Mercurial > repos > greg > vsnp_statistics
annotate vsnp_statistics.xml @ 17:932e517b5779 draft
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit fbfaeaa4485ee7e3da86ecf2e95067c915d12aa9"
| author | greg |
|---|---|
| date | Tue, 03 Aug 2021 19:52:56 +0000 |
| parents | 44b07199be73 |
| children | 076069733de7 |
| rev | line source |
|---|---|
| 16 | 1 <tool id="vsnp_statistics" name="vSNP: statistics" version="@WRAPPER_VERSION@.2+galaxy0" profile="@PROFILE@"> |
| 0 | 2 <description></description> |
| 4 | 3 <macros> |
| 4 <import>macros.xml</import> | |
| 5 </macros> | |
| 0 | 6 <requirements> |
| 8 | 7 <expand macro="biopython_requirement"/> |
| 8 <expand macro="numpy_requirement"/> | |
| 9 <expand macro="openpyxl_requirement"/> | |
| 10 <expand macro="pandas_requirement"/> | |
| 11 <expand macro="xlrd_requirement"/> | |
| 0 | 12 </requirements> |
| 13 <command detect_errors="exit_code"><![CDATA[ | |
| 14 #import re | |
| 4 | 15 |
| 8 | 16 #if $input_type_cond.input_type in ["single", "pair"]: |
| 17 #set read1 = $input_type_cond.read1 | |
| 0 | 18 #set read1_identifier = re.sub('[^\s\w\-]', '_', str($read1.element_identifier)) |
| 4 | 19 ln -s '${read1}' '${read1_identifier}' && |
| 8 | 20 #if $input_type_cond.input_type == "pair": |
| 21 #set read2 = $input_type_cond.read2 | |
| 4 | 22 #set read2_identifier = re.sub('[^\s\w\-]', '_', str($read2.element_identifier)) |
| 23 ln -s '${read2}' '${read2_identifier}' && | |
| 0 | 24 #end if |
| 25 #else: | |
| 16 | 26 #set read1 = $input_type_cond.reads_collection.forward |
| 14 | 27 #set read1_identifier = re.sub('[^\s\w\-]', '_', str($read1.element_identifier)) |
| 8 | 28 ln -s '${read1}' '${read1_identifier}' && |
| 16 | 29 #set read2 = $input_type_cond.reads_collection.reverse |
| 14 | 30 #set read2_identifier = re.sub('[^\s\w\-]', '_', str($read2.element_identifier)) |
| 8 | 31 ln -s '${read2}' '${read2_identifier}' && |
| 0 | 32 #end if |
| 4 | 33 |
| 0 | 34 python '$__tool_directory__/vsnp_statistics.py' |
| 8 | 35 --read1 '${read1_identifier}' |
| 16 | 36 #if $input_type_cond.input_type in ["pair", "paired"]: |
| 8 | 37 --read2 '${read2_identifier}' |
| 0 | 38 #end if |
| 8 | 39 #if $read1.is_of_type('fastqsanger.gz'): |
| 40 --gzipped | |
| 41 #end if | |
| 42 --dbkey '$samtools_idxstats.metadata.dbkey' | |
| 43 --samtools_idxstats '$samtools_idxstats' | |
| 44 --vsnp_azc_metrics '$vsnp_azc_metrics' | |
| 1 | 45 --output '$output' |
| 0 | 46 ]]></command> |
| 47 <inputs> | |
| 48 <conditional name="input_type_cond"> | |
| 49 <param name="input_type" type="select" label="Choose the category of the files to be analyzed"> | |
| 8 | 50 <option value="single" selected="true">Single files</option> |
| 51 <option value="paired">Paired reads</option> | |
| 52 <option value="pair">Paired reads in separate data sets</option> | |
| 0 | 53 </param> |
| 8 | 54 <when value="single"> |
| 55 <param name="read1" type="data" format="fastqsanger.gz,fastqsanger" label="Read1 fastq file"/> | |
| 4 | 56 </when> |
| 8 | 57 <when value="paired"> |
| 58 <param name="reads_collection" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="paired" label="Collection of fastqsanger paired read files"/> | |
| 59 </when> | |
| 60 <when value="pair"> | |
| 61 <param name="read1" type="data" format="fastqsanger.gz,fastqsanger" label="Read1 fastq file"/> | |
| 62 <param name="read2" type="data" format="fastqsanger.gz,fastqsanger" label="Read2 fastq file"/> | |
| 0 | 63 </when> |
| 64 </conditional> | |
