Mercurial > repos > jjohnson > gmap
annotate iit_store.xml @ 2:f6ba0f12cca2 draft
Untested work-in-progress GMAP wrappers v3.0.0, from JJ back in June 2013
| author | peterjc |
|---|---|
| date | Wed, 28 Sep 2016 10:43:44 -0400 |
| parents | 74391fc6e3f2 |
| children | 488e9d642566 |
| rev | line source |
|---|---|
|
2
f6ba0f12cca2
Untested work-in-progress GMAP wrappers v3.0.0, from JJ back in June 2013
peterjc
parents:
1
diff
changeset
|
1 <tool id="gmap_iit_store" name="GMAP IIT" version="3.0.0"> |
| 0 | 2 <description>Create a map store for known genes or SNPs</description> |
| 3 <requirements> | |
|
2
f6ba0f12cca2
Untested work-in-progress GMAP wrappers v3.0.0, from JJ back in June 2013
peterjc
parents:
1
diff
changeset
|
4 <requirement type="package" version="2013-05-09">gmap</requirement> |
| 0 | 5 </requirements> |
| 6 <version_string>iit_store --version</version_string> | |
| 7 <command interpreter="command"> /bin/bash $shscript 2> $log </command> | |
| 8 <inputs> | |
| 9 <!-- Input data --> | |
| 10 <conditional name="map"> | |
| 11 <param name="type" type="select" label="Make map for" > | |
| 12 <option value="genes">Introns and Splice sites</option> | |
| 13 <option value="snps">SNPs</option> | |
| 14 <option value="gmap">GMAP Annotation</option> | |
| 15 </param> | |
| 16 <when value="genes"> | |
| 17 <conditional name="src"> | |
| 18 <param name="src_format" type="select" label="Add splice and intron info from" > | |
| 19 <option value="refGeneTable">refGenes table from UCSC table browser</option> | |
| 20 <option value="gtf">GTF</option> | |
| 21 <option value="gff3">GFF3</option> | |
| 22 </param> | |
| 23 <when value="refGeneTable"> | |
| 24 <param name="genes" type="data" format="tabular" label="UCSC refGenes table" help="Example: ftp://hgdownload.cse.ucsc.edu/goldenPath/hg18/database/refGene.txt.gz" /> | |
| 25 <param name="col_skip" type="integer" value="1" label="Columns to skip before the id/name column (default 1)" | |
| 26 help="Note that alignment tracks in UCSC sometimes have an extra column on the left."> | |
| 27 <validator type="in_range" message="The number of colmumns to skip must >= 0." min="0."/> | |
| 28 </param> | |
| 29 </when> | |
| 30 <when value="gtf"> | |
| 31 <param name="genes" type="data" format="gtf" label="Genes as GTF" help="" /> | |
| 32 </when> | |
| 33 <when value="gff3"> | |
| 34 <param name="genes" type="data" format="gff3" label="Genes in GFF3 format" help="" /> | |
| 35 </when> | |
| 36 </conditional> | |
| 37 <param name="maps" type="select" display="checkboxes" multiple="true" force_select="true" label="Add splice and intron info from" > | |
| 38 <option value="splicesites" selected="true">splicesites.iit</option> | |
| 39 <option value="introns" selected="false">introns.iit</option> | |
| 40 </param> | |
| 41 </when> | |
| 42 <when value="snps"> | |
| 43 <conditional name="src"> | |
| 44 <param name="src_format" type="select" label="Add SNP info from" > | |
| 45 <option value="snpTable">UCSC SNP Table</option> | |
| 46 <option value="snpFile">GMAP SNP File</option> | |
| 47 </param> | |
| 48 <when value="snpTable"> | |
| 49 <param name="snps" type="data" format="tabular" label="UCSC SNPs table" help="Example: ftp://hgdownload.cse.ucsc.edu/goldenPath/hg18/database/snp130.txt.gz" /> | |
