|
0
|
1 <tool id="samtools_stats" name="Generate statistics" version="1.0.0">
|
|
|
2 <description>for a BAM or SAM file</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="1.1">samtools</requirement>
|
|
|
5 </requirements>
|
|
|
6 <version_command>samtools --version | head -n 1 | awk '{ print $2 }'</version_command>
|
|
|
7 <command><![CDATA[
|
|
|
8 #if $use_reference.use_ref_selector == "yes":
|
|
|
9 #if $use_reference.reference_source.reference_source_selector == "history":
|
|
|
10 ln -s "${use_reference.reference_source.ref_file}" && samtools faidx `basename "${use_reference.reference_source.ref_file}"` && samtools stats
|
|
|
11 #else:
|
|
|
12 samtools stats
|
|
|
13 #end if
|
|
|
14 #else:
|
|
|
15 samtools stats
|
|
|
16 #end if
|
|
|
17 "${input_file}"
|
|
|
18 --coverage ${coverage_min},${coverage_max},${coverage_step}
|
|
|
19 ${remove_dups}
|
|
|
20 #if str( $filter_by_flags.filter_flags ) == "filter":
|
|
|
21 #if $filter_by_flags.require_flags:
|
|
|
22 --required-flag ${sum([int(flag) for flag in str($filter_by_flags.require_flags).split(',')])}
|
|
|
23 #end if
|
|
|
24 #if $filter_by_flags.exclude_flags:
|
|
|
25 --filtering-flag ${sum([int(flag) for flag in str($filter_by_flags.exclude_flags).split(',')])}
|
|
|
26 #end if
|
|
|
27 #end if
|
|
|
28 --GC-depth ${gc_depth}
|
|
|
29 --insert-size ${insert_size}
|
|
|
30 #if str($read_length) != "0":
|
|
|
31 --read-length "${read_length}"
|
|
|
32 #end if
|
|
|
33 --most-inserts ${most_inserts}
|
|
|
34 --trim-quality ${trim_quality}
|
|
|
35 #if $use_reference.use_ref_selector == "yes":
|
|
|
36 #if $use_reference.reference_source.reference_source_selector != "history":
|
|
|
37 --ref-seq "${use_reference.reference_source.ref_file.fields.path}"
|
|
|
38 #else:
|
|
|
39 --ref-seq "${use_reference.reference_source.ref_file}"
|
|
|
40 #end if
|
|
|
41 #end if
|
|
|
42 > "${output}"
|
|
|
43 #if $split_output.split_output_selector == "yes":
|
|
|
44 #set outputs_to_split = str($split_output.generate_tables).split(',')
|
|
|
45 && mkdir split && echo ${split_output.generate_tables} &&
|
|
|
46 #if 'sn' in $outputs_to_split:
|
|
|
47 grep -q ^SN "${output}" ; if [ $? = 0 ] ; then grep ^SN "${output}" | cut -f 2- > "split/Summary numbers.tab" ; fi &&
|
|
|
48 #end if
|
|
|
49 #if 'ffq' in $outputs_to_split:
|
|
|
50 grep -q ^FFQ "${output}" ; if [ $? = 0 ] ; then grep ^FFQ "${output}" | cut -f 2- > "split/First Fragment Qualities.tab" ; fi &&
|
|
|
51 #end if
|
|
|
52 #if 'lfq' in $outputs_to_split:
|
|
|
53 grep -q ^LFQ "${output}" ; if [ $? = 0 ] ; then grep ^LFQ "${output}" | cut -f 2- > "split/Last Fragment Qualities.tab" ; fi &&
|
|
|
54 #end if
|
|
|
55 #if 'mpc' in $outputs_to_split:
|
|
|
56 grep -q ^MPC "${output}" ; if [ $? = 0 ] ; then grep ^MPC "${output}" | cut -f 2- > "split/Mismatches per cycle.tab" ; fi &&
|
|
|
57 #end if
|
|
|
58 #if 'gcf' in $outputs_to_split:
|
|
|
59 grep -q ^GCF "${output}" ; if [ $? = 0 ] ; then grep ^GCF "${output}" | cut -f 2- > "split/GC Content of first fragments.tab" ; fi &&
|
|
|
60 #end if
|
|
|
61 #if 'gcl' in $outputs_to_split:
|
|
|
62 grep -q ^GCL "${output}" ; if [ $? = 0 ] ; then grep ^GCL "${output}" | cut -f 2- > "split/GC Content of last fragments.tab" ; fi &&
