changeset 29:5edc472ec434 draft

"Updated to 2.10.1+galaxy0"
author peterjc
date Thu, 10 Sep 2020 13:23:34 +0000
parents 87a7ee4cb36f
children acf4e47b734c
files test-data/blastn_chimera_vs_three_human_max1.txt test-data/blastn_rhodopsin_vs_three_human.xml test-data/blastp_four_human_vs_rhodopsin.xml test-data/blastx_rhodopsin_vs_four_human.xml test-data/cd00003_and_cd00008.pin test-data/four_human_proteins.fasta.pin test-data/four_human_proteins_taxid.fasta.pin test-data/rhodopsin_nucs.fasta.nin test-data/tblastn_four_human_vs_rhodopsin.html test-data/tblastn_four_human_vs_rhodopsin.xml test-data/three_human_mRNA.fasta.nin tools/ncbi_blast_plus/README.rst tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml tools/ncbi_blast_plus/ncbi_macros.xml tools/ncbi_blast_plus/ncbi_makeblastdb.xml tools/ncbi_blast_plus/ncbi_makeprofiledb.xml
diffstat 16 files changed, 37 insertions(+), 21 deletions(-) [+]
line wrap: on
line diff
--- a/test-data/blastn_chimera_vs_three_human_max1.txt	Thu Sep 10 10:35:28 2020 +0000
+++ b/test-data/blastn_chimera_vs_three_human_max1.txt	Thu Sep 10 13:23:34 2020 +0000
@@ -1,4 +1,4 @@
-BLASTN 2.9.0+
+BLASTN 2.10.1+
 
 
 Reference: Zheng Zhang, Scott Schwartz, Lukas Wagner, and Webb
@@ -15,10 +15,10 @@
 Query= chimera chunks of AB011145 plus M10051 plus BC112106
 
 Length=9973
-                                                                      Score        E
-Sequences producing significant alignments:                          (Bits)     Value
+                                                                      Score     E
+Sequences producing significant alignments:                          (Bits)  Value
 
-ENA|AB011145|AB011145.1 Homo sapiens mRNA for KIAA0573 protein, p...  8421       0.0  
+ENA|AB011145|AB011145.1 Homo sapiens mRNA for KIAA0573 protein, p...  8421    0.0  
 
 
 >ENA|AB011145|AB011145.1 Homo sapiens mRNA for KIAA0573 protein, 
@@ -346,7 +346,7 @@
 
 
   Database: Just 3 human mRNA sequences
-    Posted date:  Apr 23, 2020  3:16 PM
+    Posted date:  Sep 9, 2020  11:23 PM
   Number of letters in database: 10,732
   Number of sequences in database:  3
 
--- a/test-data/blastn_rhodopsin_vs_three_human.xml	Thu Sep 10 10:35:28 2020 +0000
+++ b/test-data/blastn_rhodopsin_vs_three_human.xml	Thu Sep 10 13:23:34 2020 +0000
@@ -2,7 +2,7 @@
 <!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.dtd">
 <BlastOutput>
   <BlastOutput_program>blastn</BlastOutput_program>
-  <BlastOutput_version>BLASTN 2.9.0+</BlastOutput_version>
+  <BlastOutput_version>BLASTN 2.10.1+</BlastOutput_version>
   <BlastOutput_reference>Zheng Zhang, Scott Schwartz, Lukas Wagner, and Webb Miller (2000), &quot;A greedy algorithm for aligning DNA sequences&quot;, J Comput Biol 2000; 7(1-2):203-14.</BlastOutput_reference>
   <BlastOutput_db></BlastOutput_db>
   <BlastOutput_query-ID>Query_1</BlastOutput_query-ID>
--- a/test-data/blastp_four_human_vs_rhodopsin.xml	Thu Sep 10 10:35:28 2020 +0000
+++ b/test-data/blastp_four_human_vs_rhodopsin.xml	Thu Sep 10 13:23:34 2020 +0000
@@ -2,7 +2,7 @@
 <!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.dtd">
 <BlastOutput>
   <BlastOutput_program>blastp</BlastOutput_program>
-  <BlastOutput_version>BLASTP 2.9.0+</BlastOutput_version>
+  <BlastOutput_version>BLASTP 2.10.1+</BlastOutput_version>
   <BlastOutput_reference>Stephen F. Altschul, Thomas L. Madden, Alejandro A. Sch&amp;auml;ffer, Jinghui Zhang, Zheng Zhang, Webb Miller, and David J. Lipman (1997), &quot;Gapped BLAST and PSI-BLAST: a new generation of protein database search programs&quot;, Nucleic Acids Res. 25:3389-3402.</BlastOutput_reference>
   <BlastOutput_db></BlastOutput_db>
   <BlastOutput_query-ID>Q9BS26</BlastOutput_query-ID>
--- a/test-data/blastx_rhodopsin_vs_four_human.xml	Thu Sep 10 10:35:28 2020 +0000
+++ b/test-data/blastx_rhodopsin_vs_four_human.xml	Thu Sep 10 13:23:34 2020 +0000
@@ -2,7 +2,7 @@
 <!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.dtd">
 <BlastOutput>
   <BlastOutput_program>blastx</BlastOutput_program>
-  <BlastOutput_version>BLASTX 2.9.0+</BlastOutput_version>
+  <BlastOutput_version>BLASTX 2.10.1+</BlastOutput_version>
   <BlastOutput_reference>Stephen F. Altschul, Thomas L. Madden, Alejandro A. Sch&amp;auml;ffer, Jinghui Zhang, Zheng Zhang, Webb Miller, and David J. Lipman (1997), &quot;Gapped BLAST and PSI-BLAST: a new generation of protein database search programs&quot;, Nucleic Acids Res. 25:3389-3402.</BlastOutput_reference>
   <BlastOutput_db></BlastOutput_db>
   <BlastOutput_query-ID>Query_1</BlastOutput_query-ID>
Binary file test-data/cd00003_and_cd00008.pin has changed
Binary file test-data/four_human_proteins.fasta.pin has changed
Binary file test-data/four_human_proteins_taxid.fasta.pin has changed
Binary file test-data/rhodopsin_nucs.fasta.nin has changed
--- a/test-data/tblastn_four_human_vs_rhodopsin.html	Thu Sep 10 10:35:28 2020 +0000
+++ b/test-data/tblastn_four_human_vs_rhodopsin.html	Thu Sep 10 13:23:34 2020 +0000
@@ -3,7 +3,7 @@
 <BODY BGCOLOR="#FFFFFF" LINK="#0000FF" VLINK="#660099" ALINK="#660099">
 <PRE>
 
