annotate pyCRAC/pyReadCounters.xml @ 0:19b20927172d draft

Uploaded
author swebb
date Tue, 18 Jun 2013 09:11:00 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
19b20927172d Uploaded
swebb
parents:
diff changeset
1 <tool id ="pyReadCounters" name="pyReadCounters" force_history_refresh="True">
19b20927172d Uploaded
swebb
parents:
diff changeset
2 <requirements>
19b20927172d Uploaded
swebb
parents:
diff changeset
3 <requirement type="package">pyCRAC</requirement>
19b20927172d Uploaded
swebb
parents:
diff changeset
4 </requirements>
19b20927172d Uploaded
swebb
parents:
diff changeset
5 <command interpreter="perl">
19b20927172d Uploaded
swebb
parents:
diff changeset
6 pyReadCounters.pl
19b20927172d Uploaded
swebb
parents:
diff changeset
7 -f $ftype.input
19b20927172d Uploaded
swebb
parents:
diff changeset
8 --file_type $ftype.file_type
19b20927172d Uploaded
swebb
parents:
diff changeset
9 --gtf $addGTF.gtf
19b20927172d Uploaded
swebb
parents:
diff changeset
10 #if ($ftype.file_type == "novo" or $ftype.file_type == "sam") and $ftype.disc.discard == "discard":
19b20927172d Uploaded
swebb
parents:
diff changeset
11 --discarded $discarded
19b20927172d Uploaded
swebb
parents:
diff changeset
12 #end if#
19b20927172d Uploaded
swebb
parents:
diff changeset
13 #if ($ftype.file_type == "novo" or $ftype.file_type == "sam") and $ftype.addAlignOpt.alignoptions == "edit":
19b20927172d Uploaded
swebb
parents:
diff changeset
14 --alignOpt
19b20927172d Uploaded
swebb
parents:
diff changeset
15 --align_quality $ftype.addAlignOpt.align_quality
19b20927172d Uploaded
swebb
parents:
diff changeset
16 --align_score $ftype.addAlignOpt.align_score
19b20927172d Uploaded
swebb
parents:
diff changeset
17 #if int($ftype.addAlignOpt.max) > 0:
19b20927172d Uploaded
swebb
parents:
diff changeset
18 --max $ftype.addAlignOpt.max
19b20927172d Uploaded
swebb
parents:
diff changeset
19 #end if#
19b20927172d Uploaded
swebb
parents:
diff changeset
20 --distance $ftype.addAlignOpt.d
19b20927172d Uploaded
swebb
parents:
diff changeset
21 --length $ftype.addAlignOpt.length
19b20927172d Uploaded
swebb
parents:
diff changeset
22 $ftype.addAlignOpt.unique
19b20927172d Uploaded
swebb
parents:
diff changeset
23 $ftype.addAlignOpt.blocks
19b20927172d Uploaded
swebb
parents:
diff changeset
24 $ftype.addAlignOpt.mutations
19b20927172d Uploaded
swebb
parents:
diff changeset
25 #end if#
19b20927172d Uploaded
swebb
parents:
diff changeset
26 #if $addOpt.options == "edit":
19b20927172d Uploaded
swebb
parents:
diff changeset
27 --options
19b20927172d Uploaded
swebb
parents:
diff changeset
28 --range $addOpt.range
19b20927172d Uploaded
swebb
parents:
diff changeset
29 $addOpt.ignore
19b20927172d Uploaded
swebb
parents:
diff changeset
30 --overlap $addOpt.overlap
19b20927172d Uploaded
swebb
parents:
diff changeset
31 #end if#
19b20927172d Uploaded
swebb
parents:
diff changeset
32
19b20927172d Uploaded
swebb
parents:
diff changeset
33 --stats $stats
19b20927172d Uploaded
swebb
parents:
diff changeset
34 --hittable $hittable
19b20927172d Uploaded
swebb
parents:
diff changeset
35 --intronUTRoverlap $intronUTRoverlap
19b20927172d Uploaded
swebb
parents:
diff changeset
36
19b20927172d Uploaded
swebb
parents:
diff changeset
37 #if $ftype.file_type == "novo" or $ftype.file_type == "sam":
19b20927172d Uploaded
swebb
parents:
diff changeset
38 --countoutput $countoutput
19b20927172d Uploaded
swebb
parents:
diff changeset
39 #end if#
19b20927172d Uploaded
swebb
parents:
diff changeset
40
19b20927172d Uploaded
swebb
parents:
diff changeset
41 --id $stats.id
19b20927172d Uploaded
swebb
parents:
diff changeset
42 </command>
19b20927172d Uploaded
swebb
parents:
diff changeset
43 <version_command>/usr/local/bin/pyReadCounters.py --version</version_command>
19b20927172d Uploaded
swebb
parents:
diff changeset
44 <inputs>
19b20927172d Uploaded
swebb
parents:
diff changeset
45 <conditional name="addGTF">
19b20927172d Uploaded
swebb
parents:
diff changeset
46 <param name="gtfFile" type="select" label="Choose GTF File from">
19b20927172d Uploaded
swebb
parents:
diff changeset
47 <option value="default" selected="true">Defaults</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
48 <option value="other">History</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
49 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
50 <when value="default">
19b20927172d Uploaded
swebb
parents:
diff changeset
51 <param name="gtf" type="select" label="GTF File --gtf" help="GTF file containing gene ID co-ordinates">
19b20927172d Uploaded
swebb
parents:
diff changeset
52 <options from_data_table="pycrac_gtf"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
