annotate replicate_filter.xml @ 1:0cdf340364ed draft

"planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 680116d0cf6a6d7246cba655452dea43269aeba4"
author computational-metabolomics
date Tue, 28 Apr 2020 17:43:04 -0400
parents cb2acfaec200
children 6cb796aa12c8
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
1 <tool id="dimspy_replicate_filter" name="Replicate Filter" version="@TOOL_VERSION@+galaxy@GALAXY_TOOL_VERSION@">
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
2 <description> - Remove peaks that fail to appear in at least x-out-of-n (technical) replicates</description>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
3 <macros>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
4 <import>macros.xml</import>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
5 </macros>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
6 <expand macro="requirements" />
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
7 <command detect_errors="exit_code">
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
8 <![CDATA[
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
9 dimspy replicate-filter
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
10 --input '$hdf5_file_in'
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
11 --output '$hdf5_file_out'
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
12 #if $filelist
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
13 --filelist '$filelist'
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
14 #end if
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
15 --ppm $ppm
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
16 --replicates $replicates
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
17 --min-peak-present $min_peaks
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
18 #if $rsd_threshold
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
19 --rsd-threshold $rsd_threshold
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
20 #end if
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
21 --report '$report'
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
22 &&
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
23 dimspy create-sample-list
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
24 --input '$hdf5_file_out'
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
25 --output '$samplelist'
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
26 --delimiter tab
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
27 &&
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
28 dimspy hdf5-pls-to-txt
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
29 --input '$hdf5_file_out'
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
30 --output .
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
31 --delimiter $delimiter
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
32 ]]>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
33 </command>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
34 <inputs>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
35 <param name="hdf5_file_in" argument="--hdf5_file_in" type="data" format="h5" label="Peaklists (HDF5 file)" help="Peaklists generated by Process Scans (SIM-Stitch)." />
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
36 <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." />
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
37 <param name="replicates" argument="--replicates" type="integer" value="3" label="Number of technical replicates for each sample" help="" />
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
38 <param name="min_peaks" argument="--min_peaks" type="integer" value="2" label="Minimum number of technical replicates a peak has to be present in" help="" />
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
39 <param name="ppm" argument="--ppm" type="float" value="2.0" label="Ppm error tolerance" help="Maximum tolerated m/z deviation across technical replicates in parts per million (ppm)." />
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
40 <param name="rsd_threshold" argument="--rsd-threshold" type="text" value="" label="Relative standard deviation threshold" help="Maximum tolerated relative standard deviation (RSD) of the peak intensities across technical replicates. Leave empty to skip this filter step." />
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
41 <param name="delimiter" type="hidden" value="tab" argument="--delimiter" label="" help=""/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
42 </inputs>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
43 <outputs>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
44 <data name="hdf5_file_out" format="h5" label="${tool.name} on ${on_string}: Peaklists (HDF5 file)"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
45 <data name="report" format="txt" label="${tool.name} on ${on_string}: Report"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
46 <data name="samplelist" format="tsv" label="${tool.name} on ${on_string}: Sample Metadata (updated)" />
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
47 <collection name="peaklists_txt" type="list" label="${tool.name} on ${on_string}: Peaklists">
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
48 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.txt" format="tsv" directory="." visible="false" />
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
49 </collection>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
50 </outputs>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
51 <tests>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
52 <test>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
53 <param name="hdf5_file_in" value="pls.h5" ftype="h5"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
54 <param name="replicates" value="3"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
55 <param name="min_peaks" value="2"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
56 <param name="ppm" value="2.0"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
57 <param name="rsd_threshold" value=""/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
58 <output name="hdf5_file_out" value="pls_rf.h5" ftype="h5" compare="sim_size"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
59 <output name="report" value="report_pls_rf_01.txt" ftype="txt"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
60 <output name="samplelist" value="samplelist_1.txt" ftype="tsv"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
61 <output_collection name="peaklists_txt" type="list">
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
62 <element name="batch04_QC17_rep01_262_2_263_3_264" file="batch04_QC17_rep01_262_2_263_3_264.txt" ftype="tsv"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
63 </output_collection>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
64 </test>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
65 <test>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
66 <param name="hdf5_file_in" value="pls_scan5.h5" ftype="h5"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
67 <param name="replicates" value="3"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
68 <param name="min_peaks" value="2"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
69 <param name="ppm" value="2.0"/>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
70 <param name="rsd_threshold" value=""/>
1
0cdf340364ed "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 680116d0cf6a6d7246cba655452dea43269aeba4"
computational-metabolomics
parents: 0
diff changeset
71 <output name="report" value="report_pls_rf_02.txt" ftype="txt"/>
0
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
72 </test>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
73 </tests>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
74 <help>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
75 ----------------
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
76 Replicate filter
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
77 ----------------
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
78
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
79 ..
