annotate lumpy.xml @ 1:f2d9c9f18d3f draft default tip

Uploaded
author morinlab
date Sun, 04 Dec 2016 14:31:50 -0500
parents ec43f38f18c2
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
1 <tool id="lumpy" name="LUMPY" version="0.2.9">
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
2 <description>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
3 a probabilistic framework for structural variant discovery
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
4 </description>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
5 <requirements>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
6 <requirement type="package" version="0.1.19">samtools</requirement>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
7 <requirement type="package" version="0.2.9">lumpy</requirement>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
8 <requirement type="set_environment" version="0.2.9">LUMPY_SCRIPTS</requirement>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
9 <requirement type="package" version="1.9">numpy</requirement>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
10 </requirements>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
11 <command>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
12
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
13 <!-- Create Symbolic links to bam and bam indexes -->
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
14 ln -s $normal normal.bam;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
15 ln -s $normal.metadata.bam_index normal.bam.bai;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
16 ln -s $tumour tumour.bam;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
17 ln -s $tumour.metadata.bam_index tumour.bam.bai;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
18
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
19 <!-- EXTRACT DISCORDANT PAIRED END ALIGNMENTS -->
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
20 samtools view -F 1294 -b normal.bam | samtools sort - normal.pe;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
21 samtools view -F 1294 -b tumour.bam | samtools sort - tumour.pe;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
22
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
23 <!-- EXTRACT SPLIT-READ ALIGNMENTS -->
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
24 samtools view -h normal.bam |
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
25 \$LUMPY_SCRIPTS/extractSplitReads_BwaMem -i stdin |
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
26 samtools view -Sb - |
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
27 samtools sort - normal.sr;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
28 samtools view -h tumour.bam |
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
29 \$LUMPY_SCRIPTS/extractSplitReads_BwaMem -i stdin |
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
30 samtools view -Sb - |
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
31 samtools sort - tumour.sr;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
32
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
33 <!-- CREATE HISTO FILE -->
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
34 samtools view normal.bam |
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
35 tail -n+100000 |
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
36 \$LUMPY_SCRIPTS/pairend_distro.py -r 150 -X 4 -N 10000 -o normal.pe.histo > normal.stats;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
37 samtools view tumour.bam |
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
38 tail -n+100000 |
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
39 \$LUMPY_SCRIPTS/pairend_distro.py -r 150 -X 4 -N 10000 -o tumour.pe.histo > tumour.stats;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
40
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
41 <!-- Store MEAN and STD in nice format -->
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
42 cat -t normal.stats | sed s/\\^\\I/,/g > normal.stats.txt;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
43 cat -t tumour.stats | sed s/\\^\\I/,/g > tumour.stats.txt;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
44
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
45 <!-- RUN LUMPY -->
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
46
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
47 lumpy
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
48 -e
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
49 -tt $advancedsettings.tt
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
50 -mw $advancedsettings.mw
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
51 #if $x
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
52 -x $x
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
53 #end if
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
54
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
55 -pe
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
56 bam_file:normal.pe.sort.bam,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
57 histo_file:normal.pe.histo,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
58 \$(cat normal.stats.txt),
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
59 read_length:$advancedsettings.pe_read_length,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
60 min_non_overlap:$advancedsettings.pe_min_non_overlap,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
61 discordant_z:$advancedsettings.pe_discordant_z,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
62 back_distance:$advancedsettings.pe_back_distance,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
63 min_mapping_threshold:$advancedsettings.pe_min_mapping_threshold,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
64 weight:$advancedsettings.pe_weight,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
65 #if $sampleid_source.manual:
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
66 id:PE-$sampleid_source.idn
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
67 #else:
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
68 id:PE-\$(basename $normal)
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
69 #end if
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
70
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
71 -sr
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
72 bam_file:normal.sr.sort.bam,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
73 back_distance:$advancedsettings.sr_back_distance,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
74 min_mapping_threshold:$advancedsettings.sr_min_mapping_threshold,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
75 weight:$advancedsettings.sr_weight,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
76 min_clip:$advancedsettings.sr_min_clip,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
77 #if $sampleid_source.manual:
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
78 id:SE-$sampleid_source.idn
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
79 #else
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
