Mercurial > repos > immuneml > immuneml_tools

comparison immuneml_train_ml_model.xml @ 0:629e7e403e19 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
author immuneml
date Thu, 01 Jul 2021 11:36:43 +0000
parents
children ed3932e6d616
comparison
equal deleted inserted replaced
-1:000000000000 0:629e7e403e19
1 <tool id="immuneml_train_ml_model" name="Train machine learning models" version="@VERSION@.0">
2 <description></description>
3 <macros>
4 <import>prod_macros.xml</import>
5 </macros>
6 <expand macro="requirements" />
7 <command><![CDATA[
8
9 #if $iml_input
10 cp -r ${iml_input.extra_files_path}/result/* . &&
11 (mv repertoires/* . &>/dev/null || :) &&
12 rm -rf repertoires &&
13 #end if
14
15 #set $input_orig_names = []
16 #if $data_input
17 #for $input in $data_input
18 #set input_orig_names += [str($input.element_identifier)]
19 ([ -e ./"$input.element_identifier" ] && echo "File '$input.element_identifier' already exists in the input folder, skipping." || ln -s $input "$input.element_identifier") &&
20 #end for#
21 #end if
22
23 cp "$yaml_input" yaml_copy &&
24 immune-ml ./yaml_copy ${html_outfile.files_path} --tool GalaxyTrainMLModel &&
25 mv ${html_outfile.files_path}/index.html ${html_outfile} &&
26 mv ${html_outfile.files_path}/exported_models/*.zip ${optimal_model} &&
27 mv ${html_outfile.files_path}/immuneML_output.zip $archive
28 ]]>
29 </command>
30 <inputs>
31 <param name="yaml_input" type="data" format="txt" label="YAML specification" multiple="false"/>
32 <param name="data_input" type="data" multiple="true" label="Additional files" optional="true" help="This field should include individual repertoire files, metadata files, receptor data and others."/>
33 <param name="iml_input" type="data" format="iml_dataset" label="Dataset input" optional="true" help="This field accepts an ImmuneML dataset, as created by the Create Dataset tool."/>
34 </inputs>
35 <outputs>
36 <data format="zip" name="optimal_model" label="optimal_ml_settings.zip"/>
37 <data format="zip" name="archive" label="Archive: ML model training"/>
38 <data format="html" name="html_outfile" label="Summary: ML model training"/>
39 </outputs>
40
41
42 <help>
43 <![CDATA[
44
45 This tool can be used to run hyperparameter optimization over several different ML settings,
46 which include ML models and their parameters, encodings and preprocessing steps. Nested cross-validation is used to identify the optimal combination of ML settings.
47
48 This is a YAML-based Galaxy tool, if you prefer a button-based interface that assumes less ML knowledge,
49 see `Train immune receptor classifiers (easy interface) <https://galaxy.immuneml.uio.no/root?tool_id=immuneml_train_classifiers>`_ and
50 `Train immune repertoire classifiers (easy interface) <https://galaxy.immuneml.uio.no/root?tool_id=novice_immuneml_interface>`_.
51
52 For more details on how to train ML models in Galaxy, see `the documentation <https://docs.immuneml.uio.no/galaxy/galaxy_train_ml_models.html>`_.
53
54 **Tool output**
55
56 This Galaxy tool will produce the following history elements:
57
58 - Summary: ML model training: a HTML page that allows you to browse through all results, including prediction accuracies on
59 the various data splits and report results.
60
61 - Archive: ML model training: a .zip file containing the complete output folder as it was produced by immuneML. This folder
62 contains the output of the TrainMLModel instruction including all trained models and their predictions, and report results.
63 Furthermore, the folder contains the complete YAML specification file for the immuneML run, the HTML output and a log file.
64
65 - optimal_ml_settings.zip: a .zip file containing the raw files for the optimal trained ML settings (ML model, encoding, and
66 optionally preprocessing steps). This .zip file can subsequently be used as an input when `applying previously trained ML models to a new AIRR dataset in Galaxy <https://docs.immuneml.uio.no/galaxy/galaxy_apply_ml_models.html>`_.
67
68 ]]>
69
70 </help>
71
72 </tool>