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
80
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
81 --------------------
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
82
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
83 Description
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
84 -----------
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
85
1
0cdf340364ed "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 680116d0cf6a6d7246cba655452dea43269aeba4"
computational-metabolomics
parents: 0
diff changeset
86 Standard DIMS processing workflow: Process Scans -> **[Replicate Filter]** -> Align Samples -> Blank Filter -> Sample Filter -> [Missing value sample filter] -> Pre-processing -> Statistics
0
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
87
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
88 |
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
89
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
90 To draw robust conclusions from DIMS-based metabolomics datasets, the data itself must be collected and processed in a robust and reproducible way. To support this aim, study samples are often divided in to a set of equivalent aliquots, each of which is analysed under defined and consistent analytical conditions. As aliquots of the same sample are assumed to comprise identical biological material, differences in their resulting spectra are assumed to arise due to technical variability. Removing artifacts associated with this technical variability, and removing mass spectral peaks that are detected irreproducible, is possible by filtering across these technical replicate spectra. The Replicate Filter tools facilitates this process, combining the peaklists extracted (using the Process Scans tool) from each technical replicate of a given study in to a single merged peaklist, before applying a series of user-defined filters to yield a replicate-filtered peaklist.
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
91
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
92 |
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
93
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
94 **Replicate filter process**: peaks from each technical replicate (for a given study sample) are aligned using a one-dimensional hierarchical clustering procedure (applied on the mass-to-charge scale). Peaks are aligned only if the difference in their mass-to-charge ratios, when divided by the average of their mass-to-charge ratios and multiplied by 1 × 10\ :sup:`6` \ (i.e. when measured in units of parts-per-million, ppm), is less-than or equal-to the user-defined ‘ppm error tolerance’. After alignment, a set of user-defined filters are applied to retain only those peaks that:
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
95
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
96 * occur in equal-to or more-than the user-defined 'Number of technical replicates a peak has to be present in', i.e. if set to 2, then a peak must be detected in at least two of the replicate analyses, **and/or**
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
97
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
98 * have relative standard deviation (measured in %; may otherwise be referred to as the percent coefficient of variation) of intensity values, across technical replicates, that is equal-to or less-than the user-defined ‘relative standard deviation threshold’ (if defined, otherwise ignored).
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
99
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
100 **IMPORTANT**:
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
101
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
102 * When a user sets the parameter “number of technical replicates for each sample” to a value less-than the total number of technical replicates actually acquired for each study sample, this tool will automatically determine which combination of technical replicates to combine. See the parameter description (below) for further details.
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
103
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
104 * If a specific scan event has been replicated within a given file, then users should not use this tool for filtering and aligning peaks. In this case, users should instead FIRST use the Process Scans (and SIM stitch) tool - see the documentation for the Process Scans tool for a description of how to perform this.
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
105
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
106 |
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
107
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
108 **Output** - a replicate-filtered peaklist per input study sample. In each, rows correspond to replicate-filtered mass spectral peaks, while columns provide a range of metrics for each of the detected peaks (see “Output file(s)” section, below).