53 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
54 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
55 <when value="other">
19b20927172d Uploaded
swebb
parents:
diff changeset
56 <param format="GTF" name="gtf" type="data" label="GTF File --gtf" help="GTF file containing gene ID co-ordinates"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
57 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
58 </conditional>
19b20927172d Uploaded
swebb
parents:
diff changeset
59 <conditional name="ftype">
19b20927172d Uploaded
swebb
parents:
diff changeset
60 <param name="file_type" type="select" label="Input File Type --file_type" help="Use .novo or .sam input files">
19b20927172d Uploaded
swebb
parents:
diff changeset
61 <option value="novo" selected="true">Novo</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
62 <option value="sam">Sam/Bam</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
63 <option value="gtf">GTF</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
64 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
65 <when value="novo">
19b20927172d Uploaded
swebb
parents:
diff changeset
66 <param format="tabular" name="input" type="data" label="Input File --input_file" help="Alignment file of type .novo" />
19b20927172d Uploaded
swebb
parents:
diff changeset
67 <conditional name="disc">
19b20927172d Uploaded
swebb
parents:
diff changeset
68 <param name="discard" type="select" label="Print discarded reads to a separate file">
19b20927172d Uploaded
swebb
parents:
diff changeset
69 <option value="" selected="true">OFF</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
70 <option value="discard">ON</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
71 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
72 <when value="discard">
19b20927172d Uploaded
swebb
parents:
diff changeset
73 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
74 <when value="">
19b20927172d Uploaded
swebb
parents:
diff changeset
75 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
76 </conditional>
19b20927172d Uploaded
swebb
parents:
diff changeset
77 <conditional name="addAlignOpt">
19b20927172d Uploaded
swebb
parents:
diff changeset
78 <param name="alignoptions" type="select" label="Alignment Options">
19b20927172d Uploaded
swebb
parents:
diff changeset
79 <option value="default" selected="true">Default</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
80 <option value="edit">Edit</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
81 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
82 <when value="edit">
19b20927172d Uploaded
swebb
parents:
diff changeset
83 <param name="mutations" type="select" label="Option for selecting type of mutations to report --mutations" help="cross-linking sites are often highlighted by deletions and/or substitutions in the reads. You can use this option to select specific mutations that you want to have reported in the GTF output file.">
19b20927172d Uploaded
swebb
parents:
diff changeset
84 <option value="" selected="true">Off</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
85 <option value="--mutations delsonly">deletions</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
86 <option value="--mutations subsonly">substitutions</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
87 <option value="--mutations TC">T->C substitutions</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
88 <option value="--mutations nomuts">no mutations</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
89 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
90 <param format="integer" name="align_quality" type="integer" label="Align Quality --align_quality " value="0" size="5" >
19b20927172d Uploaded
swebb
parents:
diff changeset
91 <validator type="in_range" min="0" message="Please enter a value >= 0"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
92 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
93 <param format="integer" name="align_score" type="integer" label="Align Score --align_score " value="0" size="5" >
19b20927172d Uploaded
swebb
parents:
diff changeset
94 <validator type="in_range" min="0" message="Please enter a value >= 0"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
95 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
96 <param format="integer" name="max" type="integer" label="Mapped reads to read from input file --max" help="Set to 0 to align all reads." value="0" size="10" >
19b20927172d Uploaded
swebb
parents:
diff changeset
