Mercurial > repos > immuneml > immuneml_tools

annotate immuneml_create_dataset.xml @ 6:2d3dd9ff7e84 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit 74f2bd15d2b7723c8e5a22d743913706dc7d8333-dirty"
author immuneml
date Tue, 27 Jul 2021 09:30:50 +0000
parents ed3932e6d616
children
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="immune_ml_dataset" name="Create dataset" 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 #set $input_orig_names = []
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
9 #for $input in $interface_cond.data_input
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
10 #if $input
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
11 #set input_orig_names += ["./"+str($input.element_identifier)]
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
12 ([ -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
13 #end if
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
14 #end for
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
15
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
16 #if $interface_cond.interface == "simple"
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
17 python3 '$__tool_directory__/build_dataset_yaml_wrapper.py'
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
18 --output_path . --file_name specs.yaml
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
19 #if $interface_cond.dataset_cond.dataset_type == "repertoire"
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
20 --is_repertoire True
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
21 --format "$interface_cond.dataset_cond.metadata_cond.data_format"
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
22 #if $interface_cond.dataset_cond.metadata_cond.data_format != "IReceptor"
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
23 --metadata_file "$interface_cond.dataset_cond.metadata_cond.metadata_input" &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
24 cp $interface_cond.dataset_cond.metadata_cond.metadata_input "$interface_cond.dataset_cond.metadata_cond.metadata_input.element_identifier"
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
25 #end if
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
26 #else
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
27 --is_repertoire False
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
28 --format "$interface_cond.dataset_cond.data_format"
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
29 --metadata_columns "$interface_cond.dataset_cond.metadata_columns"
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
30 #if $interface_cond.dataset_cond.dataset_type == "sequence"
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
31 --paired False
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
32 #elif $interface_cond.dataset_cond.dataset_type == "receptor"
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
33 --paired True
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
34 --receptor_chains $interface_cond.dataset_cond.receptor_type
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
35 #end if
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
36 #end if
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
37 && mv ./specs.yaml create_dataset.yaml &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
38 #else
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
39 cp $yaml_input create_dataset.yaml &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
40 #end if
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
41
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
42 immune-ml ./create_dataset.yaml ${html_outfile.files_path} --tool DatasetGenerationTool &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
43
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
44 mv ${html_outfile.files_path}/index.html ${html_outfile} &&
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
45 mv ./create_dataset.yaml ${specs}
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
46
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
47 ]]>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
48 </command>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
49 <inputs>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
50 <conditional name="interface_cond">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
51 <param type="select" name="interface" label="Which interface would you like to use?" display="radio">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
52 <option value="simple">Simplified (limited options)</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
53 <option value="advanced">Advanced (full control through YAML) </option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
54 </param>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
55 <when value="simple">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
56 <conditional name="dataset_cond">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
57 <param type="select" name="dataset_type" label="Dataset type" display="radio" help="Repertoire datasets
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
58 should be used when making predictions per repertoire, such as predicting a disease state. Sequence or
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
59 receptor datasets should be used when predicting values for unpaired (single-chain) and paired immune
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
60 receptors respectively, like antigen specificity.">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
61 <option value="repertoire">Repertoire dataset</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
62 <option value="sequence">Sequence dataset (single chain)</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
63 <option value="receptor">Receptor dataset (paired chains)</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
64 </param>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
65 <when value="repertoire">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
66 <conditional name="metadata_cond">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
67 <param type="select" name="data_format" label="Data format" display="radio">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
68 <option value="AIRR">AIRR</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
69 <option value="IReceptor">iReceptor Gateway</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
70 <option value="ImmunoSEQRearrangement">immunoSEQ: rearrangement-level files</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
71 <option value="ImmunoSEQSample">immunoSEQ: sample-level files</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
72 <option value="MiXCR">MiXCR</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
73 <option value="VDJdb">VDJdb</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
