Mercurial > repos > recetox > ipapy2_compute_bio

comparison ipapy2_compute_bio.xml @ 0:ca72f5330bc9 draft default tip

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/ipapy2 commit 64b61ff2823b4f54868c0ab7a4c0dc49eaf2979a
author recetox
date Fri, 16 May 2025 08:02:29 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:ca72f5330bc9
1 <tool id="ipapy2_compute_bio" name="ipaPy2 compute bio" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@">
2 <description>compute list of biochemical connections to improve annotation accuracy</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6
7 <expand macro="requirements"/>
8
9 <command detect_errors="exit_code"><![CDATA[
10 python3 '${__tool_directory__}/ipapy2_compute_bio.py'
11 --input_dataset_database '${MS1_DB}' '${MS1_DB.ext}'
12 --input_dataset_annotations '${annotations}' '${annotations.ext}'
13 --biochemical_mode '${biochemical_mode.biochemical_mode}'
14 #if $biochemical_mode.biochemical_mode == "connections"
15 --connection_list '${biochemical_mode.connection_list}'
16 #end if
17 --output_dataset "${compute_bio_output}" "${compute_bio_output.ext}"
18 --ncores \${GALAXY_SLOTS:-1}
19 ]]></command>
20
21 <inputs>
22 <param label="MS1 DB table" name="MS1_DB" type="data" format="csv,tsv,tabular,parquet" help="pandas dataframe containing the MS1 database."/>
23 <param label="annotations" name="annotations" type="data" format="csv,tsv,tabular,parquet" optional="true" help="pandas dataframe containing all the possible annotations for the measured features."/>
24 <conditional name="biochemical_mode">
25 <param name="biochemical_mode" type="select" label="biochemical mode"
26 help="connections are computed based on the reactions or connections.">
27 <option value="reactions" selected="true">reactions</option>
28 <option value="connections">connections</option>
29 </param>
30 <when value="reactions">
31 </when>
32 <when value="connections">
33 <param name="connection_list" type="select" multiple="true" label="connections list provided" help="list of possible connections between compounds defined as formulas.">
34 <option value="C3H5NO">C3H5NO</option>
35 <option value="C6H12N4O">C6H12N4O</option>
36 <option value="C6H10N2O3S2">C6H10N2O3S2</option>
37 <option value="C3H5NOS">C3H5NOS</option>
38 <option value="C5H7NO3">C5H7NO3</option>
39 <option value="C5H8N2O2">C5H8N2O2</option>
40 <option value="C2H3NO">C2H3NO</option>
41 <option value="C6H7N3O">C6H7N3O</option>
42 <option value="C6H11NO">C6H11NO</option>
43 <option value="C6H12N2O">C6H12N2O</option>
44 <option value="C5H9NOS">C5H9NOS</option>
45 <option value="C9H9NO">C9H9NO</option>
46 <option value="C5H7NO">C5H7NO</option>
47 <option value="C3H5NO2">C3H5NO2</option>
48 <option value="C4H7NO2">C4H7NO2</option>
49 <option value="C11H10N2O">C11H10N2O</option>
50 <option value="C9H9NO2">C9H9NO2</option>
51 <option value="C5H9NO">C5H9NO</option>
52 <option value="C4H4O2">C4H4O2</option>
53 <option value="C3H5O">C3H5O</option>
54 <option value="C10H12N5O6P">C10H12N5O6P</option>
55 <option value="C10H15N2O3S">C10H15N2O3S</option>
56 <option value="C10H14N2O2S">C10H14N2O2S</option>
57 <option value="CH2ON">CH2ON</option>
58 <option value="C21H34N7O16P3S">C21H34N7O16P3S</option>
59 <option value="C21H33N7O15P3S">C21H33N7O15P3S</option>
60 <option value="C10H15N3O5S">C10H15N3O5S</option>
61 <option value="C5H7">C5H7</option>
62 <option value="C3H2O3">C3H2O3</option>
63 <option value="C16H30O">C16H30O</option>
64 <option value="C8H8NO5P">C8H8NO5P</option>
65 <option value="CH3N2O">CH3N2O</option>
66 <option value="C5H4N5">C5H4N5</option>
67 <option value="C10H11N5O3">C10H11N5O3</option>
68 <option value="C10H13N5O9P2">C10H13N5O9P2</option>
69 <option value="C9H13N3O10P2">C9H13N3O10P2</option>
70 <option value="C9H12N3O7P">C9H12N3O7P</option>
71 <option value="C4H4N3O">C4H4N3O</option>
72 <option value="C10H13N5O10P2">C10H13N5O10P2</option>
73 <option value="C10H12N5O7P">C10H12N5O7P</option>
74 <option value="C5H4N5O">C5H4N5O</option>
75 <option value="C10H11N5O4">C10H11N5O4</option>
76 <option value="C10H14N2O10P2">C10H14N2O10P2</option>
77 <option value="C10H12N2O4">C10H12N2O4</option>
78 <option value="C5H5N2O2">C5H5N2O2</option>
79 <option value="C10H13N2O7P">C10H13N2O7P</option>
80 <option value="C9H12N2O11P2">C9H12N2O11P2</option>
81 <option value="C9H11N2O8P">C9H11N2O8P</option>
82 <option value="C4H3N2O2">C4H3N2O2</option>
83 <option value="C9H10N2O5">C9H10N2O5</option>
84 <option value="C2H3O2">C2H3O2</option>
85 <option value="C2H2O">C2H2O</option>
86 <option value="C2H2">C2H2</option>
87 <option value="CO2">CO2</option>
88 <option value="CHO2">CHO2</option>
