comparison snap_caller.xml @ 23:5db0545b9004 draft

update to v0.1.7.3
author wolma
date Thu, 21 Jul 2016 03:55:49 -0400
parents c46406466625
children
comparison
equal deleted inserted replaced
22:24154c580718 23:5db0545b9004
1 <tool id="read_alignment" name="SNAP Read Alignment" version="0.1.7.2"> 1 <tool id="read_alignment" name="SNAP Read Alignment" version="0.1.7.3">
2 <description>Map sequence reads to a reference genome using SNAP</description> 2 <description>Map sequence reads to a reference genome using SNAP</description>
3 <macros> 3 <macros>
4 <import>toolshed_macros.xml</import> 4 <import>toolshed_macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="requirements"/> 6 <expand macro="requirements" />
7 <version_command>python3 -m MiModD version -q</version_command> 7 <version_command>python3 -m MiModD version -q</version_command>
8 <command> 8 <command>
9 python3 -m MiModD snap-batch -s 9 python3 -m MiModD snap-batch -s
10 ## SNAP calls (considering different cases) 10 ## SNAP calls (considering different cases)
11 11
48 </command> 48 </command>
49 49
50 <inputs> 50 <inputs>
51 ## mandatory arguments (and mode-conditionals) 51 ## mandatory arguments (and mode-conditionals)
52 52
53 <param name="ref_genome" type="data" format="fasta" label="reference genome" help="The fasta reference genome that SNAP should align reads against."/> 53 <param format="fasta" help="The fasta reference genome that SNAP should align reads against." label="reference genome" name="ref_genome" type="data" />
54 54
55 <repeat name="datasets" title="datasets" default="1" min="1"> 55 <repeat default="1" min="1" name="datasets" title="datasets">
56 <conditional name="mode_choose"> 56 <conditional name="mode_choose">
57 <param name="mode" type="select" label="choose mode" help="Reads obtained from single-end sequencing runs should be aligned in 'single' mode, paired-end reads in 'paired' mode. **WARNING**: if the read input file is in SAM/BAM format, the current version of this tool will **not** verify the mode and may produce erroneous alignments with wrong settings!"> 57 <param help="Reads obtained from single-end sequencing runs should be aligned in 'single' mode, paired-end reads in 'paired' mode. **WARNING**: if the read input file is in SAM/BAM format, the current version of this tool will **not** verify the mode and may produce erroneous alignments with wrong settings!" label="choose mode" name="mode" type="select">
58 <option value="single">single-end</option> 58 <option value="single">single-end</option>
59 <option value="paired">paired-end</option> 59 <option value="paired">paired-end</option>
60 </param> 60 </param>
61 61
62 <when value="single"> 62 <when value="single">
63 <conditional name="input"> 63 <conditional name="input">
64 <param name="iformat" type="select" label="input file format"> 64 <param label="input file format" name="iformat" type="select">
65 <option value="bam">BAM</option> 65 <option value="bam">BAM</option>
66 <option value="sam">SAM</option> 66 <option value="sam">SAM</option>
67 <option value="gz">gz</option> 67 <option value="gz">gz</option>
68 <option value="fastq">fastq</option> 68 <option value="fastq">fastq</option>
69 </param> 69 </param>
70 <when value="bam"> 70 <when value="bam">
71 <param name="ifile" type="data" format="bam" label="input file"/> 71 <param format="bam" label="input file" name="ifile" type="data" />
72 <param name="header" type="data" optional="true" format="sam" label="custom header file" /> 72 <param format="sam" label="custom header file" name="header" optional="true" type="data" />
73 </when> 73 </when>
74 <when value="sam"> 74 <when value="sam">
75 <param name="ifile" type="data" format="sam" label="input file"/> 75 <param format="sam" label="input file" name="ifile" type="data" />
76 <param name="header" type="data" optional="true" format="sam" label="custom header file" /> 76 <param format="sam" label="custom header file" name="header" optional="true" type="data" />
77 </when> 77 </when>
78 <when value="gz"> 78 <when value="gz">
79 <param name="ifile" type="data" label="input file"/> 79 <param label="input file" name="ifile" type="data" />
80 <param name="header" type="data" format="sam" label="header file" /> 80 <param format="sam" label="header file" name="header" type="data" />
