comparison frag4feature.xml @ 0:ab65999a5430 draft

"planemo upload for repository https://github.com/computational-metabolomics/mspurity-galaxy commit cb903cd93f9378cfb5eeb68512a54178dcea7bbc-dirty"
author computational-metabolomics
date Wed, 27 Nov 2019 14:23:10 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:ab65999a5430
1 <tool id="mspurity_frag4feature" name="msPurity.frag4feature" version="@TOOL_VERSION@+galaxy@GALAXY_TOOL_VERSION@">
2 <description>
3 Assign fragmentation spectra to XCMS features using msPurity
4 </description>
5 <macros>
6 <import>macros.xml</import>
7 </macros>
8 <expand macro="requirements"/>
9 <command detect_errors="exit_code"><![CDATA[
10 Rscript '$__tool_directory__/frag4feature.R'
11 --out_dir=.
12 --xset='$xset'
13 --pa='$pa'
14 --cores=\${GALAXY_SLOTS:-4}
15 #if $file_load_conditional.file_load_select=="yes"
16 --mzML_files='
17 #for $i in $file_load_conditional.input
18 $i,
19 #end for
20 '
21 --galaxy_names='
22 #for $i in $file_load_conditional.input
23 $i.name,
24 #end for
25 '
26 #end if
27 #if $useGroup
28 --useGroup
29 #end if
30
31 --ppm=$ppm
32 --plim=$plim
33 #if $intense
34 --intense
35 #end if
36 #if $convert2RawRT
37 --convert2RawRT
38 #end if
39
40
41 ]]></command>
42 <inputs>
43
44 <param argument="--xset" type="data" label="xcmsSet object"
45 help="grouped xcmsSet object saved as 'xset' in an RData file"
46 format="rdata.xcms.raw,rdata.xcms.group,rdata.xcms.retcor,rdata.xcms.fillpeaks,rdata.camera.quick,rdata.camera.positive,rdata.camera.negative,rdata"/>
47 <param argument="--pa" type="data" label="purityA object" format="rdata"
48 help="purityA object generated from msPurity_purityA.
49 Contains details of fragmentation spectra and precursor ion purity results
50 (output from purityA tool)"/>
51 <param argument="--ppm" type="float" value="10"
52 label="ppm error tolerance between precursor mz and XCMS feature mz"
53 help="Fragmentation will be ignored if the precursor mz value is not within
54 the ppm error tolerance to the XCMS feature mz"/>
55 <param argument="--plim" type="float" label="Precursor ion purity threshold"
56 value="0" max="1" min="0"
57 help="Fragmentation will be ignore if the precursor ion purity is less than the
58 threshold (further filtering on the precursor ion purity can be done at the averaging
59 stage if required)."/>
60 <param argument="--intense" type="boolean" checked="true"
61 label="Should the most intense precursor be used within the isolation window?"
62 help="If TRUE the most intense precursor will be used. If FALSE the precursor
63 closest to the center of the isolation window will be used"/>
64 <param argument="--convert2RawRT" type="boolean" checked="false"
65 label="Was retention time correction used?"
66 help="If retention time correction has been used in XCMS set this to yes"/>
67 <param argument="--useGroup" type="boolean" checked="false"
68 label="For matching fragmentation to a feature, use the grouped feature range"
69 help="For special cases where the MS2 files have no MS1 data or if the MS1 data in the MS2 file is unreliable" />
70
71 <expand macro="fileload" />
72
73 </inputs>
74 <outputs>
75 <data name="frag4feature_output_tsv" format="tsv" label="${tool.name} on ${on_string}: tsv"
76 from_work_dir="frag4feature_output.tsv" />
77 <data name="frag4feature_output_rdata" format="rdata" label="${tool.name} on ${on_string}: RData"
78 from_work_dir="frag4feature_output.RData" />
79 </outputs>
80 <tests>
81 <test>
82 <conditional name="file_load_conditional">
83 <param name="file_load_select" value="yes"/>
84 <param name="input" >
85 <collection type="list">
86 <element name="LCMSMS_2.mzML" value="LCMSMS_2.mzML"/>
87 <element name="LCMSMS_1.mzML" value="LCMSMS_1.mzML"/>
88 <element name="LCMS_2.mzML" value="LCMS_2.mzML"/>
89 <element name="LCMS_1.mzML" value="LCMS_1.mzML"/>
90 </collection>
91 </param>
92 </conditional>
93 <param name="xset" value="xset_group_LCMS_1_LCMS_2_LCMSMS_1_LCMSMS_2.RData"/>
94 <param name="pa" value="purityA_output.RData"/>
95 <output name="frag4feature_output_tsv" value="frag4feature_output.tsv"/>
96 <output name="frag4feature_output_rdata" value="frag4feature_output.RData" ftype="rdata" compare="sim_size"/>
97 </test>
98 </tests>
99
100 <help><![CDATA[
101 =============================================================
102 Link fragmentation spectra to XCMS features
103 =============================================================
104 -----------
105 Description
106 -----------
107
108 **General**
109
110 Tool to Assign fragmentation spectra (MS/MS) stored within a purityA class object to grouped features within an XCMS xset object.
