Mercurial > repos > iuc > slamdunk

comparison slamdunk.xml @ 0:3fd7458bc861 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/slamdunk commit 1edb9bd1936e05d6a9ade3cde93b970fa89acb90
author iuc
date Thu, 11 Oct 2018 20:33:07 -0400
parents
children 57bf9a0d49a5
comparison
equal deleted inserted replaced
-1:000000000000 0:3fd7458bc861
1 <tool id="slamdunk" name="Slamdunk" version="0.3.3">
2 <description>- streamlining SLAM-seq analysis with ultra-high sensitivity</description>
3 <requirements>
4 <requirement type="package" version="0.3.3">slamdunk</requirement>
5 </requirements>
6 <version_command>slamdunk --version</version_command>
7 <command detect_errors="exit_code"><![CDATA[
8 #if $reference_source.reference_source_selector == 'history':
9 ln -f -s '$reference_source.ref_file' reference.fa &&
10 #else:
11 ln -f -s '$reference_source.ref_file.fields.path' reference.fa &&
12 #end if
13 slamdunk all -r reference.fa -b '$Reference' -o ./out
14 -n $multimapper.multimappers
15 $multimapper.multimap
16 #if $multimapper.filterbed.bedtofilter:
17 -fb $multimapper.filterbed.bedtofilter
18 #end if
19 -5 $quantseq.trim5
20 -a $quantseq.maxpolyA
21 $advanced.endtoend
22 -mq $advanced.minMQ
23 -mi $advanced.minID
24 -nm=$advanced.maxNM
25 -mc $advanced.minCov
26 -mv $advanced.minVar
27 -mbq $advanced.minBaseQual
28 -rl $readLength
29 -c $covThresh
30 '$Reads'
31 ]]></command>
32 <inputs>
33 <conditional name="reference_source">
34 <param name="reference_source_selector" type="select" label="Genome" help="Select a built-in FASTA file (if available) or one from the history">
35 <option value="cached">Use a built-in FASTA</option>
36 <option value="history">Use a FASTA from history</option>
37 </param>
38 <when value="cached">
39 <param name="ref_file" type="select" label="Use built-in FASTA" help="Select genome from the list">
40 <options from_data_table="all_fasta">
41 <filter type="sort_by" column="2" />
42 <validator type="no_options" message="No reference genomes are available" />
43 </options>
44 <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
45 </param>
46 </when>
47 <when value="history">
48 <param name="ref_file" type="data" format="fasta" label="Use the following dataset as the FASTA" help="You can upload a FASTA sequence to the history and use it as reference" />
49 </when>
50 </conditional>
51 <param name="Reference" type="data" format="bed" />
52 <param name="Reads" type="data" format="fastqsanger,fastqsanger.gz" />
53 <section name="multimapper" title="Multimapper recovery"
54 expanded="false">
55 <section name="filterbed"
56 title="Use separate 3' UTR bed to filter multimappers." expanded="false">
57 <param name="bedtofilter" type="data" format="bed" optional="true"
58 label="Bed to filter" />
59 </section>
60 <param name="multimappers" type="integer" min="1" value="1"
61 label="Maximum number of alignments to report per read"
62 help="The maximum number of alignments is used to track multimapping read alignments. The more are allowed, the more sensitive the multimapper filtering will be, but also the longer the runtime will be. 100 was used in previous publications." />
63 <param name="multimap" type="boolean" truevalue="--multimap" falsevalue=""
64 label="Use reference bed file to resolve multimappers."
65 help="Enable multimapper recovery, requires -n to be set to a value > 1 to have impact." />
66 </section>
67 <section name="quantseq" title="Quantseq" expanded="false">
68 <param name="trim5" type="integer" min="0" value="12"
69 label="Number of bp to remove from the 5' end of all reads"
70 help="For Lexogen's Quantseq kit and previous SLAM-seq papers a clipping of 12 bp from the 5' end is recommended." />
71 <param name="maxpolyA" type="integer" min="0" value="4"
72 label="Maximum number of As at the 3' end of a read"
73 help="The maximum number of allowed As at the 3' end of a read. All A-stretches that exceed this threshold are clipped because they are likely part of the poly-A tail." />
74 </section>
75 <section name="advanced" title="Advanced settings." expanded="false">
76 <param name="endtoend" type="boolean" truevalue="--endtoend" falsevalue=""
77 label="Enable end-to-end alignments for mapping."
