Find Orthologs for proteins in Ensembl

Script

if ((proteinId == void) || (proteinId == null) || proteinId.equals("")) {
	throw new RunTimeException("port proteinId must have a non-empty value");
}
if ((ensemblDataset == void) || (ensemblDataset == null) || ensemblDataset.equals("")) {
	throw new RunTimeException("port ensemblDataset must have a non-empty value");
}
if((idReference == void) || (idReference == null) ||idReference.equals("")) {
	throw new RunTimeException("port idReference must have a non-empty value");	
}
if((orthologSpecie == void) || (orthologSpecie == null) ||orthologSpecie.equals("")) {
	throw new RunTimeException("port orthologSpecie must have a correct or non-empty value");	
}

String queryFormat = "CSV";
String queryFilter = "";
if(idReference.equalsIgnoreCase( "swissprot" )){
    	queryFilter = "uniprot_swissprot_accession";
} else if (idReference.equalsIgnoreCase( "trembl" )){
   	queryFilter = "uniprot_sptrembl";
} else if (idReference.equalsIgnoreCase( "ensembl" )) {
   	queryFilter = "ensembl_peptide_id";
} else {
	throw new RunTimeException("port idReference must have a correct value");	
}


// Biomart does not like encoded XML :-(        
String queryXml = "http://www.ensembl.org/biomart/martservice?query=" +
           "%3C?xml%20version=%271.0%27%20encoding=%27UTF-8%27?%3E" +
           "%3C!DOCTYPE%20Query%3E" +
           "%3CQuery%20%20virtualSchemaName%20=%20%27default%27%20formatter%20=%20%27"+ queryFormat + "%27%20header%20=%20%270%27%20uniqueRows%20=%20%271%27%20count%20=%20%27%27%20datasetConfigVersion%20=%20%270.6%27%20%3E" +
           "%3CDataset%20name%20=%20%27" + ensemblDataset.toLowerCase() + "%27%20interface%20=%20%27default%27%20%3E" +
           "%3CFilter%20name%20=%20%27" + queryFilter + "%27%20value%20=%20%27" + proteinId + "%27%20/%3E" +
           "%3CAttribute%20name%20=%20%27ensembl_peptide_id%27%20/%3E" +
           "%3CAttribute%20name%20=%20%27" + orthologSpecie.toLowerCase() + "_homolog_ensembl_peptide%27%20/%3E" +
           "%3CAttribute%20name%20=%20%27" + orthologSpecie.toLowerCase() + "_orthology_type%27%20/%3E" +
           "%3CAttribute%20name%20=%20%27" + orthologSpecie.toLowerCase() + "_homolog_subtype%27%20/%3E" +
           "%3CAttribute%20name%20=%20%27" + orthologSpecie.toLowerCase() + "_homolog_perc_id%27%20/%3E" +
           "%3CAttribute%20name%20=%20%27" + orthologSpecie.toLowerCase() + "_homolog_perc_id_r1%27%20/%3E" +
           "%3CAttribute%20name%20=%20%27" + orthologSpecie.toLowerCase() + "_homolog_ds%27%20/%3E" +
           "%3CAttribute%20name%20=%20%27" + orthologSpecie.toLowerCase() + "_homolog_dn%27%20/%3E" +
           "%3C/Dataset%3E" +
           "%3C/Query%3E";


List esemblId = new ArrayList();
List orthologId = new ArrayList();
List orthologyType = new ArrayList();
List homologSubtype = new ArrayList();
List homologPercId = new ArrayList();
List homologPercIdR1 = new ArrayList();
List homologDs = new ArrayList();
List homologDn = new ArrayList();
List summary = new ArrayList();


URL url = new URL(queryXml);
BufferedReader reader = new BufferedReader (new InputStreamReader(url.openStream()));

//read each line of text file
String line = null;
while((line = reader.readLine()) != null){
    if(line.length() > 1){
        summary.add(proteinId + "," + line);
        String[] st = line.split( "," );
        for (int i = 0; i < st.length; i++) {
            if(i==0){
                esemblId.add( st[i] );
            } else if(i==1){
                orthologId.add( st[i] );
            } else if(i==2){
                orthologyType.add( st[i] );
            } else if(i==3){
                homologSubtype.add( st[i] );
            } else if(i==4){
                homologPercId.add( st[i] );
            } else if(i==5){
                homologPercIdR1.add( st[i] );
            } else if(i==6){
                homologDs.add( st[i] );
            } else if(i==7){
                homologDn.add( st[i] );
            }
        }
    }
}