />\n+                <extra_files type="file" value="three_human_mRNA.fasta.nog" name="blastdb.nog" />\n+                <extra_files type="file" value="three_human_mRNA.fasta.nhd" name="blastdb.nhd" />\n+                <extra_files type="file" value="three_human_mRNA.fasta.nhi" name="blastdb.nhi" />\n+                <extra_files type="file" value="three_human_mRNA.fasta.nsd" name="blastdb.nsd" />\n+                <extra_files type="file" value="three_human_mRNA.fasta.nsi" name="blastdb.nsi" />\n+            </output>\n+        </test>\n+        <test>\n+            <conditional name="input">\n+                <param name="type" value="nucleotide"/>\n+                <repeat name="selection">\n+                    <conditional name="nuc_choice">\n+                        <param name="source" value="cached"/>\n+                        <param name="input_file" value="three_human_mRNA" />\n+                    </conditional> \n+                </repeat>\n+            </conditional> \n             <param name="title" value="Just 3 human mRNA sequences" />\n             <param name="parse_seqids" value="" />\n             <param name="hash_index" value="true" />\n'