Mercurial > repos > recetox > recetox_xmsannotator_advanced

comparison recetox_xmsannotator_advanced.xml @ 5:a393c4383436 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/recetox-xmsannotator commit 1ab1a1dabfcebe11720de1411927a7438c1b64c1
author recetox
date Mon, 26 Jun 2023 13:55:44 +0000
parents 464c1e80a01f
children
comparison
equal deleted inserted replaced
4:464c1e80a01f 5:a393c4383436
1 <tool id="recetox_xmsannotator_advanced" name="RECETOX xMSannotator advanced" version="@TOOL_VERSION@+galaxy0"> 1 <tool id="recetox_xmsannotator_advanced" name="recetox-xMSannotator" version="@TOOL_VERSION@+galaxy0">
2
2 <description>annotate peak intensity table including scores and confidence levels</description> 3 <description>annotate peak intensity table including scores and confidence levels</description>
3 <macros> 4 <macros>
4 <import>macros.xml</import> 5 <import>macros.xml</import>
5 </macros> 6 </macros>
6 <expand macro="creator"/> 7 <expand macro="creator"/>
8 <xrefs>
9 <xref type="bio.tools">recetox-xmsannotator</xref>
10 </xrefs>
7 <expand macro="requirements" /> 11 <expand macro="requirements" />
8 <command detect_errors="aggressive"><![CDATA[ 12 <command detect_errors="aggressive"><![CDATA[
9 Rscript -e "n_workers <- \${GALAXY_SLOTS:-1}" -e "source('${wrapper}')" 13 Rscript -e 'source("${__tool_directory__}/utils.R")' -e "n_workers <- \${GALAXY_SLOTS:-1}" -e "source('${wrapper}')"
10 ]]></command> 14 ]]></command>
11 15
12 <configfiles> 16 <configfiles>
13 <configfile name="wrapper"><![CDATA[ 17 <configfile name="wrapper"><![CDATA[
14 library(xmsannotator) 18 metadata_table <- load_table("$metadata_table", "$metadata_table.ext")
19 intensity_table <- load_table("$intensity_table", "$intensity_table.ext")
20 peak_table <- create_peak_table(metadata_table, intensity_table)
21
22 filter_by <- create_filter_by_adducts("$filter_by")
15 23
16 annotation <- advanced_annotation( 24 annotation <- advanced_annotation(
17 #if $peak_table.is_of_type("h5") 25 peak_table = peak_table,
18 peak_table = load_peak_table_hdf("${peak_table}"), 26 adduct_table = load_table("$adduct_table", "$adduct_table.ext"),
19 #elif $peak_table.is_of_type("parquet") 27 adduct_weights = load_table("$adduct_weights", "$adduct_weights.ext"),
20 peak_table = load_peak_table_parquet("${peak_table}"), 28 compound_table = load_table("$compound_table", "$compound_table.ext"),
21 #end if
22 adduct_table = load_adduct_table_parquet("${adduct_table}"),
23 compound_table = load_compound_table_parquet("${compound_table}"),
24 mass_tolerance = 1e-6 * ${mass_tolerance_ppm}, 29 mass_tolerance = 1e-6 * ${mass_tolerance_ppm},
25 time_tolerance = $time_tolerance, 30 time_tolerance = $time_tolerance,
26 correlation_threshold = as.double($clustering.correlation_threshold), 31 correlation_threshold = as.double($clustering.correlation_threshold),
27 min_cluster_size = as.integer($clustering.min_cluster_size), 32 min_cluster_size = as.integer($clustering.min_cluster_size),
28 deep_split = as.integer($clustering.deep_split), 33 deep_split = as.integer($clustering.deep_split),
29 network_type = "$clustering.network_type", 34 network_type = "$clustering.network_type",
30 #if $scoring.expected_adducts
31 expected_adducts = load_expected_adducts_csv("${scoring.expected_adducts}"),
32 #end if
33 #if $scoring.boost_compounds
34 boost_compounds = load_boost_compounds_csv("${scoring.boost_compounds}"),
35 #end if
36 redundancy_filtering = $scoring.redundancy_filtering, 35 redundancy_filtering = $scoring.redundancy_filtering,
37 n_workers = n_workers 36 n_workers = n_workers,
37 intensity_deviation_tolerance = as.double($intensity_deviation_tolerance),
38 mass_defect_tolerance = as.double($mass_defect_tolerance),