-<b>TBLASTN 2.9.0+</b>
+<b>TBLASTN 2.10.1+</b>
 
 
 <b><a
@@ -84,15 +84,15 @@
 <b>Query=</b> sp|P08100|OPSD_HUMAN Rhodopsin OS=Homo sapiens GN=RHO PE=1 SV=1
 
 Length=348
-                                                                      Score        E
-Sequences producing significant alignments:                          (Bits)     Value
+                                                                      Score     E
+Sequences producing significant alignments:                          (Bits)  Value
 
-gi|57163782|ref|NM_001009242.1| Felis catus rhodopsin (RHO), mRNA     <a href=#Subject_1>732</a>        0.0  
-gi|18148870|dbj|AB062417.1| Synthetic construct Bos taurus gene f...  <a href=#Subject_5>711</a>        0.0  
-gi|283855822|gb|GQ290312.1| Myotis ricketti voucher GQX10 rhodops...  <a href=#Subject_4>658</a>        0.0  
-gi|2734705|gb|U59921.1|BBU59921 Bufo bufo rhodopsin mRNA, complet...  <a href=#Subject_2>646</a>        0.0  
-gi|12583664|dbj|AB043817.1| Conger myriaster conf gene for fresh ...  <a href=#Subject_6>626</a>        0.0  
-gi|283855845|gb|GQ290303.1| Cynopterus brachyotis voucher 2002043...  <a href=#Subject_3>229</a>        3e-67
+gi|57163782|ref|NM_001009242.1| Felis catus rhodopsin (RHO), mRNA     <a href=#Subject_1>732</a>     0.0  
+gi|18148870|dbj|AB062417.1| Synthetic construct Bos taurus gene f...  <a href=#Subject_5>711</a>     0.0  
+gi|283855822|gb|GQ290312.1| Myotis ricketti voucher GQX10 rhodops...  <a href=#Subject_4>658</a>     0.0  
+gi|2734705|gb|U59921.1|BBU59921 Bufo bufo rhodopsin mRNA, complet...  <a href=#Subject_2>646</a>     0.0  
+gi|12583664|dbj|AB043817.1| Conger myriaster conf gene for fresh ...  <a href=#Subject_6>626</a>     0.0  
+gi|283855845|gb|GQ290303.1| Cynopterus brachyotis voucher 2002043...  <a href=#Subject_3>229</a>     3e-67
 
