|
0
|
1 <tool id="fastq_screen" name="fastq_screen" version="0.4.2">
|
|
|
2 <description>Screen for contamination</description>
|
|
|
3 <requirements>
|
|
2
|
4 <requirement type="package" version="2.1.0">bowtie2</requirement>
|
|
0
|
5 <requirement type="package" version="0.4.2">fastq_screen</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command>
|
|
|
8 fastq_screen --aligner="bowtie2" --outdir="." --conf="$fastqrunconf"
|
|
|
9 #if $sampN > 0:
|
|
|
10 --subset "$sampN"
|
|
|
11 #end if
|
|
|
12 "$input1"
|
|
|
13 #if $singlePaired.sPaired == "paired":
|
|
|
14 "$input2"
|
|
|
15 #end if
|
|
|
16 ; mv *_screen.png ${outpng} ; mv *_screen.txt ${outtext}
|
|
|
17 </command>
|
|
|
18
|
|
|
19 <stdio>
|
|
|
20 <regex match=".*" source="both" level="warning" description="fastqc_screen perl script output"/>
|
|
|
21 </stdio>
|
|
|
22
|
|
|
23 <inputs>
|
|
|
24 <param name="jobName" type="text" size="120" value="fastq_screen" label="Job narrative (included in output names as a reminder)"
|
|
|
25 help="Only letters, numbers and underscores _ will be retained in this field">
|
|
|
26 <sanitizer invalid_char="">
|
|
|
27 <valid initial="string.letters,string.digits"><add value="_" /> </valid>
|
|
|
28 </sanitizer>
|
|
|
29 </param>
|
|
|
30 <param name="sampN" type="integer" size="20" value="500000" label="Sample this number of reads. Set to 0 or less to use all"
|
|
|
31 help="Time/precision trade off - fewer reads takes a little less time trading off precision of the estimates."/>
|
|
|
32 <conditional name="singlePaired">
|
|
|
33 <param name="sPaired" type="select" label="Single ended or mate-pair ended reads in this library?">
|
|
|
34 <option value="single" selected="true">Single-end</option>
|
|
|
35 <option value="paired">Paired-end</option>
|
|
|
36 </param>
|
|
|
37 <when value="single">
|
|
|
38 <param format="fastqsanger,fastq" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/>
|
|
|
39 </when>
|
|
|
40 <when value="paired">
|
|
|
41 <param format="fastqsanger,fastq" name="input1" type="data" label="RNA-Seq FASTQ file, forward reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
|
|
|
42 <param format="fastqsanger,fastq" name="input2" type="data" label="RNA-Seq FASTQ file, reverse reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
|
|
|
43 </when>
|
|
|
44 </conditional>
|
|
|
45
|
|
|
46 <!-- Genome source. -->
|
|
|
47 <repeat name="refGenomes" title="Installed organism reference sequences to check for alignment to your fastq" min="1"
|
|
|
48 help="For checking cell culture sequence for contamination, Mycoplasma Genitalium might be a good choice eg">
|
|
|
49 <param name="ref" type="select" label="Bowtie2 reference genome">
|
|
|
50 <options from_data_table="bowtie2_indexes">
|
|
|
51 <filter type="sort_by" column="3"/>
|
|
|
52 <validator type="no_options" message="No indexes are available for bowtie2"/>
|
|
|
53 </options>
|
|
|
54 </param>
|
|
|
55 </repeat>
|
|
|
56 </inputs>
|
|
|
57
|
|
|
58 <outputs>
|
|
|
59 <data format="tabular" name="outtext" label="${jobName}.xls"/>
|
|
|
60 <data format="png" name="outpng" label="${jobName}.png"/>
|
|
|
61 </outputs>
|
|
|
62 <configfiles>
|
|
|
63 <configfile name="fastqrunconf">
|
|
|
64 ###### autogenerated by fastq_screen.xml for fastq_screen run
|
|
2
|
65 BOWTIE2 bowtie2
|
|
0
|
66 #for $refs in $refGenomes:
|
|
|
67 DATABASE $refs.ref.fields.value $refs.ref.fields.path BOWTIE2
|
|
|
68 #end for
|
|
|
69 </configfile>
|
|
|
70 </configfiles>
|
|
|
71
|
|
|
72 <help>
|
|
|
73
|
|
|
74 **What it does**
|
|
|
75 This is a Galaxy wrapper exposing software from Babraham -fastq_screen_
|
|
|
76 Designed to search sequence data in fastq files for matches to contaminants or to check the likely
|
|
|
77 species.
|
|
|
78 In QC checking, you can use it to look for (eg) sequence from contaminating mycoplasmae in cell cultures - it may be non-differential but it will be pro-inflammatory and, well, less than ideal.
|
|
|
79
|
|
|
80 Here's the help from the perl script used by this wrapper:
|
|
|
81
|
|
|
82 Fastq Screen - Screen sequences against a panel of databases
|
|
|
83
|
|
|
84 Synopsis
|
|
|
85
|
|
|
86 fastq_screen [OPTION]... [FastQ FILE]...
