annotate tools/blast_rbh/blast_rbh.xml @ 8:d3eb5cda7270 draft

Uploaded v0.1.2, self comparison and easier command line API
author peterjc
date Tue, 10 Jun 2014 10:09:50 -0400
parents 493243f8eb88
children 982458013bdb
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
1 <tool id="blast_reciprocal_best_hits" name="BLAST Reciprocal Best Hits (RBH)" version="0.1.2">
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
2 <description>from two FASTA files</description>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
3 <requirements>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
4 <requirement type="binary">makeblastdb</requirement>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
5 <requirement type="binary">blastp</requirement>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
6 <requirement type="binary">blastn</requirement>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
7 <requirement type="package" version="2.2.29">blast+</requirement>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
8 </requirements>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
9 <version_command interpreter="python">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
10 blast_rbh.py --version
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
11 </version_command>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
12 <command interpreter="python">
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
13 blast_rbh.py "$fasta_a" "$fasta_b"
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
14 -a $seq.dbtype
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
15 #if $seq.dbtype=="nucl"
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
16 -t $seq.nucl_type
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
17 #else
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
18 -t $seq.prot_type
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
19 #end if
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
20 -i $identity
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
21 -c $q_cover
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
22 -o "$output"
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
23 </command>
7
493243f8eb88 Uploaded v0.1.0g, check return code
peterjc
parents: 6
diff changeset
24 <stdio>
493243f8eb88 Uploaded v0.1.0g, check return code
peterjc
parents: 6
diff changeset
25 <!-- Anything other than zero is an error -->
493243f8eb88 Uploaded v0.1.0g, check return code
peterjc
parents: 6
diff changeset
26 <exit_code range="1:" />
493243f8eb88 Uploaded v0.1.0g, check return code
peterjc
parents: 6
diff changeset
27 <exit_code range=":-1" />
493243f8eb88 Uploaded v0.1.0g, check return code
peterjc
parents: 6
diff changeset
28 </stdio>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
29 <inputs>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
30 <!-- Galaxy does not have sub-types for protein vs nucletide FASTA -->
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
31 <param name="fasta_a" type="data" format="fasta"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
32 label="Genes/proteins from species A"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
33 description="FASTA file, one sequence per gene/protein." />
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
34 <param name="fasta_b" type="data" format="fasta"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
35 label="Genes/proteins from species B"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
36 description="FASTA file, one sequence per gene/protein." />
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
37 <conditional name="seq">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
38 <param name="dbtype" type="select" label="Molecule type of FASTA inputs">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
39 <option value="prot">protein</option>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
40 <option value="nucl">nucleotide</option>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
41 </param>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
42 <when value="prot">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
43 <param name="prot_type" type="select" display="radio" label="Type of BLAST">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
44 <option value="blastp">blastp - Traditional BLASTP to compare a protein query to a protein database</option>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
45 <option value="blastp-short">blastp-short - BLASTP optimized for queries shorter than 30 residues</option>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
46 </param>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
47 </when>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
48 <when value="nucl">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
49 <param name="nucl_type" type="select" display="radio" label="Type of BLAST">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
50 <option value="megablast">megablast - Traditional megablast used to find very similar (e.g., intraspecies or closely related species) sequences</option>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
51 <option value="blastn">blastn - Traditional BLASTN requiring an exact match of 11, for somewhat similar sequences</option>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
52 <option value="blastn-short">blastn-short - BLASTN program optimized for sequences shorter than 50 bases</option>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
53 <option value="dc-megablast">dc-megablast - Discontiguous megablast used to find more distant (e.g., interspecies) sequences</option>
4
57245c11b8cb Uploaded v0.1.0d, TBLASTX support; changed output columns
peterjc
parents: 2
diff changeset
54 <option value="tblastx">tblastx - TBLASTX program using translated query against translated database (protein level matches)</option>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
55 </param>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
56 </when>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
57 </conditional>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
58 <param name="identity" type="float" value="70" min="0" max="100"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
59 label="Minimum percentage identity for BLAST matches"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
60 help="Default is 70%, use 0 for no filtering." />
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
61 <param name="q_cover" type="float" value="50" min="0" max="100"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
62 label="Minimum percentage query coverage for BLAST matches"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
63 help="Default is 50%, use 0 for no filtering." />
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
64 </inputs>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
65 <outputs>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
66 <data name="output" format="tabular" label="BLAST RBH: $fasta_a.name vs $fasta_b.name" />
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
67 </outputs>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
68 <requirements>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
69 </requirements>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
70 <tests>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
71 <test>
1
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
72 <param name="fasta_a" value="four_human_proteins.fasta" ftype="fasta"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
73 <param name="fasta_b" value="rhodopsin_proteins.fasta" ftype="fasta"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
74 <param name="dbtype" value="prot"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
75 <param name="nucl_type" value="blastp"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
76 <param name="identity" value="0.0"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
77 <param name="q_cover" value="0.0"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
78 <output name="output" file="rbh_blastp_four_human_vs_rhodopsin_proteins.tabular" ftype="tabular"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
79 </test>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
80 <test>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
81 <param name="fasta_a" value="rhodopsin_nucs.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
82 <param name="fasta_b" value="three_human_mRNA.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
83 <param name="dbtype" value="nucl"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