74 <option value="TenxGenomics">10x Genomics ‘Clonotype consensus annotations’ (CSV)</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
75 </param>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
76 <when value="AIRR">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
77 <param name="metadata_input" type="data" format="txt" label="Metadata file" multiple="false" help="The metadata file describes metadata information for all repertoires included in the dataset. Every repertoire ARR file described in the metadata file must be selected under 'Data files'."/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
78 </when>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
79 <when value="ImmunoSEQRearrangement">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
80 <param name="metadata_input" type="data" format="txt" label="Metadata file" multiple="false" help="The metadata file describes metadata information for all repertoires included in the dataset. Every repertoire immunoSEQ rearrangement file described in the metadata file must be selected under 'Data files'."/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
81 </when>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
82 <when value="ImmunoSEQSample">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
83 <param name="metadata_input" type="data" format="txt" label="Metadata file" multiple="false" help="The metadata file describes metadata information for all repertoires included in the dataset. Every repertoire immunoSEQ sample file described in the metadata file must be selected under 'Data files'."/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
84 </when>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
85 <when value="MiXCR">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
86 <param name="metadata_input" type="data" format="txt" label="Metadata file" multiple="false" help="The metadata file describes metadata information for all repertoires included in the dataset. Every repertoire MiXCR file described in the metadata file must be selected under 'Data files'."/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
87 </when>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
88 <when value="VDJdb">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
89 <param name="metadata_input" type="data" format="txt" label="Metadata file" multiple="false" help="The metadata file describes metadata information for all repertoires included in the dataset. Every repertoire VDJdb file described in the metadata file must be selected under 'Data files'."/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
90 </when>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
91 <when value="TenxGenomics">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
92 <param name="metadata_input" type="data" format="txt" label="Metadata file" multiple="false" help="The metadata file describes metadata information for all repertoires included in the dataset. Every repertoire 10x Genomics file described in the metadata file must be selected under 'Data files'."/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
93 </when>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
94 </conditional>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
95 </when>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
96 <when value="sequence">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
97 <param type="select" name="data_format" label="Data format" display="radio">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
98 <option value="AIRR">AIRR</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
99 <option value="IReceptor">iReceptor Gateway</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
100 <option value="ImmunoSEQRearrangement">ImmunoSEQ: rearrangement-level files</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
101 <option value="ImmunoSEQSample">ImmunoSEQ: sample-level files</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
102 <option value="MiXCR">MiXCR</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
103 <option value="VDJdb">VDJdb</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
104 <option value="TenxGenomics">10xGenomics ‘Clonotype consensus annotations’ (CSV)</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
105 </param>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
106 <param type="text" name="metadata_columns" optional="false" label="Metadata columns" help="Please
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
107 specify the names of the columns that contain metadata. The metadata columns specified here can be
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
108 used as labels for prediction. Multiple metadata columns may be specified and separated by comma,
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
109 for example: Epitope,Epitope gene,Epitope species"/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
110 </when>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
111 <when value="receptor">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
112 <param type="select" name="data_format" label="Data format" display="radio">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
113 <option value="AIRR">AIRR</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
114 <option value="IReceptor">iReceptor Gateway</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
115 <option value="VDJdb">VDJdb</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
116 <option value="TenxGenomics">10xGenomics ‘Clonotype consensus annotations’ (CSV)</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
117 </param>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
118 <param type="select" name="receptor_type" label="Receptor type" display="radio">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
119 <option value="TRA_TRB">T cell alpha/beta</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
120 <option value="TRG_TRD">T cell gamma/delta</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
121 <option value="IGH_IGL">B cell heavy/light</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
122 <option value="IGH_IGK">B cell heavy/kappa</option>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
123 </param>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
124 <param type="text" name="metadata_columns" optional="false" label="Metadata columns" help="Please
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
125 specify the names of the columns that contain metadata. The metadata columns specified here can be
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
126 used as labels for prediction. Multiple metadata columns may be specified and separated by comma,
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
