annotate tools/blast_rbh/blast_rbh.xml @ 14:40c85a67e645 draft

Uploaded v0.1.6, offer the new blastp-fast tasked added in BLAST+ 2.2.30.
author peterjc
date Thu, 27 Nov 2014 11:41:08 -0500
parents 4454596ed127
children 904dfe4faae7
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
14
40c85a67e645 Uploaded v0.1.6, offer the new blastp-fast tasked added in BLAST+ 2.2.30.
peterjc
parents: 13
diff changeset
1 <tool id="blast_reciprocal_best_hits" name="BLAST Reciprocal Best Hits (RBH)" version="0.1.6">
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>
12
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
4 <requirement type="package" version="1.64">biopython</requirement>
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
5 <requirement type="python-module">Bio</requirement>
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
6 <requirement type="binary">makeblastdb</requirement>
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
7 <requirement type="binary">blastp</requirement>
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
8 <requirement type="binary">blastn</requirement>
13
4454596ed127 Uploaded
peterjc
parents: 12
diff changeset
9 <requirement type="package" version="2.2.30">blast+</requirement>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
10 </requirements>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
11 <version_command interpreter="python">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
12 blast_rbh.py --version
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
13 </version_command>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
14 <command interpreter="python">
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
15 blast_rbh.py "$fasta_a" "$fasta_b"
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
16 -a $seq.dbtype
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
17 #if $seq.dbtype=="nucl"
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
18 -t $seq.nucl_type
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
19 #else
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
20 -t $seq.prot_type
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
21 #end if
12
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
22 $make_nr
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
23 -i $identity
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
24 -c $q_cover
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
25 -o "$output"
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
26 </command>
7
493243f8eb88 Uploaded v0.1.0g, check return code
peterjc
parents: 6
diff changeset
27 <stdio>
493243f8eb88 Uploaded v0.1.0g, check return code
peterjc
parents: 6
diff changeset
28 <!-- Anything other than zero is an error -->
493243f8eb88 Uploaded v0.1.0g, check return code
peterjc
parents: 6
diff changeset
29 <exit_code range="1:" />
493243f8eb88 Uploaded v0.1.0g, check return code
peterjc
parents: 6
diff changeset
30 <exit_code range=":-1" />
493243f8eb88 Uploaded v0.1.0g, check return code
peterjc
parents: 6
diff changeset
31 </stdio>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
32 <inputs>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
33 <!-- Galaxy does not have sub-types for protein vs nucletide FASTA -->
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
34 <param name="fasta_a" type="data" format="fasta"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
35 label="Genes/proteins from species A"
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 <param name="fasta_b" type="data" format="fasta"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
38 label="Genes/proteins from species B"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
39 description="FASTA file, one sequence per gene/protein." />
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
40 <conditional name="seq">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
41 <param name="dbtype" type="select" label="Molecule type of FASTA inputs">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
42 <option value="prot">protein</option>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
43 <option value="nucl">nucleotide</option>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
44 </param>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
45 <when value="prot">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
46 <param name="prot_type" type="select" display="radio" label="Type of BLAST">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
47 <option value="blastp">blastp - Traditional BLASTP to compare a protein query to a protein database</option>
14
40c85a67e645 Uploaded v0.1.6, offer the new blastp-fast tasked added in BLAST+ 2.2.30.
peterjc
parents: 13
diff changeset
48 <option value="blastp-fast">blastp-fast - Uses longer words as described by Shiryev et al (2007)</option>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
49 <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
50 </param>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
51 </when>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
52 <when value="nucl">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
53 <param name="nucl_type" type="select" display="radio" label="Type of BLAST">
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
54 <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
55 <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
56 <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
57 <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
58 <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
59 </param>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
60 </when>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
61 </conditional>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
62 <param name="identity" type="float" value="70" min="0" max="100"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
63 label="Minimum percentage identity for BLAST matches"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
64 help="Default is 70%, use 0 for no filtering." />
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
65 <param name="q_cover" type="float" value="50" min="0" max="100"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
66 label="Minimum percentage query coverage for BLAST matches"
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
67 help="Default is 50%, use 0 for no filtering." />
12
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
68 <param name="make_nr" type="boolean" checked="false" truevalue="--nr" falsevalue=""
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
69 label="Process input FASTA files to collapse identical sequences"
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
70 help="i.e. First make the input non-redundant" />
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
71 </inputs>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
72 <outputs>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
73 <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
74 </outputs>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
75 <requirements>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
76 </requirements>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
77 <tests>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
78 <test>
1
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
79 <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
80 <param name="fasta_b" value="rhodopsin_proteins.fasta" ftype="fasta"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
81 <param name="dbtype" value="prot"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
82 <param name="nucl_type" value="blastp"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
83 <param name="identity" value="0.0"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
84 <param name="q_cover" value="0.0"/>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
85 <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
86 </test>
a68f4e5789d7 Uploaded v0.1.0a, including a blastp test.