|
|
|
63 #end if
|
|
|
64 #if 'gcc' in $outputs_to_split:
|
|
|
65 grep -q ^GCC "${output}" ; if [ $? = 0 ] ; then grep ^GCC "${output}" | cut -f 2- > "split/ACGT content per cycle.tab" ; fi &&
|
|
|
66 #end if
|
|
|
67 #if 'is' in $outputs_to_split:
|
|
|
68 grep -q ^IS "${output}" ; if [ $? = 0 ] ; then grep ^IS "${output}" | cut -f 2- > "split/Insert sizes.tab" ; fi &&
|
|
|
69 #end if
|
|
|
70 #if 'rl' in $outputs_to_split:
|
|
|
71 grep -q ^RL "${output}" ; if [ $? = 0 ] ; then grep ^RL "${output}" | cut -f 2- > "split/Read lengths.tab" ; fi &&
|
|
|
72 #end if
|
|
|
73 #if 'id' in $outputs_to_split:
|
|
|
74 grep -q ^ID "${output}" ; if [ $? = 0 ] ; then grep ^ID "${output}" | cut -f 2- > "split/Indel distribution.tab" ; fi &&
|
|
|
75 #end if
|
|
|
76 #if 'ic' in $outputs_to_split:
|
|
|
77 grep -q ^IC "${output}" ; if [ $? = 0 ] ; then grep ^IC "${output}" | cut -f 2- > "split/Indels per cycle.tab" ; fi &&
|
|
|
78 #end if
|
|
|
79 #if 'cov' in $outputs_to_split:
|
|
|
80 grep -q ^COV "${output}" ; if [ $? = 0 ] ; then grep ^COV "${output}" | cut -f 2- > "split/Coverage distribution.tab" ; fi &&
|
|
|
81 #end if
|
|
|
82 #if 'gcd' in $outputs_to_split:
|
|
|
83 grep -q ^GCD "${output}" ; if [ $? = 0 ] ; then grep ^GCD "${output}" | cut -f 2- > "split/GC depth.tab" ; fi
|
|
|
84 #end if
|
|
|
85 #end if
|
|
|
86 ]]></command>
|
|
|
87 <stdio>
|
|
|
88 <exit_code range="1:" level="fatal" description="Error" />
|
|
|
89 </stdio>
|
|
|
90 <inputs>
|
|
|
91 <param name="input_file" type="data" format="sam,bam" label="BAM file" />
|
|
|
92 <param name="coverage_min" type="integer" value="1" label="Minimum coverage" />
|
|
|
93 <param name="coverage_max" type="integer" value="1000" label="Maximum coverage" />
|
|
|
94 <param name="coverage_step" type="integer" value="1" label="Coverage step" />
|
|
|
95 <param name="remove_dups" type="boolean" truevalue="--remove-dups" falsevalue="" checked="False" label="Exclude reads marked as duplicates" />
|
|
|
96 <conditional name="split_output">
|
|
|
97 <param name="split_output_selector" type="select" label="Output">
|
|
|
98 <option value="no" selected="True">Output to a summary file</option>
|
|
|
99 <option value="yes">Extract separate statistics</option>
|
|
|
100 </param>
|
|
|
101 <when value="no" />
|
|
|
102 <when value="yes">
|
|
|
103 <param name="generate_tables" type="select" display="checkboxes" multiple="True" label="Statistics to extract">
|
|
|
104 <option value="sn">Summary numbers</option>
|
|
|
105 <option value="ffq">First Fragment Qualities</option>
|
|
|
106 <option value="lfq">Last Fragment Qualities</option>
|
|
|
107 <option value="mpc">Mismatches per cycle</option>
|
|
|
108 <option value="gcf">GC Content of first fragments</option>
|
|
|
109 <option value="gcl">GC Content of last fragments</option>
|
|
|
110 <option value="gcc">ACGT content per cycle</option>
|
|
|
111 <option value="is">Insert sizes</option>
|
|
|
112 <option value="rl">Read lengths</option>
|
|
|
113 <option value="id">Indel distribution</option>
|
|
|
114 <option value="ic">Indels per cycle</option>
|
|
|