111
112 Please note that the xcmsSet object needs to have been grouped.
113
114 The data inputs are:
115
116 * A purityA object (generated from purityA) saved in an rdata file.
117 * A xcmsSet grouped object (generated from xcms_group) saved in an rdata file
118 * [optional] a dataset collection of the mzML files to resubmit
119
120 XCMS calculates individual chromatographic peaks for each mzML file (saved in xset@peaks), these are then grouped together
121 (using xcms.group). Ideally the mzML files that contain the MS/MS spectra also contain sufficient MS1 scans for XCMS to detect
122 MS1 chromatographic features. If this is the case, to determine if a MS2 spectra is to be linked to an XCMS grouped feature,
123 the associated acquisition time of the MS/MS event has to be within the retention time window defined for the individual peaks
124 associated for each file. The precursor m/z value also has to be within the user ppm tolerance to XCMS feature.
125
126 See below for representation of the linking (the \*------\* represent a many-to-many relationship) e.g. 1 or more MS/MS events can be
127 linked to 1 or more individual feature and an individual XCMS feature can be linked to 1 or more grouped XCMS features
128
129 * \[grouped XCMS feature - across files\] \*------\* \[individual XCMS feature - per file\] \*------\* \[MS/MS spectra\]
130
131 Alternatively, if the "useGroup" argument is set to TRUE, the full width of the grouped peak (determined as the minimum rtmin
132 and maximum rtmax of the all associated individual peaks) will be used. This option should be used if the mzML file with
133 MS/MS has very limited MS1 data and so individual chromatographic peaks might not be detected with the mzML files containing the
134 MS/MS data. However, it should be noted this may lead to potential inaccurate linking.
135
136 * \[grouped XCMS peaks\] \*------\* \[MS/MS spectra\]
137
138 **Example LC-MS/MS processing workflow**
139
140
141 * Purity assessments
142 + (mzML files) -> purityA -> (pa)
143 * XCMS processing
144 + (mzML files) -> xcms.xcmsSet -> xcms.merge -> xcms.group -> xcms.retcor -> xcms.group -> (xset)
145 * Fragmentation processing
146 + (xset, pa) -> **frag4feature** -> filterFragSpectra -> averageAllFragSpectra -> createDatabase -> spectralMatching -> (sqlite spectral database)
147
148 **Additional notes**
149
150 * If using only a single file, then grouping still needs to be performed within XCMS before frag4feature can be used.
151 * Fragmentation spectra below a certain precursor ion purity can be be removed (see plim argument).
152 * A SQLite database can be created directly here but the functionality has been deprecated and the createDatabase function should now be used
153 * Can experience some problems when using XCMS version < 3 and obiwarp retention time correction.
154
155 See Bioconductor documentation for more details, function msPurity::frag4feature()
156
157 -----------
158 Outputs
159 -----------
160 * frag4feature_rdata: An updated purityA object saved as rdata file with fragmentation-feature links added
161 * frag4feature_grouped_msms: A flat file of all the XCMS peaks for each grouped feature and the corresponding fragmentation scans
162 * frag4feature_sqlite: An SQLite database of the data (including fragmentation scans)
163
164 ]]></help>
165
166 <expand macro="citations" />
167
168 </tool>