PageRenderTime 20ms CodeModel.GetById 15ms app.highlight 2ms RepoModel.GetById 1ms app.codeStats 0ms

/tools/fastq/fastq_stats.xml

https://bitbucket.org/cistrome/cistrome-harvard/
XML | 71 lines | 56 code | 15 blank | 0 comment | 0 complexity | 9e0df94fbbaf18fec84ac7e434ebd3f1 MD5 | raw file
 1<tool id="fastq_stats" name="FASTQ Summary Statistics" version="1.0.0">
 2  <description>by column</description>
 3  <command interpreter="python">fastq_stats.py '$input_file' '$output_file' '${input_file.extension[len( 'fastq' ):]}'</command>
 4  <inputs>
 5    <param name="input_file" type="data" format="fastqsanger,fastqillumina,fastqsolexa,fastqcssanger" label="FASTQ File"/>
 6  </inputs>
 7  <outputs>
 8    <data name="output_file" format="tabular" />
 9  </outputs>
10  <tests>
11    <test>
12      <param name="input_file" value="fastq_stats1.fastq" ftype="fastqsanger" />
13      <output name="output_file" file="fastq_stats_1_out.tabular" />
14    </test>
15  </tests>
16  <help>
17This tool creates summary statistics on a FASTQ file. 
18
19.. class:: infomark
20
21**TIP:** This statistics report can be used as input for the **Boxplot** tools.
22
23-----
24
25**The output file will contain the following fields:**
26
27* column      = column number (1 to 36 for a 36-cycles read Solexa file)
28* count       = number of bases found in this column.
29* min         = Lowest quality score value found in this column.
30* max         = Highest quality score value found in this column.
31* sum         = Sum of quality score values for this column.
32* mean        = Mean quality score value for this column.
33* Q1          = 1st quartile quality score.
34* med         = Median quality score.
35* Q3          = 3rd quartile quality score.
36* IQR         = Inter-Quartile range (Q3-Q1).
37* lW          = 'Left-Whisker' value (for boxplotting).
38* rW          = 'Right-Whisker' value (for boxplotting).
39* outliers    = Scores falling beyond the left and right whiskers (comma separated list).
40* A_Count     = Count of 'A' nucleotides found in this column.
41* C_Count     = Count of 'C' nucleotides found in this column.
42* G_Count     = Count of 'G' nucleotides found in this column.
43* T_Count     = Count of 'T' nucleotides found in this column.
44* N_Count     = Count of 'N' nucleotides found in this column.
45* Other_Nucs  = Comma separated list of other nucleotides found in this column.
46* Other_Count = Comma separated count of other nucleotides found in this column.
47
48For example::
49
50  #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
51  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       
52  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      
53  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     
54  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     
55  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     
56
57-----
58
59.. class:: warningmark
60
61Adapter bases in color space reads are excluded from statistics.
62
63------
64
65**Citation**
66
67If 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. &lt;http://www.ncbi.nlm.nih.gov/pubmed/20562416&gt;`_
68
69
70  </help>
71</tool>