annotate fastqvalidator.xml @ 0:0ac2d4f158bf

Uploaded
author nilesh
date Fri, 12 Jul 2013 16:24:02 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
1 <tool id="fastq_validator_wrapper" name="FastQ Validator">
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
2 <description>for each sequence in a file</description>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
3 <requirements>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
4 <requirement type="package" version="1.0.0">fastq_validator</requirement>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
5 </requirements>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
6 <command> fastQValidator --file $input --minReadLen $minReadLen --maxErrors $maxErrors --printableErrors $printableErrors $baseComposition $disableSeqIDCheck $quiet $avgQual $spacetype $params > $output</command>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
7 <inputs>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
8 <param name="input" type="data" format="fastq,txt" label="FASTQ file"/>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
9 <param name="minReadLen" value="10" type="integer" min="1" label="Minimum allowed read length (Default=10)"/>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
10 <param name="maxErrors" type="integer" value="-1" min="-1" label="Number of errors to allow (Default=-1)" />
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
11 <param name="printableErrors" type="integer" value="20" optional="true" min="0" label="Max errors to print before suppressing (Default=20)" />
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
12 <param name="baseComposition" type="boolean" optional="true" label="Print Base Composition Statistics" truevalue="--baseComposition" falsevalue=""/>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
13 <param name="avgQual" type="boolean" optional="true" label="Print Avg Phred Quality/Cycle and Overall Avg Quality" truevalue="--avgQual" falsevalue=""/>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
14 <param name="disableSeqIDCheck" type="boolean" optional="true" label="Disable unique sequence identifier check (check to save memory)" truevalue="--disableSeqIDCheck" falsevalue=""/>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
15 <param name="quiet" type="boolean" optional="false" label="Suppress error/summary statistics display" truevalue="--quiet" falsevalue=""/>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
16 <param name="params" type="boolean" optional="false" label="Print parameter settings" truevalue="--params" falsevalue=""/>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
17 <param name="spacetype" type="select" label="Space Options for Raw Sequence (Default=Auto)" display="radio">
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
18 <option selected="true" value="--auto">Auto</option>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
19 <option value="--baseSpace">BaseSpace</option>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
20 <option value="--colorSpace">ColorSpace</option>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
21 </param>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
22 </inputs>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
23 <outputs>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
24 <data format="txt" name="output" />
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
25 </outputs>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
26 <help>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
27
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
28 About
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
29 +++++
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
30
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
31 The fastQValidator validates the format of fastq files.
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
32 The initial version of a FASTQ Validator is complete. It was built using LibStatGen: FASTQ which is part of the libStatGen library.
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
33
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
34
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
35 Info on Errors
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
36 ++++++++++++++
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
37
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
38 Number of Errors to allow (default+-1):
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
39 Number of errors to allow before quitting reading/validating the file. -1 (default) indicates to not quit until the entire file is read. 0 indicates not to read/validate anything.
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
40
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
41 Max errors to print before suppressing (defualt+20):
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
42 Maximum number of errors to print before suppressing them (Defaults to 20). Different than maxErrors since printableErrors will continue reading and validating the file until the end, but just doesn't print the errors.
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
43
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
44 **Info on Space Options for Raw Sequence**
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
45 auto: Determine baseSpace/colorSpace from the Raw Sequence in the file (Default)
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
46 baseSpace: ACTGN only
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
47 colorSpace: 0123. only (with 1 character primer base)
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
48
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
49
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
50 Output
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
51 ++++++
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
52
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
53 When running the fastQValidator Executable, if the --params option is specified, the output starts with a summary of the parameters::
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
54
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
55 =============================================================================
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
56 The following parameters are available. Ones with "[]" are in effect::
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
57
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
58 Input Parameters
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
59 --file [../fastqValidator/test/testFile.txt], --baseComposition,
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
60 --disableSeqIDCheck, --quiet, --params [ON], --minReadLen [10],
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
61 --maxErrors [-1]
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
62 Space Type : --baseSpace, --colorSpace, --auto [ON]
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
63 Errors : --ignoreErrors, --printableErrors [20]
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
64 =============================================================================
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
65
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
66 The Validator Executable outputs error messages for invalid sequences based on Validation Criteria. For Example: ::
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
67
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
68 ======================================================================
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
69 ERROR on Line 25: The sequence identifier line was too short.
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
70 ERROR on Line 29: First line of a sequence does not begin wtih @
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
71 ERROR on Line 33: No Sequence Identifier specified before the comment.
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
72 ======================================================================
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
73
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
74 Base Composition Percentages by Index are printed if --printBaseComp is set to ON. For Example: ::
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
75
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
76 ========================================================================
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
77 Base Composition Statistics:
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
78 Read Index %A %C %G %T %N Total Reads At Index
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
79 0 100.00 0.00 0.00 0.00 0.00 20
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
80 1 5.00 95.00 0.00 0.00 0.00 20
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
81 2 5.00 0.00 5.00 90.00 0.00 20
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
82 ========================================================================
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
83
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
84 Phred Quality by Index are printed if --avgQual is set to ON in a version after May 29, 2012. Only valid qualities are included in these averages. For Example::
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
85
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
86 ==================================================
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
87 Average Phred Quality by Read Index (starts at 0):
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
88 Read Index Average Quality
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
89 0 44.10
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
90 1 45.55
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
91 2 51.11
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
92 3 47.68
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
93 4 47.37
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
94
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
95 Overall Average Phred Quality = 50.40
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
96 ==================================================
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
97
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
98 Summary of the number of lines, sequences, and errors: ::
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
99
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
100 =======================================================================
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
101 Finished processing testFile.txt with 92 lines containing 20 sequences.
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
102 There were a total of 17 errors.
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
103 =======================================================================
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
104
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
105 </help>
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
106
0ac2d4f158bf Uploaded
nilesh
parents:
diff changeset
107 </tool>