78 help="Enable end-to-end alignments for mapping in slamdunk with --endtoend" />
79 <param name="minMQ" type="integer" min="0" value="2"
80 label="Minimum mapping quality"
81 help="Minimum mapping quality to consider alignments (default: 2)." />
82 <param name="minMQ" type="integer" label="Minimum mapping quality" min="0" value="2"
83 help="Minimum mapping quality to consider alignments (default: 2)." />
84 <param name="minID" type="float" min="0" value="0.95"
85 label="Minimum alignment identity"
86 help="Minimum alignment-identity to consider alignments (default: 0.95)." />
87 <param name="maxNM" type="integer" value="-1"
88 label="Maximum number of mismatches"
89 help="Maximum number of mismatches to consider alignments. Negative numbers deactivate filter (default: -1)." />
90 <param name="minCov" type="integer" min="0" value="10"
91 label="Minimum coverage to call variant"
92 help="Minimum coverage to call variant (default: 10)." />
93 <param name="minVar" type="float" min="0" value="0.8"
94 label="Minimum variant fraction to call variant"
95 help="Minimum variant fraction to call variant (default: 0.8)." />
96 <param name="minBaseQual" type="integer" min="0" value="27"
97 label="Minimum base quality"
98 help="Minimum base quality for T>C conversions (default: 27)." />
99 </section>
100 <param name="covThresh" type="integer" min="1" value="1"
101 label="T>C conversion threshold"
102 help="Number of T>C conversions required to count a read as a T>C read (default: 1)." />
103 <param name="readLength" type="integer" min="50" value="50"
104 label="Read length"
105 help="Maximum read length (before trimming)." />
106 </inputs>
107 <outputs>
108 <data name="outputBam" format="bam" from_work_dir="./out/filter/*.bam" />
109 <data name="outputTsv" format="tabular" from_work_dir="./out/count/*_tcount.tsv" />
110 </outputs>
111 <tests>
112 <test>
113 <param name="reference_source_selector" value="history" />
114 <param name="ref_file" value="ref.fa" />
115 <param name="Reference" value="actb.bed" />
116 <param name="Reads" value="reads.fq" />
117 <param name="readLength" value="100" />
118 <section name="quantseq">
119 <param name="trim5" value="0" />
120 </section>
121 <section name="advanced">
122 <param name="minBaseQual" value="27" />
123 </section>
124 <output name="outputTsv" file="reads_slamdunk_mapped_filtered_tcount.tsv"
125 lines_diff="2" />
126 </test>
127 <test>
128 <!-- test built-in fasta -->
129 <param name="reference_source_selector" value="cached" />
130 <param name="Reference" value="actb.bed" />
131 <param name="Reads" ftype="fastqsanger" dbkey="hg38" value="reads.fq" />
132 <param name="readLength" value="100" />
133 <section name="quantseq">
134 <param name="trim5" value="0" />
135 </section>
136 <section name="advanced">
137 <param name="minBaseQual" value="27" />
138 </section>
139 <output name="outputTsv" file="reads_slamdunk_mapped_filtered_tcount.tsv"
140 lines_diff="2" />
141 </test>
142 </tests>
143 <help><![CDATA[
144 SLAM-seq
145 ========
146
147 SLAM-seq is a novel sequencing protocol that directly uncovers 4-thiouridine incorporation events in RNA by high-throughput sequencing. When combined with metabolic labeling protocols, SLAM-seq allows to study the intracellular RNA dynamics, from transcription, RNA processing to RNA stability.
148
149 Original publication: `Herzog et al., Nature Methods, 2017; doi:10.1038/nmeth.4435 <https://www.nature.com/nmeth/journal/vaop/ncurrent/full/nmeth.4435.html>`_
150
151 Slamdunk
152 ========
153
154 To analyze a given SLAM-seq dataset with *slamdunk* without recovering multimappers, you only need to provide the following files and keep everything else to the default parameters.
155
156 =============== ==========================================================================================================================================================
157 Parameter Description
158 =============== ==========================================================================================================================================================
159 **Genome** The reference fasta file (Genome assembly).
160 **Reference** BED-file containing coordinates for 3' UTRs.
161 **Reads** Sample FASTQ(gz) files.
162 **Read length** Maximum length of reads (usually 50, 100, 150).
163 =============== ==========================================================================================================================================================
164
165 This will run the entire *slamdunk* analysis with the most relevant output files being:
166
167 * Tab-separated *tcount* file containing the SLAM-seq statistics per UTR
168 * BAM-file with the final mapped reads for visualization and further processing
169
170 ------------------------------------------------------
171
172 Multimapper recovery
173 --------------------
174
175 To utilize multimapper recovery, modify the following parameters. You must either choose a separate 3' UTR file or activate filtering
176 on the supplied reference file. Will only yield different results than a unique-mapping run by specifying a number > 1 as maximum number of multimapper aligments to consider.
177
178 =================================================== =========================================================
179 Parameter Description
180 =================================================== =========================================================
181 **Maximum number of alignments to report per read** The maximum number of multimapper alignments to consider.
182 **Use separate 3' UTR bed to filter multimappers.** 3' UTR bed file to filter.
183 **Use reference bed file to resolve multimappers.** Use reference as 3' UTR bed file to filter.
184 =================================================== =========================================================
185
186 ------------------------------------------------------
187
188 T>C conversions
189 ---------------
190
191 Depending on the use case, more stringent or more lenient measures of T>C conversion and T>C reads are required such as 2 T>C by `Muhar et al., Science, 2018; http://doi.org/10.1126/science.aao2793 <http://science.sciencemag.org/content/early/2018/04/04/science.aao2793>`_
192
193 This can be controlled by the following parameter:
194
195 ============================ ================================================================================
196 Parameter Description
197 ============================ ================================================================================
198 **T>C conversion threshold** Minimum number of T>C conversions to consider a read as T>C read.
199 ============================ ================================================================================
200
201
202 ]]></help>
203 <citations>
204 <citation type="bibtex">
205 @misc{Neumann2018,
206 author = {Neumann, Tobias},
207 year = {2018},
208 title = Slamdunk},
209 publisher = {GitHub},
210 journal = {GitHub repository},
211 url = {https://github.com/t-neumann/slamdunk},
212 }
213 </citation>
214 </citations>
215 </tool>