97 <validator type="in_range" min="0" max="100000000" message="Please enter a value between 1 and 100000000 or 0 to align all reads"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
98 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
99 <param format="integer" name="d" type="integer" label="Distance --distance " value="1000" size="6" help="Set the maximum number of bp allowed between two non-overlapping paired reads">
19b20927172d Uploaded
swebb
parents:
diff changeset
100 <validator type="in_range" min="1" message="Please enter a value >= 0"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
101 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
102 <param format="integer" name="length" type="integer" label="Set the maximum length of reads --length" value="1000" size="7" help="Set the read length threshold between 15 and 1000">
19b20927172d Uploaded
swebb
parents:
diff changeset
103 <validator type="in_range" min="15" max="1000" message="Please enter a value between 15 and 1000"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
104 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
105 <param name="unique" type="select" label="Remove reads with multiple alignment locations --unique">
19b20927172d Uploaded
swebb
parents:
diff changeset
106 <option value="" selected="true">OFF</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
107 <option value="--unique">ON</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
108 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
109 <param name="blocks" type="select" label="Only count reads with same start and end coords once --blocks">
19b20927172d Uploaded
swebb
parents:
diff changeset
110 <option value="" selected="true">OFF</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
111 <option value="--blocks">ON</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
112 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
113 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
114 <when value="default">
19b20927172d Uploaded
swebb
parents:
diff changeset
115 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
116 </conditional>
19b20927172d Uploaded
swebb
parents:
diff changeset
117 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
118 <when value="sam">
19b20927172d Uploaded
swebb
parents:
diff changeset
119 <param format="sam,bam" name="input" type="data" label="Input File --input_file" help="Alignment file of type .sam or .bam" />
19b20927172d Uploaded
swebb
parents:
diff changeset
120 <conditional name="disc">
19b20927172d Uploaded
swebb
parents:
diff changeset
121 <param name="discard" type="select" label="Print discarded reads to a separate file">
19b20927172d Uploaded
swebb
parents:
diff changeset
122 <option value="" selected="true">OFF</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
123 <option value="discard">ON</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
124 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
125 <when value="discard">
19b20927172d Uploaded
swebb
parents:
diff changeset
126 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
127 <when value="">
19b20927172d Uploaded
swebb
parents:
diff changeset
128 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
129 </conditional>
19b20927172d Uploaded
swebb
parents:
diff changeset
130 <conditional name="addAlignOpt">
19b20927172d Uploaded
swebb
parents:
diff changeset
131 <param name="alignoptions" type="select" label="Alignment Options">
19b20927172d Uploaded
swebb
parents:
diff changeset
132 <option value="default" selected="true">Default</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
133 <option value="edit">Edit</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
134 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
135 <when value="edit">
19b20927172d Uploaded
swebb
parents:
diff changeset
136 <param name="mutations" type="select" label="Option for selecting type of mutations to report --mutations" help="cross-linking sites are often highlighted by deletions and/or substitutions in the reads. You can use this option to select specific mutations that you want to have reported in the GTF output file.">
19b20927172d Uploaded
swebb
parents:
diff changeset
137 <option value="" selected="true">Off</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
138 <option value="--mutations delsonly">deletions</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
139 <option value="--mutations subsonly">substitutions</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
140 <option value="--mutations TC">T->C mutations</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
141 <option value="--mutations nomuts">no mutations</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
