Mercurial > repos > immuneml > immuneml_tools

annotate 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
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
1 <tool id="immuneml_train_ml_model" name="Train machine learning models" version="@VERSION@.0">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
2 <description></description>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
3 <macros>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
4 <import>prod_macros.xml</import>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
5 </macros>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
6 <expand macro="requirements" />
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
7 <command><![CDATA[
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
8
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
9 #if $iml_input
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
10 cp -r ${iml_input.extra_files_path}/result/* . &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
11 (mv repertoires/* . &>/dev/null || :) &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
12 rm -rf repertoires &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
13 #end if
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
14
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
15 #set $input_orig_names = []
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
16 #if $data_input
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
17 #for $input in $data_input
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
18 #set input_orig_names += [str($input.element_identifier)]
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
19 ([ -e ./"$input.element_identifier" ] && echo "File '$input.element_identifier' already exists in the input folder, skipping." || ln -s $input "$input.element_identifier") &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
20 #end for#
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
21 #end if
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
22
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
23 cp "$yaml_input" yaml_copy &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
24 immune-ml ./yaml_copy ${html_outfile.files_path} --tool GalaxyTrainMLModel &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
25 mv ${html_outfile.files_path}/index.html ${html_outfile} &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
26 mv ${html_outfile.files_path}/exported_models/*.zip ${optimal_model} &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
27 mv ${html_outfile.files_path}/immuneML_output.zip $archive
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
28 ]]>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
29 </command>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
30 <inputs>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
31 <param name="yaml_input" type="data" format="txt" label="YAML specification" multiple="false"/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
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."/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
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."/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
34 </inputs>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
35 <outputs>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
36 <data format="zip" name="optimal_model" label="optimal_ml_settings.zip"/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
37 <data format="zip" name="archive" label="Archive: ML model training"/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
38 <data format="html" name="html_outfile" label="Summary: ML model training"/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
39 </outputs>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
40
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
41
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
42 <help>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
43 <![CDATA[
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
44
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
45 This tool can be used to run hyperparameter optimization over several different ML settings,
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
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.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
47
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
48 This is a YAML-based Galaxy tool, if you prefer a button-based interface that assumes less ML knowledge,
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
49 see `Train immune receptor classifiers (easy interface) <https://galaxy.immuneml.uio.no/root?tool_id=immuneml_train_classifiers>`_ and
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
50 `Train immune repertoire classifiers (easy interface) <https://galaxy.immuneml.uio.no/root?tool_id=novice_immuneml_interface>`_.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
51
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
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>`_.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
53
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
54 **Tool output**
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
55
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
56 This Galaxy tool will produce the following history elements:
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
57
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
58 - Summary: ML model training: a HTML page that allows you to browse through all results, including prediction accuracies on
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
59 the various data splits and report results.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
60
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
61 - Archive: ML model training: a .zip file containing the complete output folder as it was produced by immuneML. This folder
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
62 contains the output of the TrainMLModel instruction including all trained models and their predictions, and report results.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
63 Furthermore, the folder contains the complete YAML specification file for the immuneML run, the HTML output and a log file.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
64
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
65 - optimal_ml_settings.zip: a .zip file containing the raw files for the optimal trained ML settings (ML model, encoding, and
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
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>`_.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
67
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
68 ]]>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
69
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
70 </help>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
71
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
72 </tool>