81 </when> 81 </when>
82 <when value="fastq"> 82 <when value="fastq">
83 <param name="ifile" type="data" format="fastq" label="input file"/> 83 <param format="fastq" label="input file" name="ifile" type="data" />
84 <param name="header" type="data" format="sam" label="header file" /> 84 <param format="sam" label="header file" name="header" type="data" />
85 </when> 85 </when>
86 </conditional> 86 </conditional>
87 </when> 87 </when>
88 <when value="paired"> 88 <when value="paired">
89 <conditional name="input"> 89 <conditional name="input">
90 <param name="iformat" type="select" label="input file format"> 90 <param label="input file format" name="iformat" type="select">
91 <option value="bam">BAM</option> 91 <option value="bam">BAM</option>
92 <option value="sam">SAM</option> 92 <option value="sam">SAM</option>
93 <option value="gz">gz</option> 93 <option value="gz">gz</option>
94 <option value="fastq">fastq</option> 94 <option value="fastq">fastq</option>
95 </param> 95 </param>
96 <when value="bam"> 96 <when value="bam">
97 <param name="ifile" type="data" format="bam" label="input file"/> 97 <param format="bam" label="input file" name="ifile" type="data" />
98 <param name="header" type="data" optional="true" format="sam" label="custom header file" /> 98 <param format="sam" label="custom header file" name="header" optional="true" type="data" />
99 </when> 99 </when>
100 <when value="sam"> 100 <when value="sam">
101 <param name="ifile" type="data" format="sam" label="input file"/> 101 <param format="sam" label="input file" name="ifile" type="data" />
102 <param name="header" type="data" optional="true" format="sam" label="custom header file" /> 102 <param format="sam" label="custom header file" name="header" optional="true" type="data" />
103 </when> 103 </when>
104 <when value="fastq"> 104 <when value="fastq">
105 <param name="ifile1" type="data" format="fastq" label="inputfile with the first set of reads of paired-end data"/> 105 <param format="fastq" label="inputfile with the first set of reads of paired-end data" name="ifile1" type="data" />
106 <param name="ifile2" type="data" format="fastq" label="inputfile with the second set of reads of paired-end data"/> 106 <param format="fastq" label="inputfile with the second set of reads of paired-end data" name="ifile2" type="data" />
107 <param name="header" type="data" format="sam" label="header file" help="required" /> 107 <param format="sam" help="required" label="header file" name="header" type="data" />
108 </when> 108 </when>
109 <when value="gz"> 109 <when value="gz">
110 <param name="ifile1" type="data" label="inputfile with the first set of reads of paired-end data"/> 110 <param label="inputfile with the first set of reads of paired-end data" name="ifile1" type="data" />
111 <param name="ifile2" type="data" label="inputfile with the second set of reads of paired-end data"/> 111 <param label="inputfile with the second set of reads of paired-end data" name="ifile2" type="data" />
112 <param name="header" type="data" format="sam" label="header file" help="required" /> 112 <param format="sam" help="required" label="header file" name="header" type="data" />
113 </when> 113 </when>
114 </conditional> 114 </conditional>
115 </when> 115 </when>
116 </conditional> 116 </conditional>
117 </repeat> 117 </repeat>
118 118
119 <param name="oformat" type="select" label="output file format"> 119 <param label="output file format" name="oformat" type="select">
120 <option value="bam">BAM</option> 120 <option value="bam">BAM</option>
121 <option value="sam">SAM</option> 121 <option value="sam">SAM</option>
122 </param> 122 </param>
123 123
124 ## optional arguments 124 ## optional arguments
125 125
126 <conditional name="set"> 126 <conditional name="set">
127 <param name="settings_mode" type="select" label="further parameter settings" help="This section lets you specify the detailed parameter settings for the SNAP aligner. Only change them if you know what you are doing, i.e., read the documentation first."> 127 <param help="This section lets you specify the detailed parameter settings for the SNAP aligner. Only change them if you know what you are doing, i.e., read the documentation first." label="further parameter settings" name="settings_mode" type="select">