142 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
143 <param format="integer" name="align_quality" type="integer" label="Align Quality --align_quality " value="0" size="5" >
19b20927172d Uploaded
swebb
parents:
diff changeset
144 <validator type="in_range" min="0" message="Please enter a value >= 0"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
145 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
146 <param format="integer" name="align_score" type="integer" label="Align Score --align_score " value="0" size="5" >
19b20927172d Uploaded
swebb
parents:
diff changeset
147 <validator type="in_range" min="0" message="Please enter a value >= 0"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
148 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
149 <param format="integer" name="max" type="integer" label="Mapped reads to read from input file --max" help="Set to 0 to align all reads." value="0" size="10" >
19b20927172d Uploaded
swebb
parents:
diff changeset
150 <validator type="in_range" min="0" max="100000000" message="Please enter a value between 1 and 100000000 or 0 to align all reads"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
151 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
152 <param format="integer" name="d" type="integer" label="Distance --distance " value="1000" size="6" help="Set the maximum number of bp allowed between two non-overlapping paired reads">
19b20927172d Uploaded
swebb
parents:
diff changeset
153 <validator type="in_range" min="1" message="Please enter a value >= 0"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
154 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
155 <param format="integer" name="length" type="integer" label="Set the maximum length of reads --length" value="1000" size="7" help="Set the read length threshold between 15 and 1000">
19b20927172d Uploaded
swebb
parents:
diff changeset
156 <validator type="in_range" min="15" max="1000" message="Please enter a value between 15 and 1000"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
157 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
158 <param name="unique" type="select" label="Remove reads with multiple alignment locations --unique">
19b20927172d Uploaded
swebb
parents:
diff changeset
159 <option value="" selected="true">OFF</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
160 <option value="--unique">ON</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
161 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
162 <param name="blocks" type="select" label="Only count reads with same start and end coords once --blocks">
19b20927172d Uploaded
swebb
parents:
diff changeset
163 <option value="" selected="true">OFF</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
164 <option value="--blocks">ON</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
165 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
166 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
167 <when value="default">
19b20927172d Uploaded
swebb
parents:
diff changeset
168 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
169 </conditional>
19b20927172d Uploaded
swebb
parents:
diff changeset
170 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
171 <when value="gtf">
19b20927172d Uploaded
swebb
parents:
diff changeset
172 <param format="gtf" name="input" type="data" label="Input File --input_file" help="File of type .gtf" />
19b20927172d Uploaded
swebb
parents:
diff changeset
173 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
174 </conditional>
19b20927172d Uploaded
swebb
parents:
diff changeset
175 <conditional name="addOpt">
19b20927172d Uploaded
swebb
parents:
diff changeset
176 <param name="options" type="select" label="Standard Options">
19b20927172d Uploaded
swebb
parents:
diff changeset
177 <option value="default" selected="true">Default</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
178 <option value="edit">Edit</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
179 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
180 <when value="edit">
19b20927172d Uploaded
swebb
parents:
diff changeset
181 <param format="integer" name="range" type="integer" label="Range --range" value="0" size="5" help="Manually set the length of the 5' and 3' UTRs 0>50000">
19b20927172d Uploaded
swebb
parents:
diff changeset
182 <validator type="in_range" min="0" max="50000" message="Please enter a value between 0 and 50000"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
183 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