| 50 <param name="snpsex" type="data" format="tabular" optional="true" label="UCSC SNP Exceptions table" help="Example: ftp://hgdownload.cse.ucsc.edu/goldenPath/hg18/database/snp130Exceptions.txt.gz" /> | |
| 51 <param name="weight" type="select" label="Include SNPs with at least Confidence Level" help=""> | |
| 52 <option value="1" selected="true">1 (High)</option> | |
| 53 <option value="2">2 (Medium)</option> | |
| 54 <option value="3">3 (All)</option> | |
| 55 </param> | |
| 56 </when> | |
| 57 <when value="snpFile"> | |
| 58 <param name="snps" type="data" format="gmap_snps" optional="true" label="GMAP SNPs file" | |
| 59 help="Format (3 columns):<B> | |
| 60 <br>>rs62211261 21:14379270 CG | |
| 61 <br>>rs62211262 21:14379281 CG | |
| 62 </B> | |
| 63 <br>Each line must start with a > character, then be followed by an | |
| 64 identifier (which may have duplicates). Then there should be the | |
| 65 chromosomal coordinate of the SNP. (Coordinates are all 1-based, so | |
| 66 the first character of a chromosome is number 1.) Finally, there | |
| 67 should be the two possible alleles: ( AC AG AT CG CT GT or AN CN GN TN) | |
| 68 <br>These alleles must correspond to the possible nucleotides on the plus strand of the genome. | |
| 69 If the one of these two letters does not match the allele in the reference | |
| 70 sequence, that SNP will be ignored in subsequent processing as a probable error. | |
| 71 The N stands for any other allele." /> | |
| 72 </when> | |
| 73 </conditional> | |
| 74 </when> | |
| 75 <when value="gmap"> | |
| 76 <param name="annotation" type="data" format="gmap_annotation" label="GMAP mapfile" | |
| 77 help="Format (2 or columns): <B> | |
| 78 <br>>label coords optional_tag | |
| 79 <br>optional_annotation (which may be zero, one, or multiple lines) | |
| 80 </B> | |
| 81 <br>Each line must start with a > character, then be followed by an identifier (which may have duplicates). | |
| 82 <br>Then there should be the chromosomal coordinate range. (Coordinates are all 1-based, so the first character of a chromosome is number 1.) | |
| 83 <br>The coords should be of the form | |
| 84 <br> chr:position | |
| 85 <br> chr:startposition..endposition | |
| 86 <br>The term chr:position is equivalent to chr:position..position. | |
| 87 <br>If you want to indicate that the interval is on the minus strand or reverse direction, then endposition may be less than startposition. | |
| 88 " /> | |
| 89 </when> | |
| 90 </conditional> | |
| 91 </inputs> | |
| 92 <outputs> | |
| 93 <data format="txt" name="log" label="${tool.name} on ${on_string}: log"/> | |
| 94 <data format="splicesites.iit" name="splicesites_iit" label="${tool.name} on ${on_string} splicesites.iit"> | |
| 95 <filter>(map['type'] == 'genes' and 'splicesites' in map['maps'])</filter> | |
| 96 </data> | |
| 97 <data format="introns.iit" name="introns_iit" label="${tool.name} on ${on_string} introns.iit"> | |
| 98 <filter>(map['type'] == 'genes' and 'introns' in map['maps'])</filter> | |
| 99 </data> | |
| 100 <data format="snps.iit" name="snps_iit" label="${tool.name} on ${on_string} snps.iit"> | |
| 101 <filter>(map['type'] == 'snps')</filter> | |
| 102 </data> | |
| 103 <data format="iit" name="map_iit" label="${tool.name} on ${on_string} map.iit"> | |
| 104 <filter>(map['type'] == 'gmap')</filter> | |
| 105 </data> | |
| 106 </outputs> | |