128 <option value="default">default settings</option> 128 <option value="default">default settings</option>
129 <option value="change">change settings</option> 129 <option value="change">change settings</option>
130 </param> 130 </param>
131 131
132 ## default settings 132 ## default settings
133 133
134 <when value="default"> 134 <when value="default">
135 <param name="seedsize" type="hidden" value="20"/> 135 <param name="seedsize" type="hidden" value="20" />
136 <param name="slack" type="hidden" value="0.3"/> 136 <param name="slack" type="hidden" value="0.3" />
137 <param name="sp_min" type="hidden" value="100"/> 137 <param name="sp_min" type="hidden" value="100" />
138 <param name="sp_max" type="hidden" value="10000"/> 138 <param name="sp_max" type="hidden" value="10000" />
139 <param name="maxdist" type="hidden" value="8"/> 139 <param name="maxdist" type="hidden" value="8" />
140 <param name="confdiff" type="hidden" value="2"/> 140 <param name="confdiff" type="hidden" value="2" />
141 <param name="confadpt" type="hidden" value="7"/> 141 <param name="confadpt" type="hidden" value="7" />
142 142
143 <param name="maxseeds" type="hidden" value="25"/> 143 <param name="maxseeds" type="hidden" value="25" />
144 <param name="maxhits" type="hidden" value="250"/> 144 <param name="maxhits" type="hidden" value="250" />
145 <param name="clipping" type="hidden" value="++"/> 145 <param name="clipping" type="hidden" value="++" />
146 146
147 <param name="selectivity" type="hidden" value="off"/> 147 <param name="selectivity" type="hidden" value="off" />
148 <param name="filter_output" type="hidden" value="off"/> 148 <param name="filter_output" type="hidden" value="off" />
149 <param name="sort" type="hidden" value="0"/> 149 <param name="sort" type="hidden" value="0" />
150 <param name="mmatch_notation" type="hidden" value="general"/> 150 <param name="mmatch_notation" type="hidden" value="general" />
151 <param name="discard_overlapping_mates" type="hidden" value="" /> 151 <param name="discard_overlapping_mates" type="hidden" value="" />
152 </when> 152 </when>
153 153
154 ## change settings 154 ## change settings
155 155
156 <when value="change"> 156 <when value="change">
157 <param name="seedsize" type="integer" value="20" label="seed size (default: 20)" help="Length of the seeds used in the reference genome hash table (SNAP index option -s)."/> 157 <param help="Length of the seeds used in the reference genome hash table (SNAP index option -s)." label="seed size (default: 20)" name="seedsize" type="integer" value="20" />
158 <param name="slack" type="float" value="0.3" label="hash table slack size (default: 0.3)" help="Corresponds to the -h option of SNAP index."/> 158 <param help="Corresponds to the -h option of SNAP index." label="hash table slack size (default: 0.3)" name="slack" type="float" value="0.3" />
159 159
160 ## paired-end specific options 160 ## paired-end specific options
161 <param name="sp_min" type="integer" value="100" label="minimum spacing to allow between paired ends (default: 100)" help="Corresponds to the first value of the SNAP option -s. Affects paired-end data only."/> 161 <param help="Corresponds to the first value of the SNAP option -s. Affects paired-end data only." label="minimum spacing to allow between paired ends (default: 100)" name="sp_min" type="integer" value="100" />
162 <param name="sp_max" type="integer" value="10000" label="maximum spacing to allow between paired ends (default: 10000)" help="Corresponds to the second value of the SNAP option -s. Affects paired-end data only."/> 162 <param help="Corresponds to the second value of the SNAP option -s. Affects paired-end data only." label="maximum spacing to allow between paired ends (default: 10000)" name="sp_max" type="integer" value="10000" />
