Mercurial > repos > bgruening > flexynesis_utils

comparison flexynesis_utils.xml @ 0:1fea022f106e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/flexynesis commit b2463fb68d0ae54864d87718ee72f5e063aa4587
author bgruening
date Tue, 24 Jun 2025 05:56:08 +0000
parents
children 35f41ee7ca20
comparison
equal deleted inserted replaced
-1:000000000000 0:1fea022f106e
1 <tool id="flexynesis_utils" name="Flexynesis utils" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2 <description>Utility functions for Flexynesis</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <required_files>
8 <include path="flexynesis_plot.py" />
9 <include path="flexynesis_utils.py" />
10 </required_files>
11 <command detect_errors="exit_code"><![CDATA[
12 @CHECK_NON_COMMERCIAL_USE@
13 mkdir -p inputs/ output/ &&
14 #if $utils_conditional.util != "compute_ami_ari" and $utils_conditional.util != "split_data" and $utils_conditional.util != "binarize":
15 ln -s '$utils_conditional.X' 'inputs/$utils_conditional.X.element_identifier.$utils_conditional.X.ext' &&
16 #end if
17 #if $utils_conditional.util != "split_data" and $utils_conditional.util != "binarize":
18 ln -s '$utils_conditional.labels' 'inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext' &&
19 cat '$flexynesis_utils_config' &&
20 python '$flexynesis_utils_config'
21 #end if
22 #if $utils_conditional.util == "split_data":
23 ln -s '$utils_conditional.clin' inputs/clin.csv &&
24 #set $omics_names = []
25 #for $omics_file in $utils_conditional.omics:
26 ln -s '$omics_file' 'inputs/${omics_file.element_identifier}.${omics_file.ext}' &&
27 #silent $omics_names.append('inputs/' + str($omics_file.element_identifier) + '.' + str($omics_file.ext))
28 #end for
29
30 python '$__tool_directory__/flexynesis_utils.py'
31 --util split
32 --clin inputs/clin.csv
33 --omics '$(",".join($omics_names))'
34 --split $utils_conditional.split
35 --out output
36 #end if
37 #if $utils_conditional.util == "binarize":
38 ln -s '$utils_conditional.mutation' 'inputs/${utils_conditional.mutation.element_identifier}.${utils_conditional.mutation.ext}' &&
39 python '$__tool_directory__/flexynesis_utils.py'
40 --util binarize
41 --mutation 'inputs/${utils_conditional.mutation.element_identifier}.${utils_conditional.mutation.ext}'
42 --gene_idx $utils_conditional.gene_idx
43 --sample_idx $utils_conditional.sample_idx
44 --out output
45 #end if
46 ]]></command>
47 <configfiles>
48 <configfile name="flexynesis_utils_config"><![CDATA[
49 import sys
50 sys.path.append('$__tool_directory__/')
51
52 import numpy as np
53 import pandas as pd
54 from flexynesis import (
55 louvain_clustering,
56 get_optimal_clusters,
57 compute_ami_ari,
58 k_means_clustering
59 )
60
61 from flexynesis_plot import (
62 load_omics
63 )
64
65 #if $utils_conditional.util == "louvain_clustering":
66 label_data = load_omics('inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext')
67 X = load_omics('inputs/$utils_conditional.X.element_identifier.$utils_conditional.X.ext')
68
69 cluster_labels, G, partition = louvain_clustering(
70 #if $utils_conditional.threshold != "":
71 threshold=$utils_conditional.threshold,
72 #end if
73 #if $utils_conditional.k != "":
74 k=$utils_conditional.k,
75 #end if
76 X=X)
77 cluster_df = pd.DataFrame(data=cluster_labels, index=X.index, columns=['louvain_cluster'])
78 label_data = label_data.merge(cluster_df[['louvain_cluster']], left_index=True, right_index=True, how='left')
79
80 output_path = f"output/clustered_labels.csv"
81 label_data.to_csv(output_path, index=True)
82
83 #else if $utils_conditional.util == "get_optimal_clusters":
84 label_data = load_omics('inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext')
