Mercurial > repos > nml > refseq_masher

changeset 1:2c1cb37a3ffe draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/phac-nml/refseq_masher commit e83730c5df84a960af58ff09db7eb09d11df2398
author nml
date Wed, 08 May 2019 09:15:56 -0400
parents 26df66c32861
children 1ec42f033bb4
files contains.xml matches.xml
diffstat 2 files changed, 20 insertions(+), 18 deletions(-) [+]
line wrap: on
line diff
--- a/contains.xml	Thu Feb 15 13:59:31 2018 -0500
+++ b/contains.xml	Wed May 08 09:15:56 2019 -0400
@@ -1,4 +1,4 @@
-<tool id="refseq_masher_contains" name="RefSeq Masher Contains" version="0.1.1">
+<tool id="refseq_masher_contains" name="RefSeq Masher Contains" version="0.1.2">
   <description>
     Find NCBI RefSeq Genomes contained in your sequences
   </description>
@@ -9,9 +9,10 @@
 <![CDATA[
 
 #import re
+#import os
 
 #if $input.type == 'fasta'
-#set $input_files = '"{}"'.format($input.fasta.name)
+#set $input_files = '"{}.fasta"'.format(os.path.splitext($input.fasta.name)[0])
   ln -s "$input.fasta" $input_files &&
 #elif $input.type == 'paired'
 #set $_forward_ext = '.fastq.gz' if $re.match(r'.*\.gz$', $input.forward.name) else '.fastq'
@@ -171,7 +172,7 @@
 Find what NCBI RefSeq genomes are contained within your sequence data using Mash_ with a Mash sketch database of 54,925 NCBI RefSeq Genomes.
 
 
-Source code available on Github at https://github.com/phac-nml/refseq_masher
+Source code available on Github at github.com/phac-nml/refseq_masher
 
 
 `contains` - find what NCBI RefSeq Genomes are contained in your input sequences
@@ -217,8 +218,8 @@
 
 We're going to download the FASTQ files for ERR260489_::
 
-    wget ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR260/ERR260489/ERR260489_1.fastq.gz
-    wget ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR260/ERR260489/ERR260489_2.fastq.gz
+    wget ftp.sra.ebi.ac.uk/vol1/fastq/ERR260/ERR260489/ERR260489_1.fastq.gz
+    wget ftp.sra.ebi.ac.uk/vol1/fastq/ERR260/ERR260489/ERR260489_2.fastq.gz
 
 
 We're going to run `refseq_masher` against these FASTQ files::
@@ -295,7 +296,7 @@
 this work except in compliance with the License. You may obtain a copy of the
 License at:
 
-http://www.apache.org/licenses/LICENSE-2.0
+www.apache.org/licenses/LICENSE-2.0
 
 Unless required by applicable law or agreed to in writing, software distributed
 under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
@@ -309,10 +310,10 @@
 
 
 
-.. _Mash: https://genomebiology.biomedcentral.com/articles/10.1186/s13059-016-0997-x
-.. _SAMEA1877340: https://www.ebi.ac.uk/ena/data/view/SAMEA1877340
-.. _PRJEB1775: https://www.ebi.ac.uk/ena/data/view/PRJEB1775
-.. _ERR260489: https://www.ebi.ac.uk/ena/data/view/ERR260489&display=html
+.. _Mash: genomebiology.biomedcentral.com/articles/10.1186/s13059-016-0997-x
+.. _SAMEA1877340: www.ebi.ac.uk/ena/data/view/SAMEA1877340
+.. _PRJEB1775: www.ebi.ac.uk/ena/data/view/PRJEB1775
+.. _ERR260489: www.ebi.ac.uk/ena/data/view/ERR260489&display=html
 
 ]]>
   </help>
--- a/matches.xml	Thu Feb 15 13:59:31 2018 -0500
+++ b/matches.xml	Wed May 08 09:15:56 2019 -0400
@@ -1,4 +1,4 @@
-<tool id="refseq_masher_matches" name="RefSeq Masher Matches" version="0.1.1">
+<tool id="refseq_masher_matches" name="RefSeq Masher Matches" version="0.1.2">
   <description>
     Find closest matching NCBI RefSeq Genomes to your sequences
   </description>
@@ -9,9 +9,10 @@
 <![CDATA[
 
 #import re
+#import os
 
 #if $input.type == 'fasta'
-#set $input_files = '"{}"'.format($input.fasta.name)
+#set $input_files = '"{}.fasta"'.format(os.path.splitext($input.fasta.name)[0])
   ln -s "$input.fasta" $input_files &&
 #elif $input.type == 'paired'
 #set $_forward_ext = '.fastq.gz' if $re.match(r'.*\.gz$', $input.forward.name) else '.fastq'
@@ -182,7 +183,7 @@
 Find what NCBI RefSeq genomes most closely match your sequence data using Mash_ with a Mash sketch database of 54,925 NCBI RefSeq Genomes.
 
 
-Source code available on Github at https://github.com/phac-nml/refseq_masher
+Source code available on Github at github.com/phac-nml/refseq_masher
 
 
 `matches` - find the closest matching NCBI RefSeq Genomes in your input sequences
@@ -217,7 +218,7 @@
 
 
     # download sequence file
-    wget ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/329/025/GCF_000329025.1_ASM32902v1/GCF_000329025.1_ASM32902v1_genomic.fna.gz
+    wget ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/329/025/GCF_000329025.1_ASM32902v1/GCF_000329025.1_ASM32902v1_genomic.fna.gz
 
     # find RefSeq matches
     refseq_masher -vv matches GCF_000329025.1_ASM32902v1_genomic.fna.gz
@@ -268,7 +269,7 @@
 this work except in compliance with the License. You may obtain a copy of the
 License at:
 
-http://www.apache.org/licenses/LICENSE-2.0
+www.apache.org/licenses/LICENSE-2.0
 
 Unless required by applicable law or agreed to in writing, software distributed
 under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
@@ -280,9 +281,9 @@
 
 **Gary van Domselaar**: gary.vandomselaar@phac-aspc.gc.ca
 
-.. _Mash: https://genomebiology.biomedcentral.com/articles/10.1186/s13059-016-0997-x
-.. _FNA.GZ: ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/329/025/GCF_000329025.1_ASM32902v1/GCF_000329025.1_ASM32902v1_genomic.fna.gz
-.. _CHS44: ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/329/025/GCF_000329025.1_ASM32902v1/
+.. _Mash: genomebiology.biomedcentral.com/articles/10.1186/s13059-016-0997-x
+.. _FNA.GZ: ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/329/025/GCF_000329025.1_ASM32902v1/GCF_000329025.1_ASM32902v1_genomic.fna.gz
+.. _CHS44: ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/329/025/GCF_000329025.1_ASM32902v1/
 
 
 ]]>