115 <option value="cov">Coverage distribution</option>
|
|
|
116 <option value="gcd">GC depth</option>
|
|
|
117 </param>
|
|
|
118 </when>
|
|
|
119 </conditional>
|
|
|
120 <conditional name="filter_by_flags">
|
|
|
121 <param name="filter_flags" type="select" label="Set filter by flags">
|
|
|
122 <option value="nofilter" selected="True">Do not filter</option>
|
|
|
123 <option value="filter">Filter by flags to exclude or require</option>
|
|
|
124 </param>
|
|
|
125 <when value="filter">
|
|
|
126 <param name="require_flags" type="select" display="checkboxes" multiple="True" label="Require">
|
|
|
127 <option value="1">Read is paired</option>
|
|
|
128 <option value="2">Read is mapped in a proper pair</option>
|
|
|
129 <option value="4">The read is unmapped</option>
|
|
|
130 <option value="8">The mate is unmapped</option>
|
|
|
131 <option value="16">Read strand</option>
|
|
|
132 <option value="32">Mate strand</option>
|
|
|
133 <option value="64">Read is the first in a pair</option>
|
|
|
134 <option value="128">Read is the second in a pair</option>
|
|
|
135 <option value="256">The alignment or this read is not primary</option>
|
|
|
136 <option value="512">The read fails platform/vendor quality checks</option>
|
|
|
137 <option value="1024">The read is a PCR or optical duplicate</option>
|
|
|
138 </param>
|
|
|
139 <param name="exclude_flags" type="select" display="checkboxes" multiple="True" label="Exclude">
|
|
|
140 <option value="1">Read is paired</option>
|
|
|
141 <option value="2">Read is mapped in a proper pair</option>
|
|
|
142 <option value="4">The read is unmapped</option>
|
|
|
143 <option value="8">The mate is unmapped</option>
|
|
|
144 <option value="16">Read strand</option>
|
|
|
145 <option value="32">Mate strand</option>
|
|
|
146 <option value="64">Read is the first in a pair</option>
|
|
|
147 <option value="128">Read is the second in a pair</option>
|
|
|
148 <option value="256">The alignment or this read is not primary</option>
|
|
|
149 <option value="512">The read fails platform/vendor quality checks</option>
|
|
|
150 <option value="1024">The read is a PCR or optical duplicate</option>
|
|
|
151 </param>
|
|
|
152 </when>
|
|
|
153 <when value="nofilter" />
|
|
|
154 </conditional>
|
|
|
155 <param name="gc_depth" type="float" value="2000" label="GC-depth bin size" />
|
|
|
156 <param name="insert_size" type="integer" value="8000" label="Maximum insert size" />
|
|
|
157 <param name="read_group" type="text" optional="true" label="Limit to a specific read group name" />
|
|
|
158 <param name="read_length" type="integer" value="0" optional="true" label="Minimum read length to generate statistics for" />
|
|
|
159 <param name="most_inserts" type="float" value="0.99" label="Report only the main part of inserts" />
|
|
|
160 <param name="trim_quality" type="integer" value="0" label="BWA trim parameter" />
|
|
|
161 <conditional name="use_reference">
|
|
|
162 <param name="use_ref_selector" type="select" label="Use reference sequence">
|
|
|
163 <option value="yes">Use reference</option>
|
|
|
164 <option value="no">Do not use reference</option>
|
|
|
165 </param>
|
|
|
166 <when value="yes">
|
|
|
