|
0
|
1 <tool id="fastq_stats" name="FASTQ Summary Statistics" version="1.0.0">
|
|
|
2 <description>by column</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="1.0.0">galaxy_sequence_utils</requirement>
|
|
|
5 </requirements>
|
|
|
6 <command interpreter="python">fastq_stats.py '$input_file' '$output_file' '${input_file.extension[len( 'fastq' ):]}'</command>
|
|
|
7 <inputs>
|
|
|
8 <param name="input_file" type="data" format="fastqsanger,fastqillumina,fastqsolexa,fastqcssanger" label="FASTQ File"/>
|
|
|
9 </inputs>
|
|
|
10 <outputs>
|
|
|
11 <data name="output_file" format="tabular" />
|
|
|
12 </outputs>
|
|
|
13 <tests>
|
|
|
14 <test>
|
|
|
15 <param name="input_file" value="fastq_stats1.fastq" ftype="fastqsanger" />
|
|
|
16 <output name="output_file" file="fastq_stats_1_out.tabular" />
|
|
|
17 </test>
|
|
|
18 </tests>
|
|
|
19 <help>
|
|
|
20 This tool creates summary statistics on a FASTQ file.
|
|
|
21
|
|
|
22 .. class:: infomark
|
|
|
23
|
|
|
24 **TIP:** This statistics report can be used as input for the **Boxplot** tools.
|
|
|
25
|
|
|
26 -----
|
|
|
27
|
|
|
28 **The output file will contain the following fields:**
|
|
|
29
|
|
|
30 * column = column number (1 to 36 for a 36-cycles read Solexa file)
|
|
|
31 * count = number of bases found in this column.
|
|
|
32 * min = Lowest quality score value found in this column.
|
|
|
33 * max = Highest quality score value found in this column.
|
|
|
34 * sum = Sum of quality score values for this column.
|
|
|
35 * mean = Mean quality score value for this column.
|
|
|
36 * Q1 = 1st quartile quality score.
|
|
|
37 * med = Median quality score.
|
|
|
38 * Q3 = 3rd quartile quality score.
|
|
|
39 * IQR = Inter-Quartile range (Q3-Q1).
|
|
|
40 * lW = 'Left-Whisker' value (for boxplotting).
|
|
|
41 * rW = 'Right-Whisker' value (for boxplotting).
|
|
|
42 * outliers = Scores falling beyond the left and right whiskers (comma separated list).
|
|
|
43 * A_Count = Count of 'A' nucleotides found in this column.
|
|
|
44 * C_Count = Count of 'C' nucleotides found in this column.
|
|
|
45 * G_Count = Count of 'G' nucleotides found in this column.
|
|
|
46 * T_Count = Count of 'T' nucleotides found in this column.
|
|
|
47 * N_Count = Count of 'N' nucleotides found in this column.
|
|
|
48 * Other_Nucs = Comma separated list of other nucleotides found in this column.
|
|
|
49 * Other_Count = Comma separated count of other nucleotides found in this column.
|
|
|
50
|
|
|
51 For example::
|
|
|
52
|
|
|
53 #column count min max sum mean Q1 med Q3 IQR lW rW outliers A_Count C_Count G_Count T_Count N_Count other_bases other_base_count
|
|
|
54 1 14336356 2 33 450600675 31.4306281875 32.0 33.0 33.0 1.0 31 33 2,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30 4482314 2199633 4425957 3208745 19707
|
|
|
55 2 14336356 2 34 441135033 30.7703737965 30.0 33.0 33.0 3.0 26 34 2,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25 4419184 2170537 4627987 3118567 81
|
|
|
56 3 14336356 2 34 433659182 30.2489127642 29.0 32.0 33.0 4.0 23 34 2,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22 4310988 2941988 3437467 3645784 129
|
|
|
57 4 14336356 2 34 433635331 30.2472490917 29.0 32.0 33.0 4.0 23 34 2,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22 4110637 3007028 3671749 3546839 103
|
|
|
58 5 14336356 2 34 432498583 30.167957813 29.0 32.0 33.0 4.0 23 34 2,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22 4348275 2935903 3293025 3759029 124
|
|
|
59
|
|
|
60 -----
|
|
|
61
|
|
|
62 .. class:: warningmark
|
|
|
63
|
|
|
64 Adapter bases in color space reads are excluded from statistics.
|
|
|
65
|
|
|
66 ------
|
|
|
67
|
|
|
68 **Citation**
|
|
|
69
|
|
|
70 If you use this tool, please cite `Blankenberg D, Gordon A, Von Kuster G, Coraor N, Taylor J, Nekrutenko A; Galaxy Team. Manipulation of FASTQ data with Galaxy. Bioinformatics. 2010 Jul 15;26(14):1783-5. <http://www.ncbi.nlm.nih.gov/pubmed/20562416>`_
|
|
|
71
|
|
|
72
|
|
|
73 </help>
|
|
|
74 </tool>
|
