|
0
|
1 <tool id="feature_alignment" name="Feature Alignment" version="0.1">
|
|
|
2 <description>of peakgroups below a FDR</description>
|
|
3
|
3 <requirements>
|
|
|
4 <requirement type="package" version="2.7">python</requirement>
|
|
|
5 <requirement type="package" version="0.3.2">msproteomicstools</requirement>
|
|
|
6 </requirements>
|
|
0
|
7 <stdio>
|
|
|
8 <exit_code level="fatal" range="1:"/>
|
|
|
9 </stdio>
|
|
|
10 <version_command>feature_alignment.py --version</version_command>
|
|
3
|
11 <command>
|
|
0
|
12 <![CDATA[
|
|
|
13 feature_alignment.py
|
|
7
|
14 --in #echo '" "'.join([ str($file) for $file in $inputs ]) #
|
|
0
|
15 --file_format $oformat
|
|
|
16 #if str($out) == "openswath":
|
|
|
17 --out $out
|
|
|
18 #end if
|
|
|
19 --out_matrix out_matrix.tsv
|
|
|
20 --out_ids $out_ids
|
|
|
21 --fdr_cutoff $fdr_cutoff
|
|
|
22 #if $max_fdr_quality and $max_fdr_quality is not None:
|
|
|
23 --max_fdr_quality "$max_fdr_quality"
|
|
|
24 #end if
|
|
|
25 --max_rt_diff $max_rt_diff
|
|
|
26 --iso_max_rt_diff $iso_max_rt_diff
|
|
|
27 --frac_selected $frac_selected
|
|
|
28 --method $method
|
|
|
29 --matrix_output_method $matrix_output_method
|
|
|
30 --realign_method $realign_method
|
|
|
31 &&
|
|
|
32 mv out_matrix.tsv $out_matrix
|
|
|
33
|
|
|
34 ]]></command>
|
|
|
35 <inputs>
|
|
|
36
|
|
|
37 <param name="inputs" type="data" multiple="True"
|
|
|
38 label="A list of mProphet output files containing all peakgroups" help="(--in)"/>
|
|
|
39 <param name="oformat" type="select" label="Which input file format is used" help="(--file_format)">
|
|
|
40 <option value="openswath">OpenSwath</option>
|
|
|
41 <option value="peakview" selected="True">Peakview</option>
|
|
|
42 </param>
|
|
|
43
|
|
|
44 <param name="fdr_cutoff" type="float" value="0.01" label="Seeding score cutoff" help="(--fdr_cutoff)" />
|
|
|
45 <param name="max_fdr_quality" type="text" default="-1.0"
|
|
|
46 label="Extension score cutoff"
|
|
|
47 help="During the extension phase of the algorithm, peakgroups of this quality will still be considered for alignment (in FDR) - it is possible to give a range in the format lower,higher+stepsize,stepsize - e.g. 0,0.31,0.01 (-1 will set it to fdr_cutoff) (--max_fdr_quality)"/>
|
|
2
|
48 <param name="max_rt_diff" type="integer" value="30" default="30"
|
|
0
|
49 label="Maximal difference in RT for two aligned features" help="(--max_rt_diff)"/>
|
|
2
|
50 <param name="iso_max_rt_diff" type="text" value="10" default="10"
|
|
0
|
51 label="Maximal difference in RT for two isotopic channels in the same run" help="(--iso_max_rt_diff)" />
|
|
|
52 <param name="frac_selected" type="float" value="0.0" min="0" max="1"
|
|
|
53 label="Do not write peakgroup if selected in less than this fraction of runs" help="(--frac_selected)"/>
|
|
|
54 <param name="method" type="select"
|
|
|
55 label="Which method to use for the clustering"
|
|
1
|
56 help="Note that the MST options will perform a local, MST guided alignment while the other options will use a reference-guided alignment. The global option will also move peaks which are below the selected FDR threshold. (--method)" >
|
|
0
|
57 <option value='best_overall' selected="True">best_overall</option>
|
|
|
58 <option value='best_cluster_score'>best_cluster_score</option>
|
|
|
59 <option value='global_best_cluster_score'>global_best_cluster_score</option>
|
|
|
60 <option value='global_best_overall'>global_best_overall</option>
|
|
|
61 <option value='LocalMST'>LocalMST</option>
|
|
|
62 <option value='LocalMSTAllCluster'>LocalMSTAllCluster</option>
|
|
|
63 </param>
|
|
|
64
|
|
|
65 <param name="matrix_output_method" type="select"
|
|
|
66 label="Which columns are written besides Intensity" help="(--matrix_output_method)">
|
|
|
67 <option value='none' selected="True">None</option>
|
|
|
68 <option value='RT'>RT</option>
|
|
|
69 <option value='score'>Score</option>
|
|
|
70 <option value='source'>Source</option>
|
|
|
71 <option value='full'>Full</option>
|
|
|
72 </param>
|
|
|
73 <param name="realign_method" type="select" label="How to re-align runs in retention time" help="(--realign_method)">
|
|
|
74 <option value='diRT' selected="True">Use only deltaiRT from the input file</option>
|
|
|
75 <option value='linear'>Perform a linear regression using best peakgroups</option>
|
|
|
76 <!--option value='splineR'>Perform a spline fit using R</option-->
|
|
|
77 <!--option value='splineR_external'>Perform a spline fit using R</option-->
|
|
|
78 <option value='splinePy'>Use Python native spline from scikits.datasmooth (slow!)</option>
|
|
|
79 <option value='lowess'>Use Robust locally weighted regression (lowess smoother)</option>
|
|
|
80 <option value='CVSpline'>Splines with cross-validation</option>
|
|
|
81 <option value='nonCVSpline'>Splines without cross-validation</option>
|
|
|
82 <option value='earth' >Use Multivariate Adaptive Regression Splines using py-earth</option>
|
|
|
83 </param>
|
|
|
84 </inputs>
|
|
|
85 <outputs>
|
|
|
86 <!-- Matrix containing one peak group per row -->
|
|
|
87 <data format="tabular" name="out_matrix"/>
|
|
|
88 <!-- Id file only containing the ids -->
|
|
|
89 <data format="tabular" name="out_ids"/>
|
|
|
90 <!-- Output file with filtered peakgroups for quantification (only works for OpenSWATH) -->
|
|
|
91 <data format="text" name="out">
|
|
|
92 <filter>oformat == 'openswath'</filter>
|
|
|
93 </data>
|
|
|
94 </outputs>
|
|
|
95 <help>
|
|
|
96 <![CDATA[
|
|
|
97
|
|
|
98 **What it does**
|
|
|
99
|
|
|
100 This program will select all peakgroups below the FDR cutoff in all files and try to align them to each other.
|
|
|
101 If only one file is given, it will act as peakgroup selector (best by m_score)
|
|
|
102 and will apply the provided FDR cutoff.
|
|
|
103 ]]>
|
|
|
104 </help>
|
|
|
105 <citations>
|
|
|
106 </citations>
|
|
|
107 </tool>
|
|
|
108
|
