upstream-extended/iuc/tool_collections/galaxy_sequence_utils/fastq_stats/fastq_stats.xml
1<tool id="fastq_stats" name="FASTQ Summary Statistics" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2 <description>by column</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <edam_topics>
7 <edam_topic>topic_0622</edam_topic>
8 </edam_topics>
9 <edam_operations>
10 <edam_operation>operation_3180</edam_operation>
11 </edam_operations>
12 <expand macro="requirements"/>
13 <command><![CDATA[
14gx-fastq-stats '$input_file' '$output_file' '${input_file.extension[len('fastq'):]}'
15 ]]></command>
16 <inputs>
17 <param name="input_file" type="data" format="fastqsanger,fastqillumina,fastqsolexa,fastqcssanger,fastqsanger.gz,fastqillumina.gz,fastqsolexa.gz,fastqcssanger.gz,fastqsanger.bz2,fastqillumina.bz2,fastqsolexa.bz2,fastqcssanger.bz2" label="FASTQ File"/>
18 </inputs>
19 <outputs>
20 <data name="output_file" format="tabular"/>
21 </outputs>
22 <tests>
23 <test>
24 <param name="input_file" value="fastq_stats1.fastq" ftype="fastqsanger"/>
25 <output name="output_file" file="fastq_stats_1_out.tabular"/>
26 </test>
27 </tests>
28 <help><![CDATA[
29**What is does**
30
31This tool creates summary statistics on a FASTQ file.
32
33.. class:: infomark
34
35**TIP:** This statistics report can be used as input for the **Boxplot** tools.
36
37-----
38
39**The output file will contain the following fields:**
40
41* column = column number (1 to 36 for a 36-cycles read Solexa file)
42* count = number of bases found in this column.
43* min = Lowest quality score value found in this column.
44* max = Highest quality score value found in this column.
45* sum = Sum of quality score values for this column.
46* mean = Mean quality score value for this column.
47* Q1 = 1st quartile quality score.
48* med = Median quality score.
49* Q3 = 3rd quartile quality score.
50* IQR = Inter-Quartile range (Q3-Q1).
51* lW = 'Left-Whisker' value (for boxplotting).
52* rW = 'Right-Whisker' value (for boxplotting).
53* outliers = Scores falling beyond the left and right whiskers (comma separated list).
54* A_Count = Count of 'A' nucleotides found in this column.
55* C_Count = Count of 'C' nucleotides found in this column.
56* G_Count = Count of 'G' nucleotides found in this column.
57* T_Count = Count of 'T' nucleotides found in this column.
58* N_Count = Count of 'N' nucleotides found in this column.
59* Other_Nucs = Comma separated list of other nucleotides found in this column.
60* Other_Count = Comma separated count of other nucleotides found in this column.
61
62For example::
63
64 #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
65 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
66 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
67 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
68 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
69 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
70
71-----
72
73.. class:: warningmark
74
75Adapter bases in color space reads are excluded from statistics.
76 ]]></help>
77 <citations>
78 <citation type="doi">10.1093/bioinformatics/btq281</citation>
79 </citations>
80</tool>