Mercurial > repos > devteam > fastx_nucleotides_distribution
changeset 3:3b6c41fc2d21 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/fastx_toolkit/fastx_nucleotides_distribution commit bbb2e6b6769b03602a8ab97001f88fbec52080a1
author | iuc |
---|---|
date | Tue, 08 May 2018 12:51:52 -0400 |
parents | 05f35740cd79 |
children | 67e441bc4265 |
files | fastx_nucleotides_distribution.xml macros.xml test-data/fastq_stats1.out test-data/fastx_nt_distribution.png test-data/fastx_nucleotides_distribution-in1.txt test-data/fastx_nucleotides_distribution-out1.png tool_dependencies.xml |
diffstat | 7 files changed, 157 insertions(+), 26 deletions(-) [+] |
line wrap: on
line diff
--- a/fastx_nucleotides_distribution.xml Tue Jun 03 15:07:52 2014 -0400 +++ b/fastx_nucleotides_distribution.xml Tue May 08 12:51:52 2018 -0400 @@ -1,19 +1,28 @@ -<tool id="cshl_fastx_nucleotides_distribution" version="1.0.0" name="Draw nucleotides distribution chart"> - <description></description> - <requirements> - <requirement type="package" version="0.0.13">fastx_toolkit</requirement> - </requirements> - <command>fastx_nucleotide_distribution_graph.sh -t '$input.name' -i $input -o $output</command> - - <inputs> - <param format="txt" name="input" type="data" label="Statistics Text File" help="output of 'FASTX Statistics' tool" /> - </inputs> - - <outputs> - <data format="png" name="output" metadata_source="input" /> - </outputs> -<help> - +<tool id="cshl_fastx_nucleotides_distribution" version="1.0.1" name="Draw nucleotides distribution chart"> + <description></description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements" /> + <command detect_errors="exit_code"><![CDATA[ +fastx_nucleotide_distribution_graph.sh +-t '$input.name' +-i '$input' +-o '$output' + ]]></command> + <inputs> + <param name="input" type="data" format="txt" label="Statistics text file" help="Output of 'FASTX Statistics' tool" /> + </inputs> + <outputs> + <data name="output" format="png" metadata_source="input" /> + </outputs> + <tests> + <test> + <param name="input" value="fastx_nucleotides_distribution-in1.txt" /> + <output name="output" file="fastx_nucleotides_distribution-out1.png" compare="sim_size" delta="512" /> + </test> + </tests> + <help><![CDATA[ **What it does** Creates a stacked-histogram graph for the nucleotide distribution in the Solexa library. @@ -29,7 +38,7 @@ The following chart clearly shows the barcode used at the 5'-end of the library: **GATCT** .. image:: fastq_nucleotides_distribution_1.png - + In the following chart, one can almost 'read' the most abundant sequence by looking at the dominant values: **TGATA TCGTA TTGAT GACTG AA...** .. image:: fastq_nucleotides_distribution_2.png @@ -47,7 +56,7 @@ This tool is based on `FASTX-toolkit`__ by Assaf Gordon. .. __: http://hannonlab.cshl.edu/fastx_toolkit/ - -</help> -<!-- FASTQ-Nucleotides-Distribution is part of the FASTX-toolkit, by A.Gordon (gordon@cshl.edu) --> + ]]></help> + <expand macro="citations" /> + <!-- FASTQ-Nucleotides-Distribution is part of the FASTX-toolkit, by A.Gordon (gordon@cshl.edu) --> </tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Tue May 08 12:51:52 2018 -0400 @@ -0,0 +1,54 @@ +<?xml version="1.0"?