| 8 | 65 <param name="samtools_idxstats" type="data" format="tabular" label="Samtools idxstats file"/> |
| 66 <param name="vsnp_azc_metrics" type="data" format="tabular" label="vSNP: add zero coverage metrics file"/> | |
| 0 | 67 </inputs> |
| 68 <outputs> | |
|
5
d0fbdeaaa488
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents:
4
diff
changeset
|
69 <data name="output" format="tabular"/> |
| 0 | 70 </outputs> |
| 71 <tests> | |
| 4 | 72 <!-- A single fastq file --> |
| 73 <test expect_num_outputs="1"> | |
| 8 | 74 <param name="input_type" value="single"/> |
| 4 | 75 <param name="read1" value="Mcap_Deer_DE_SRR650221.fastq.gz" ftype="fastqsanger.gz" dbkey="89"/> |
| 76 <param name="samtools_idxstats" value="samtools_idxstats1.tabular" ftype="tabular" dbkey="89"/> | |
| 8 | 77 <param name="vsnp_azc_metrics" value="add_zc_metrics1.tabular" ftype="tabular" dbkey="89"/> |
|
5
d0fbdeaaa488
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents:
4
diff
changeset
|
78 <output name="output" file="vsnp_statistics1.tabular" ftype="tabular"/> |
| 4 | 79 </test> |
| 80 <!-- A set of paired fastq files --> | |
| 81 <test expect_num_outputs="1"> | |
| 8 | 82 <param name="input_type" value="pair"/> |
| 0 | 83 <param name="read1" value="13-1941-6_S4_L001_R1_600000.fastq.gz" ftype="fastqsanger.gz" dbkey="89"/> |
| 84 <param name="read2" value="13-1941-6_S4_L001_R2_600000.fastq.gz" ftype="fastqsanger.gz" dbkey="89"/> | |
| 4 | 85 <param name="samtools_idxstats" value="samtools_idxstats2.tabular" ftype="tabular" dbkey="89"/> |
| 8 | 86 <param name="vsnp_azc_metrics" value="add_zc_metrics2.tabular" ftype="tabular" dbkey="89"/> |
|
5
d0fbdeaaa488
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents:
4
diff
changeset
|
87 <output name="output" file="vsnp_statistics2.tabular" ftype="tabular"/> |
| 4 | 88 </test> |
| 8 | 89 <!-- A collection of paired fastq files --> |
| 4 | 90 <test expect_num_outputs="1"> |
| 8 | 91 <param name="input_type" value="paired"/> |
| 4 | 92 <param name="reads_collection"> |
| 93 <collection type="paired"> | |
| 94 <element name="forward" value="13-1941-6_S4_L001_R1_600000.fastq.gz" ftype="fastqsanger.gz"/> | |
| 95 <element name="reverse" value="13-1941-6_S4_L001_R2_600000.fastq.gz" ftype="fastqsanger.gz"/> | |
| 96 </collection> | |
| 97 </param> | |
| 8 | 98 <param name="samtools_idxstats" value="samtools_idxstats5.tabular" ftype="tabular" dbkey="89"/> |
| 99 <param name="vsnp_azc_metrics" value="add_zc_metrics5.tabular" ftype="tabular" dbkey="89"/> | |
|
5
d0fbdeaaa488
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents:
4
diff
changeset
|
100 <output name="output" file="vsnp_statistics4.tabular" ftype="tabular"/> |
| 0 | 101 </test> |
| 102 </tests> | |
| 103 <help> | |
| 104 **What it does** | |
| 105 | |
| 4 | 106 Accepts associated fastq files, SAMtools idxstats files and **vSNP: add zero coverage** metrics files and extracts information from them |
| 8 | 107 to produce an Excel spreadsheet containing statistics for each sample. The samples can be a single read, a single set of paired reads in |
| 108 separate datasets or collection of paired reads. The output statistics include reference, file size, mean read length, mean read quality, | |
| 4 | 109 reads passing Q30, total reads, all mapped reads, unmapped reads, unmapped reads percentage of total, reference with coverage, average depth |
| 110 of coverage and good SNP count. | |
| 0 | 111 </help> |
| 4 | 112 <expand macro="citations"/> |
| 0 | 113 </tool> |
| 114 |