85 X = load_omics('inputs/$utils_conditional.X.element_identifier.$utils_conditional.X.ext')
86
87 kmeans_cluster_labels, optimal_k, silhouette_scores = get_optimal_clusters(
88 data=X,
89 min_k=$utils_conditional.min_k,
90 max_k=$utils_conditional.max_k)
91
92 print(f"Optimal number of clusters: {optimal_k}\n")
93 print(f"Silhouette scores: \n{silhouette_scores}")
94
95 cluster_df = pd.DataFrame(data=kmeans_cluster_labels, index=X.index, columns=['optimal_kmeans_cluster'])
96 label_data = label_data.merge(cluster_df[['optimal_kmeans_cluster']], left_index=True, right_index=True, how='left')
97
98 output_path = f"output/optimal_clusters_labels.csv"
99 label_data.to_csv(output_path, index=True)
100
101 #else if $utils_conditional.util == "k_means_clustering":
102 label_data = load_omics('inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext')
103 X = load_omics('inputs/$utils_conditional.X.element_identifier.$utils_conditional.X.ext')
104
105 cluster_labels, kmeans = k_means_clustering(
106 data=X,
107 k=$utils_conditional.k)
108
109 print(f"{kmeans}")
110 cluster_df = pd.DataFrame(data=cluster_labels, index=X.index, columns=['kmeans_cluster'])
111 label_data = label_data.merge(cluster_df[['kmeans_cluster']], left_index=True, right_index=True, how='left')
112
113 output_path = f"output/kmeans_labels.csv"
114 label_data.to_csv(output_path, index=True)
115
116 #else if $utils_conditional.util == "compute_ami_ari":
117 label_data = load_omics('inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext')
118
119 true_label = label_data.columns[$utils_conditional.true_label-2]
120 predicted_label = label_data.columns[$utils_conditional.predicted_label-2]
121
122 true_labels = label_data[true_label]
123 predicted_labels = label_data[predicted_label]
124
125 ami_ari = compute_ami_ari(labels1=true_labels, labels2=predicted_labels)
126
127 print(f"AMI: {ami_ari['ami']}")
128 print(f"ARI: {ami_ari['ari']}")
129
130 output_path = f"output/ami_ari.txt"
131 with open(output_path, 'w') as f:
132 f.write(f"AMI: {ami_ari['ami']}\n")
133 f.write(f"ARI: {ami_ari['ari']}\n")
134
135 #end if
136 ]]></configfile>
137 </configfiles>
138 <inputs>
139 <expand macro="commercial_use_param"/>
140 <conditional name="utils_conditional">
141 <param name="util" type="select" label="Flexynesis utils">
142 <option value="louvain_clustering">Louvain Clustering</option>
143 <option value="get_optimal_clusters">Get Optimal Clusters</option>
144 <option value="k_means_clustering">K-Means Clustering</option>
145 <option value="compute_ami_ari">Compute AMI and ARI</option>
146 <option value="split_data">Split data to train and test</option>
147 <option value="binarize">Binarize mutation data</option>
148 </param>
149 <when value="louvain_clustering">
150 <param argument="--X" type="data" format="tabular,csv" label="Matrix" help="Input matrix, (samples, features)"/>
151 <expand macro="plots_common_input"/>
152 <param argument="--threshold" type="float" min="0" optional="true" label="Distance threshold to create an edge between two nodes"/>
153 <param argument="--k" type="integer" min="0" optional="true" label="Number of nearest neighbors to connect for each node"/>
154 </when>
155 <when value="get_optimal_clusters">
156 <param argument="--X" type="data" format="tabular,csv" label="Matrix" help="Input matrix, (samples, features)"/>
157 <expand macro="plots_common_input"/>
158 <param argument="--min_k" type="integer" min="0" value="2" optional="false" label="Minimum number of clusters to try"/>
159 <param argument="--max_k" type="integer" min="0" value="10" optional="false" label="Maximum number of clusters to try"/>
160 </when>
161 <when value="k_means_clustering">
