comparison tetyper.xml @ 0:8bc80c2a15b3 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/tetyper commit ee0a9acc788f8c313bb9fd91a42c6f9c66ac5bef"
author iuc
date Thu, 28 Nov 2019 14:41:08 -0500
parents
children 36093854bfc7
comparison
equal deleted inserted replaced
-1:000000000000 0:8bc80c2a15b3
1 <tool id="tetyper" name="TETyper" version="@TOOL_VERSION@+galaxy0">
2 <description>Transposable Element Typer</description>
3 <macros>
4 <token name="@TOOL_VERSION@">1.1</token>
5 </macros>
6 <requirements>
7 <requirement type="package" version="@TOOL_VERSION@">tetyper</requirement>
8 </requirements>
9 <command detect_errors="exit_code">
10 <![CDATA[
11 TETyper.py
12 --threads \${GALAXY_SLOTS:-1}
13 #if $collection_paired.selector == "paired"
14 --fq1 '${collection_paired.forward_input}' --fq2 '${collection_paired.reverse_input}'
15 #elif $collection_paired.selector == "collection":
16 --fq1 '${collection_paired.input_pair.forward}' --fq2 '${collection_paired.input_pair.reverse}'
17 #end if
18 --ref '${reference}'
19 --flank_len '${flank_length}'
20 --min_reads '${min_reads}'
21 --min_each_strand '${min_each_strand}'
22 --min_mapped_len '${min_mapped_len}'
23 --min_qual '${min_qual}'
24 #if $snp_profiles
25 --snp_profiles '${snp_profiles}'
26 #end if
27 #if $struct_profiles
28 --struct_profiles '${struct_profiles}'
29 #end if
30 --outprefix output
31 ]]>
32 </command>
33 <inputs>
34 <conditional name="collection_paired">
35 <param name="selector" type="select" label="Collection or paired reads" >
36 <option value="collection">Collection</option>
37 <option value="paired" selected="True">Paired</option>
38 </param>
39 <when value="collection">
40 <param format="fastq,fastq.gz" name="input_pair" type="data_collection" collection_type="paired" label="Collection of paired reads" help="FASTQ datasets" />
41 </when>
42 <when value="paired">
43 <param format="fastq,fastq.gz" name="forward_input" type="data" label="Forward strand" help="FASTQ dataset"/>
44 <param format="fastq,fastq.gz" name="reverse_input" type="data" label="Reverse strand" help="FASTQ dataset"/>
45 </when>
46 </conditional>
47 <param name="reference" type="data" format="fasta" label="Transposable Element Reference"/>
48 <param name="flank_length" type="integer" min="4" value="5" max="16" label="Flank Length" help="Length of flanking region to extract."/>
49 <param name="min_reads" type="integer" min="1" value="10" max="100" label="Minimum Reads" help="Minimum read number for including a specific flanking sequence."/>
50 <param name="min_each_strand" type="integer" min="1" value="1" max="100" label="Minimum Reads (each strand)" help="Minimum read number for each strand for including a specific flanking sequence."/>
51 <param name="min_mapped_len" type="integer" min="8" value="30" max="100" label="Minimum Mapped Length" help="Minimum length of mapping for a read to be used in determining flanking sequences. Higher values are more robust to spurious mapping. Lower values will recover more reads."/>
52 <param name="min_qual" type="integer" min="0" value="10" max="100" label="Minimum quality" help="Minimum quality value across extracted flanking sequence." />
53 <param name="snp_profiles" type="data" format="text" label="SNP Profiles" optional="true" />
54 <param name="struct_profiles" type="data" format="text" label="Structural Variant Profiles" optional="true" />
55 <param name="include_log" type="boolean" label="Include log in output"/>
56 </inputs>
57 <outputs>
58 <data name="summary" format="tabular" from_work_dir="output_summary.txt" label="${tool.name} on ${on_string}: summary"/>
59 <data name="snps" format="vcf" from_work_dir="output.vcf" label="${tool.name} on ${on_string}: SNPs"/>
60 <data name="blast" format="tabular" from_work_dir="output_blast.txt" label="${tool.name} on ${on_string}: BLAST alignment"/>
61 <data name="alignment" format="bam" from_work_dir="output.bam" label="${tool.name} on ${on_string}: BWA alignment"/>
62 <data name="log" format="text" from_work_dir="output.log" label="${tool.name} on ${on_string}: log">
63 <filter>include_log</filter>
64 </data>
65 </outputs>
66 <tests>
67 <test>
68 <param name="reference" value="Tn4401b-1.fasta" />
69 <conditional name="collection_paired">
70 <param name="selector" value="paired" />
71 <param name="forward_input" value="ERR1911133_Tn4401b-1_mapped_subsampled_1.fastq" />
72 <param name="reverse_input" value="ERR1911133_Tn4401b-1_mapped_subsampled_2.fastq" />
73 </conditional>
74 <output name="summary" file="output_summary_1.txt" />
75 </test>
76 <test>
77 <param name="reference" value="Tn4401b-1.fasta" />
78 <conditional name="collection_paired">
79 <param name="selector" value="paired" />
80 <param name="forward_input" value="ERR1911133_Tn4401b-1_mapped_subsampled_1.fastq" />
81 <param name="reverse_input" value="ERR1911133_Tn4401b-1_mapped_subsampled_2.fastq" />
82 </conditional>
83 <param name="snp_profiles" value="Tn4401b_snp_profiles.txt" />
84 <param name="struct_profiles" value="Tn4401b_struct_profiles.txt" />
85 <output name="summary" file="output_summary_2.txt" />
86 </test>
87 </tests>
88 <help>
89 <![CDATA[
90 **What it does**
91
92 TETyper is designed for typing a specific transposable element (TE) of interest from paired-end sequencing data. It determines single nucleotide variants (SNVs) and deletions within the TE, as well as flanking sequences surrounding the TE.
