/tools/metag_tools/shrimp_color_wrapper.xml
https://bitbucket.org/cistrome/cistrome-harvard/ · XML · 181 lines · 151 code · 30 blank · 0 comment · 0 complexity · fb666bb1391403f115604e03941525a8 MD5 · raw file
- <tool id="shrimp_color_wrapper" name="SHRiMP for Color-space" version="1.0.0">
- <description>reads mapping against reference sequence </description>
- <command interpreter="python">
- #if $param.skip_or_full=="skip" #shrimp_color_wrapper.py $input_target $input_query $output1
- #else #shrimp_color_wrapper.py $input_target $input_query $output1 $param.spaced_seed $param.seed_matches_per_window $param.seed_hit_taboo_length $param.seed_generation_taboo_length $param.seed_window_length $param.max_hits_per_read $param.max_read_length $param.kmer $param.sw_match_value $param.sw_mismatch_value $param.sw_gap_open_ref $param.sw_gap_open_query $param.sw_gap_ext_ref $param.sw_gap_ext_query $param.sw_crossover_penalty $param.sw_full_hit_threshold $param.sw_vector_hit_threshold
- #end if#
- </command>
- <inputs>
- <page>
- <param name="input_query" type="data" format="csfasta" label="Align sequencing reads" help="No dataset? Read tip below"/>
- <param name="input_target" type="data" format="fasta" label="against reference" />
- <conditional name="param">
- <param name="skip_or_full" type="select" label="SHRiMP settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full List">
- <option value="skip">Commonly used</option>
- <option value="full">Full Parameter List</option>
- </param>
- <when value="skip" />
- <when value="full">
- <param name="spaced_seed" type="text" size="30" value="1111001111" label="Spaced Seed" />
- <param name="seed_matches_per_window" type="integer" size="5" value="2" label="Seed Matches per Window" />
- <param name="seed_hit_taboo_length" type="integer" size="5" value="4" label="Seed Hit Taboo Length" />
- <param name="seed_generation_taboo_length" type="integer" size="5" value="0" label="Seed Generation Taboo Length" />
- <param name="seed_window_length" type="float" size="10" value="115.0" label="Seed Window Length" help="in percentage"/>
- <param name="max_hits_per_read" type="integer" size="10" value="100" label="Maximum Hits per Read" />
- <param name="max_read_length" type="integer" size="10" value="1000" label="Maximum Read Length" />
- <param name="kmer" type="integer" size="10" value="-1" label="Kmer Std. Deviation Limit" help="-1 as None"/>
- <param name="sw_match_value" type="integer" size="10" value="100" label="S-W Match Value" />
- <param name="sw_mismatch_value" type="integer" size="10" value="-150" label="S-W Mismatch Value" />
- <param name="sw_gap_open_ref" type="integer" size="10" value="-400" label="S-W Gap Open Penalty (Reference)" />
- <param name="sw_gap_open_query" type="integer" size="10" value="-400" label="S-W Gap Open Penalty (Query)" />
- <param name="sw_gap_ext_ref" type="integer" size="10" value="-70" label="S-W Gap Extend Penalty (Reference)" />
- <param name="sw_gap_ext_query" type="integer" size="10" value="-70" label="S-W Gap Extend Penalty (Query)" />
- <param name="sw_crossover_penalty" type="integer" size="10" value="-140" label="S-W Crossover Penalty" />
- <param name="sw_full_hit_threshold" type="float" size="10" value="68.0" label="S-W Full Hit Threshold" help="in percentage"/>
- <param name="sw_vector_hit_threshold" type="float" size="10" value="60.0" label="S-W Vector Hit Threshold" help="in percentage"/>
- </when>
- </conditional>
- </page>
- </inputs>
- <outputs>
- <data name="output1" format="tabular"/>
- </outputs>
- <requirements>
- <requirement type="binary">rmapper-cs</requirement>
- </requirements>
- <tests>
- <test>
- <param name="skip_or_full" value="skip" />
- <param name="input_target" value="Ssuis.fasta" ftype="fasta" />
- <param name="input_query" value="shrimp_cs_test1.csfasta" ftype="csfasta"/>
- <output name="output1" file="shrimp_cs_test1.out" />
- </test>
- </tests>
- <help>
-
- .. class:: warningmark
- To use this tool your dataset needs to be in the *csfasta* (as ABI SOLiD color-space sequences) format. Click pencil icon next to your dataset to set the datatype to *csfasta*.
