Mercurial > repos > iuc > fastani

annotate fastani.xml @ 0:2c7ac12ad75a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
author iuc
date Tue, 18 Feb 2020 15:58:57 -0500
parents
children 3c6e0e8df873
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
1 <tool id="fastani" name="FastANI" version="@VERSION@">
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
2 <description> fast alignment-free computation of whole-genome Average Nucleotide Identity</description>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
3 <macros>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
4 <import>macros.xml</import>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
5 </macros>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
6 <expand macro="requirements" />
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
7 <version_command>fastANI --version</version_command>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
8 <command detect_errors="exit_code">
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
9 <![CDATA[
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
10 #import re
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
11
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
12 ### SET UP INPUTS ###
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
13 #for $input_q in $query:
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
14 #set $file_name = re.sub('[^\w_]', '_', $input_q.element_identifier)
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
15 ln -fs '$input_q' '${file_name}_query' &&
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
16 echo '${file_name}_query' >> query.lst &&
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
17 #end for
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
18
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
19 #for $input_r in $reference:
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
20 #set $file_name = re.sub('[^\w_]', '_', $input_r.element_identifier)
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
21 ln -fs '$input_r' '${file_name}_ref' &&
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
22 echo '${file_name}_ref' >> ref.lst &&
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
23 #end for
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
24
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
25
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
26 ### COMMAND ###
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
27
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
28 fastANI --ql query.lst --rl ref.lst -o output -t "\${GALAXY_SLOTS:-1}"
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
29
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
30 ]]></command>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
31 <inputs>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
32 <param name="query" type="data" format="fasta" multiple="true" label="Query Sequence(s)"
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
33 help="Specify any number of query sequences in fasta format as input." />
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
34 <param name="reference" type="data" format="fasta" multiple="true" label="Reference Sequence(s)"
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
35 help="Specify any number of reference sequences in fasta format as input." />
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
36 </inputs>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
37 <outputs>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
38 <data name="output" format="tabular" from_work_dir="output" label="${tool.name} on ${on_string} Output"/>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
39 </outputs>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
40 <tests>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
41 <test>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
42 <param name="query" value="E.coli_1.fasta" />
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
43 <param name="reference" value="S.flexneri_1.fasta" />
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
44 <output name="output" file="single.out" compare="sim_size" />
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
45 </test>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
46 <test>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
47 <param name="query" value="E.coli_1.fasta,E.coli_2.fasta" />
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
48 <param name="reference" value="S.flexneri_1.fasta,S.flexneri_2.fasta" />
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
49 <output name="output" file="multi.out" compare="sim_size" />
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
50 </test>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
51 </tests>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
52 <help><![CDATA[
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
53
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
54 FastANI
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
55 =======
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
56
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
57 FastANI is developed for fast alignment-free computation of whole-genome
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
58 Average Nucleotide Identity (ANI). ANI is defined as mean nucleotide
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
59 identity of orthologous gene pairs shared between two microbial genomes.
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
60 FastANI supports pairwise comparison of both complete and draft genome
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
61 assemblies. Its underlying procedure follows a similar workflow as described
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
62 by `Goris et al. 2007 <https://doi.org/10.1099/ijs.0.64483-0>`_. However, it avoids expensive sequence alignments and
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
63 uses `Mashmap <https://github.com/marbl/MashMap>`_ as its MinHash based sequence mapping engine to compute the
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
64 orthologous mappings and alignment identity estimates. Based on our
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
65 experiments with complete and draft genomes, its accuracy is on par with
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
66 `BLAST-based ANI solver <http://enve-omics.ce.gatech.edu/ani/>`_ and it achieves two to three orders of magnitude
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
67 speedup. Therefore, it is useful for pairwise ANI computation of large
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
68 number of genome pairs. More details about its speed, accuracy and potential
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
69 applications are described here: `"High Throughput ANI Analysis of 90K
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
70 Prokaryotic Genomes Reveals Clear Species Boundaries" <https://doi-org.uml.idm.oclc.org/10.1038/s41467-018-07641-9>`_.
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
71
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
72 Please visit the authors at: https://github.com/ParBLiSS/FastANI
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
73
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
74
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
75 Inputs
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
76 ------
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
77
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
78 **Query Sequence(s):**
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
79 Input one or more query genomes in fasta format
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
80
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
81 **Reference Sequence(s):**
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
82 Input one or more reference genomes to be compared to the query genomes
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
83
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
84
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
85 Output
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
86 ------
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
87
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
88 Tabular table output with columns: Query Genome, Reference Genome, ANI Value, Count of Bidirectional Fragment Mappings, and Total Query Fragments.
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
89
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
90 Output table looks as such:
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
91
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
92 +------------+------------+-----------+--------+--------+
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
93 | Genome A | Genome C | 97.5883 | 1405 | 1594 |
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
94 +------------+------------+-----------+--------+--------+
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
95 | Genome A | Genome D | 95.6663 | 1405 | 1594 |
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
96 +------------+------------+-----------+--------+--------+
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
97 | Genome B | Genome C | 92.4281 | 1409 | 1553 |
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
98 +------------+------------+-----------+--------+--------+
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
99 | Genome B | Genome D | 99.9242 | 1396 | 1553 |
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
100 +------------+------------+-----------+--------+--------+
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
101
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
102 |
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
103 | Thanks to Thanh Lê for building the initial Galaxy wrapper.
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
104 ]]></help>
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
105 <expand macro="citations" />
2c7ac12ad75a "planemo upload commit 01a4c6cb401a89acddd991825fcaa304052d275f"
iuc
parents:
diff changeset
106 </tool>