annotate ectyper.xml @ 5:daba54cd25ca draft

planemo upload for repository https://github.com/phac-nml/galaxy_tools/tree/master/tools/ectyper commit f574c20c5f06498727d186afc4d1a92f5344eb59

1 <tool id="ectyper" name="ectyper" version="1.0.0">
2   <description>ectyper is a standalone serotyping module for Escherichia coli. It supports fasta and fastq file formats.</description>
3   <xrefs>
4     <xref type="bio.tools">ectyper</xref>
5   </xrefs>
6   <requirements>
7      <requirement type="package" version="1.0.0">ectyper</requirement>
8   </requirements>
9   <command detect_errors="exit_code">
10   <![CDATA[
11   #set $genomes = ''
12   #if hasattr($input, '__iter__')
13     #for $i in $input
14         ln -s "${i}" "${i.element_identifier}" &&
15         #if len($genomes) > 0
16           #set $genomes = $genomes + ',' + str($i.element_identifier)
17         #else
18           #set $genomes = str($i.element_identifier)
19         #end if      
20     #end for
21   #else
22     ln -s "${input}" "${input.element_identifier}" &&
23     #set $genomes = $input.element_identifier
24   #end if
25 
26   #if $adv_param.mash_input
27     ln -s "${adv_param.mash_input}" mash_sketch.msh &&
28   #end if
29 
30 
31   #if $adv_param.db_input
32     ln -s "${adv_param.db_input}" custom_db.json &&
33   #end if
34 
35 
36   ectyper  --cores \${GALAXY_SLOTS:-4} 
37   --input "${genomes}" 
38   -opid '$adv_param.opid'
39   -opcov '$adv_param.opcov'
40   -hpid '$adv_param.hpid'
41   -hpcov '$adv_param.hpcov'
42 
43   #if $adv_param.verifyEcoli
44     --verify
45   #end if
46 
47   #if $adv_param.mash_input
48     --refseq mash_sketch.msh
49   #end if
50 
51   #if $adv_param.db_input
52     --dbpath custom_db.json
53   #end if
54 
55   --output '.'
56   ]]>
57   </command>
58   <inputs>
59     <param name="input" type="data"  format="fastq,fasta" label="Genome(s) input(s)" help="FASTA or FASTQ file(s)"/>
60     <section name="adv_param" title="Advanced parameters" expanded="False">
61       <param name="opid" label="O antigen minimum %identity" type="integer" value="90" min="1" max="100"/>
62       <param name="opcov" label="O antigen minimum %coverage" type="integer" value="90" min="1" max="100"/>
63       <param name="hpid" label="H antigen minimum %identity" type="integer" value="95" min="1" max="100"/>
64       <param name="hpcov" label="H antigen minimum %coverage" type="integer" value="50" min="1" max="100"/>
65       <param name="verifyEcoli" type="boolean" checked="true" label="Enable E. coli species verification"/>
66       <param name="blastresults" type="boolean" checked="false"  label="Include BLAST allele alignment results tab-delim file in the outputs?" />
67       <param name="logging" type="boolean" checked="false"  label="Include log file in the run outputs?" />
68       <param name="mash_input" type="data" optional="true" format="binary" label="Mash genome sketches (Optional)" help="Optionally provide custom MASH genome sketch to help with species identification (otherwise default RefSeq sketch is used)"/>
69       <param name="db_input" type="data" optional="true" format="json" label="Custom database of alleles (Optional)" help="Optionally provide custom database of alleles in JSON format"/>
70     </section>
71   </inputs>
72   <outputs>
73     <data name="output_result" format="tabular" from_work_dir="output.tsv" label="${tool.name} serotype report on ${input.element_identifier}"> </data>
74     <data name="output_log" format="txt" from_work_dir="ectyper.log" label="${tool.name} log file on ${input.element_identifier}">
75         <filter>adv_param['logging']==True</filter>
76     </data>
77     <data name="output_blast" format="tabular" from_work_dir="blast_output_alleles.txt"  label="${tool.name} BLAST results file on ${input.element_identifier}">
78          <filter>adv_param['blastresults']==True</filter>
79     </data>
80   </outputs>
81   <tests>
82     <test expect_num_outputs="1">
83       <param name="input" value="Escherichia2.fastq"/>
84       <assert_stderr>
85             <has_text text="O22"/> 
86             <has_text text="H8"/> 
87       </assert_stderr>
88       <output name="output_result" ftype="tabular" >
89           <assert_contents>
90               <has_text_matching expression="O22"/>
91          </assert_contents>
92       </output>
93     </test>
94   </tests>
95 
96   <help>
97 **Syntax**
98 
99 
00 This tool identifies the serotype of both assembled or assembly-free Escherichia coli genome samples based on a set of the key O and H antigen determinant genes including *wzm/wzt* or *wzx/wzy* and *fliC/flkA/flmA*.
01 Unique to the tool, species identification module allows for non-E.coli genomes identification including other Escherichia genus species.
02 This version improves antigen call rates on "difficult samples" by use of an adaptive threshold. This is especially useful when antigen genes are truncated or poorly covered by raw reads.
03 If no antigen call is being predicted by the tool, try to lower %coverage parameter first. For more information on the new Quality Control module and running parameter details please visit https://github.com/phac-nml/ecoli_serotyping.
04 
05 
06 -----
07 
08 **Input:**
09 
10 Accepts a variety of inputs including both single and/or multiple FASTQ and/or FASTA file(s). Inputs might contain pure raw reads, but for more accurate results, draft assemblies are recommended.
11 
12 
13 The default MASH RefSeq genome sketch (https://gembox.cbcb.umd.edu/mash/refseq.genomes.k21s1000.msh) containing approximately 91K genomes is included and automatically updated every 6 months.
14 
15 
16 
17 **Output:**
18 
19 Tab-delimited report listing identified O and H antigens together with corresponding the highest-scoring alleles and normalized BLAST score defined as (%identity x %coverage) / 1e4.
20 If *verifyEcoli* parameter is enabled, final report will contain allele quality control information on results for reporting purposes. PASS (REPORTABLE) QC flag means that O and H antigen calls are of sufficient to unambiguously resolve them from all other antigens.
21 
22 -----
23 
24 **Parameters (Optional):**
25   - **Enable E. coli species verification:** for species verification in case samples are of non-E.coli origin
26   - **Include BLAST allele alignment results tab-delim file in the outputs?** Get reference allele sequences and detailed BLAST output
27   - **Include log file in the run outputs?:** Get optional logs of the ectyper run for a more detailed results assessment and troubleshooting
28 
29   </help>
30 <citations>
31     <citation type="bibtex">
32   @misc{githubectyper,
33   author = {Laing Chad},
34   title = {ECtyper - serotyping module for Escherichia coli},
35   publisher = {GitHub},
36   journal = {GitHub repository},
37   url = {https://github.com/phac-nml/ecoli_serotyping}
38     }</citation>
39 </citations>
40 </tool>