- -----
-
- **What it does**
-
- SHRiMP (SHort Read Mapping Package) is a software package for aligning genomic reads against a target genome.
-
- -----
- **Input formats**
- A multiple color-space file, for example::
- >2_263_779_F3
- T132032030200202202003211302222202230022110222
- -----
- **Outputs**
- The tool returns the default SHRiMP output::
-
- 1 2 3 4 5 6 7 8 9 10
- --------------------------------------------------------------------------------------------------------------------
- >2_263_779_F3 Streptococcus_suis + 814344 814388 1 45 45 3660 8x19x3x2x6x4x3
- where::
- 1. (>2_263_779_F3) - Read id
- 2. (Streptococcus_suis) - Reference sequence id
- 3. (+) - Strand of the read
- 4. (814344) - Start position of the alignment in the reference
- 5. (814388) - End position of the alignment in the reference
- 6. (1) - Start position of the alignment in the read
- 7. (45) - End position of the alignment in the read
- 8. (45) - Length of the read
- 9. (3660) - Score
- 10. (8x19x3x2x6x4x3) - Edit string
-
- -----
- **SHRiMP parameter list**
- The commonly used parameters with default value setting::
- -s Spaced Seed (default: 111111011111)
- The spaced seed is a single contiguous string of 0's and 1's.
- 0's represent wildcards, or positions which will always be
- considered as matching, whereas 1's dictate positions that
- must match. A string of all 1's will result in a simple kmer scan.
- -n Seed Matches per Window (default: 2)
- The number of seed matches per window dictates how many seeds
- must match within some window length of the genome before that
- region is considered for Smith-Waterman alignment. A lower
- value will increase sensitivity while drastically increasing
- running time. Higher values will have the opposite effect.
- -t Seed Hit Taboo Length (default: 4)
- The seed taboo length specifies how many target genome bases
- or colours must exist prior to a previous seed match in order
- to count another seed match as a hit.
- -9 Seed Generation Taboo Length (default: 0)
-
- -w Seed Window Length (default: 115.00%)
- This parameter specifies the genomic span in bases (or colours)
- in which *seed_matches_per_window* must exist before the read
- is given consideration by the Simth-Waterman alignment machinery.
- -o Maximum Hits per Read (default: 100)
- This parameter specifies how many hits to remember for each read.
- If more hits are encountered, ones with lower scores are dropped
- to make room.
- -r Maximum Read Length (default: 1000)
- This parameter specifies the maximum length of reads that will
- be encountered in the dataset. If larger reads than the default
- are used, an appropriate value must be passed to *rmapper*.
- -d Kmer Std. Deviation Limit (default: -1 [None])
- This option permits pruning read kmers, which occur with
- frequencies greater than *kmer_std_dev_limit* standard
- deviations above the average. This can shorten running
- time at the cost of some sensitivity.
- *Note*: A negative value disables this option.
- -m S-W Match Value (default: 100)
- The value applied to matches during the Smith-Waterman score calculation.
- -i S-W Mismatch Value (default: -150)
- The value applied to mismatches during the Smith-Waterman
- score calculation.
- -g S-W Gap Open Penalty (Reference) (default: -400)
- The value applied to gap opens along the reference sequence
- during the Smith-Waterman score calculation.
- *Note*: Note that for backward compatibility, if -g is set
- and -q is not set, the gap open penalty for the query will
- be set to the same value as specified for the reference.
- -q S-W Gap Open Penalty (Query) (default: -400)
- The value applied to gap opens along the query sequence during
- the Smith-Waterman score calculation.
- -e S-W Gap Extend Penalty (Reference) (default: -70)
- The value applied to gap extends during the Smith-Waterman score calculation.
- *Note*: Note that for backward compatibility, if -e is set
- and -f is not set, the gap exten penalty for the query will
- be set to the same value as specified for the reference.
- -f S-W Gap Extend Penalty (Query) (default: -70)
- The value applied to gap extends during the Smith-Waterman score calculation.
- -x
- -h S-W Full Hit Threshold (default: 68.00%)
- In letter-space, this parameter determines the threshold
- score for both vectored and full Smith-Waterman alignments.
- Any values less than this quantity will be thrown away.
- *Note* This option differs slightly in meaning between letter-space and color-space.
- -v
-
- -----
- **Reference**
-
- **SHRiMP**: Stephen M. Rumble, Michael Brudno, Phil Lacroute, Vladimir Yanovsky, Marc Fiume, Adrian Dalca. shrimp at cs dot toronto dot edu.
- </help>
- </tool>