184 <param name="ignore" type="select" label="Ignore strand information? --ignorestrand">
19b20927172d Uploaded
swebb
parents:
diff changeset
185 <option value="" selected="true">No</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
186 <option value="--ignorestrand">Yes</option>
19b20927172d Uploaded
swebb
parents:
diff changeset
187 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
188 <param format="integer" name="overlap" type="integer" label="Overlap --overlap" value="1" size="5" help="Sets the number of nucleotides a read has to overlap with a gene before it is considered a hit. ">
19b20927172d Uploaded
swebb
parents:
diff changeset
189 <validator type="in_range" min="1" message="Please enter a positive integer"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
190 </param>
19b20927172d Uploaded
swebb
parents:
diff changeset
191 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
192 <when value="default">
19b20927172d Uploaded
swebb
parents:
diff changeset
193 </when>
19b20927172d Uploaded
swebb
parents:
diff changeset
194 </conditional>
19b20927172d Uploaded
swebb
parents:
diff changeset
195 <param name="label" type="text" format="txt" size="30" value="pyReadCounters" label="Enter output file label -o" />
19b20927172d Uploaded
swebb
parents:
diff changeset
196 </inputs>
19b20927172d Uploaded
swebb
parents:
diff changeset
197 <outputs>
19b20927172d Uploaded
swebb
parents:
diff changeset
198 <data format="tabular" name="stats" label="${label.value}_file_statistics.txt"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
199 <data format="tabular" name="hittable" label="${label.value}_hittable.txt"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
200 <data format="gtf" name="intronUTRoverlap" label="${label.value}_intron_and_UTR_overlap.txt"/>
19b20927172d Uploaded
swebb
parents:
diff changeset
201 <data format="gtf" name="countoutput" label="${label.value}_count_output.gtf">
19b20927172d Uploaded
swebb
parents:
diff changeset
202 <filter>ftype['file_type'] == "novo" or ftype['file_type'] == "sam"</filter>
19b20927172d Uploaded
swebb
parents:
diff changeset
203 </data>
19b20927172d Uploaded
swebb
parents:
diff changeset
204 <data format="txt" name="discarded" label="${label.value}_discarded.txt">
19b20927172d Uploaded
swebb
parents:
diff changeset
205 <filter>(ftype['file_type'] == "novo" or ftype['file_type'] == "sam") and ftype['disc']['discard'] == "discard"</filter>
19b20927172d Uploaded
swebb
parents:
diff changeset
206 </data>
19b20927172d Uploaded
swebb
parents:
diff changeset
207 </outputs>
19b20927172d Uploaded
swebb
parents:
diff changeset
208 <help>
19b20927172d Uploaded
swebb
parents:
diff changeset
209
19b20927172d Uploaded
swebb
parents:
diff changeset
210 .. class:: infomark
19b20927172d Uploaded
swebb
parents:
diff changeset
211
19b20927172d Uploaded
swebb
parents:
diff changeset
212 **pyReadCounters**
19b20927172d Uploaded
swebb
parents:
diff changeset
213
19b20927172d Uploaded
swebb
parents:
diff changeset
214 pyReadCounters is part of the pyCRAC_ package. Produces a gene hittable file, two GTF output files showing to which genomic features the reads overlap.
19b20927172d Uploaded
swebb
parents:
diff changeset
215 Finally the tool produces a read statistics file that provides information about the complexity of your dataset.
19b20927172d Uploaded
swebb
parents:
diff changeset
216
19b20927172d Uploaded
swebb
parents:
diff changeset
217 **Output file examples**
19b20927172d Uploaded
swebb
parents:
diff changeset
218
19b20927172d Uploaded
swebb
parents:
diff changeset
219 A hittable file::
19b20927172d Uploaded
swebb
parents:
diff changeset
220
19b20927172d Uploaded
swebb
parents:
diff changeset
221 # generated by pyReadCounters version 1.1.0, Mon Apr 16 20:34:22 2012
19b20927172d Uploaded
swebb
parents:
diff changeset
222 # /usr/local/bin/pyReadCounters.py -f RNAseq_data.novo -c 1 --unique
19b20927172d Uploaded
swebb
parents:
diff changeset
223 # total number of reads 12534556
19b20927172d Uploaded
swebb
parents:
diff changeset
224 # total number of paired reads 10947376
19b20927172d Uploaded
swebb
parents:
diff changeset
225 # total number of single reads 483095
19b20927172d Uploaded
swebb
parents:
diff changeset
226 # total number of mapped reads: 11430471
19b20927172d Uploaded
swebb
parents:
diff changeset
227 # total number of overlapping genomic features 7019550
19b20927172d Uploaded
swebb
parents:
diff changeset
228 # sense 5960669
19b20927172d Uploaded
swebb
parents:
diff changeset
229 # anti-sense 1058881
19b20927172d Uploaded
swebb
parents:
diff changeset
230 # feature sense_overlap anti-sense_overlap number of reads
