Mercurial > repos > iuc > dram_annotate

comparison dram_annotate.xml @ 0:3f9129750546 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/dram commit df10ba86507266a6a6f83c9bbefb7191a41b46f5
author iuc
date Sat, 10 Dec 2022 21:13:10 +0000
parents
children 3925138d40bf
comparison
equal deleted inserted replaced
-1:000000000000 0:3f9129750546
1 <tool id="dram_annotate" name="DRAM annotate" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2 <description>metagenome-assembled-genomes (MAGs)</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <expand macro="stdio"/>
8 <command detect_errors="exit_code"><![CDATA[
9 #import os
10
11 ## DRAM names the genbank output based on the input_fasta file name
12 #set input_fasta_file_name = $os.path.splitext($os.path.basename(str($input_fasta)))[0]
13 #set output_gbk_file_name = $input_fasta_file_name + '.gbk'
14
15 DRAM.py annotate
16 --input_fasta '$input_fasta'
17 --output_dir 'output_dir'
18 --min_contig_size $min_contig_size
19 --prodigal_mode '$prodigal_mode'
20 --trans_table $trans_table
21 --bit_score_threshold $bit_score_threshold
22 --rbh_bit_score_threshold $rbh_bit_score_threshold
23 $kofam_use_dbcan2_thresholds
24 #if str($custom_fasta_dbs_cond.custom_dbs_fasta) == 'yes':
25 #for additional_db in $custom_fasta_dbs_cond.custom_fasta_dbs:
26 --custom_db_name '$additional_db.custom_db_name'
27 --custom_fasta_loc '$additional_db.custom_fasta_loc'
28 #end for
29 #end if
30 #if str($custom_hmm_dbs_cond.custom_dbs_hmm) == 'yes':
31 #for additional_db in $custom_hmm_dbs_cond.custom_hmm_dbs:
32 --custom_hmm_name '$additional_db.custom_hmm_name'
33 --custom_hmm_loc '$additional_db.custom_hmm_loc'
34 #if $additional_db.custom_hmm_cutoffs_loc:
35 --custom_hmm_cutoffs_loc '$additional_db.custom_hmm_cutoffs_loc'
36 #end if
37 #end for
38 #end if
39 $use_uniref
40 $use_vogdb
41 $low_mem_mode
42 $skip_trnascan
43 --threads \${GALAXY_SLOTS:-10}
44 && test -f 'output_dir/genes.faa' && mv 'output_dir/genes.faa' '$output_genes_faa' || echo 'No genes.faa output produced'
45 && test -f 'output_dir/genes.fna' && mv 'output_dir/genes.fna' '$output_genes_fna' || echo 'No genes.fna output produced'
46 && test -f 'output_dir/genes.gff' && mv 'output_dir/genes.gff' '$output_genes_gff' || echo 'No genes.gff output produced'
47 && test -f 'output_dir/scaffolds.fna' && mv 'output_dir/scaffolds.fna' '$output_scaffolds_fna' || echo 'No scaffolds.fna output produced'
48 && test -f 'output_dir/rrnas.tsv' && mv 'output_dir/rrnas.tsv' '$output_rrnas' || echo 'No rrnas.tsv output produced'
49 && test -f 'output_dir/trnas.tsv' && mv 'output_dir/trnas.tsv' '$output_trnas' || echo 'No trnas.tsv output produced'
50 && test -f 'output_dir/genbank/$output_gbk_file_name' && mv 'output_dir/genbank/$output_gbk_file_name' '$output_genbank' || echo 'No genbank output produced'
51 && test -f 'output_dir/annotations.tsv' && mv 'output_dir/annotations.tsv' '$output_annotations' || echo 'No annotations.tsv output produced'
52 ]]></command>
53 <inputs>
54 <param argument="--input_fasta" type="data" format="fasta,fasta.gz" label="FASTA file"/>
55 <param argument="--min_contig_size" type="integer" value="2500" min="0" label="Minimum contig size to be used for gene prediction"/>
56 <param argument="--prodigal_mode" type="select" label="Select mode of prodigal to use for gene calling" help="Single mode requires genomes which are high quality with low contamination and long contigs (average length >3 Kbp)">
57 <option value="single" selected="true">single</option>
58 <option value="meta">meta</option>
