comparison snap_caller.xml @ 4:ffee8534a5c4

upgrade to mimodd version 0.1.6
author Wolfgang Maier
date Thu, 04 Jun 2015 17:52:04 +0200
parents 72d20758ba2c
children bdd1995c9e66
comparison
equal deleted inserted replaced
3:ba685c655e18 4:ffee8534a5c4
29 --selectivity '$set.selectivity' 29 --selectivity '$set.selectivity'
30 #end if 30 #end if
31 #if $str($set.filter_output) != "off": 31 #if $str($set.filter_output) != "off":
32 --filter-output $set.filter_output 32 --filter-output $set.filter_output
33 #end if 33 #end if
34 #if $str($set.sort) != "off": 34 #if $str($set.sort) == "off":
35 --sort $set.sort 35 --no-sort
36 #end if 36 #end if
37 #if $str($set.mmatch_notation) == "general": 37 #if $str($set.mmatch_notation) != "general":
38 -M 38 -X
39 #end if 39 #end if
40 --max-mate-overlap '$set.max_mate_overlap' 40 #if $set.discard_overlapping_mates:
41 --discard-overlapping-mates
42 ## remove ',' (and possibly adjacent whitespace) and replace with ' '
43 '#echo ("' '".join($set.discard_overlapping_mates.replace(" ", "").split(',')))#'
44 #end if
41 --verbose 45 --verbose
42 " 46 "
43 #end for 47 #end for
44 </command> 48 </command>
45 49
142 146
143 <param name="selectivity" type="hidden" value="off"/> 147 <param name="selectivity" type="hidden" value="off"/>
144 <param name="filter_output" type="hidden" value="off"/> 148 <param name="filter_output" type="hidden" value="off"/>
145 <param name="sort" type="hidden" value="0"/> 149 <param name="sort" type="hidden" value="0"/>
146 <param name="mmatch_notation" type="hidden" value="general"/> 150 <param name="mmatch_notation" type="hidden" value="general"/>
147 <param name="max_mate_overlap" type="hidden" value="0" /> 151 <param name="discard_overlapping_mates" type="hidden" value="" />
148 </when> 152 </when>
149 153
150 ## change settings 154 ## change settings
151 155
152 <when value="change"> 156 <when value="change">
153 <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 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)."/>
154 <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 name="slack" type="float" value="0.3" label="hash table slack size (default: 0.3)" help="Corresponds to the -h option of SNAP index."/>
155 159
156 ## paired-end specific options 160 ## paired-end specific options
157 <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."/> 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."/>
158 <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."/> 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."/>
159 <param name="max_mate_overlap" type="float" value="0" label="Maximal overlap between the reads in a pair (as a fraction of their combined length; default: 0, no overlap allowed)" help="If the reads of a read pair overlap by more than this fraction of their combined length, they are filtered out" /> 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." />
160
161 <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 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."/>
162 <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 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."/>
163 <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 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."/>
164 <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 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."/>
165 <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 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."/>
223 226
224 While it is not our recommended approach, you can, if you prefer it, align reads from fastq files or SAM/BAM files without header read-group information. To do so, you **must** specify a SAM file that provides the missing information in its header along with the input dataset. You can generate a SAM header file with the *NGS Run Annotation* tool. 227 While it is not our recommended approach, you can, if you prefer it, align reads from fastq files or SAM/BAM files without header read-group information. To do so, you **must** specify a SAM file that provides the missing information in its header along with the input dataset. You can generate a SAM header file with the *NGS Run Annotation* tool.
225 228
226 Optionally, a SAM header file can also be used to replace existing read-group information in a headered SAM/BAM input file. This can be used to resolve read-group ID conflicts between multiple input files at tool runtime. 229 Optionally, a SAM header file can also be used to replace existing read-group information in a headered SAM/BAM input file. This can be used to resolve read-group ID conflicts between multiple input files at tool runtime.
227 230
228 4) Currently, you cannot configure aligner-specific options separately for specific input files from within this Galaxy tool. If you need this advanced level of control, you should use the command line tool ``mimodd snap-batch``. 231 5) The options available under *further parameter settings* can have **big** effects on the alignment quality. You are strongly encouraged to consult the `tool documentation`_ for detailed explanations of the available options.
232
233 6) Currently, you cannot configure aligner-specific options separately for specific input files from within this Galaxy tool. If you need this advanced level of control, you should use the command line tool ``mimodd snap-batch``.
229 234
230 .. _Fastq Manipulation category: https://toolshed.g2.bx.psu.edu/repository/browse_repositories_in_category?id=310ff67d4caf6531 235 .. _Fastq Manipulation category: https://toolshed.g2.bx.psu.edu/repository/browse_repositories_in_category?id=310ff67d4caf6531
231 .. _recipe for using gzipped fastq files in Galaxy: http://mimodd.readthedocs.org/en/latest/recipes.html#use-gzipped-fastq-files-in-galaxy 236 .. _recipe for using gzipped fastq files in Galaxy: http://mimodd.readthedocs.org/en/latest/recipes.html#use-gzipped-fastq-files-in-galaxy
232 .. _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
233 239
234 </help> 240 </help>
235 </tool> 241 </tool>
236 242