163 <param name="discard_overlapping_mates" type="text" display="checkboxes" multiple="true" label="discard overlapping read pairs of type" help="Consider overlapping mate pairs of the given orientation type(s) anomalous and discard them; allowed values: RF, FR, FF, RR; multiple types may be specified as a comma-separated list and ALL can be used as a shortcut for discarding all overlapping mate pairs; leave blank to retain all overlapping pairs. Affects paired-end data only." /> 163 <param display="checkboxes" help="Consider overlapping mate pairs of the given orientation type(s) anomalous and discard them; allowed values: RF, FR, FF, RR; multiple types may be specified as a comma-separated list and ALL can be used as a shortcut for discarding all overlapping mate pairs; leave blank to retain all overlapping pairs. Affects paired-end data only." label="discard overlapping read pairs of type" multiple="true" name="discard_overlapping_mates" type="text" />
164 <param name="maxdist" type="integer" value="8" label="edit distance (default: 8)" help="maximum edit distance allowed per read or pair (SNAP option -d); higher values allow more divergent alignments to be found, but increase the rate of misalignments."/> 164 <param help="maximum edit distance allowed per read or pair (SNAP option -d); higher values allow more divergent alignments to be found, but increase the rate of misalignments." label="edit distance (default: 8)" name="maxdist" type="integer" value="8" />
165 <param name="maxhits" type="integer" value="250" label="maximum hits per seed (default: 250)" help="Maximum hits to consider per seed (SNAP option -h); don't use a seed region in the alignment process if it matches more than maxhits regions in the reference genome. Higher values reduce the rate of misalignments, but reduce performance."/> 165 <param help="Maximum hits to consider per seed (SNAP option -h); don't use a seed region in the alignment process if it matches more than maxhits regions in the reference genome. Higher values reduce the rate of misalignments, but reduce performance." label="maximum hits per seed (default: 250)" name="maxhits" type="integer" value="250" />
166 <param name="confdiff" type="integer" value="2" label="confidence threshold (default: 2)" help="Confidence threshold (SNAP option -c); the minimum edit distance difference between two alternate alignments required to reject the poorer alignment as suboptimal; higher values increase the rate of ambiguously aligned reads."/> 166 <param help="Confidence threshold (SNAP option -c); the minimum edit distance difference between two alternate alignments required to reject the poorer alignment as suboptimal; higher values increase the rate of ambiguously aligned reads." label="confidence threshold (default: 2)" name="confdiff" type="integer" value="2" />
167 <param name="confadpt" type="integer" value="7" label="adaptive confdiff behaviour (default: 7)" help="Specifies how many seeds of a read may be ignored (based on the maximum hits value above) before the confidence threshold above gets increased by one for that read; helps fine-tuning alignment accuracy in repetitive regions of the genome."/> 167 <param help="Specifies how many seeds of a read may be ignored (based on the maximum hits value above) before the confidence threshold above gets increased by one for that read; helps fine-tuning alignment accuracy in repetitive regions of the genome." label="adaptive confdiff behaviour (default: 7)" name="confadpt" type="integer" value="7" />
168 <param name="maxseeds" type="integer" value="25" label="maximum seeds per read (default: 25)" help="Number of seeds to use per read (SNAP option -n) when trying to match it to the reference genome; higher numbers will increase the rate of aligned reads and reduce the rate of misalignments, but will reduce performance."/> 168 <param help="Number of seeds to use per read (SNAP option -n) when trying to match it to the reference genome; higher numbers will increase the rate of aligned reads and reduce the rate of misalignments, but will reduce performance." label="maximum seeds per read (default: 25)" name="maxseeds" type="integer" value="25" />
169 <param name="clipping" type="select" label="read clipping (default: from back and front)" help="Specifies from which end of a read low-quality bases should be clipped (SNAP option -Cxx)"> 169 <param help="Specifies from which end of a read low-quality bases should be clipped (SNAP option -Cxx)" label="read clipping (default: from back and front)" name="clipping" type="select">