59 <option value="train">train</option>
60 </param>
61 <param argument="--trans_table" type="integer" value="11" min="1" max="25" label="Translation table for prodigal to use for gene calling"/>
62 <param argument="--bit_score_threshold" type="integer" value="60" min="1" label="Minimum bitScore of search to retain hits"/>
63 <param argument="--rbh_bit_score_threshold" type="integer" value="350" min="1" label="Minimum bitScore of reverse best hits to retain hits"/>
64 <param argument="--kofam_use_dbcan2_thresholds" type="boolean" truevalue="--kofam_use_dbcan2_thresholds" falsevalue="" checked="false" label="Use dbcan2 suggested HMM cutoffs for KOfam annotation instead of KOfam recommended cutoffs?"/>
65 <conditional name="custom_fasta_dbs_cond">
66 <param name="custom_dbs_fasta" type="select" label="Specify additional fasta files against which to annotate?">
67 <option value="no" selected="true">No</option>
68 <option value="yes">Yes</option>
69 </param>
70 <when value="no"/>
71 <when value="yes">
72 <repeat name="custom_fasta_dbs" title="FASTA file" min="1">
73 <param argument="--custom_db_name" type="text" value="CF1" label="Custom FASTA database name">
74 <validator type="empty_field"/>
75 <expand macro="sanitizer"/>
76 </param>
77 <param argument="--custom_fasta_loc" type="data" format="fasta,fasta.gz" label="Custom database FASTA file"/>
78 </repeat>
79 </when>
80 </conditional>
81 <conditional name="custom_hmm_dbs_cond">
82 <param name="custom_dbs_hmm" type="select" label="Specify additional hmm files against which to annotate?">
83 <option value="no" selected="true">No</option>
84 <option value="yes">Yes</option>
85 </param>
86 <when value="no"/>
87 <when value="yes">
88 <repeat name="custom_hmm_dbs" title="HMM file" min="1">
89 <param argument="--custom_hmm_name" type="text" value="CH1" label="Custom HMM database name">
90 <validator type="empty_field"/>
91 <expand macro="sanitizer"/>
92 </param>
93 <param argument="--custom_hmm_loc" type="data" format="hmm2,hmm3" label="Custom database HMM file"/>
94 <param argument="--custom_hmm_cutoffs_loc" type="data" format="tabular,tsv" optional="true" label="Custom HMM cutoffs and descriptions file" help="Optional, leave blank to ignore"/>
95 </repeat>
96 </when>
97 </conditional>
98 <param argument="--use_uniref" type="boolean" truevalue="--use_uniref" falsevalue="" checked="false" label="Annotate the input FASTA files against UniRef?" help="Increases run time and memory requirements"/>
99 <param argument="--use_vogdb" type="boolean" truevalue="--use_vogdb" falsevalue="" checked="false" label="Annotate the input FASTA files against VOGDB?" help="Decreases run time"/>
100 <param argument="--low_mem_mode" type="boolean" truevalue="--low_mem_mode" falsevalue="" checked="false" label="Skip annotating with uniref and use kofam?" help="Decreases memory requirements"/>
101 <param argument="--skip_trnascan" type="boolean" truevalue="--skip_trnascan" falsevalue="" checked="false" label="Skip transcan"/>
102 </inputs>
103 <outputs>
104 <data name="output_genes_faa" format="fasta" label="${tool.name} on ${on_string}: genes.faa"/>
105 <data name="output_genes_fna" format="fasta" label="${tool.name} on ${on_string}: genes.fna"/>
106 <data name="output_genes_gff" format="gff3" label="${tool.name} on ${on_string}: genes.gff"/>
107 <data name="output_scaffolds_fna" format="fasta" label="${tool.name} on ${on_string}: scaffolds"/>
108 <data name="output_rrnas" format="tabular" label="${tool.name} on ${on_string}: rrnas"/>
109 <data name="output_trnas" format="tabular" label="${tool.name} on ${on_string}: trnas"/>