> +<macros> + <token name="@CATS@"> + #if $input.is_of_type('fasta.gz', 'fastqsanger.gz', 'fastqsolexa.gz', 'fastqillumina.gz'): + zcat -f '$input' | + #elif $input.is_of_type('fastqsanger.bz2', 'fastqsolexa.bz2', 'fastqillumina.bz2'): + bzcat -f '$input' | + #else: + cat '$input' | + #end if + </token> + <token name="@FQQUAL@"> + <![CDATA[ + #if $input.is_of_type('fastqsanger', 'fastqsanger.gz', 'fastqsanger.bz2'): + -Q 33 + #elif $input.is_of_type('fastqsolexa', 'fastqsolexa.gz', 'fastqsolexa.bz2', 'fastqillumina', 'fastqillumina.gz', 'fastqillumina.bz2'): + -Q 64 + #end if + ]]> + </token> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@VERSION@">fastx_toolkit</requirement> + <yield /> + </requirements> + </xml> + <token name="@VERSION@">0.0.14</token> + <token name="@SANGER@">fastqsanger,fastqsanger.gz,fastqsanger.bz2</token> + <token name="@SOLEXA@">fastqsolexa,fastqsolexa.gz,fastqsolexa.bz2</token> + <token name="@ILLUMINA@">fastqillumina,fastqillumina.gz,fastqillumina.bz2</token> + <token name="@FASTQS@">@SANGER@,@SOLEXA@,@ILLUMINA@</token> + <token name="@FASTAS@">fasta,fasta.gz</token> + <xml name="citations"> + <citations> + <citation type="bibtex"> + @UNPUBLISHED{agordon, + author = "Assaf Gordon", + title = "FASTQ/A short-reads pre-processing tools", + year = "2010", + note = "http://hannonlab.cshl.edu/fastx_toolkit/", + url = "http://hannonlab.cshl.edu/fastx_toolkit/"} + </citation> + </citations> + </xml> + <xml name="fasta_input"> + <param name="input" type="data" format="@FASTAS@" label="Input FASTA file" /> + </xml> + <xml name="fastq_input"> + <param name="input" type="data" format="@FASTQS@" label="Input FASTQ file" /> + </xml> + <xml name="fastx_input"> + <param name="input" type="data" format="@FASTAS@,@FASTQS@" label="Input file in FASTA or FASTQ format" /> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/fastq_stats1.out Tue May 08 12:51:52 2018 -0400 @@ -0,0 +1,37 @@ +column count min max sum mean Q1 med Q3 IQR lW rW A_Count C_Count G_Count T_Count N_Count Max_count +1 9 23 34 288 32.00 33 33 33 0 33 33 3 1 4 1 0 9 +2 9 28 33 287 31.89 31 33 33 2 28 33 3 3 2 1 0 9 +3 9 13 34 268 29.78 28 33 33 5 21 34 5 1 0 3 0 9 +4 9 17 33 261 29.00 30 33 33 3 26 33 1 2 3 3 0 9 +5 9 22 33 269 29.89 30 33 33 3 26 33 3 3 3 0 0 9 +6 9 22 33 277 30.78 30 33 33 3 26 33 5 3 0 1 0 9 +7 9 21 33 258 28.67 24 33 33 9 21 33 4 1 3 1 0 9 +8 9 12 33 263 29.22 32 33 33 1 31 33 2 1 1 5 0 9 +9 9 29 33 290 32.22 33 33 33 0 33 33 3 3 2 1 0 9 +10 9 23 33 277 30.78 32 33 33 1 31 33 1 4 2 2 0 9 +11 9 12 33 245 27.22 21 31 33 12 12 33 5 2 1 1 0 9 +12 9 13 33 214 23.78 15 24 33 18 13 33 2 4 2 1 0 9 +13 9 5 33 249 27.67 29 31 33 4 23 33 2 1 1 5 0 9 +14 9 5 33 233 25.89 24 33 33 9 11 33 3 3 2 1 0 9 +15 9 15 33 251 27.89 24 33 33 9 15 33 5 1 1 2 0 9 +16 9 23 34 269 29.89 24 33 33 9 23 34 3 1 2 3 0 9 +17 9 13 34 266 29.56 33 33 33 0 33 33 2 3 1 3 0 9 +18 9 21 34 272 30.22 31 33 33 2 28 34 0 5 1 3 0 9 +19 9 5 34 244 27.11 27 30 33 6 18 34 4 4 1 0 0 9 +20 9 11 34 241 26.78 23 32 33 10 11 34 3 4 2 0 0 9 +21 9 13 33 240 26.67 24 27 33 9 13 33 1 4 0 4 0 9 +22 9 5 33 190 21.11 13 21 33 