162 <param argument="--X" type="data" format="tabular,csv" label="Matrix" help="Input matrix, (samples, features)"/>
163 <expand macro="plots_common_input"/>
164 <param argument="--k" type="integer" min="0" optional="true" label="The number of clusters to form"/>
165 </when>
166 <when value="compute_ami_ari">
167 <expand macro="plots_common_input"/>
168 <param name="true_label" type="data_column" data_ref="labels" label="Column name in the labels file to use for the true labels"/>
169 <param name="predicted_label" type="data_column" data_ref="labels" label="Column name in the labels file to use for the predicted labels"/>
170 </when>
171 <when value="split_data">
172 <param argument="--clin" type="data" format="csv" optional="false" label="Clinical data" help="Samples in rows"/>
173 <param argument="--omics" type="data" format="tabular,csv" optional="false" multiple="true" label="Omics data" help="samples in columns"/>
174 <param argument="--split" type="float" min="0" max="1" value="0.7" label="Training/Test split ratio" help="Proportion of data to use for training (e.g., 0.7 means 70% train, 30% test)"/>
175 </when>
176 <when value="binarize">
177 <param argument="--mutation" type="data" format="tabular,csv" label="Mutation data" help="Mutation data with both genes and samples in rows"/>
178 <param argument="--gene_idx" type="data_column" data_ref="mutation" label="Column in the mutation file with genes"/>
179 <param argument="--sample_idx" type="data_column" data_ref="mutation" label="Column in the mutation file with samples"/>
180 </when>
181 </conditional>
182 </inputs>
183 <outputs>
184 <data name="util_out" auto_format="true" from_work_dir="output/*" label="${tool.name} on ${on_string}: ${utils_conditional.util}">
185 <filter>utils_conditional['util'] != "split_data"</filter>
186 </data>
187 <collection name="train_out" type="list" label="${tool.name} on ${on_string}: train datasets">
188 <discover_datasets pattern="__name_and_ext__" format="csv" directory="output/train"/>
189 <filter>utils_conditional['util'] == "split_data"</filter>
190 </collection>
191 <collection name="test_out" type="list" label="${tool.name} on ${on_string}: test datasets">
192 <discover_datasets pattern="__name_and_ext__" format="csv" directory="output/test"/>
193 <filter>utils_conditional['util'] == "split_data"</filter>
194 </collection>
195 </outputs>
196 <tests>
197 <!-- test 1: Louvain clustering -->
198 <test expect_num_outputs="1">
199 <param name="non_commercial_use" value="True"/>
200 <conditional name="utils_conditional">
201 <param name="util" value="louvain_clustering"/>
202 <param name="X" value="embeddings.csv"/>
203 <param name="labels" value="labels_pr.csv"/>
204 <param name="k" value="15"/>
205 </conditional>
206 <output name="util_out">
207 <assert_contents>
208 <has_text text="sample_id,variable,class_label,probability,known_label,predicted_label,split,louvain_cluster"/>
209 <has_text text="MB-4818,CLAUDIN_SUBTYPE,LumA,0.8582904,LumB,LumA,test,3.0"/>
210 </assert_contents>
211 </output>
212 </test>
213 <!-- test 2: Get optimal clusters -->
214 <test expect_num_outputs="1">
215 <param name="non_commercial_use" value="True"/>
216 <conditional name="utils_conditional">
217 <param name="util" value="get_optimal_clusters"/>
218 <param name="X" value="embeddings.csv"/>
219 <param name="labels" value="labels_pr.csv"/>
220 <param name="min_k" value="2"/>
221 <param name="max_k" value="10"/>
222 </conditional>
223 <assert_stdout>
224 <has_text text="Optimal number of clusters: 2"/>
225 <has_text text="Silhouette scores: "/>
226 </assert_stdout>
227 <output name="util_out">
228 <assert_contents>
