Mercurial > repos > galaxyp > flashlfq

comparison flashlfq.xml @ 3:41c0c75301b3 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/flashlfq commit 59fca11aabb90cd875d93e7da8791a49e1e2c01a-dirty
author galaxyp
date Thu, 25 Jan 2018 15:03:28 -0500
parents d042eabcd6ec
children 597199e75dcc
comparison
equal deleted inserted replaced
2:d042eabcd6ec 3:41c0c75301b3
3 <requirements> 3 <requirements>
4 <requirement type="package" version="0.1.99">flashlfq</requirement> 4 <requirement type="package" version="0.1.99">flashlfq</requirement>
5 </requirements> 5 </requirements>
6 <command><![CDATA[ 6 <command><![CDATA[
7 #import re 7 #import re
8 #set $idt_path = $re.sub('[.][^.]*$','',$idt.display_name.split('/')[-1]) + ".psmtsv" 8 #set $idt_path = $re.sub('\s','_',$re.sub('[.][^.]*$','',$idt.display_name.split('/')[-1])) + ".psmtsv"
9 ## cp '${idt}' '${idt_path}'; 9 ## cp '${idt}' '${idt_path}';
10 ln -s '${idt}' '${idt_path}'; 10 ln -s '${idt}' '${idt_path}';
11 #for $peak_list in $peak_lists: 11 #for $peak_list in $peak_lists:
12 #set $input_name = $re.sub('[.][^.]*$','',$peak_list.display_name.split('/')[-1]) + ".mzML" 12 #set $input_name = $re.sub('[.][^.]*$','',$peak_list.display_name.split('/')[-1]) + ".mzML"
13 ln -s '${peak_list}' '${input_name}'; 13 ln -s '${peak_list}' '${input_name}';
14 #end for 14 #end for
15 FlashLFQ --idt $idt_path --rep `pwd` --ppm $ppm --iso $iso --nis $nis 15 FlashLFQ --idt '$idt_path' --rep `pwd` --ppm $ppm --iso $iso --nis $nis
16 #if $intensity == 'integrate': 16 #if $intensity == 'integrate':
17 --int true 17 --int true
18 #end if 18 #end if
19 #if $charge == 'precursor': 19 #if $charge == 'precursor':
20 --chg true 20 --chg true
26 && cp *_FlashLFQ_QuantifiedModifiedSequences.tsv '$quantifiedModifiedSequences' 26 && cp *_FlashLFQ_QuantifiedModifiedSequences.tsv '$quantifiedModifiedSequences'
27 && cp *_FlashLFQ_QuantifiedPeaks.tsv '$quantifiedPeaks' 27 && cp *_FlashLFQ_QuantifiedPeaks.tsv '$quantifiedPeaks'
28 && cp *_FlashLFQ_QuantifiedProteins.tsv '$quantifiedProteins' 28 && cp *_FlashLFQ_QuantifiedProteins.tsv '$quantifiedProteins'
29 ]]></command> 29 ]]></command>
30 <inputs> 30 <inputs>
31 <param name="idt" type="data" format="tabular" label="identification file"/> 31 <param name="idt" type="data" format="tabular" label="identification file"
32 help="MetaMorpheus,Morpheus"/>
32 <param name="peak_lists" type="data" format="mzml" multiple="true" label="spectrum files"/> 33 <param name="peak_lists" type="data" format="mzml" multiple="true" label="spectrum files"/>
33 <param name="ppm" type="float" value="10" min="1" max="20" label="monoisotopic ppm tolerance"/> 34 <param name="ppm" type="float" value="10" min="1" max="20" label="monoisotopic ppm tolerance"/>
34 <param name="iso" type="float" value="5" min="1" max="10" label="isotopic distribution tolerance in ppm"/> 35 <param name="iso" type="float" value="5" min="1" max="10" label="isotopic distribution tolerance in ppm"/>
35 <param name="nis" type="integer" value="2" min="1" max="30" label="number of isotopes required to be observed"/> 36 <param name="nis" type="integer" value="2" min="1" max="30" label="number of isotopes required to be observed"/>
36 <param name="intensity" type="select" label="intensity"> 37 <param name="intensity" type="select" label="intensity">
46 <param name="mbr" type="boolean" truevalue="--mbr true" falsevalue="--mbr false" checked="false" 47 <param name="mbr" type="boolean" truevalue="--mbr true" falsevalue="--mbr false" checked="false"
47 label="match between runs"/> 48 label="match between runs"/>
48 </inputs> 49 </inputs>
49 <outputs> 50 <outputs>
50 <data name="log" format="txt" label="${tool.name} on ${on_string}: Log" /> 51 <data name="log" format="txt" label="${tool.name} on ${on_string}: Log" />
51 <data name="quantifiedBaseSequences" format="tabular" label="${tool.name} on ${on_string}: QuantifiedBaseSequences.tsv" /> 52 <data name="quantifiedPeaks" format="tabular" label="${tool.name} on ${on_string}: QuantifiedPeaks.tsv">
52 <data name="quantifiedModifiedSequences" format="tabular" label="${tool.name} on ${on_string}: QuantifiedModifiedSequences.tsv" /> 53 <actions>
53 <data name="quantifiedPeaks" format="tabular" label="${tool.name} on ${on_string}: QuantifiedPeaks.tsv" /> 54 <action name="column_names" type="metadata"
54 <data name="quantifiedProteins" format="tabular" label="${tool.name} on ${on_string}: QuantifiedProteins.tsv" /> 55 default="File Name,Base Sequence,Full Sequence,Protein Group,Peptide Monoisotopic Mass,MS2 Retention Time,Precursor Charge,Theoretical MZ,Peak intensity,Peak RT Start,Peak RT Apex,Peak RT End,Peak MZ,Peak Charge,Num Charge States Observed,Peak Detection Type,PSMs Mapped,Base Sequences Mapped,Full Sequences Mapped,Peak Split Valley RT,Peak Apex Mass Error (ppm)"/>
56 </actions>
57 </data>
58 <data name="quantifiedBaseSequences" format="tabular" label="${tool.name} on ${on_string}: QuantifiedBaseSequences.tsv">
59 <actions>
