comparison biomodels_BIOMD0000001076.xml @ 1:99ebf69e9b45 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/biomodelsML commit 96a70f2836d71103eeffcd2f40a312d5dfbc753e
author bgruening
date Fri, 05 Jan 2024 13:10:02 +0000
parents
children e66700f4c7eb
comparison
equal deleted inserted replaced
0:1748c5d74df5 1:99ebf69e9b45
1 <tool id="biomodels_BIOMD0000001076" name="Prediction of Breast Cancer (BC)" version="@VERSION@" profile="23.05">
2 <description>proteins involved in cancer immunotherapy using molecular descriptors and Multi Layer Perceptron (MLP) neural network</description>
3 <macros>
4 <token name="@VERSION@">1</token>
5 </macros>
6 <creator>
7 <organization name="EMBL's European Bioinformatics Institute (EMBL-EBI)" url="https://www.ebi.ac.uk/biomodels/" email="biomodels-net-support@lists.sf.net" />
8 <person name="Anup Kumar" email="kumara@informatik.uni-freiburg.de" />
9 </creator>
10 <requirements>
11 <container type="docker">docker.io/anupkumar/biomodels_biomd0000001076:@VERSION@</container>
12 </requirements>
13 <command><![CDATA[
14 cp /home/\$NB_USER/MLP_model3.onnx ./ &&
15 python '$biom_script_BIOMD0000001076'
16 ]]>
17 </command>
18 <configfiles>
19 <configfile name="biom_script_BIOMD0000001076">
20 <![CDATA[
21 import os
22 import numpy
23 import onnxruntime as rt
24 import pandas as pd
25
26 #if $input_file.ext == "tabular":
27 data_test = pd.read_csv('$input_file', sep="\t")
28 #elif $input_file.ext == "csv":
29 data_test = pd.read_csv('$input_file', sep=",")
30 #end if
31
32 Xdatap = data_test.iloc[:,:-1].values
33 sess = rt.InferenceSession(os.getcwd() + "/MLP_model3.onnx")
34 input_name = sess.get_inputs()[0].name
35 label_name = sess.get_outputs()[0].name
36 pred_onx = sess.run([label_name], {input_name: Xdatap.astype(numpy.float32)})[0]
37 data_test["Predictions"] = pred_onx
38 data_test.to_csv('$output_file', sep="\t", index=None)
39
40 ]]>
41 </configfile>
42 </configfiles>
43 <inputs>
44 <param name="input_file" type="data" label="Test data" format="tabular,csv" multiple="false" />
45 </inputs>
46 <outputs>
47 <data format="tabular" name="output_file" label="Predicted data"></data>
48 </outputs>
49 <tests>
50 <test>
51 <param name="input_file" value="test_data_BIOMD0000001076.tabular" ftype="tabular" />
52 <output name="output_file" file="pred_data_BIOMD0000001076.tabular">
53 <assert_contents>
54 <has_n_columns n="302" />
55 <has_n_lines n="401" />
56 </assert_contents>
57 </output>
58 </test>
59 <test>
60 <param name="input_file" value="test_data_BIOMD0000001076.csv" ftype="csv" />
61 <output name="output_file" file="pred_data_BIOMD0000001076.tabular">
62 <assert_contents>
63 <has_n_columns n="302" />
64 <has_n_lines n="401" />
65 </assert_contents>
66 </output>
67 </test>
68 </tests>
69 <help>
70 <![CDATA[
71 **What it does**
72
73 The tool makes prediction of breast cancer-related proteins: non-breast cancer related protein (0) or related to breast cancer protein (1). 300 features are used to train a Multi Layer Perceptron (artificial neural network) for such a prediction. The model is available via a Docker container. The original GitHub repository can be accessed at https://github.com/muntisa/neural-networks-for-breast-cancer-proteins.
74
75
76 **Description**
77
78 This study introduces a predictive classifier for breast cancer-related proteins, utilising a combination of protein sequence descriptors and machine learning techniques. The best-performing classifier is a Multi Layer Perceptron (artificial neural network) with 300 features, achieving an average Area Under the Receiver Operating Characteristics (AUROC) score of 0.984 through 3-fold cross-validation. Notably, the model identified top-ranked cancer immunotherapy proteins associated with breast cancer that should be studied for further biomarker discovery and therapeutic targeting. Please note that in this model, the output '0' means BC non-related protein and '1' means BC related protein.
79
80 **Input file**
81
82 Provide a tabular file (as tabular or csv) containing all the features as mentioned above.
83
84 **Output file**
85
86 Returns predicted data as a tabular file - the predictions are concatenated as a last column of the test data.
87
88 ]]>
89 </help>
90 <citations>
91 <citation type="doi">10.1038/s41598-020-65584-y</citation>
92 </citations>
93 </tool>