84 <param name="nucl_type" value="megablast"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
85 <param name="identity" value="0.0"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
86 <param name="q_cover" value="0.0"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
87 <output name="output" file="rbh_megablast_rhodopsin_nucs_vs_three_human_mRNA.tabular" ftype="tabular"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
88 </test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
89 <test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
90 <param name="fasta_a" value="rhodopsin_nucs.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
91 <param name="fasta_b" value="three_human_mRNA.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
92 <param name="dbtype" value="nucl"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
93 <param name="nucl_type" value="megablast"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
94 <param name="identity" value="92"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
95 <param name="q_cover" value="86"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
96 <output name="output" file="rbh_megablast_rhodopsin_nucs_vs_three_human_mRNA.tabular" ftype="tabular"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
97 </test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
98 <!-- push the percentage identity over the 92.07% level -->
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
99 <test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
100 <param name="fasta_a" value="rhodopsin_nucs.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
101 <param name="fasta_b" value="three_human_mRNA.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
102 <param name="dbtype" value="nucl"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
103 <param name="nucl_type" value="megablast"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
104 <param name="identity" value="92.5"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
105 <param name="q_cover" value="86"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
106 <output name="output" file="rbh_none.tabular" ftype="tabular"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
107 </test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
108 <!-- push the coverage over the 86% level -->
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
109 <test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
110 <param name="fasta_a" value="rhodopsin_nucs.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
111 <param name="fasta_b" value="three_human_mRNA.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
112 <param name="dbtype" value="nucl"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
113 <param name="nucl_type" value="megablast"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
114 <param name="identity" value="92"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
115 <param name="q_cover" value="87"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
116 <output name="output" file="rbh_none.tabular" ftype="tabular"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
117 </test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
118 <test>
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
119 <param name="fasta_a" value="rhodopsin_nucs.fasta" ftype="fasta"/>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
120 <param name="fasta_b" value="three_human_mRNA.fasta" ftype="fasta"/>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
121 <param name="dbtype" value="nucl"/>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
122 <param name="nucl_type" value="tblastx"/>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
123 <param name="identity" value="0.0"/>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
124 <param name="q_cover" value="0.0"/>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
125 <output name="output" file="rbh_tblastx_rhodopsin_nucs_vs_three_human_mRNA.tabular" ftype="tabular"/>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
126 </test>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
127 <test>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
128 <param name="fasta_a" value="three_human_mRNA.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
129 <param name="fasta_b" value="rhodopsin_nucs.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
130 <param name="dbtype" value="nucl"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
131 <param name="nucl_type" value="blastn"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
132 <param name="identity" value="0.0"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
133 <param name="q_cover" value="0.0"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
134 <output name="output" file="rbh_blastn_three_human_mRNA_vs_rhodopsin_nucs.tabular" ftype="tabular"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
135 </test>
6
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
136 <!-- this pair of examples test tied best hits -->
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
137 <test>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
138 <param name="fasta_a" value="k12_ten_proteins.fasta" ftype="fasta"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
139 <param name="fasta_b" value="k12_edited_proteins.fasta" ftype="fasta"/>
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
140 <param name="dbtype" value="prot"/>
6
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
141 <param name="nucl_type" value="blastp"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
142 <param name="identity" value="0.0"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
143 <param name="q_cover" value="0.0"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
144 <output name="output" file="rbh_blastp_k12.tabular" ftype="tabular"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
145 </test>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
146 <test>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
147 <param name="fasta_a" value="k12_edited_proteins.fasta" ftype="fasta"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
148 <param name="fasta_b" value="k12_ten_proteins.fasta" ftype="fasta"/>
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
149 <param name="dbtype" value="prot"/>
6
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
150 <param name="nucl_type" value="blastp"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
151 <param name="identity" value="0.0"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
152 <param name="q_cover" value="0.0"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
153 <output name="output" file="rbh_blastp_k12.tabular" ftype="tabular"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
154 </test>
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
155 <!-- this tests self-comparison -->
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
156 <test>
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
157 <param name="fasta_a" value="k12_edited_proteins.fasta" ftype="fasta"/>
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
158 <param name="fasta_b" value="k12_edited_proteins.fasta" ftype="fasta"/>
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
159 <param name="dbtype" value="prot"/>
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
160 <param name="nucl_type" value="blastp"/>
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
161 <param name="identity" value="80.0"/>
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
162 <param name="q_cover" value="80.0"/>
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
163 <output name="output" file="rbh_blastp_k12_self.tabular" ftype="tabular"/>
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
164 </test>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
165 </tests>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
166 <help>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
167 **What it does**
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
168
2
8aa6385b9a05 Uploaded v0.1.0b, more verbose output
peterjc
parents: 1
diff changeset
169 Takes two FASTA files (*species A* and *species B*), builds a BLAST database
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
170 for each, runs reciprocal BLAST searchs (*A vs B*, and *B vs A*), optionally
2
8aa6385b9a05 Uploaded v0.1.0b, more verbose output
peterjc
parents: 1
diff changeset
171 filters the HSPs, and then compiles a list of the reciprocal best hits (RBH).