39 mass_defect_precision = as.double($mass_defect_precision),
40 peak_rt_width = as.integer($peak_rt_width),
41 maximum_isotopes = as.integer($maximum_isotopes),
42 min_ions_per_chemical = as.integer($min_ions_per_chemical),
43 filter_by = filter_by
38 ) 44 )
39 45
40 save_parquet(data = annotation, file = "${annotation_parquet}") 46 save_table(annotation, "$output_file", "$output_file.ext")
41 ]]></configfile> 47 ]]></configfile>
42 </configfiles> 48 </configfiles>
43 49
44 <inputs> 50 <inputs>
45 <expand macro="inputs"/> 51 <expand macro="inputs"/>
46 <expand macro="tolerance"> 52 <expand macro="tolerance">
47 <param name="time_tolerance" type="float" value="10" min="0"> 53 <param name="time_tolerance" type="float" value="10" min="0">
48 <label>Retention time tolerance [s]</label> 54 <label>Retention time tolerance [s]</label>
49 <help> 55 <help>
50 Retention time tolerance in seconds for finding peaks derived from the same parent metabolite. 56 Retention time tolerance in seconds for finding peaks derived from the same parent compound.
51 </help> 57 </help>
52 </param> 58 </param>
53 </expand> 59 </expand>
54 <section name="clustering" title="Clustering"> 60 <section name="clustering" title="Clustering">
55 <param name="correlation_method" type="select" display="radio" label="Correlation method">
56 <option value="pearson" selected="true">pearson</option>
57 <option value="spearman">spearman</option>
58 </param>
59 <param name="correlation_threshold" type="float" value="0.7"> 61 <param name="correlation_threshold" type="float" value="0.7">
60 <label>Correlation threshold</label> 62 <label>Correlation threshold</label>
61 <help>Correlation threshold between peaks to qualify as adducts/isotopes of the same metabolite.</help> 63 <help>Correlation threshold between peaks to qualify as adducts/isotopes of the same metabolite.</help>
62 </param> 64 </param>
63 <param name="min_cluster_size" type="integer" value="10" min="1"> 65 <param name="min_cluster_size" type="integer" value="10" min="1">
75 <label>Network type</label> 77 <label>Network type</label>
76 <help> 78 <help>
77 Network type parameter affects how the network's adjacency matrix is created from the correlation 79 Network type parameter affects how the network's adjacency matrix is created from the correlation
78 matrix (see WGCNA package documentation). 80 matrix (see WGCNA package documentation).
79 </help> 81 </help>
80 <option value="signed">signed</option> 82 <option value="signed">Signed</option>
81 <option value="unsigned" selected="true">unsigned</option> 83 <option value="unsigned" selected="true">Unsigned</option>
82 </param> 84 </param>
83 </section> 85 </section>
84 <section name="scoring" title="Scoring" expanded="true"> 86 <section name="scoring" title="Scoring" expanded="true">
85 <param name="strict_boosting" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE"> 87 <param name="strict_boosting" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE">
86 <label>Strict boosting</label> 88 <label>Strict boosting</label>
87 <help> 89 <help>
88 Boost the scores of metabolites that not only belongs to the same pathway but also to the same 90 Boost the scores of metabolites that not only belongs to the same pathway but also to the same
89 cluster. Otherwise, do not account for cluster membership. 91 cluster. Otherwise, do not account for cluster membership.
90 </help>
91 </param>
92 <param name="expected_adducts" type="data" format="csv" optional="true">
93 <label>Expected adducts</label>
94 <help>
95 Require the presence of certain adducts for a high confidence match. By default, at least the
96 presence of an M+H adduct is required for a high confidence match.
