<?xml version="1.0" encoding="UTF-8"?>
<s:scufl xmlns:s="http://org.embl.ebi.escience/xscufl/0.1alpha" version="0.2" log="0">
  <s:workflowdescription lsid="urn:lsid:www.mygrid.org.uk:operation:SSAVFCN82D1" author="Arnaud Kerhornou" title="Gene prediction workflow using SGP2 that takes a FASTA sequence input." />
  <s:processor name="StringArticleName" boring="true">
    <s:stringconstant>content</s:stringconstant>
  </s:processor>
  <s:processor name="Decode_base64_to_byte">
    <s:local>org.embl.ebi.escience.scuflworkers.java.DecodeBase64</s:local>
  </s:processor>
  <s:processor name="fromFASTAToDNASequence_2">
    <s:description>Converts a DNA FASTA sequence into a DNA sequence</s:description>
    <s:biomobywsdl>
      <s:mobyEndpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:mobyEndpoint>
      <s:serviceName>fromFASTAToDNASequence</s:serviceName>
      <s:authorityName>genome.imim.es</s:authorityName>
    </s:biomobywsdl>
  </s:processor>
  <s:processor name="runSGP2GFF">
    <s:description>Ab initio gene prediction service. It runs geneid with synteny evidences to improve the accuracy of the results and returns the output predictions in GFF format. To generate the synteny evidences, use a service that provides tblastx.</s:description>
    <s:biomobywsdl>
      <s:mobyEndpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:mobyEndpoint>
      <s:serviceName>runSGP2GFF</s:serviceName>
      <s:authorityName>genome.imim.es</s:authorityName>
      <s:Parameter s:name="profile">Human Vs Mouse</s:Parameter>
    </s:biomobywsdl>
  </s:processor>
  <s:processor name="runGFF2JPEG">
    <s:description>Runs gff2ps software to vizualize a set of GFF annotations maps. It returns an encoded image in JPEG format.</s:description>
    <s:biomobywsdl>
      <s:mobyEndpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:mobyEndpoint>
      <s:serviceName>runGFF2JPEG</s:serviceName>
      <s:authorityName>genome.imim.es</s:authorityName>
    </s:biomobywsdl>
  </s:processor>
  <s:processor name="fromGenericSequenceCollectionToFASTA">
    <s:description>Converts a collection of generic sequences into FASTA sequences</s:description>
    <s:biomobywsdl>
      <s:mobyEndpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:mobyEndpoint>
      <s:serviceName>fromGenericSequenceCollectionToFASTA</s:serviceName>
      <s:authorityName>genome.imim.es</s:authorityName>
    </s:biomobywsdl>
  </s:processor>
  <s:processor name="fromFASTAToDNASequence_1">
    <s:description>Converts a DNA FASTA sequence into a DNA sequence</s:description>
    <s:biomobywsdl>
      <s:mobyEndpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:mobyEndpoint>
      <s:serviceName>fromFASTAToDNASequence</s:serviceName>
      <s:authorityName>genome.imim.es</s:authorityName>
    </s:biomobywsdl>
  </s:processor>
  <s:processor name="runWUTBlastx_2Seqs">
    <s:description>It compares the six-frame translations of a nucleotide query sequence against the six-frame translations of a nucleotide sequence (used as a database) using the Washington University BLAST algorithm.</s:description>
    <s:biomobywsdl>
      <s:mobyEndpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:mobyEndpoint>
      <s:serviceName>runWUTBlastx_2Seqs</s:serviceName>
      <s:authorityName>inb.bsc.es</s:authorityName>
      <s:Parameter s:name="nogaps">off</s:Parameter>
      <s:Parameter s:name="gap_open">9</s:Parameter>
      <s:Parameter s:name="filter">none</s:Parameter>
      <s:Parameter s:name="statistics">sump</s:Parameter>
      <s:Parameter s:name="word_size">3</s:Parameter>
      <s:Parameter s:name="alignments">15</s:Parameter>
