Mercurial > repos > iuc > semibin_train

comparison train.xml @ 0:fe0ba89f385f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/semibin commit aa9bfb2fb62547ee8bac34f0de5b3beaa0bfd1a4
author iuc
date Fri, 14 Oct 2022 22:07:50 +0000
parents
children f9f3d70127c2
comparison
equal deleted inserted replaced
-1:000000000000 0:fe0ba89f385f
1 <tool id="semibin_train" name="SemiBin: Train" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2 <description>
3 the semi-supervised deep learning model
4 </description>
5 <macros>
6 <import>macros.xml</import>
7 </macros>
8 <expand macro="biotools"/>
9 <expand macro="requirements"/>
10 <expand macro="version"/>
11 <command detect_errors="exit_code"><![CDATA[
12 #import re
13 #if $mode.select == 'single'
14 #if $mode.input_fasta.ext.endswith(".gz")
15 gunzip -c '$mode.input_fasta' > 'contigs.fasta' &&
16 #else
17 ln -s '$mode.input_fasta' 'contigs.fasta' &&
18 #end if
19 #else
20 #for $e in $mode.input_fasta
21 #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($e.element_identifier))
22 #if $e.ext.endswith(".gz")
23 gunzip -c '$e' > '${identifier}.fasta' &&
24 #else
25 ln -s '$e' '${identifier}.fasta' &&
26 #end if
27 #end for
28 #end if
29 SemiBin train
30 --mode '$mode.select'
31 #if $mode.select == 'single'
32 --input-fasta 'contigs.fasta'
33 --data '$mode.data'
34 --data-split '$mode.data_split'
35 --cannot-link '$mode.cannot_link'
36 #else
37 #for $e in $mode.input_fasta
38 --input-fasta '${e.element_identifier}.fasta'
39 #end for
40 #for $e in $mode.data
41 --data '$e'
42 #end for
43 #for $e in $mode.data_split
44 --data-split '$e'
45 #end for
46 #for $e in $mode.cannot_link
47 --cannot-link '$e'
48 #end for
49 #end if
50 --output 'output'
51 --threads \${GALAXY_SLOTS:-1}
52 --epoches $epoches
53 --batch-size $batch_size
54 --random-seed $random_seed
55 #if $min_len.method == 'min-len'
56 --min-len $min_len.min_len
57 #else if $min_len.method == 'ratio'
58 --ratio $min_len.ratio
59 #end if
60 --orf-finder '$orf_finder'
61 ]]></command>
62 <inputs>
63 <conditional name="mode">
64 <param argument="select" type="select" label="Mode to train the models">
65 <option value="single" selected="true">From one sample</option>
66 <option value="several">From multiple samples (train model across several samples can get better pre-trained model for single-sample binning)</option>
67 </param>
68 <when value="single">
69 <param argument="--input-fasta" type="data" format="fasta,fasta.gz" label="Contig sequences"/>
70 <param argument="--data" type="data" format="csv" label="Train data"/>
71 <param argument="--data-split" type="data" format="csv" label="Split train data"/>
72 <param argument="--cannot-link" type="data" format="txt" label="Cannot-link constraints"/>
73 </when>
74 <when value="several">
75 <param argument="--input-fasta" type="data" multiple="true" format="fasta,fasta.gz" label="Contig sequences"/>
76 <param argument="--data" type="data" format="csv" multiple="true" label="Train data"/>
77 <param argument="--data-split" type="data" format="csv" multiple="true" label="Split train data"/>
78 <param argument="--cannot-link" type="data" format="txt" multiple="true" label="Cannot-link constraints"/>
79 </when>
80 </conditional>
81 <expand macro="min_len"/>
82 <expand macro="orf-finder"/>
83 <expand macro="random-seed"/>
84 <expand macro="epoches"/>
85 <expand macro="batch-size"/>
86 </inputs>
87 <outputs>
88 <expand macro="train_output"/>
89 </outputs>
90 <tests>
91 <test expect_num_outputs="1">
92 <conditional name="mode">
93 <param name="select" value="single"/>
94 <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
95 <param name="data" ftype="csv" value="data.csv"/>
96 <param name="data_split" ftype="csv" value="data_split.csv"/>
97 <param name="cannot_link" ftype="txt" value="cannot.txt"/>
98 </conditional>
99 <conditional name="min_len">
100 <param name="method" value="min-len"/>
101 <param name="min_len" value="2500" />
102 </conditional>
103 <param name="orf_finder" value="prodigal"/>
104 <param name="random-seed" value="0"/>
105 <param name="epoches" value="1"/>
106 <param name="batch_size" value="2048"/>
107 <output name="model" ftype="h5">
108 <assert_contents>
109 <has_size value="3119000" delta="1000" />
110 </assert_contents>
111 </output>
112 </test>
113 <test expect_num_outputs="1">
114 <conditional name="mode">
115 <param name="select" value="several"/>
116 <param name="input_fasta" ftype="fasta" value="input_single.fasta,input_single_2.fasta,input_single_3.fasta"/>
117 <param name="data" ftype="csv" value="data.csv,data.csv,data.csv"/>
118 <param name="data_split" ftype="csv" value="data_split.csv,data_split.csv,data_split.csv"/>
119 <param name="cannot_link" ftype="txt" value="cannot.txt,cannot.txt,cannot.txt"/>
120 </conditional>
121 <conditional name="min_len">
122 <param name="method" value="ratio"/>
123 <param name="ratio" value="0.05" />
124 </conditional>
125 <param name="orf_finder" value="prodigal"/>
126 <param name="random-seed" value="0"/>
127 <param name="epoches" value="20"/>
128 <param name="batch_size" value="2048"/>
129 <output name="model" ftype="h5">
130 <assert_contents>
131 <has_size value="3119000" delta="1000" />
132 </assert_contents>
133 </output>
134 </test>
135 </tests>
136 <help><![CDATA[
137 @HELP_HEADER@
138
139 This tool trains the semi-supervised deep learning model
140
141 Inputs
142 ======
143
144 @HELP_INPUT_FASTA@
145 @HELP_CANNOT@
146 @HELP_DATA@
147
148 Outputs
149 =======
150
151 @HELP_MODEL@
152 ]]></help>
153 <expand macro="citations"/>
154 </tool>