Mercurial > repos > computational-metabolomics > dimspy_align_samples

comparison align_samples.xml @ 0:49d20b18fc6a draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 80069808371b58f45da0c8133c27d67ac1a5b448"
author computational-metabolomics
date Wed, 17 Feb 2021 10:51:22 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:49d20b18fc6a
1 <tool id="dimspy_align_samples" name="Align Samples" version="@TOOL_VERSION@+galaxy1">
2 <description> - Align peaks across Peaklists</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements" />
7 <command detect_errors="exit_code">
8 <![CDATA[
9 dimspy align-samples
10 --input '$hdf5_file_in'
11 --output '$hdf5_file_out'
12 #if $filelist
13 --filelist '$filelist'
14 #end if
15 --ppm $ppm
16 --ncpu \${GALAXY_SLOTS:-1}
17 --block-size $adv.block_size
18 #if $hdf5_to_txt.standard
19 &&
20 @HDF5_PM_TO_TXT@
21 #end if
22 #if $hdf5_to_txt.comprehensive
23 &&
24 @HDF5_PM_TO_TXT_COMPREHENSIVE@
25 #end if
26 ]]>
27 </command>
28 <inputs>
29 <param name="hdf5_file_in" argument="--input" type="data" format="h5" label="Peaklists (HDF5 file)" help="" />
30 <param name="filelist" argument="--filelist" type="data" format="tsv,tabular" optional="true" label="Filelist / Samplelist" help="Only provide a filelist if you like to exclude Peaklists, update the metadata (e.g. classLabel), or if you have not provided a filelist for Process Scans or Replicate Filter." />
31 <param name="ppm" argument="--ppm" type="float" value="2.0" label="Ppm error tolerance" help="Maximum tolerated m/z deviation across samples in parts per million (ppm)." />
32 <param name="delimiter" argument="--delimiter" type="hidden" value="tab" />
33 <expand macro="hdf5_pm_to_txt" />
34 <section name="adv" title="Advanced options" expanded="False">
35 <param name="block_size" argument="--block-size" type="integer" value="5000" label="Block size" help="The size of each block of peaks to perform clustering on." />
36 </section>
37 </inputs>
38 <outputs>
39 <expand macro="outputs_peak_intensity_matrix" />
40 </outputs>
41 <tests>
42 <test>
43 <param name="hdf5_file_in" value="pls_rf.h5" ftype="h5"/>
44 <param name="ppm" value="2.0"/>
45 <param name="delimiter" value="tab"/>
46 <conditional name="hdf5_to_txt" >
47 <param name="standard" value="True"/>
48 <param name="comprehensive" value="False"/>
49 <param name="samples_representations" value="rows"/>
50 <param name="matrix_attr" value="intensity"/>
51 </conditional>
52 <output name="hdf5_file_out" file="pm_as.h5" ftype="h5" compare="sim_size"/>
53 <output name="matrix_file_out" file="peak_matrix_as.txt" ftype="tsv"/>
54 </test>
55 <test>
56 <param name="hdf5_file_in" value="pls_rf.h5" ftype="h5"/>
57 <param name="ppm" value="2.0"/>
58 <param name="delimiter" value="tab"/>
59 <conditional name="hdf5_to_txt" >
60 <param name="standard" value="True"/>
61 <param name="comprehensive" value="False"/>
62 <param name="samples_representations" value="rows"/>
63 <param name="matrix_attr" value="intensity"/>
64 </conditional>
65 <section name="adv">
66 <param name="block_size" value="10000"/>
67 </section>
68 <output name="hdf5_file_out" file="pm_as.h5" ftype="h5" compare="sim_size"/>
69 <output name="matrix_file_out" file="peak_matrix_as.txt" ftype="tsv"/>
70 </test>
71 <test>
72 <param name="hdf5_file_in" value="pls_rf.h5" ftype="h5"/>
73 <param name="ppm" value="2.0"/>
74 <param name="delimiter" value="tab"/>
75 <conditional name="hdf5_to_txt">
76 <param name="standard" value="True"/>
77 <param name="comprehensive" value="False"/>
78 <param name="representation_samples" value="columns"/>