|
|
|
87
|
|
|
88 Function
|
|
|
89
|
|
|
90 Fastq Screen is intended to be used as part of a QC pipeline.
|
|
|
91 It allows you to take a sequence dataset and search it
|
|
|
92 against a set of bowtie databases. It will then generate
|
|
|
93 both a text and a graphical summary of the results to see if
|
|
|
94 the sequence dataset contains the kind of sequences you expect
|
|
|
95 or not.
|
|
|
96
|
|
|
97 Options
|
|
|
98
|
|
|
99 --help -h Print program help and exit
|
|
|
100
|
|
|
101 --subset Don't use the whole sequence file to search, but
|
|
|
102 create a temporary dataset of this size. The
|
|
|
103 dataset created will be of approximately (within
|
|
|
104 a factor of 2) of this size. If the real dataset
|
|
|
105 is smaller than twice the specified size then the
|
|
|
106 whole dataset will be used. Subsets will be taken
|
|
|
107 evenly from throughout the whole original dataset
|
|
|
108
|
|
|
109 --paired Files are paired end. Files must be specified in
|
|
|
110 the correct order with pairs of files coming
|
|
|
111 immediately after one another. Results files will
|
|
|
112 be named after the first file in the pair if the
|
|
|
113 names differ between the two files.
|
|
|
114
|
|
|
115 --outdir Specify a directory in which to save output files.
|
|
|
116 If no directory is specified then output files
|
|
|
117 are saved into the same directory as the input
|
|
|
118 file.
|
|
|
119
|
|
|
120 --illumina1_3 Assume that the quality values are in encoded in
|
|
|
121 Illumina v1.3 format. Defaults to Sanger format
|
|
|
122 if this flag is not specified
|
|
|
123
|
|
|
124 --quiet Supress all progress reports on stderr and only
|
|
|
125 report errors
|
|
|
126
|
|
|
127 --version Print the program version and exit
|
|
|
128
|
|
|
129 --threads Specify across how many threads bowtie will be
|
|
|
130 allowed to run. Overrides the default value set
|
|
|
131 in the conf file
|
|
|
132
|
|
|
133 --conf Manually specify a location for the configuration
|
|
|
134 file to be used for this run. If not specified
|
|
|
135 then the file will be taken from the same directory
|
|
|
136 as the fastq_screen program
|
|
|
137
|
|
|
138 --color FastQ files are in colorspace. This requires that
|
|
|
139 the libraries configures in the config file are
|
|
|
140 colorspace indices.
|
|
|
141
|
|
|
142 --bowtie Specify extra parameters to be passed to bowtie.
|
|
|
143 These parameters should be quoted to clearly
|
|
|
144 delimit bowtie parameters from fastq_screen
|
|
|
145 parameters. You should not try to use this option
|
|
|
146 to override the normal search or reporting options
|
|
|
147 for bowtie which are set automatically but it might
|
|
|
148 be useful to allow reads to be trimmed before
|
|
|
149 alignment etc.
|
|
|
150
|
|
|
151 --bowtie2 Specify extra parameters to be passed to bowtie 2.
|
|
|
152 These parameters should be quoted to clearly
|
|
|
153 delimit bowtie2 parameters from fastq_screen
|
|
|
154 parameters. You should not try to use this option
|
|
|
155 to override the normal search or reporting options
|
|
|
156 for bowtie which are set automatically but it might
|
|
|
157 be useful to allow reads to be trimmed before
|
|
|
158 alignment etc.
|
|
|
159
|
|
|
160 --nohits Writes to a file the sequences that did not map to
|
|
|
161 any of the specified genome libraries. If the
|
|
|
162 subset option is also specified, only reads from
|
|
|
163 the temporary dataset that failed to align to the
|
|
|
164 reference genomes will be written to the output file.
|
|
|
165
|
|
|
166 --aligner Specify the aligner to use for the mapping. Valid
|
|
|
167 arguments are 'bowtie' or 'bowtie2'.
|
|
|
168
|
|
|
169
|
|
|
170 **Attributions**
|
|
|
171
|
|
|
172 Note that each component has its own license.
|
|
|
173 Good luck with figuring out your obligations.
|
|
|
174
|
|
|
175 fastq_screen - see the web site at Fastq_screen_
|
|
|
176
|
|
|
177 Galaxy_ (that's what you are using right now!) for gluing everything together
|
|
|
178
|
|
|
179
|
|
|
180 Code and documentation comprising this tool was written by Ross Lazarus and that part is Licensed_ the same way as other rgenetics artefacts
|
|
|
181
|
|
|
182 .. _Fastq_screen: http://www.bioinformatics.babraham.ac.uk/projects/fastq_screen
|
|
|
183
|
|
|
184 .. _Galaxy: http://getgalaxy.org
|
|
|
185
|
|
|
186 .. _Licensed: https://www.gnu.org/licenses/lgpl.html
|
|
|
187
|
|
|
188 </help>
|
|
|
189 </tool>
|