110 <data name="output_genbank" format="genbank" label="${tool.name} on ${on_string}: genbank"/>
111 <data name="output_annotations" format="tabular" label="${tool.name} on ${on_string}: annotations"/>
112 </outputs>
113 <tests>
114 <test expect_num_outputs="8">
115 <param name="input_fasta" value="input_annotate1.fasta.gz" ftype="fasta.gz"/>
116 <param name="prodigal_mode" value="meta"/>
117 <output name="output_genes_faa">
118 <assert_contents>
119 <has_text text="rank"/>
120 </assert_contents>
121 </output>
122 <output name="output_genes_fna">
123 <assert_contents>
124 <has_text text="rank"/>
125 </assert_contents>
126 </output>
127 <output name="output_genes_gff">
128 <assert_contents>
129 <has_text text="gff-version 3"/>
130 </assert_contents>
131 </output>
132 <output name="output_scaffolds_fna">
133 <assert_contents>
134 <has_text text="scaffold"/>
135 </assert_contents>
136 </output>
137 <output name="output_rrnas">
138 <assert_contents>
139 <has_text text="scaffold"/>
140 </assert_contents>
141 </output>
142 <output name="output_trnas">
143 <assert_contents>
144 <has_text text="fasta"/>
145 </assert_contents>
146 </output>
147 <output name="output_genbank">
148 <assert_contents>
149 <has_text text="LOCUS"/>
150 </assert_contents>
151 </output>
152 <output name="output_annotations">
153 <assert_contents>
154 <has_text text="fasta"/>
155 </assert_contents>
156 </output>
157 </test>
158 <!-- These settings require a db which doesn't exist in the test environment -->
159 <test expect_failure="true">
160 <param name="input_fasta" value="input_annotate1.fasta.gz" ftype="fasta.gz"/>
161 <param name="custom_dbs_fasta" value="yes"/>
162 <repeat name="custom_fasta_dbs">
163 <param name="custom_db_name" value="CF1"/>
164 <param name="custom_fasta_loc" value="annotate_custom.fasta" ftype="fasta"/>
165 </repeat>
166 <param name="custom_dbs_hmm" value="yes"/>
167 <repeat name="custom_hmm_dbs">
168 <param name="custom_hmm_name" value="CH1"/>
169 <param name="custom_hmm_loc" value="annotate_custom.hmm" ftype="hmm3"/>
170 </repeat>
171 <param name="prodigal_mode" value="meta"/>
172 <assert_stderr>
173 <has_text text="returned non-zero exit status"/>
174 </assert_stderr>
175 </test>
176 </tests>
177 <help>
178 **What it does**
179
180 @WHATITDOESHEADER@
181
182 This tool annotates genes by assigning database identifiers to them. Short contigs (default less than 2,500 bp) are initially
183 removed and then Prodigal is used to detect open reading frames (ORFs) and to predict their amino acid sequences. Next, DRAM
184 searches all amino acid sequences against multiple databases, providing a single Raw output. When gene annotation is complete,
185 all results are merged in a single tabular annotation table, including the best hit for each database, for user comparison.
186
187 This tool accepts assembly-derived fastA files which may come from unbinned data (metagenome contig or scaffold files) or
188 genome-resolved data from one or many organisms (isolate genomes, single-amplified genome (SAGs), MAGs).
189
190 This tool produces the following outputs.
191
192 * A tabular file with all annotations from Pfam, UniProt, dbCAN and MEROPS databases for all genes in the input genomes
193 * Genbank files for each genome
194 * A gff file of all annotations across genomes
195 * A fasta file of each open reading frame amino acid sequence and best ranked annotation
196 * Tabular files with tRNAs and rRNAs
197
198 @WHATITDOESFOOTER@
199 </help>
200 <expand macro="citations"/>
201 </tool>