167 <conditional name="reference_source">
|
|
|
168 <param name="reference_source_selector" type="select" label="Choose a reference sequence for GC depth">
|
|
|
169 <option value="cached">Locally cached</option>
|
|
|
170 <option value="history">History</option>
|
|
|
171 </param>
|
|
|
172 <when value="cached">
|
|
|
173 <param name="ref_file" type="select" label="Using genome">
|
|
|
174 <options from_data_table="fasta_indexes" />
|
|
|
175 <filter type="data_meta" ref="input_file" key="dbkey" column="1" />
|
|
|
176 </param>
|
|
|
177 </when>
|
|
|
178 <when value="history">
|
|
|
179 <param name="ref_file" type="data" format="fasta" label="Using file" />
|
|
|
180 </when>
|
|
|
181 </conditional>
|
|
|
182 </when>
|
|
|
183 <when value="no" />
|
|
|
184 </conditional>
|
|
|
185 </inputs>
|
|
|
186 <outputs>
|
|
|
187 <data format="tabular" name="output" label="${tool.name} on ${on_string}">
|
|
|
188 <discover_datasets pattern="(?P<designation>.+)\.tab" ext="tabular" visible="true" directory="split" />
|
|
|
189 </data>
|
|
|
190 </outputs>
|
|
|
191 <tests>
|
|
|
192 <test>
|
|
|
193 <param name="input_file" value="phiX.bam" ftype="bam" />
|
|
|
194 <param name="use_ref_selector" value="no" />
|
|
|
195 <output name="output" file="samtools_stats_out1.tab" ftype="tabular" lines_diff="2" />
|
|
|
196 </test>
|
|
|
197 <test>
|
|
|
198 <param name="input_file" value="phiX.bam" ftype="bam" />
|
|
|
199 <param name="use_ref_selector" value="no" />
|
|
|
200 <param name="split_output_selector" value="yes" />
|
|
|
201 <param name="generate_tables" value="sn,gcf,gcl,gcc,cov,gcd" />
|
|
|
202 <output name="output" file="samtools_stats_out2.tab" lines_diff="2">
|
|
|
203 <discovered_dataset designation="Summary numbers" ftype="tabular" file="samtools_stats_out2/sn.tab" />
|
|
|
204 <discovered_dataset designation="GC Content of first fragments" ftype="tabular" file="samtools_stats_out2/gcf.tab" />
|
|
|
205 <discovered_dataset designation="GC Content of last fragments" ftype="tabular" file="samtools_stats_out2/gcl.tab" />
|
|
|
206 <discovered_dataset designation="ACGT content per cycle" ftype="tabular" file="samtools_stats_out2/gcc.tab" />
|
|
|
207 <discovered_dataset designation="Coverage distribution" ftype="tabular" file="samtools_stats_out2/cov.tab" />
|
|
|
208 <discovered_dataset designation="GC depth" ftype="tabular" file="samtools_stats_out2/gcd.tab" />
|
|
|
209 </output>
|
|
|
210 </test>
|
|
|
211 </tests>
|
|
|
212 <help>
|
|
|
213 **What it does**
|
|
|
214
|
|
|
215 This tool runs the ``samtools stats`` command in the SAMtools toolkit.
|
|
|
216
|
|
|
217 Collects statistics from BAM files. The output can be visualized using plot-bamstats.
|
|
|
218
|
|
|
219 **Citation**
|
|
|
220
|
|
|
221 For the underlying tool, please cite `Li H, Handsaker B, Wysoker A, Fennell T, Ruan J, Homer N, Marth G, Abecasis G, Durbin R; 1000 Genome Project Data Processing Subgroup. The Sequence Alignment/Map format and SAMtools. Bioinformatics. 2009 Aug 15;25(16):2078-9. <http://www.ncbi.nlm.nih.gov/pubmed/19505943>`_
|
|
|
222
|
|
|
223
|
|
|
224 If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.*
|
|
|
225 </help>
|
|
|
226 </tool>
|
|
|
227
|