19b20927172d Uploaded
swebb
parents:
diff changeset
231
19b20927172d Uploaded
swebb
parents:
diff changeset
232 ## protein_coding 3190701
19b20927172d Uploaded
swebb
parents:
diff changeset
233 YEF3 49930 3629 24221
19b20927172d Uploaded
swebb
parents:
diff changeset
234 PMA1 32621 2650 21776
19b20927172d Uploaded
swebb
parents:
diff changeset
235 COX1 24559 1037 15174
19b20927172d Uploaded
swebb
parents:
diff changeset
236 TFP1 21539 1689 13506
19b20927172d Uploaded
swebb
parents:
diff changeset
237 HSC82 21177 1458 12729
19b20927172d Uploaded
swebb
parents:
diff changeset
238 ADH1 20245 1467 11351
19b20927172d Uploaded
swebb
parents:
diff changeset
239 AI5_ALPHA 20022 918 13101
19b20927172d Uploaded
swebb
parents:
diff changeset
240 AI4 19390 886 12638
19b20927172d Uploaded
swebb
parents:
diff changeset
241 AI3 17823 798 11473
19b20927172d Uploaded
swebb
parents:
diff changeset
242 AI2 17590 790 11297
19b20927172d Uploaded
swebb
parents:
diff changeset
243 RPL10 16822 1113 8797
19b20927172d Uploaded
swebb
parents:
diff changeset
244 ENO2 16336 1125 8913
19b20927172d Uploaded
swebb
parents:
diff changeset
245 TEF1 15578 1333 5450
19b20927172d Uploaded
swebb
parents:
diff changeset
246
19b20927172d Uploaded
swebb
parents:
diff changeset
247 An example of a GTF 'count_output' file::
19b20927172d Uploaded
swebb
parents:
diff changeset
248
19b20927172d Uploaded
swebb
parents:
diff changeset
249 ##gff-version 2
19b20927172d Uploaded
swebb
parents:
diff changeset
250 # generated by Counters version 1.2.0, Tue Jan 8 22:47:29 2013
19b20927172d Uploaded
swebb
parents:
diff changeset
251 # pyReadCounters.py -f PAR_CLIP_unique.novo --mutations=TC -v
19b20927172d Uploaded
swebb
parents:
diff changeset
252 # total number of reads: 2455251
19b20927172d Uploaded
swebb
parents:
diff changeset
253 # total number of paired reads: 0
19b20927172d Uploaded
swebb
parents:
diff changeset
254 # total number of single reads: 2455251
19b20927172d Uploaded
swebb
parents:
diff changeset
255 # total number of mapped reads: 2455251
19b20927172d Uploaded
swebb
parents:
diff changeset
256 # total number of overlapping genomic features: 5153943
19b20927172d Uploaded
swebb
parents:
diff changeset
257 # sense: 2640600
19b20927172d Uploaded
swebb
parents:
diff changeset
258 # anti-sense: 2513343
19b20927172d Uploaded
swebb
parents:
diff changeset
259 chrXIV reads exon 661572 661605 2 + . gene_id "INT_0_6716,YNR016C"; gene_name "INT_0_6716,ACC1"; # 661596S;
19b20927172d Uploaded
swebb
parents:
diff changeset
260 chrXIV reads exon 661720 661738 1 + . gene_id "INT_0_6716,YNR016C"; gene_name "INT_0_6716,ACC1"; # 661726S;
19b20927172d Uploaded
swebb
parents:
diff changeset
261 chrXIV reads exon 661839 661878 4 + . gene_id "INT_0_6716,YNR016C"; gene_name "INT_0_6716,ACC1"; # 661875S;
19b20927172d Uploaded
swebb
parents:
diff changeset
262
19b20927172d Uploaded
swebb
parents:
diff changeset
263 This output file also reports whether a read contains a mutation.
19b20927172d Uploaded
swebb
parents:
diff changeset
264
19b20927172d Uploaded
swebb
parents:
diff changeset
265 For example::
19b20927172d Uploaded
swebb
parents:
diff changeset
266
19b20927172d Uploaded
swebb
parents:
diff changeset
267 # 661596S
19b20927172d Uploaded
swebb
parents:
diff changeset
268
19b20927172d Uploaded
swebb
parents:
diff changeset
269 Indicates that the read had a nucleotide substitution ("S") at genomic coordinate 661596. The chromosome name can be found in the first column.
19b20927172d Uploaded
swebb
parents:
diff changeset
270
19b20927172d Uploaded
swebb
parents:
diff changeset
271 .. _pyCRAC: http://sandergranneman.bio.ed.ac.uk/Granneman_Lab/pyCRAC_software.html
19b20927172d Uploaded
swebb
parents:
diff changeset
272
19b20927172d Uploaded
swebb
parents:
diff changeset
273 ------
19b20927172d Uploaded
swebb
parents:
diff changeset
274
19b20927172d Uploaded
swebb
parents:
diff changeset
275 **Parameter list**
19b20927172d Uploaded
swebb
parents:
diff changeset
276
19b20927172d Uploaded
swebb
parents:
diff changeset
277 File input options::
19b20927172d Uploaded
swebb
parents:
diff changeset
278
19b20927172d Uploaded
swebb
parents:
diff changeset
279 -f FILE, --input_file=FILE
19b20927172d Uploaded
swebb
parents:
diff changeset
280 provide the path to your novo, SAM/BAM or gtf data
19b20927172d Uploaded
swebb
parents:
diff changeset
281 file. Default is standard input. Make sure to specify
19b20927172d Uploaded
swebb
parents:
diff changeset
282 the file type of the file you want to have analyzed
19b20927172d Uploaded
swebb
parents:
diff changeset
283 using the --file_type option!