60 <action name="column_names" type="metadata"
61 default="Sequence,Protein Group,${','.join(['Intensity_' + i.name for i in $peak_lists])},${','.join(['Detection Type_' + i.name for i in $peak_lists])}"/>
62 </actions>
63 </data>
64 <data name="quantifiedModifiedSequences" format="tabular" label="${tool.name} on ${on_string}: QuantifiedModifiedSequences.tsv">
65 <actions>
66 <action name="column_names" type="metadata"
67 default="Sequence,Protein Group,${','.join(['Intensity_' + i.name for i in $peak_lists])},${','.join(['Detection Type_' + i.name for i in $peak_lists])}"/>
68 </actions>
69 </data>
70 <data name="quantifiedProteins" format="tabular" label="${tool.name} on ${on_string}: QuantifiedProteins.tsv">
71 <actions>
72 <action name="column_names" type="metadata"
73 default="Protein"/>
74 </actions>
75 </data>
55 </outputs> 76 </outputs>
56 <tests> 77 <tests>
57 <test> 78 <test>
58 <param name="idt" value="aggregatePSMs_5ppmAroundZero.psmtsv" ftype="tabular"/> 79 <param name="idt" value="aggregatePSMs_5ppmAroundZero.psmtsv" ftype="tabular"/>
59 <param name="scans" value="sliced-mzml.mzML" ftype="mzml"/> 80 <param name="peak_lists" value="sliced-mzml.mzML" ftype="mzml"/>
60 <param name="ppm" value="12"/> 81 <param name="ppm" value="12"/>
61 <param name="iso" value="6"/> 82 <param name="iso" value="6"/>
62 <output name="log"> 83 <output name="log">
63 <assert_contents> 84 <assert_contents>
64 <has_text text="ppmTolerance = 12" /> 85 <has_text text="ppmTolerance = 12" />
89 --mbr [bool|match between runs] 110 --mbr [bool|match between runs]
90 --rmm [bool|require observed monoisotopic mass peak] 111 --rmm [bool|require observed monoisotopic mass peak]
91 --nis [int|number of isotopes required to be observed] 112 --nis [int|number of isotopes required to be observed]
92 113
93 114
115 **Tab-Delimited Identification Text File**
116
117 The first line of the text file should contain column headers identifying what each column is. Note that MetaMorpheus (.psmtsv), Morpheus, MaxQuant (msms.txt), and TDPortal tab-delimited column headers are supported natively and such files can be read without modification. For search software that lists decoys and PSMs above 1% FDR (e.g., MetaMorpheus), you may want to remove these prior to FlashLFQ analysis. FlashLFQ will probably crash if ambiguous PSMs are passed into it (e.g., a PSM with more than 2 peptides listed in one line).
118
119 The following headers are required in the list of MS/MS identifications:
120
121 - **File Name** - File extensions should be tolerated, but no extension is tested more extensively (e.g. use MyFile and not MyFile.mzML)
122 - **Base Sequence** - Should only contain amino acid sequences, or it will likely result in a crash
123 - **Full Sequence** - Modified sequence. Can contain any letters, but must be consistent between the same peptidoform to get accurate results
124 - **Peptide Monoisotopic Mass** - Theoretical monoisotopic mass, including modification mass
125 - **Scan Retention Time** - MS/MS identification scan retention time
126 - **Precursor Charge** - Charge of the ion selected for MS/MS resulting in the identification
127 - **Protein Accession** - Protein accession(s) for the peptide; protein quantification is still preliminary
128
129
130 **Outputs**:
131
132 - **QuantifiedProteins.tsv** - Protein intensities are summed here within a run.
133
134 - **QuantifiedPeaks.tsv** - Each chromatographic peak is shown here, even peaks that were not quantifiable (peak intensity = 0). Details about each peak, such as number of PSMs mapped, start/apex/end retention times, ppm error, etc are contained in this file. A peptide can have multiple peaks over the course of a run (e.g., oxidized peptidoforms elute at different times, etc). Ambiguous peaks are displayed with a | (pipe) delimiter to indicate more than one peptide mapped to that peak.
135
136 - **QuantifiedModifiedSequences.tsv** - Similar to QuantifiedBaseSequences, but instead of being summed by Base Sequence, peptide intensities are summed by modified sequence; this makes it convenient to compare modified peptidoform intensities across runs.
137
138 - **QuantifiedBaseSequences.tsv** - Peptide intensities are summed here within a run (including differently-modified forms of the same amino acid sequence) and displayed in a convenient format for comparing across runs. The identification type (MS/MS or MBR) is also indicated. A peptide with more than 30% of its intensity coming from ambiguous peak(s) is considered not quantifiable and is given an intensity of -1.
139
140
141 - **Log.txt** - Log of the FlashLFQ run. Includes timestamps and quantification time for each file, total analysis time, directories used, and settings.
142
143
94 ]]></help> 144 ]]></help>
95 <citations> 145 <citations>
96 <citation type="doi">10.1021/acs.jproteome.7b00608</citation> 146 <citation type="doi">10.1021/acs.jproteome.7b00608</citation>
97 </citations> 147 </citations>
98 </tool> 148 </tool>