peterjc
parents: 0
diff changeset
87 <test>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
88 <param name="fasta_a" value="rhodopsin_nucs.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
89 <param name="fasta_b" value="three_human_mRNA.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
90 <param name="dbtype" value="nucl"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
91 <param name="nucl_type" value="megablast"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
92 <param name="identity" value="0.0"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
93 <param name="q_cover" value="0.0"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
94 <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
95 </test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
96 <test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
97 <param name="fasta_a" value="rhodopsin_nucs.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
98 <param name="fasta_b" value="three_human_mRNA.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
99 <param name="dbtype" value="nucl"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
100 <param name="nucl_type" value="megablast"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
101 <param name="identity" value="92"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
102 <param name="q_cover" value="86"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
103 <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
104 </test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
105 <!-- push the percentage identity over the 92.07% level -->
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
106 <test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
107 <param name="fasta_a" value="rhodopsin_nucs.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
108 <param name="fasta_b" value="three_human_mRNA.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
109 <param name="dbtype" value="nucl"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
110 <param name="nucl_type" value="megablast"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
111 <param name="identity" value="92.5"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
112 <param name="q_cover" value="86"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
113 <output name="output" file="rbh_none.tabular" ftype="tabular"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
114 </test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
115 <!-- push the coverage over the 86% level -->
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
116 <test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
117 <param name="fasta_a" value="rhodopsin_nucs.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
118 <param name="fasta_b" value="three_human_mRNA.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
119 <param name="dbtype" value="nucl"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
120 <param name="nucl_type" value="megablast"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
121 <param name="identity" value="92"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
122 <param name="q_cover" value="87"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
123 <output name="output" file="rbh_none.tabular" ftype="tabular"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
124 </test>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
125 <test>
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
126 <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
127 <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
128 <param name="dbtype" value="nucl"/>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
129 <param name="nucl_type" value="tblastx"/>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
130 <param name="identity" value="0.0"/>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
131 <param name="q_cover" value="0.0"/>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
132 <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
133 </test>
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
134 <test>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
135 <param name="fasta_a" value="three_human_mRNA.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
136 <param name="fasta_b" value="rhodopsin_nucs.fasta" ftype="fasta"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
137 <param name="dbtype" value="nucl"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
138 <param name="nucl_type" value="blastn"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
139 <param name="identity" value="0.0"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
140 <param name="q_cover" value="0.0"/>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
141 <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
142 </test>
6
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
143 <!-- this pair of examples test tied best hits -->
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
144 <test>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
145 <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
146 <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
147 <param name="dbtype" value="prot"/>
6
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
148 <param name="nucl_type" value="blastp"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
149 <param name="identity" value="0.0"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
150 <param name="q_cover" value="0.0"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
151 <output name="output" file="rbh_blastp_k12.tabular" ftype="tabular"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
152 </test>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
153 <test>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
154 <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
155 <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
156 <param name="dbtype" value="prot"/>
6
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
157 <param name="nucl_type" value="blastp"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
158 <param name="identity" value="0.0"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
159 <param name="q_cover" value="0.0"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
160 <output name="output" file="rbh_blastp_k12.tabular" ftype="tabular"/>
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
161 </test>
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
162 <!-- this tests self-comparison -->
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
163 <test>
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
164 <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
165 <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
166 <param name="dbtype" value="prot"/>
14
40c85a67e645 Uploaded v0.1.6, offer the new blastp-fast tasked added in BLAST+ 2.2.30.