 
 ><a name=Subject_1></a> gi|57163782|ref|NM_001009242.1| Felis catus rhodopsin (RHO), 
--- a/test-data/tblastn_four_human_vs_rhodopsin.xml	Thu Sep 10 10:35:28 2020 +0000
+++ b/test-data/tblastn_four_human_vs_rhodopsin.xml	Thu Sep 10 13:23:34 2020 +0000
@@ -2,7 +2,7 @@
 <!DOCTYPE BlastOutput PUBLIC "-//NCBI//NCBI BlastOutput/EN" "http://www.ncbi.nlm.nih.gov/dtd/NCBI_BlastOutput.dtd">
 <BlastOutput>
   <BlastOutput_program>tblastn</BlastOutput_program>
-  <BlastOutput_version>TBLASTN 2.9.0+</BlastOutput_version>
+  <BlastOutput_version>TBLASTN 2.10.1+</BlastOutput_version>
   <BlastOutput_reference>Stephen F. Altschul, Thomas L. Madden, Alejandro A. Sch&amp;auml;ffer, Jinghui Zhang, Zheng Zhang, Webb Miller, and David J. Lipman (1997), &quot;Gapped BLAST and PSI-BLAST: a new generation of protein database search programs&quot;, Nucleic Acids Res. 25:3389-3402.</BlastOutput_reference>
   <BlastOutput_db></BlastOutput_db>
   <BlastOutput_query-ID>Query_1</BlastOutput_query-ID>
Binary file test-data/three_human_mRNA.fasta.nin has changed
--- a/tools/ncbi_blast_plus/README.rst	Thu Sep 10 10:35:28 2020 +0000
+++ b/tools/ncbi_blast_plus/README.rst	Thu Sep 10 13:23:34 2020 +0000
@@ -136,6 +136,13 @@
 ============== ===============================================================
 Version        Changes
 -------------- ---------------------------------------------------------------
+2.10.1+galaxy0 - Updated for NCBI BLAST+ 2.10.1 release.
+               - Supports locally installed v4 or v5 format BLAST databases
+                 (listed in the ``blastdb*.loc`` files).
+               - ``makeblastdb`` and ``makeprofiledb`` still produce v4 format
+                 databases (pending updates to the Galaxy datatypes for v5).
+               - Minimum word size for ``blastn`` now 4 (update from Anthony
+                 Bretaudeau).
 2.9.0+galaxy0  - Updated for NCBI BLAST+ 2.9.0 release (contribution from
                  Anthony Bretaudeau).
 2.7.1+galaxy0  - Adopted BLAST version with integer Galaxy wrapper suffix.
--- a/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml	Thu Sep 10 10:35:28 2020 +0000
+++ b/tools/ncbi_blast_plus/ncbi_blastn_wrapper.xml	Thu Sep 10 13:23:34 2020 +0000
@@ -61,7 +61,7 @@
             <expand macro="input_strand" />
             <expand macro="input_max_hits" />
             <param name="identity_cutoff" argument="-perc_identity" type="float" min="0" max="100" value="0" label="Percent identity cutoff" help="Use zero for no cutoff" />
-            <expand macro="input_word_size" />
+            <expand macro="input_word_size_blastn" />
             <param argument="-ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped" falsevalue="" checked="false" />
             <expand macro="input_parse_deflines" />
             <expand macro="advanced_optional_id_files" />
--- a/tools/ncbi_blast_plus/ncbi_macros.xml	Thu Sep 10 10:35:28 2020 +0000
+++ b/tools/ncbi_blast_plus/ncbi_macros.xml	Thu Sep 10 13:23:34 2020 +0000
@@ -1,5 +1,5 @@
 <macros>
-    <token name="@TOOL_VERSION@">2.9.0</token>
+    <token name="@TOOL_VERSION@">2.10.1</token>
     <token name="@VERSION_SUFFIX@">0</token>
     <token name="@PROFILE@">16.10</token>
     <xml name="parallelism">
@@ -493,6 +493,12 @@
         help="Leave blank for default, otherwise minimum 2" />
     </xml>
 
+    <xml name="input_word_size_blastn">
+        <param argument="-word_size" type="integer" min="4" optional="true"
+        label="Word size for wordfinder algorithm"
+        help="Leave blank for default, otherwise minimum 4" />
+    </xml>
+
     <xml name="input_strand">
         <param argument="-strand" type="select" label="Query strand(s) to search against database/subject">
             <option value="-strand both">Both</option>
--- a/tools/ncbi_blast_plus/ncbi_makeblastdb.xml	Thu Sep 10 10:35:28 2020 +0000
+++ b/tools/ncbi_blast_plus/ncbi_makeblastdb.xml	Thu Sep 10 13:23:34 2020 +0000
@@ -24,6 +24,7 @@
     #end if
 #end for
 | makeblastdb -out '${os.path.join($outfile.files_path, "blastdb")}'
+-blastdb_version 4
 $parse_seqids
 $hash_index
 -in -
--- a/tools/ncbi_blast_plus/ncbi_makeprofiledb.xml	Thu Sep 10 10:35:28 2020 +0000
+++ b/tools/ncbi_blast_plus/ncbi_makeprofiledb.xml	Thu Sep 10 13:23:34 2020 +0000
@@ -8,7 +8,9 @@
     <command detect_errors="aggressive" strict="true">
 ##Unlike makeblastdb, makeprofiledb needs directory to exist already:
 mkdir -p $outfile.files_path &amp;&amp;
-makeprofiledb -out '${os.path.join($outfile.files_path, "blastdb")}'
+makeprofiledb
+-blastdb_version 4
+-out '${os.path.join($outfile.files_path, "blastdb")}'
 
 ##We turn $input_file into $infiles with a configfile entry defined below
 -in '$infiles'