19b20927172d Uploaded
swebb
parents:
diff changeset
284 -o OUTPUT_FILE, --output_file=OUTPUT_FILE
19b20927172d Uploaded
swebb
parents:
diff changeset
285 Use this flag to override the standard file names. Do
19b20927172d Uploaded
swebb
parents:
diff changeset
286 NOT add an extension.
19b20927172d Uploaded
swebb
parents:
diff changeset
287 --file_type=FILE_TYPE
19b20927172d Uploaded
swebb
parents:
diff changeset
288 use this option to specify the file type (i.e.
19b20927172d Uploaded
swebb
parents:
diff changeset
289 'novo','sam' or 'gtf'). This will tell the program
19b20927172d Uploaded
swebb
parents:
diff changeset
290 which parsers to use for processing the files. Default
19b20927172d Uploaded
swebb
parents:
diff changeset
291 = 'novo'
19b20927172d Uploaded
swebb
parents:
diff changeset
292 --gtf=annotation_file.gtf
19b20927172d Uploaded
swebb
parents:
diff changeset
293 type the path to the gtf annotation file that you want
19b20927172d Uploaded
swebb
parents:
diff changeset
294 to use
19b20927172d Uploaded
swebb
parents:
diff changeset
295
19b20927172d Uploaded
swebb
parents:
diff changeset
296 Common pyCRAC options::
19b20927172d Uploaded
swebb
parents:
diff changeset
297
19b20927172d Uploaded
swebb
parents:
diff changeset
298 --ignorestrand
19b20927172d Uploaded
swebb
parents:
diff changeset
299 To ignore strand information and all reads overlapping
19b20927172d Uploaded
swebb
parents:
diff changeset
300 with genomic features will be considered sense reads.
19b20927172d Uploaded
swebb
parents:
diff changeset
301 Useful for analysing ChIP or RIP data
19b20927172d Uploaded
swebb
parents:
diff changeset
302 --overlap=1
19b20927172d Uploaded
swebb
parents:
diff changeset
303 sets the number of nucleotides a read has to overlap
19b20927172d Uploaded
swebb
parents:
diff changeset
304 with a gene before it is considered a hit. Default =
19b20927172d Uploaded
swebb
parents:
diff changeset
305 1 nucleotide
19b20927172d Uploaded
swebb
parents:
diff changeset
306 -r 100, --range=100
19b20927172d Uploaded
swebb
parents:
diff changeset
307 allows you to add regions flanking the genomic
19b20927172d Uploaded
swebb
parents:
diff changeset
308 feature. If you set '-r 50' or '--range=50', then the
19b20927172d Uploaded
swebb
parents:
diff changeset
309 program will add 50 nucleotides to each feature on
19b20927172d Uploaded
swebb
parents:
diff changeset
310 each side regardless of whether the GTF file has genes
19b20927172d Uploaded
swebb
parents:
diff changeset
311 with annotated UTRs
19b20927172d Uploaded
swebb
parents:
diff changeset
312
19b20927172d Uploaded
swebb
parents:
diff changeset
313 Options for SAM/BAM and Novo files::
19b20927172d Uploaded
swebb
parents:
diff changeset
314
19b20927172d Uploaded
swebb
parents:
diff changeset
315 --mutations=delsonly
19b20927172d Uploaded
swebb
parents:
diff changeset
316 Use this option to only track mutations that are of
19b20927172d Uploaded
swebb
parents:
diff changeset
317 interest. For CRAC data this is usually deletions
19b20927172d Uploaded
swebb
parents:
diff changeset
318 (--mutations=delsonly). For PAR-CLIP data this is
19b20927172d Uploaded
swebb
parents:
diff changeset
319 usually T-C mutations (--mutations=TC). Other options
19b20927172d Uploaded
swebb
parents:
diff changeset
320 are\: do not report any mutations: --mutations=nomuts.