127 for example: Epitope,Epitope gene,Epitope species"/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
128 </when>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
129 </conditional>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
130 <param name="data_input" type="data" multiple="true" label="Data files" min="1" max="2000" help="This field should include individual repertoire or receptor files, or iReceptor zip files. Multiple files can be selected by holding down the control/command or shift key, or by clicking 'browse datasets' (folder button on the right). Important: make sure all the files you want to include in the dataset are highlighted in blue or gray."/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
131 </when>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
132 <when value="advanced">
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
133 <param name="yaml_input" type="data" format="txt" label="YAML specification" multiple="false"/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
134 <param name="data_input" type="data" multiple="true" label="Data and metadata files" optional="true" help="This field should include individual repertoire or receptor files, or iReceptor zip files, and optionally a metadata file. Multiple files can be selected by holding down the control/command or shift key, or by clicking 'browse datasets' (folder button on the right). Important: make sure all the files you want to include in the dataset are highlighted."/>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
135 </when>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
136 </conditional>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
137 </inputs>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
138 <outputs>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
139 <data format="txt" name="specs" label="create_dataset.yaml"/>
3
ed3932e6d616 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents: 0
diff changeset
140 <data format="immuneml_receptors" name="html_outfile" label="ImmuneML dataset"/>
0
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
141 </outputs>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
142
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
143
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
144 <help><![CDATA[
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
145
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
146 In Galaxy, an immuneML dataset is simply a Galaxy collection containing all relevant files (including an optional metadata file).
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
147 The Create dataset Galaxy tool allows users to import data from various formats and create immuneML datasets in Galaxy.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
148 These datasets are in an optimized binary (Pickle) format, which ensures that you can quickly import the dataset into
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
149 Galaxy tools without having to repeatedly specify the import parameters.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
150
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
151 Before creating a dataset, the relevant data files must first be uploaded to the Galaxy interface. This can be done either
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
152 by uploading files from your local computer (use the 'Upload file' tool under the 'Get local data' menu), or by fetching
6
2d3dd9ff7e84 "planemo upload commit 74f2bd15d2b7723c8e5a22d743913706dc7d8333-dirty"
immuneml
parents: 3
diff changeset
153 remote data from the iReceptor Plus Gateway or VDJdb (see `How to import remote AIRR datasets in Galaxy <https://docs.immuneml.uio.no/latest/galaxy/galaxy_import_remote_data.html>`_).
0
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
154
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
155 The imported immuneML dataset is stored in a Galaxy collection, which will appear as a history item on the right side of the screen,
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
156 and can later be selected as input to other tools.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
157
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
158 The tool has a simplified and an advanced interface. The simplified interface is fully button-based, and relies
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
159 on default settings for importing datasets. The advanced interface gives full control over import settings through a YAML
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
160 specification. In most cases, the simplified interface will suffice.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
161
6
2d3dd9ff7e84 "planemo upload commit 74f2bd15d2b7723c8e5a22d743913706dc7d8333-dirty"
immuneml
parents: 3
diff changeset
162 For the exhaustive documentation of this tool and more information about immuneML datasets, see the tutorial `How to make an immuneML dataset in Galaxy <https://docs.immuneml.uio.no/latest/galaxy/galaxy_dataset.html>`_.
0
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
163
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
164 **Tool output**
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
165
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
166 This Galaxy tool will produce the following history elements:
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
167
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
168 - ImmuneML dataset: a sequence, receptor or repertoire dataset which can be used as an input to other immuneML tools. The history element contains a summary HTML page describing general characteristics of the dataset, including the name of the dataset
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
169 (which is used in the dataset definition of a yaml specification), the dataset type and size, available labels, and a link to download the raw data files.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
170
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
171 - create_dataset.yaml: the YAML specification file that was used by immuneML to create the dataset.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
172 This file can be downloaded and altered (for example to export files in AIRR format, or use non-standard import parameters),
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
173 and run again using the 'Advanced' interface.
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
174
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
175 ]]>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
176 </help>
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
177
629e7e403e19 "planemo upload commit 2fed2858d4044a3897a93a5604223d1d183ceac0-dirty"
immuneml
parents:
diff changeset
178 </tool>