79 <param name="matrix_attr" value="intensity"/>
80 </conditional>
81 <output name="hdf5_file_out" file="pm_as.h5" ftype="h5" compare="sim_size"/>
82 <output name="matrix_file_out" file="peak_matrix_as_t.txt" ftype="tsv"/>
83 </test>
84 <test>
85 <param name="hdf5_file_in" value="pls_rf.h5" ftype="h5"/>
86 <param name="ppm" value="2.0"/>
87 <param name="delimiter" value="tab"/>
88 <conditional name="hdf5_to_txt">
89 <param name="standard" value="True"/>
90 <param name="comprehensive" value="True"/>
91 <param name="samples_representations" value="rows"/>
92 <param name="matrix_attr" value="mz"/>
93 </conditional>
94 <output name="hdf5_file_out" file="pm_as.h5" ftype="h5" compare="sim_size"/>
95 <output name="matrix_file_out" file="peak_matrix_as_mz.txt" ftype="tsv"/>
96 <output name="matrix_comprehensive_file_out" file="peak_matrix_as_mz_compr.txt" ftype="tsv"/>
97 </test>
98 </tests>
99 <help>
100 -------------
101 Align Samples
102 -------------
103
104 ..
105
106 -------------------------------
107
108 Description
109 -----------
110
111 Standard DIMS processing workflow: Process Scans -> [Replicate Filter] -> **Align Samples** -> Blank Filter -> Sample Filter -> [Missing values sample filter] -> Pre-processing -> Statistics
112
113 |
114
115 This tool takes the peaklists for all study samples and merges them in to single aligned peak matrix. The peak matrix comprises a table, with samples along one axis and the mass-to-charge ratios of detected mass spectral peaks along the opposite axis. At the intersection of sample and mass-to-charge ratio, the intensity is given for a specific peak in a specific sample (if no intensity recorded, then ‘0’ is inserted).
116
117 -------------------------------
118
119 Parameters
120 ----------
121
122 **Peaklists (HDF5 file)** (REQUIRED) - a HDF5 file containing all peaklists to undergo alignment.
123
124 |
125
126 **Filelist / Samplelist** (REQUIRED) - a file of type ‘tabular’ with the following required columns (additional metadata columns may also be included, e.g. “collectionTime”, etc.):
127
128 - **filename** - the name of the .raw or .mzML files from which peaklists were extracted using the “Process Scans” tool
129
130 - **batch** - a numeric value indicating the analysis batches samples were analysed in (if a single large analytica run then the default = 1)
131
132 - **classLabel** - a string indicating the experiment classes the samples belong to (e.g. control, QC, blank/placebo, exposed/treatment)
133
134 - **injectionOrder** - a numeric value indicating the order in which samples were analysed.
135
136 |
137
138 **ppm error tolerance** (REQUIRED; default = 2.0) - a numeric value equal-to or greater-than 0.
139
140 This parameter will influence the alignment of peaks from input peaklists. Peaks from distinct peaklists (corresponding to individual study samples) are aligned if the difference between their mass-to-charge ratios, when divided by the average of their mass-to-charge ratios and multiplied by 1 × 10\ :sup:`6` \, is equal-to or less-than than this parameter value (i.e. the difference between the mass-to-charge ratios, measured on the ppm scale, is less than the user-defined “ppm error tolerance”).
141
142 |
143
144 @help_options_addtional_output@
145
146 |
147
148 ------------------------------
149
150 Output file(s)
151 --------------
152
153 @help_outputs_matrix@
154
155 -------------------------------------------------------------
156
157 @github_developers_contributors@
158 @license@
159 </help>
160 <expand macro="citations" />
161 </tool>