229 <has_text text="sample_id,variable,class_label,probability,known_label,predicted_label,split,optimal_kmeans_cluster"/>
230 <has_text text="MB-4818,CLAUDIN_SUBTYPE,LumA,0.8582904,LumB,LumA,test,0.0"/>
231 </assert_contents>
232 </output>
233 </test>
234 <!-- test 3: K-Means clustering -->
235 <test expect_num_outputs="1">
236 <param name="non_commercial_use" value="True"/>
237 <conditional name="utils_conditional">
238 <param name="util" value="k_means_clustering"/>
239 <param name="X" value="embeddings.csv"/>
240 <param name="labels" value="labels_pr.csv"/>
241 <param name="k" value="2"/>
242 </conditional>
243 <assert_stdout>
244 <has_text text="KMeans(n_clusters=2, random_state=42)"/>
245 </assert_stdout>
246 <output name="util_out">
247 <assert_contents>
248 <has_text text="sample_id,variable,class_label,probability,known_label,predicted_label,split,kmeans_cluster"/>
249 <has_text text="MB-4818,CLAUDIN_SUBTYPE,LumA,0.8582904,LumB,LumA,test,0.0"/>
250 </assert_contents>
251 </output>
252 </test>
253 <!-- test 4: Compute AMI and ARI -->
254 <test expect_num_outputs="1">
255 <param name="non_commercial_use" value="True"/>
256 <conditional name="utils_conditional">
257 <param name="util" value="compute_ami_ari"/>
258 <param name="labels" value="labels.csv"/>
259 <param name="true_label" value="5"/>
260 <param name="predicted_label" value="6"/>
261 </conditional>
262 <assert_stdout>
263 <has_text_matching expression="AMI: 0.5108[0-9]+"/>
264 <has_text_matching expression="ARI: 0.5258[0-9]+"/>
265 </assert_stdout>
266 <output name="util_out">
267 <assert_contents>
268 <has_text_matching expression="AMI: 0.5108[0-9]+"/>
269 <has_text_matching expression="ARI: 0.5258[0-9]+"/>
270 </assert_contents>
271 </output>
272 </test>
273 <!-- test 5: Split data to train and test -->
274 <test expect_num_outputs="2">
275 <param name="non_commercial_use" value="True"/>
276 <conditional name="utils_conditional">
277 <param name="util" value="split_data"/>
278 <param name="clin" value="train/clin"/>
279 <param name="omics" value="train/cnv,train/gex"/>
280 <param name="split" value="0.7"/>
281 </conditional>
282 <output_collection name="train_out" type="list" count="3">
283 <element name="clin">
284 <assert_contents>
285 <has_text_matching expression="sample"/>
286 <has_n_lines n="645"/>
287 </assert_contents>
288 </element>
289 <element name="cnv">
290 <assert_contents>
291 <has_text_matching expression="gene"/>
292 <has_n_lines n="25"/>
293 </assert_contents>
294 </element>
295 <element name="gex">
296 <assert_contents>
297 <has_text_matching expression="gene"/>
298 <has_n_lines n="25"/>
299 </assert_contents>
300 </element>
301 </output_collection>
302 <output_collection name="test_out" type="list" count="3">
303 <element name="clin">
304 <assert_contents>
305 <has_text_matching expression="sample"/>
306 <has_n_lines n="277"/>
307 </assert_contents>
308 </element>
309 <element name="cnv">
310 <assert_contents>
311 <has_text_matching expression="gene"/>
312 <has_n_lines n="25"/>
313 </assert_contents>
314 </element>
315 <element name="gex">
316 <assert_contents>
317 <has_text_matching expression="gene"/>
318 <has_n_lines n="25"/>
319 </assert_contents>
320 </element>
321 </output_collection>
322 </test>
323 <!-- test 6: Binarize mutation data -->
324 <test expect_num_outputs="1">
325 <param name="non_commercial_use" value="True"/>
326 <conditional name="utils_conditional">
327 <param name="util" value="binarize"/>
328 <param name="mutation" value="mut.tabular"/>
329 <param name="gene_idx" value="1"/>
330 <param name="sample_idx" value="17"/>
331 </conditional>
332 <output name="util_out">
333 <assert_contents>
334 <has_n_lines n="1611"/>
335 <has_text text="Hugo_Symbol"/>
