<?xml version="1.0" encoding="UTF-8"?>
<!--WARNING: Do not change anything inside this workflow file. BioExtract won't recognize your changes, or may even refuse to import it. Instead, modify the workflow in BioExtract after importing. This workflow file can be imported into BioExtract only.-->
  <s:bioextract xmlns:s="http://bioextract.org" version="2.1" log="0">
<s:workflowdescription description="Query NCBI Nucleotide Core for a specific sequence (e.g. Accession = ab070068). Execute EMBOSS getorf tool (emboss.sourceforge.net/apps/release/5.0/emboss/apps/getorf.html) to find the ORF protein translations.  Execute NCBI BlastP to perform a search using the ORF protein translations to identify sequences which have some relationship with know protein space.  Save the set of records identified by the blastp search. Execute EBI's InterProScan tool ((http://www.ebi.ac.uk/Tools/webservices/services/interproscan) to access InterProScan." author="Carol Lushbough" uid="4EAEAF9D-D711-0EE5-7FD7-8F7FBBDAE495" title="Nucleotide EBI InterProScan"/>
<s:processor name="query"><s:stringconstant>NCBI Core Nucleotide:ab070068</s:stringconstant></s:processor><s:processor name="getorf"><s:description>"Finds and extracts open reading frames                  (ORFs)"</s:description><s:soaplabwsdl>http://www.ebi.ac.uk/soaplab/services/nucleic_gene_finding.getorf</s:soaplabwsdl><s:helpurl>"http://emboss.sourceforge.net/apps/release/4.1/emboss/apps/getorf.html"</s:helpurl><s:parameter name="table" value="0"/><s:parameter name="minsize" value="200"/><s:parameter name="maxsize" value="1000000"/><s:parameter name="find" value="0"/><s:parameter name="flanking" value="100"/><s:parameter name="osformat_outseq" value="fasta"/></s:processor><s:processor name="Blastp"><s:description>"Protein BLAST: Search protein databases using a protein query"</s:description><s:helpurl>"http://www.ncbi.nlm.nih.gov/BLAST/blastcgihelp.shtml"</s:helpurl><s:parameter name="Select database" value="nr"/><s:parameter name="Do CD-Search" value="checkbox-on"/><s:parameter name="Limit to the organism" value="All organisms"/><s:parameter name="Expect" value="10"/><s:parameter name="Word size" value="w_3"/><s:parameter name="Matrix" value="BLOSUM62"/><s:parameter name="Gap costs" value="Existence_11_Extension_1"/><s:parameter name="Filter: Low-complexity" value="checkbox-on"/><s:parameter name="Show graphical overview" value="checkbox-on"/><s:parameter name="Show database linkouts" value="checkbox-on"/><s:parameter name="Number of descriptions" value="d_10"/><s:parameter name="Number of alignments" value="a_10"/><s:parameter name="maximum number of sequences" value="10"/></s:processor><s:processor name="saveset"><s:stringconstant>"NCBIORFBlastPab070068.dba"</s:stringconstant><s:description name="NCBI ORF BlastP ab070068"/></s:processor><s:processor name="EBI_InterproScan"><s:description>"Runs the InterproScan service from the European Bioinformatics institute (EBI) "</s:description><s:helpurl>"http://bioinfo.mpiz-koeln.mpg.de/axis/services/EBI_InterproScan"</s:helpurl><s:parameter name="seqtype" value="protein"/><s:parameter name="apps" value="all"/><s:parameter name="outformat" value="raw"/></s:processor><s:link source="query:value" sink="getorf:sequence_usa" />
<s:link source="getorf:outseq" sink="Blastp:sequences_direct_data" />
 <s:link source="Blastp:Graphics_in_PNG" sink="Blastp" />
<s:sink name="Blastp">
 <s:metadata> <s:mimeTypes>
<s:mimeType>image/png</s:mimeType>
 </s:mimeTypes> </s:metadata> </s:sink>
  </s:bioextract>