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
109
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
110 ------------------
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
111
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
112 Parameters
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
113 ----------
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
114
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
115 * **Number of technical replicates for each sample** (REQUIRED; default = 3) - the total number of technical replicates acquired for each study sample. This value must be set to the lowest number of technical replicates acquired for ANY of the study samples, or alternatively, may be set to the minimum number of replicates the user would like to select from the total number of technical replicates for a biological sample.
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
116
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
117 * **Minimum number of technical replicates a peak has to be present in** (REQUIRED; default = 2) - For a given biological sample, the number of replicates that will be used to generate the replicate-filtered peaklist. By default, if this parameter is set to a value less-than the total number of technical replicates acquired for each biological sample, then the tool automatically determines which combination of technical replicates yields the best overall rank. Otherwise, all technical replicates are used. Ranking of the combinations of technical replicates is based on the average of the following three scores:
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
118
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
119 # score 1: peak count / peak count present in n-out-n (e.g. 3-out-of-3)
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
120
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
121 # score 2: peak count present in x-out-of-n (e.g. 3-out-of-3) / MAX peak count present in x-out-of-n across sets of replicates
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
122
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
123 # score 3: RSD categories (0-5 (score=1.0), 5-10 (score=0.9), 10-15 (score=0.8), etc)
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
124
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
125 * **ppm error tolerance** (REQUIRED; default = 2) - this parameter will influence the alignment of peaks across technical replicates. Peaks from distinct technical replicates of a given study sample 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 × 106, 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 threshold).
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
126
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
127 * **Relative standard deviation threshold** (OPTIONAL) - a numerical value from 0 upwards that defines the acceptable percentage relative standard deviation (otherwise termed the percent coefficient of variation) of a peak’s intensity across technical replicates. Peaks are removed from the output ‘replicate-filtered’ peaklist if this condition is not met.
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
128
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
129 -------------------
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
130
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
131 Output file(s)
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
132 --------------
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
133
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
134 |
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
135
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
136 The Replicate Filter tool will output three file types:
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
137
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
138 1) **A HDF5 file containing the replicate-filtered Peaklists**
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
139
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
140 2) **A replicate-filtered peaklist**, in .tsv format, for each biological sample defined in the filelist/samplelist. Tab-delimited text file containing a numeric data matrix, with . as decimal, and NA for missing values. Each row corresponds to a mass spectral peak. Columns provide metrics associated with each mass spectral peak. Metrics include:
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
141
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
142 @help_columns_peaklist@
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
143
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
144 @example_peaklist@
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
145
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
146 |
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
147
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
148 3) **A tabular “report” file** that details, for each biological sample included in the filelist/samplelist:
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
149
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
150 - **Set** - a numeric index value that is unique to a specific biological sample
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
151
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
152 - **Rank** - a positive integer indicating which combination of technical replicates offered the best-ranked replicate-filtered peaklist.
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
153
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
154 - **Name** - a string indicating which of the technical replicates for a given biological sample were combined together.
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
155
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
156 - **Peaks_[XooY]** - a numeric value indicating the total number of peaks that were present in X-out-of-Y technical replicates.
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
157
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
158 - **Median_rsd_[XooY]** - the median of the percent relative standard deviations of all peaks in the replicate-filtered peaklist that were present in X-out-of-Y technical replicates.
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
159
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
160 - **Score** - a numeric value between 0 and 1 that serves to indicate the best combination of technical replicates for a given biological sample (as defined by the ‘name’ column)
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
161
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
162 --------------------------
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
163
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
164 @github_developers_contributors@
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
165 @license@
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
166 </help>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
167 <expand macro="citations" />
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
168 </tool>
cb2acfaec200 "planemo upload for repository https://github.com/computational-metabolomics/dimspy-galaxy commit 6321871098b2c4bc9e321d20b7e66fff3d641839"
computational-metabolomics
parents:
diff changeset
169