peterjc
parents: 13
diff changeset
167 <param name="nucl_type" value="blastp-fast"/>
8
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
168 <param name="identity" value="80.0"/>
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
169 <param name="q_cover" value="80.0"/>
d3eb5cda7270 Uploaded v0.1.2, self comparison and easier command line API
peterjc
parents: 7
diff changeset
170 <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
171 </test>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
172 </tests>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
173 <help>
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
174 **What it does**
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
175
2
8aa6385b9a05 Uploaded v0.1.0b, more verbose output
peterjc
parents: 1
diff changeset
176 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
177 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
178 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
179
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
180 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
181 information about the BLAST matches used:
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
182
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
183 ====== ==================================
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
184 Column Description
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
185 ------ ----------------------------------
2
8aa6385b9a05 Uploaded v0.1.0b, more verbose output
peterjc
parents: 1
diff changeset
186 1 ID from *species A*
8aa6385b9a05 Uploaded v0.1.0b, more verbose output
peterjc
parents: 1
diff changeset
187 2 ID from *species B*
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
188 3 Length of sequence *A*
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
189 4 Length of sequence *B*
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
190 5 Percentage of sequence *A* covered
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
191 6 Percentage of sequence *B* covered
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
192 7 HSP alignment length
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
193 8 HSP percentage identity
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
194 9 HSP bitscore
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
195 ====== ==================================
2
8aa6385b9a05 Uploaded v0.1.0b, more verbose output
peterjc
parents: 1
diff changeset
196
5
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
197 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
198 ``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
199 tabular output.
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
200
c84b6c21e3d4 Uploaded v0.1.0e, test TBLASTX mode; more columns in output
peterjc
parents: 4
diff changeset
201 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
202 *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
203 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
204 sequence length (adjusted by a factor of three for TBLASTX).
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
205
6
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
206 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
207 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
208 can happen following gene duplication, or for (near) identical gene
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
209 duplicates.
e47960bcdccb Uploaded v0.1.0f, exclude tied best hits
peterjc
parents: 5
diff changeset
210
12
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
211 The tool can optionally make the FASTA files non-redundant by replacing
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
212 repeated identical sequences with a single representative before building
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
213 the databases and running BLAST.
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
214
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
215 Finally, the tool can be run using the same FASTA input file to look for
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
216 RBH within the dataset. In this case, self matches are discarded.
661276ad882e Uploaded v0.1.3, uses Biopython for making NR
peterjc
parents: 10
diff changeset
217
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
218 .. class:: warningmark
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
219
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
220 **Note**
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
221
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
222 If you are trying to use BLAST RBH matches to identify candidate orthologues
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
223 or transfer annotation, you *must* use a percentage identity and minimum
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
224 coverage threshold or similiar. See:
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
225
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
226 Punta and Ofran (2008) The Rough Guide to In Silico Function Prediction,
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
227 or How To Use Sequence and Structure Information To Predict Protein
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
228 Function. PLoS Comput Biol 4(10): e1000160.
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
229 http://dx.doi.org/10.1371/journal.pcbi.1000160
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
230
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
231 The defaults are to require 70% sequence identity over the aligned region
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
232 (using ``pident`` in the BLAST+ tabular output), and that the HSP alignment
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
233 covers at least 50% of the query sequence (using ``qcovhsp`` in the BLAST+
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
234 tabular output).
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
235
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
236
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
237 **References**
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
238
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
239 A specific paper covering this tool is planned, but please also cite:
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
240
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
241 Christiam Camacho et al. (2009).
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
242 BLAST+: architecture and applications.
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
243 BMC Bioinformatics. 15;10:421.
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
244 http://dx.doi.org/10.1186/1471-2105-10-421
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
245
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
246 This wrapper is available to install into other Galaxy Instances via the Galaxy
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
247 Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/blast_rbh
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
248 </help>
10
982458013bdb Uploaded v0.1.2b, fixed dependency definition
peterjc
parents: 8
diff changeset
249 <citations>
982458013bdb Uploaded v0.1.2b, fixed dependency definition
peterjc
parents: 8
diff changeset
250 <citation type="doi">10.1186/1471-2105-10-421</citation>
982458013bdb Uploaded v0.1.2b, fixed dependency definition
peterjc
parents: 8
diff changeset
251 <!-- TODO: Add BibTeX entry / preprint DOI for Galaxy BLAST+ paper -->
982458013bdb Uploaded v0.1.2b, fixed dependency definition
peterjc
parents: 8
diff changeset
252 </citations>
0
a96608a125fb Uploaded v0.1.0, first release
peterjc
parents:
diff changeset
253 </tool>