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
172
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
173 The output from this tool is a tabular file containing multiple columns, with
2
8aa6385b9a05 Uploaded v0.1.0b, more verbose output
peterjc
parents: 1
diff changeset
174 information about the BLAST matches used:
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
175
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
176 ====== ==================================
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
177 Column Description
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
178 ------ ----------------------------------
2
8aa6385b9a05 Uploaded v0.1.0b, more verbose output
peterjc
parents: 1
diff changeset
179 1 ID from *species A*
8aa6385b9a05 Uploaded v0.1.0b, more verbose output
peterjc
parents: 1
diff changeset
180 2 ID from *species B*
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
181 3 Length of sequence *A*
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
182 4 Length of sequence *B*
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
183 5 Percentage of sequence *A* covered
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
184 6 Percentage of sequence *B* covered
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
185 7 HSP alignment length
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
186 8 HSP percentage identity
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
187 9 HSP bitscore
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
188 ====== ==================================
2
8aa6385b9a05 Uploaded v0.1.0b, more verbose output
peterjc
parents: 1
diff changeset
189
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
190 These values correspond to the ``qseqid``/``sseqid``, ``qlen``/``slen``,
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
191 ``qcovhsp``, ``length``, ``pident`` and ``bitscore`` values in the BLAST+
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
192 tabular output.
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
193
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
194 For the alignment length, bitscore and percentage identity the values for
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
195 *A vs B* and *B vs A* are typically the same, so their minimum is shown.
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
196 The coverage values are given by the HSP alignment length divided by the
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
197 sequence length (adjusted by a factor of three for TBLASTX).
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
198
6
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
199 Note that if a sequence has equally scoring top BLAST matches to multiple
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
200 sequence in the other file, it will not be considered for an RBH. This
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
201 can happen following gene duplication, or for (near) identical gene
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
202 duplicates.
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
203
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
204 .. class:: warningmark
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
205
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
206 **Note**
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
207
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
208 If you are trying to use BLAST RBH matches to identify candidate orthologues
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
209 or transfer annotation, you *must* use a percentage identity and minimum
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
210 coverage threshold or similiar. See:
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
211
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
212 Punta and Ofran (2008) The Rough Guide to In Silico Function Prediction,
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
213 or How To Use Sequence and Structure Information To Predict Protein
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
214 Function. PLoS Comput Biol 4(10): e1000160.
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
215 http://dx.doi.org/10.1371/journal.pcbi.1000160
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
216
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
217 The defaults are to require 70% sequence identity over the aligned region
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
218 (using ``pident`` in the BLAST+ tabular output), and that the HSP alignment
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
219 covers at least 50% of the query sequence (using ``qcovhsp`` in the BLAST+
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
220 tabular output).
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
221
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
222
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
223 **References**
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
224
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
225 A specific paper covering this tool is planned, but please also cite:
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
226
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
227 Christiam Camacho et al. (2009).
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
228 BLAST+: architecture and applications.
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
229 BMC Bioinformatics. 15;10:421.
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
230 http://dx.doi.org/10.1186/1471-2105-10-421
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
231
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
232 This wrapper is available to install into other Galaxy Instances via the Galaxy
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
233 Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/blast_rbh
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
234 </help>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
235 </tool>