89 <option value="H2O">H2O</option>
90 <option value="H3O6P2">H3O6P2</option>
91 <option value="C2H4">C2H4</option>
92 <option value="CO">CO</option>
93 <option value="C2O2">C2O2</option>
94 <option value="H2">H2</option>
95 <option value="O">O</option>
96 <option value="P">P</option>
97 <option value="CH2">CH2</option>
98 <option value="HPO3">HPO3</option>
99 <option value="NH2">NH2</option>
100 <option value="PP">PP</option>
101 <option value="NH">NH</option>
102 <option value="SO3">SO3</option>
103 <option value="N">N</option>
104 <option value="C6H10O5">C6H10O5</option>
105 <option value="C6H10O6">C6H10O6</option>
106 <option value="C5H8O4">C5H8O4</option>
107 <option value="C12H20O11">C12H20O11</option>
108 <option value="C6H11O8P">C6H11O8P</option>
109 <option value="C6H8O6">C6H8O6</option>
110 <option value="C4H6N2O2">C4H6N2O2</option>
111 <option value="C4H5NO3">C4H5NO3</option>
112 <option value="C18H30O15">C18H30O15</option>
113 </param>
114 </when>
115 </conditional>
116 </inputs>
117
118 <outputs>
119 <data label="${tool.name} on ${on_string}" name="compute_bio_output" format_source="MS1_DB"/>
120 </outputs>
121
122 <tests>
123 <test>
124 <param name="MS1_DB" value="compute_bio_db.csv"/>
125 <param name="annotations" value="clean_annotations.csv"/>
126 <param name="biochemical_mode" value="reactions"/>
127 <!-- Not the best way to test, but the results are stochastic hence difficult to test-->
128 <output name="compute_bio_output">
129 <assert_contents>
130 <has_text text="C00079" />
131 <has_n_columns n="2" sep=","/>
132 <has_n_lines n="2" delta="3" />
133 </assert_contents>
134 </output>
135 </test>
136 </tests>
137
138 <help><![CDATA[
139
140 .. _ipapy2_compute_bio:
141
142 ===============================
143 ipaPy2 Compute Bio Connections
144 ===============================
145
146 **Tool Description**
147
148 This tool generates a table of biochemical connections between compounds in your MS1 database. These connections are used by the IPA method to update annotation probabilities by considering known biochemical relationships, such as reactions or user-defined connections. The resulting table can be used in downstream annotation refinement tools (e.g., the ipaPy2 Gibbs sampler).
149
150 How it works
151 ------------
152
153 - The tool examines the compounds in your MS1 database and determines which pairs are biochemically related.
154 - Two modes are available:
155
156 - **Reactions mode**: Connections are computed based on known biochemical reactions (recommended for most users).
157 - **Connections mode**: Connections are computed based on a user-provided list of possible connections (e.g., specific transformation formulas).
158
159 - The output is a two-column table listing all pairs of compounds that are considered biochemically connected.
160
161 Inputs
162 ------
163
164 1. **MS1 DB table**
165 A table (CSV, TSV, Parquet, or Tabular) containing the MS1 database of compounds.
166
167 2. **Annotations**
168 (Optional) Table of possible annotations for the measured features.
169
170 3. **Biochemical mode**
171 - **reactions**: Compute connections based on known biochemical reactions.
172 - **connections**: Use a user-provided list of possible connections (formulas).
173
174 4. **Connections list**
175 (Only required if using "connections" mode)
176 A list of possible connections between compounds, defined as formulas.
177
178 Outputs
179 -------
180
181 - **compute_bio_output**
182 A two-column table listing all pairs of compounds that are considered biochemically connected. This table can be used as input for downstream annotation refinement tools.
183
184 Example
185 -------
186
187 Suppose you have an MS1 database (`compute_bio_db.csv`) and want to compute biochemical connections using the reactions mode:
188
189 .. code-block::
190
191 MS1_DB: compute_bio_db.csv
192 biochemical_mode: reactions
193
194 Alternatively, to use a custom list of connections:
195
196 .. code-block::
197
198 MS1_DB: compute_bio_db.csv
199 biochemical_mode: connections
200 connection_list: [C2H4O2, C6H12O6, ...]
201
202 Notes
203 -----
204
205 - The output table is essential for integrating biochemical knowledge into annotation refinement.
206 - Ensure your input files are correctly formatted and contain the required columns.
207 - The tool supports multiple file formats for flexibility.
208
209 References
210 ----------
211
212 - For more details on biochemical connection computation and its use in IPA, refer to the ipaPy2 documentation or associated publications.
213
214 ]]></help>
215
216 <expand macro="citations"/>
217 </tool>