19b20927172d Uploaded
swebb
parents:
diff changeset
321 Only report specific base mutations, for example only
19b20927172d Uploaded
swebb
parents:
diff changeset
322 in T's, C's and G's :--mutations=[TCG]. The brackets
19b20927172d Uploaded
swebb
parents:
diff changeset
323 are essential. Other nucleotide combinations are also
19b20927172d Uploaded
swebb
parents:
diff changeset
324 possible
19b20927172d Uploaded
swebb
parents:
diff changeset
325 --align_quality=100, --mapping_quality=100
19b20927172d Uploaded
swebb
parents:
diff changeset
326 with these options you can set the alignment quality
19b20927172d Uploaded
swebb
parents:
diff changeset
327 (Novoalign) or mapping quality (SAM) threshold. Reads
19b20927172d Uploaded
swebb
parents:
diff changeset
328 with qualities lower than the threshold will be
19b20927172d Uploaded
swebb
parents:
diff changeset
329 ignored. Default = 0
19b20927172d Uploaded
swebb
parents:
diff changeset
330 --align_score=100
19b20927172d Uploaded
swebb
parents:
diff changeset
331 with this option you can set the alignment score
19b20927172d Uploaded
swebb
parents:
diff changeset
332 threshold. Reads with alignment scores lower than the
19b20927172d Uploaded
swebb
parents:
diff changeset
333 threshold will be ignored. Default = 0
19b20927172d Uploaded
swebb
parents:
diff changeset
334 --unique
19b20927172d Uploaded
swebb
parents:
diff changeset
335 with this option reads with multiple alignment
19b20927172d Uploaded
swebb
parents:
diff changeset
336 locations will be removed. Default = Off
19b20927172d Uploaded
swebb
parents:
diff changeset
337 --blocks
19b20927172d Uploaded
swebb
parents:
diff changeset
338 with this option reads with the same start and end
19b20927172d Uploaded
swebb
parents:
diff changeset
339 coordinates on a chromosome will be counted as one
19b20927172d Uploaded
swebb
parents:
diff changeset
340 cDNA. Default = Off
19b20927172d Uploaded
swebb
parents:
diff changeset
341 -m 100000, --max=100000
19b20927172d Uploaded
swebb
parents:
diff changeset
342 maximum number of mapped reads that will be analyzed.
19b20927172d Uploaded
swebb
parents:
diff changeset
343 Default = All
19b20927172d Uploaded
swebb
parents:
diff changeset
344 -d 1000, --distance=1000
19b20927172d Uploaded
swebb
parents:
diff changeset
345 this option allows you to set the maximum number of
19b20927172d Uploaded
swebb
parents:
diff changeset
346 base-pairs allowed between two non-overlapping paired
19b20927172d Uploaded
swebb
parents:
diff changeset
347 reads. Default = 1000
19b20927172d Uploaded
swebb
parents:
diff changeset
348 --discarded=FILE
19b20927172d Uploaded
swebb
parents:
diff changeset
349 prints the lines from the alignments file that were
19b20927172d Uploaded
swebb
parents:
diff changeset
350 discarded by the parsers. This file contains reads
19b20927172d Uploaded
swebb
parents:
diff changeset
351 that were unmapped (NM), of poor quality (i.e. QC) or
19b20927172d Uploaded
swebb
parents:
diff changeset
352 paired reads that were mapped to different chromosomal
19b20927172d Uploaded
swebb
parents:
diff changeset
353 locations or were too far apart on the same
19b20927172d Uploaded
swebb
parents:
diff changeset
354 chromosome. Useful for debugging purposes
19b20927172d Uploaded
swebb
parents:
diff changeset
355 -l 100, --length=1000
19b20927172d Uploaded
swebb
parents:
diff changeset
356 to set read length threshold. Default = 1000
19b20927172d Uploaded
swebb
parents:
diff changeset
357
19b20927172d Uploaded
swebb
parents:
diff changeset
358 </help>
19b20927172d Uploaded
swebb
parents:
diff changeset
359 </tool>