| 107 <configfiles> | |
| 108 <configfile name="shscript"> | |
| 109 #!/bin/bash | |
| 110 #set $catcmd = 'gzcat -f' | |
| 111 #set $catcmd = 'cat' | |
| 112 #set $ds = chr(36) | |
| 113 #set $gt = chr(62) | |
| 114 #set $lt = chr(60) | |
| 115 #set $ad = chr(38) | |
| 116 #set $ep = chr(33) | |
| 117 #set $toerr = ''.join([$gt,$ad,'2']) | |
| 118 #import os.path | |
| 119 #if $map.type == 'genes': | |
| 120 if [ $ep -e $map.src.genes ]; then echo "$map.src.genes does not exist" $toerr; exit 1; fi | |
| 121 if [ $ep -s $map.src.genes ]; then echo "$map.src.genes is empty" $toerr; exit 2; fi | |
| 122 #if $map.src.src_format == 'refGeneTable': | |
| 123 #if 'splicesites' in [ $map.maps.__str__ ]: | |
| 124 $catcmd $map.src.genes | psl_splicesites -s $map.src.col_skip | iit_store -o $splicesites_iit | |
| 125 #end if | |
| 126 #if 'introns' in [ $map.maps.__str__ ]: | |
| 127 $catcmd $map.src.genes | psl_introns -s $map.src.col_skip | iit_store -o $introns_iit | |
| 128 #end if | |
| 129 #elif $map.src.src_format == 'gtf': | |
| 130 #if 'splicesites' in [ $map.maps.__str__ ]: | |
| 131 $catcmd $map.src.genes | gtf_splicesites | iit_store -o $splicesites_iit | |
| 132 #end if | |
| 133 #if 'introns' in [ $map.maps.__str__ ]: | |
| 134 $catcmd $map.src.genes | gtf_introns | iit_store -o $introns_iit | |
| 135 #end if | |
| 136 #elif $map.src.src_format == 'gff3': | |
| 137 #if 'splicesites' in [ $map.maps.__str__ ]: | |
| 138 $catcmd $map.src.genes | gff3_splicesites | iit_store -o $splicesites_iit | |
| 139 #end if | |
| 140 #if 'introns' in [ $map.maps.__str__ ]: | |
| 141 $catcmd $map.src.genes | gff3_introns | iit_store -o $introns_iit | |
| 142 #end if | |
| 143 #end if | |
| 144 #elif $map.type == 'snps': | |
| 145 if [ $ep -s $map.src.snps ]; then echo "$map.src.snps is empty" $toerr; exit 2; fi | |
| 146 #if $map.src.snpsex.__str__ != 'None': | |
| 147 $catcmd $map.src.snps | dbsnp_iit -w $map.src.weight -e $map.src.snpsex | iit_store -o $snps_iit | |
| 148 #else: | |
| 149 $catcmd $map.src.snps | dbsnp_iit -w $map.src.weight | iit_store -o $snps_iit | |
| 150 #end if | |
| 151 #else: | |
| 152 $catcmd $map.src.snps | iit_store -o $map_iit | |
| 153 #end if | |
| 154 </configfile> | |
| 155 </configfiles> | |
| 156 | |
| 157 <tests> | |
| 158 </tests> | |
| 159 | |
| 160 <help> | |
| 161 | |
| 162 | |
| 163 **iit_store** | |
| 164 | |
| 165 GMAP IIT creates an Interval Index Tree map of known splice sites, introns, or SNPs (it uses iit_store described in the GMAP documentation). The maps can be used in GMAP_ (Genomic Mapping and Alignment Program for mRNA and EST sequences) and GSNAP_ (Genomic Short-read Nucleotide Alignment Program). Maps are typically used for known splice sites, introns, or SNPs. | |
| 166 | |
| 167 You will want to read the README_ | |
| 168 | |
| 169 Publication_ citation: Thomas D. Wu, Colin K. Watanabe Bioinformatics 2005 21(9):1859-1875; doi:10.1093/bioinformatics/bti310 | |
| 170 | |
| 171 .. _GMAP: http://research-pub.gene.com/gmap/ | |
| 172 .. _GSNAP: http://research-pub.gene.com/gmap/ | |
| 173 .. _README: http://research-pub.gene.com/gmap/src/README | |
| 174 .. _Publication: http://bioinformatics.oxfordjournals.org/cgi/content/full/21/9/1859 | |
| 175 | |
| 176 | |
| 177 **inputs** | |
| 178 | |
| 179 </help> | |
| 180 </tool> | |
| 181 |