93
94 **Input**
95
96 **SNP Profiles**: A tab-delimited file with the following columns:
97
98 1. Profile ID
99 2. Homozygous SNPs
100 3. Heterozygous SNPs
101
102 SNPs are represented in the format [REF][POSITION][ALT], and separated by pipe (`|`) characters. SNPs should be ordered by position. Valid alt-bases for heterozygous SNPs are: `M,R,W,S,Y,K`
103
104 For example:
105
106 ::
107
108 1 none none
109 2 C8015T none
110 3 C8015T|T9621C none
111 4 T7199A|C8015T|T9621C none
112 6 C7509G|T7917G none
113 N2 none C8015Y
114 N4 none A5178R
115 N5 none C8015Y|T9663Y
116
117 **Structural Variant Profiles**: A tab-delimited file with the following columns:
118
119 1. Profile ID
120 2. Structural Variants
121
122 Structural Variants are represented in the format [START-POSITION]-[END-POSITION], and separated by pipe (`|`) characters.
123
124 For example:
125
126 ::
127
128 Tn4401b none
129 Tn4401a 7020-7118
130 Tn4401h 6919-7106
131 Tn4401_truncC 1-7127|9198-10006
132
133 **Output**
134
135 TETyper will produce a tab-seperated output file with the following outputs:
136
137 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
138 | Column | Description |
139 +==========================+==================================================================================================================================================================================================================================================+
140 | Deletions | A list of sequence ranges corresponding to regions of the reference classified as deletions for this sample, or "none" for no deletions. |
141 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
142 | Structural_variant | If --struct_profiles is specified and the pattern of deletions above corresponds to one of these profiles, then the profile name is given, otherwise "unknown". |
143 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
144 | SNPs_homozygous | A list of homozygous SNPs identified, or "none". |
145 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
146 | SNPs_heterozygous | A list of heterozygous SNPs identified, or "none". |
147 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
148 | Heterozygous_SNP_counts | For each heterozygous SNP, the number of reads supporting the reference and alternative calls, or "none" if there are no heterozygous SNPs. |
149 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
150 | SNP_variant | If --snp_profiles is specified and the pattern of homozygous and heterozygous SNPs corresponds to one of these profiles, then the profile name is given. Otherwise "unknown". |
151 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
152 | Combined_variant | Single name combining Structural_variant and SNP_variant, separated by "-". |
153 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
154 | Left_flanks | A list of distinct sequences passing quality filters that flank the start position of the reference. |
155 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
156 | Right_flanks | A list of distinct sequences passing quality filters that flank the end position of the reference. |
157 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
158 | Left_flank_counts | The number of high quality reads supporting each of the left flanking sequences. |
159 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
160 | Right_flank_counts | The number of high quality reads supporting each of the right flanking sequences. |
161 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
162 | X_Y_presence | If --show_region is specified as --show_region X-Y, this column shows 1 if the entirety of that region is classified as present (i.e. no overlap with deleted regions), or 0 otherwise. If --show_region is unspecified, this column is omitted. |
163 +--------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
164
165 ]]>
166 </help>
167 <citations>
168 <citation type="doi">10.1099/mgen.0.000232</citation>
169 </citations>
170 </tool>