97 </help>
98 </param>
99 <param name="boost_compounds" type="data" format="csv" optional="true">
100 <label>Validated compounds score boosting (optional)</label>
101 <help>
102 Table of previously validated compounds to boost their scores and confidence levels.
103 The 1st column of the table must contain IDs of compounds.
104 The optional 2nd and 3rd columns may contain mz values and retention times.
105 </help> 92 </help>
106 </param> 93 </param>
107 <param name="min_isp" type="integer" min="0" value="1"> 94 <param name="min_isp" type="integer" min="0" value="1">
108 <label>Minimum number of expected isotopes</label> 95 <label>Minimum number of expected isotopes</label>
109 <help> 96 <help>
119 <param name="redundancy_filtering" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE"> 106 <param name="redundancy_filtering" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE">
120 <label>Redundancy filtering</label> 107 <label>Redundancy filtering</label>
121 <help>Whether to filter out low-scored multiple matcher or not.</help> 108 <help>Whether to filter out low-scored multiple matcher or not.</help>
122 </param> 109 </param>
123 </section> 110 </section>
111 <param name="intensity_deviation_tolerance" type="float" value="0.1">
112 <label>Tolerance of intensity deviation</label>
113 <help>A numeric threshold by which an intensity ratio of two isotopic peaks may differ from their actual abundance ratio.</help>
114 </param>
115 <param name="mass_defect_tolerance" type="float" value="0.1">
116 <label>Tolerance of mass defect</label>
117 <help>Maximum difference in mass defect between two peaks of the same compound.</help>
118 </param>
119 <param name="mass_defect_precision" type="float" value="0.01">
120 <label>Precision for computing mass defect</label>
121 </param>
122 <param name="peak_rt_width" type="integer" value="1">
123 <label>Estimated chromatographic peak width</label>
124 </param>
125 <param name="maximum_isotopes" type="integer" value="10">
126 <label>Maximum isotopes</label>
127 </param>
128 <param name="min_ions_per_chemical" type="integer" value="2">
129 <label>Minimum ions per chemical</label>
130 </param>
131 <param name="filter_by" type="select" label="Adducts to filter by" multiple="true" optional="true">
132 <option value="M-H" selected="true">M-H</option>
133 <option value="M+H" selected="true">M+H</option>
134 <option value="2M-H">2M-H</option>
135 <option value="M-2H">M-2H</option>
136 </param>
124 </inputs> 137 </inputs>
125 138
126 <outputs> 139 <outputs>
127 <expand macro="outputs"/> 140 <expand macro="outputs"/>
128 </outputs> 141 </outputs>
129 142
143 <tests>
144 <test>
145 <param name="metadata_table" value="metadata_table.parquet" ftype="parquet" />
146 <param name="intensity_table" value="intensity_table.parquet" ftype="parquet" />
147 <param name="compound_table" value="database.parquet" ftype="parquet" />
148 <param name="adduct_table" value="adduct_table.parquet" ftype="parquet" />
149 <output name="output_file" file="expected_output.parquet" ftype="parquet"/>
150 </test>
151 <test>
152 <param name="metadata_table" value="metadata_table.csv" ftype="csv" />
153 <param name="intensity_table" value="intensity_table.csv" ftype="csv" />
154 <param name="compound_table" value="database.csv" ftype="csv" />
155 <param name="adduct_table" value="adduct_table.csv" ftype="csv" />
156 <output name="output_file" file="expected_output.csv" ftype="csv"/>
157 </test>
158 </tests>
159
130 <help> 160 <help>
131 <![CDATA[ 161 <![CDATA[
132 @HELP@ 162 @HELP@
133 Then, a score and a confidence level is assigned to each match based on peak correlation
134 clustering, metabolite pathway associations, adducts expectations, and isotope conformations.
135 ]]> 163 ]]>
136 </help> 164 </help>
137 165
138 <citations> 166 <citations>
139 <expand macro="citations"/> 167 <expand macro="citations"/>