170 <option value="++">from back and front</option> 170 <option value="++">from back and front</option>
171 <option value="x+">from back only</option> 171 <option value="x+">from back only</option>
172 <option value="+x">from front only</option> 172 <option value="+x">from front only</option>
173 <option value="xx">no clipping</option> 173 <option value="xx">no clipping</option>
174 </param> 174 </param>
175 <param name="selectivity" type="integer" value="1" label="selectivity (default: 1)" help="randomly choose 1/selectivity of the reads to score (SNAP option -S). The tool uses the default of 1 (or a 0 setting) to indicate that all reads should be worked with." /> 175 <param help="randomly choose 1/selectivity of the reads to score (SNAP option -S). The tool uses the default of 1 (or a 0 setting) to indicate that all reads should be worked with." label="selectivity (default: 1)" name="selectivity" type="integer" value="1" />
176 <param name="filter_output" type="select" label="filter output (default: no filtering)" help="filter output (SNAP option -F for certain classes of reads."> 176 <param help="filter output (SNAP option -F for certain classes of reads." label="filter output (default: no filtering)" name="filter_output" type="select">
177 <option value="off">no filtering</option> 177 <option value="off">no filtering</option>
178 <option value="a">aligned only</option> 178 <option value="a">aligned only</option>
179 <option value="s">single-aligned only</option> 179 <option value="s">single-aligned only</option>
180 <option value="u">unaligned only</option> 180 <option value="u">unaligned only</option>
181 </param> 181 </param>
182 <param name="sort" type="select" label="output sorting (default: sort by read coordinates)" help="Sort the output file by alignment location (SNAP option --so)."> 182 <param help="Sort the output file by alignment location (SNAP option --so)." label="output sorting (default: sort by read coordinates)" name="sort" type="select">
183 <option value="0">sort by read coordinates</option> 183 <option value="0">sort by read coordinates</option>
184 <option value="off">no sorting</option> 184 <option value="off">no sorting</option>
185 </param> 185 </param>
186 <param name="mmatch_notation" type="select" label="CIGAR symbols for alignment matches/mismatches (default: M notation)" help="Indicates whether CIGAR strings in the generated SAM/BAM file should use M (alignment match) rather than = and X (sequence (mis-)match). Warning: Downstream variant calling based on samtools currently relies on the old-style M notation!!" > 186 <param help="Indicates whether CIGAR strings in the generated SAM/BAM file should use M (alignment match) rather than = and X (sequence (mis-)match). Warning: Downstream variant calling based on samtools currently relies on the old-style M notation!!" label="CIGAR symbols for alignment matches/mismatches (default: M notation)" name="mmatch_notation" type="select">
187 <option value="general">use M for both matches and mismatches</option> 187 <option value="general">use M for both matches and mismatches</option>
188 <option value="differentiate">use = for matches, X for mismatches</option> 188 <option value="differentiate">use = for matches, X for mismatches</option>
189 </param> 189 </param>
190 </when> 190 </when>
191 </conditional> 191 </conditional>
192 </inputs> 192 </inputs>
193 193
194 <outputs> 194 <outputs>
195 <data name="outputfile" format="bam" label="Aligned reads from MiModd ${tool.name} on ${on_string}"> 195 <data format="bam" label="Aligned reads from MiModd ${tool.name} on ${on_string}" name="outputfile">
196 <change_format> 196 <change_format>
197 <when input="oformat" value="sam" format="sam"/> 197 <when format="sam" input="oformat" value="sam" />
198 </change_format> 198 </change_format>
199 </data> 199 </data>
200 </outputs> 200 </outputs>
201 201
202 <help> 202 <help>
237 .. _MiModD user guide: http://mimodd.readthedocs.org/en/latest 237 .. _MiModD user guide: http://mimodd.readthedocs.org/en/latest
238 .. _tool documentation: http://mimodd.readthedocs.org/en/latest/tool_doc.html#snap 238 .. _tool documentation: http://mimodd.readthedocs.org/en/latest/tool_doc.html#snap
239 239
240 </help> 240 </help>
241 </tool> 241 </tool>
242