336 <has_text text="AADACL2,0.0,0.0"/>
337 <has_text text="ABCB1,0.0,0.0,0.0,1.0"/>
338 </assert_contents>
339 </output>
340 </test>
341 </tests>
342 <help><![CDATA[
343 @COMMON_HELP@
344
345 Flexynesis Utils provides a collection of clustering and evaluation utilities for multi-omics data analysis. This tool offers four main functionalities:
346
347 1. **Louvain Clustering**: Community detection clustering algorithm that partitions data into clusters based on network modularity optimization
348 2. **Get Optimal Clusters**: Determines the optimal number of clusters using K-means clustering with silhouette score evaluation
349 3. **K-Means Clustering**: Standard K-means clustering algorithm for partitioning data into k clusters
350 4. **Compute AMI and ARI**: Calculates Adjusted Mutual Information (AMI) and Adjusted Rand Index (ARI) to evaluate clustering performance
351 5. **Split data to train and test**: Splits multi-omics data into training and testing sets based on a specified ratio
352 6. **Binarize mutation data**: Converts mutation data into a binary format, indicating presence or absence of mutations for each gene in each sample
353
354 **Louvain Clustering**
355 Uses the Louvain algorithm for community detection in networks. This method builds a graph from the input data and finds communities (clusters) by optimizing modularity.
356
357 Outputs Original labels file with added 'louvain_cluster' column
358
359 **Get Optimal Clusters**
360 Performs K-means clustering for a range of k values and determines the optimal number of clusters using silhouette analysis.
361
362 Outputs Original labels file with added 'optimal_kmeans_cluster' column
363 Console output shows the optimal k value and silhouette scores for each k.
364
365 **K-Means Clustering**
366 Standard K-means clustering algorithm that partitions data into k clusters by minimizing within-cluster sum of squares.
367
368 Outputs Original labels file with added 'kmeans_cluster' column
369
370 **Compute AMI and ARI**
371 Evaluates clustering performance by comparing true labels with predicted labels using two standard metrics:
372 - *AMI (Adjusted Mutual Information)*: Measures mutual information between clusterings, adjusted for chance
373 - *ARI (Adjusted Rand Index)*: Measures similarity between clusterings, adjusted for chance
374
375 Outputs Text file containing AMI and ARI scores
376 Both metrics range from 0 to 1, where 1 indicates perfect agreement
377
378 **Search cBioPortal**
379 Fetches available data files from cBioPortal for a specified study ID. This allows users to explore and retrieve data from cBioPortal studies.
380 Outputs a text file listing available data files for the specified study ID
381
382 **Split data to train and test**
383 Splits multi-omics data into training and testing sets based on a specified ratio. This is useful for preparing datasets for machine learning tasks.
384 You can use `Flexynesis cBioPortal import` to fetch data from cBioPortal and then use this tool to split the data into training and testing sets.
385
386 **Binarize mutation data**
387 Converts mutation data into a binary format, indicating presence or absence of mutations for each gene in each sample. This is useful for preparing mutation data for analysis.
388 The output will be a tabular file with genes as rows and samples as columns, where each cell indicates whether a mutation is present (1) or absent (0).
389
390
391 .. _Documentation: https://bimsbstatic.mdc-berlin.de/akalin/buyar/flexynesis/site/
392 .. _copyright holders: https://github.com/BIMSBbioinfo/flexynesis
393 ]]></help>
394 <expand macro="creator"/>
395 <expand macro="citations"/>
396 </tool>