miRNA GFF to entrez gene
Created: 2011-01-26 11:10:40
Last updated: 2012-01-11 14:32:54
This workflow reads a GFF file of miRNA cooridinates and uses BioMart to search human ensemble genes for the gene that codes for the miRNA. The workflow returns a list of miRNAid, chromosome, start, stop, strand, entrez gene id, gene name, gene strand. Example input file here: ftp://mirbase.org/pub/mirbase/CURRENT/genomes/hsa.gff
Preview
Run
Run this Workflow in the Taverna Workbench...
Workflow Components
Authors (0)
Titles (0)
Descriptions (0)
Dependencies (0)
Inputs (1)
| Name |
Description |
| Beanshell_url |
|
Processors (5)
| Name |
Type |
Description |
| get_File_from_Web |
beanshell |
ScriptURL inputURL = null;
if (base != void) {
inputURL = new URL(new URL(base), url);
}
else {
inputURL = new URL(url);
}
URLConnection con = inputURL.openConnection();
InputStream in = con.getInputStream();
InputStreamReader isr = new InputStreamReader(in);
Reader inReader = new BufferedReader(isr);
StringBuffer buf = new StringBuffer();
int ch;
while ((ch = inReader.read()) > -1) {
buf.append((char)ch);
}
inReader.close();
contents = buf.toString();
|
| split_mirbase_GFF |
beanshell |
Scriptimport java.util.regex.Matcher;
import java.util.regex.Pattern;
String name_input = file;
String[] name_array = name_input.split("\n");
chr = new ArrayList();
start = new ArrayList();
end = new ArrayList();
miRNAid = new ArrayList();
region = new ArrayList();
strand = new ArrayList();
//ACC="MI0006363"; ID="hsa-mir-1302-2";
Pattern p = Pattern.compile("ID=\"(.*)\"");
for(int line = 0; line < name_array.length; line++)
{
String temp = name_array[line];
if (!temp.startsWith("#")) {
String [] cols = temp.split("\t");
chr.add(cols[0]);
start.add(cols[3]);
end.add(cols[4]);
strand.add(cols[6]);
String r;
//if (cols[6].startsWith("+")) {
// r = cols[0] + ":" + cols[3] + ":" + cols[4] + ":1";
// }//
//else {
// r = cols[0] + ":" + cols[3] + ":" + cols[4] + ":-1";
// }
r = cols[0] + ":" + cols[3] + ":" + cols[4];
region.add(r);
String t = cols[8];
Matcher m = p.matcher(t);
boolean matchFound = m.find();
if (matchFound) {
// Get all groups for this match
miRNAid.add(m.group(1));
}
}
}
|
| hsapiens_gene_ensembl |
biomart |
|
| Beanshell |
beanshell |
Script//output = "";
//if (geneid != null){
// output = mirnaid + "\t" + geneid + "\n";
//}
combined = new ArrayList();
output = new ArrayList();
for (Iterator i = geneid.iterator(); i.hasNext();) {
String item = (String) i.next();
if (item != null) {
combined.add(mirnaid + "\t" + chr + "\t" + start + "\t" + stop + "\t" + strand + "\t" + item + "\t" + genename + "\t" + genestrand + "\n");
}
}
output = combined;
|
| Flatten_List |
localworker |
Scriptflatten(inputs, outputs, depth) {
for (i = inputs.iterator(); i.hasNext();) {
element = i.next();
if (element instanceof Collection && depth > 0) {
flatten(element, outputs, depth - 1);
} else {
outputs.add(element);
}
}
}
outputlist = new ArrayList();
flatten(inputlist, outputlist, 1); |
Beanshells (3)
| Name |
Description |
Inputs |
Outputs |
| get_File_from_Web |
|
url
|
contents
|
| split_mirbase_GFF |
|
file
|
chr
start
end
miRNAid
region
strand
|
| Beanshell |
|
mirnaid
geneid
chr
start
stop
strand
genestrand
genename
|
output
|
Outputs (4)
| Name |
Description |
| hsapiens_gene_ensembl_hsapiens_gene_ensembl.entrezgene |
|
| Beanshell_output |
|
| split_mirbase_GFF_miRNAid |
|
| split_mirbase_GFF_region |
|
Datalinks (16)
| Source |
Sink |
| Beanshell_url |
get_File_from_Web:url |
| get_File_from_Web:contents |
split_mirbase_GFF:file |
| split_mirbase_GFF:region |
hsapiens_gene_ensembl:hsapiens_gene_ensembl.chromosomal_region_filter |
| split_mirbase_GFF:miRNAid |
Beanshell:mirnaid |
| hsapiens_gene_ensembl:hsapiens_gene_ensembl.entrezgene |
Beanshell:geneid |
| split_mirbase_GFF:chr |
Beanshell:chr |
| split_mirbase_GFF:end |
Beanshell:stop |
| split_mirbase_GFF:start |
Beanshell:start |
| split_mirbase_GFF:strand |
Beanshell:strand |
| hsapiens_gene_ensembl:hsapiens_gene_ensembl.strand |
Beanshell:genestrand |
| hsapiens_gene_ensembl:hsapiens_gene_ensembl.external_gene_id |
Beanshell:genename |
| Beanshell:output |
Flatten_List:inputlist |
| hsapiens_gene_ensembl:hsapiens_gene_ensembl.entrezgene |
hsapiens_gene_ensembl_hsapiens_gene_ensembl.entrezgene |
| Flatten_List:outputlist |
Beanshell_output |
| split_mirbase_GFF:miRNAid |
split_mirbase_GFF_miRNAid |
| split_mirbase_GFF:region |
split_mirbase_GFF_region |
Uploader
License
All versions of this Workflow are
licensed under:
Version 1
(of 1)
Credits (0)
(People/Groups)
None
Attributions (0)
(Workflows/Files)
None
Shared with Groups (1)
Featured In Packs (0)
None
Log in to add to one of your Packs
Attributed By (0)
(Workflows/Files)
None
Favourited By (0)
No one
Statistics
Other workflows that use similar services
(0)
There are no workflows in myExperiment that use similar services to this Workflow.
Download Workflow
]
Reviews
(0)
No comments yet
Log in to make a comment