80 id:SE-\$(basename $normal)
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
81 #end if
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
82
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
83 -pe
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
84 bam_file:n=tumour.pe.sort.bam,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
85 histo_file:tumour.pe.histo,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
86 \$(cat tumour.stats.txt),
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
87 read_length:$advancedsettings.pe_read_length,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
88 min_non_overlap:$advancedsettings.pe_min_non_overlap,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
89 discordant_z:$advancedsettings.pe_discordant_z,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
90 back_distance:$advancedsettings.pe_back_distance,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
91 min_mapping_threshold:$advancedsettings.pe_min_mapping_threshold,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
92 weight:$advancedsettings.pe_weight,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
93 #if $sampleid_source.manual:
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
94 id:PE-$sampleid_source.idt
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
95 #else:
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
96 id:PE-\$(basename $tumour)
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
97 #end if
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
98
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
99 -sr
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
100 bam_file:tumour.sr.sort.bam,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
101 back_distance:$advancedsettings.sr_back_distance,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
102 min_mapping_threshold:$advancedsettings.sr_min_mapping_threshold,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
103 weight:$advancedsettings.sr_weight,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
104 min_clip:$advancedsettings.sr_min_clip,
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
105 #if $sampleid_source.manual:
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
106 id:SE-$sampleid_source.idt
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
107 #else
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
108 id:SE-\$(basename $tumour)
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
109 #end if
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
110
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
111 > $outfile;
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
112
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
113 </command>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
114 <inputs>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
115 <conditional name="sampleid_source">
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
116 <param label="Choose the source to fetch Sample Identifiers" name="sampleid_selector" type="select">
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
117 <option value="bamfile">BAM File Name</option>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
118 <option value="manual">Manual</option>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
119 </param>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
120 <when value="manual">
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
121 <param name="idn" type="text" label="Tumour ID (Name)"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
122 <param name="idt" type="text" label="Normal ID (Name)"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
123 </when>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
124 </conditional>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
125 <param type="data" format="bam" name="normal" label="Normal Alignment File"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
126 <param type="data" format="bam" name="tumour" label="Tumour Alignment File"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
127 <param type="data" format="bed" name="x" label="Exluded Regions BED file" optional="true"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
128 <section name="advancedsettings" title="Advanced Settings" expanded="false">
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
129 <param type="integer" value="5" name="mw" label="Minimum Weight for Call"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
130 <param type="integer" value="3" name="tt" label="Trim Threshold"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
131 <param type="integer" name="pe_back_distance" value="20" label="Paired End Back Distance" help="Distance into the read to add the breakpoint interval"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
132 <param type="integer" name="pe_min_mapping_threshold" value="1" label="Paired End Min Mapping Threshold" help="Minimum mapping quality that a read must have to be considered"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
133 <param type="integer" name="pe_weight" value="1" label="Paired End Weight" help="Weight of each piece of evidence from this sample"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
134 <param type="integer" name="pe_discordant_z" value="4" label="Paired End Discordant Value" help="Number of standard deviations away from the mean to be considered as a normal library size"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
135 <param type="integer" name="pe_read_length" value="150" label="Paired End Read Length" help="Length of sequenced reads"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
136 <param type="integer" name="pe_min_non_overlap" value="150" label="Paired End Min Non Overlap" help="Number of base pair positions that must be unique to each end of a read pair"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
137 <param type="integer" name="sr_back_distance" value="20" label="Split Read Back Distance" help="Distance into the read to add the breakpoint interval"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
138 <param type="integer" name="sr_min_mapping_threshold" value="1" label="Split Read Min Mapping Threshold" help="Minimum mapping quality that a read must have to be considered"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
139 <param type="integer" name="sr_weight" value="1" label="Split Read Weight" help="Weight of each piece of evidence from this sample"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
140 <param type="integer" name="sr_min_clip" value="1" label="Spliy Read Min Clip" help="Minimum number of clipped bases to consider in a split read"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
141 </section>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
142 </inputs>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
143 <outputs>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
144 <data type="vcf" name="outfile"/>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
145 </outputs>
ec43f38f18c2 Uploaded
morinlab
parents:
diff changeset
146 </tool>