20 5 33 1 4 0 3 1 9 +23 9 5 33 205 22.78 16 26 33 17 5 33 4 4 1 0 0 9 +24 9 5 33 247 27.44 28 31 33 5 21 33 1 5 1 2 0 9 +25 9 11 34 241 26.78 24 33 33 9 11 34 3 4 0 2 0 9 +26 9 5 33 212 23.56 18 31 33 15 5 33 0 6 0 3 0 9 +27 9 5 33 227 25.22 21 26 33 12 5 33 3 4 1 1 0 9 +28 9 21 33 255 28.33 24 31 33 9 21 33 2 4 3 0 0 9 +29 9 5 33 228 25.33 21 30 33 12 5 33 2 4 1 2 0 9 +30 9 10 33 213 23.67 16 28 33 17 10 33 3 4 2 0 0 9 +31 9 5 33 236 26.22 21 31 33 12 5 33 1 4 1 3 0 9 +32 9 5 33 210 23.33 12 29 33 21 5 33 3 3 0 3 0 9 +33 9 5 33 183 20.33 9 21 33 24 5 33 1 4 2 2 0 9 +34 9 5 33 150 16.67 7 17 22 15 5 33 3 4 1 1 0 9 +35 9 13 33 217 24.11 21 24 29 8 13 33 1 4 1 3 0 9 +36 9 5 33 195 21.67 18 21 32 14 5 33 3 2 1 3 0 9
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/fastx_nucleotides_distribution-in1.txt Tue May 08 12:51:52 2018 -0400 @@ -0,0 +1,37 @@ +column count min max sum mean Q1 med Q3 IQR lW rW A_Count C_Count G_Count T_Count N_Count Max_count +1 9 23 34 288 32.00 33 33 33 0 33 33 3 1 4 1 0 9 +2 9 28 33 287 31.89 31 33 33 2 28 33 3 3 2 1 0 9 +3 9 13 34 268 29.78 28 33 33 5 21 34 5 1 0 3 0 9 +4 9 17 33 261 29.00 30 33 33 3 26 33 1 2 3 3 0 9 +5 9 22 33 269 29.89 30 33 33 3 26 33 3 3 3 0 0 9 +6 9 22 33 277 30.78 30 33 33 3 26 33 5 3 0 1 0 9 +7 9 21 33 258 28.67 24 33 33 9 21 33 4 1 3 1 0 9 +8 9 12 33 263 29.22 32 33 33 1 31 33 2 1 1 5 0 9 +9 9 29 33 290 32.22 33 33 33 0 33 33 3 3 2 1 0 9 +10 9 23 33 277 30.78 32 33 33 1 31 33 1 4 2 2 0 9 +11 9 12 33 245 27.22 21 31 33 12 12 33 5 2 1 1 0 9 +12 9 13 33 214 23.78 15 24 33 18 13 33 2 4 2 1 0 9 +13 9 5 33 249 27.67 29 31 33 4 23 33 2 1 1 5 0 9 +14 9 5 33 233 25.89 24 33 33 9 11 33 3 3 2 1 0 9 +15 9 15 33 251 27.89 24 33 33 9 15 33 5 1 1 2 0 9 +16 9 23 34 269 29.89 24 33 33 9 23 34 3 1 2 3 0 9 +17 9 13 34 266 29.56 33 33 33 0 33 33 2 3 1 3 0 9 +18 9 21 34 272 30.22 31 33 33 2 28 34 0 5 1 3 0 9 +19 9 5 34 244 27.11 27 30 33 6 18 34 4 4 1 0 0 9 +20 9 11 34 241 26.78 23 32 33 10 11 34 3 4 2 0 0 9 +21 9 13 33 240 26.67 24 27 33 9 13 33 1 4 0 4 0 9 +22 9 5 33 190 21.11 13 21 33 20 5 33 1 4 0 3 1 9 +23 9 5 33 205 22.78 16 26 33 17 5 33 4 4 1 0 0 9 +24 9 5 33 247 27.44 28 31 33 5 21 33 1 5 1 2 0 9 +25 9 11 34 241 26.78 24 33 33 9 11 34 3 4 0 2 0 9 +26 9 5 33 212 23.56 18 31 33 15 5 33 0 6 0 3 0 9 +27 9 5 33 227 25.22 21 26 33 12 5 33 3 4 1 1 0 9 +28 9 21 33 255 28.33 24 31 33 9 21 33 2 4 3 0 0 9 +29 9 5 33 228 25.33 21 30 33 12 5 33 2 4 1 2 0 9 +30 9 10 33 213 23.67 16 28 33 17 10 33 3 4 2 0 0 9 +31 9 5 33 236 26.22 21 31 33 12 5 33 1 4 1 3 0 9 +32 9 5 33 210 23.33 12 29 33 21 5 33 3 3 0 3 0 9 +33 9 5 33 183 20.33 9 21 33 24 5 33 1 4 2 2 0 9 +34 9 5 33 150 16.67 7 17 22 15 5 33 3 4 1 1 0 9 +35 9 13 33 217 24.11 21 24 29 8 13 33 1 4 1 3 0 9 +36 9 5 33 195 21.67 18 21 32 14 5 33 3 2 1 3 0 9
--- a/tool_dependencies.xml Tue Jun 03 15:07:52 2014 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,6 +0,0 @@ -<?xml version="1.0"?> -<tool_dependency> - <package name="fastx_toolkit" version="0.0.13"> - <repository changeset_revision="1cd326991d32" name="package_fastx_toolkit_0_0_13" owner="devteam" toolshed="http://testtoolshed.g2.bx.psu.edu" /> - </package> -</tool_dependency>