      <s:Parameter s:name="matrix">blosum62</s:Parameter>
      <s:Parameter s:name="expected_threshold">10.0</s:Parameter>
      <s:Parameter s:name="scores">25</s:Parameter>
      <s:Parameter s:name="gap_extension">2</s:Parameter>
    </s:biomobywsdl>
  </s:processor>
  <s:processor name="translateGeneIDGFFPredictions">
    <s:description>Translates the GeneID gene predictions, given in GFF format, into a set of aminoacid sequences</s:description>
    <s:biomobywsdl>
      <s:mobyEndpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:mobyEndpoint>
      <s:serviceName>translateGeneIDGFFPredictions</s:serviceName>
      <s:authorityName>genome.imim.es</s:authorityName>
      <s:Parameter s:name="translation_table">Standard (1)</s:Parameter>
    </s:biomobywsdl>
  </s:processor>
  <s:processor name="Parse_Moby_Data_BLAST_Text">
    <s:description>Processor to parse the datatype BLAST-Text</s:description>
    <s:biomobyparser>
      <s:endpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:endpoint>
      <s:datatype>BLAST-Text</s:datatype>
      <s:articleName>wutblastx_report</s:articleName>
      <s:description>Processor to parse the datatype BLAST-Text</s:description>
    </s:biomobyparser>
  </s:processor>
  <s:processor name="Parse_Moby_Data_GFF">
    <s:description>Processor to parse the datatype GFF</s:description>
    <s:biomobyparser>
      <s:endpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:endpoint>
      <s:datatype>GFF</s:datatype>
      <s:articleName>geneid_predictions</s:articleName>
      <s:description>Processor to parse the datatype GFF</s:description>
    </s:biomobyparser>
  </s:processor>
  <s:processor name="Parse_Moby_Data_b64_encoded_jpeg">
    <s:description>Processor to parse the datatype b64_encoded_jpeg</s:description>
    <s:biomobyparser>
      <s:endpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:endpoint>
      <s:datatype>b64_encoded_jpeg</s:datatype>
      <s:articleName>image</s:articleName>
      <s:description>Processor to parse the datatype b64_encoded_jpeg</s:description>
    </s:biomobyparser>
  </s:processor>
  <s:processor name="String_1">
    <s:description>a string</s:description>
    <s:biomobyobject>
      <s:mobyEndpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:mobyEndpoint>
      <s:serviceName>String</s:serviceName>
      <s:authorityName />
    </s:biomobyobject>
  </s:processor>
  <s:processor name="String_2">
    <s:description>a string</s:description>
    <s:biomobyobject>
      <s:mobyEndpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:mobyEndpoint>
      <s:serviceName>String</s:serviceName>
      <s:authorityName />
    </s:biomobyobject>
  </s:processor>
  <s:processor name="FASTA_NA_1">
    <s:description>NA sequence in FASTA format</s:description>
    <s:biomobyobject>
      <s:mobyEndpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:mobyEndpoint>
      <s:serviceName>FASTA_NA</s:serviceName>
      <s:authorityName />
    </s:biomobyobject>
  </s:processor>
  <s:processor name="FASTA_NA_2">
    <s:description>NA sequence in FASTA format</s:description>
    <s:biomobyobject>
      <s:mobyEndpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:mobyEndpoint>
      <s:serviceName>FASTA_NA</s:serviceName>
      <s:authorityName />
    </s:biomobyobject>
  </s:processor>
  <s:processor name="Parse_Moby_Data_FASTA">
    <s:description>Processor to parse the datatype FASTA</s:description>
    <s:biomobyparser>
      <s:endpoint>http://moby.ucalgary.ca/moby/MOBY-Central.pl</s:endpoint>
      <s:datatype>FASTA</s:datatype>
      <s:articleName>sequences</s:articleName>
      <s:description>Processor to parse the datatype FASTA</s:description>
    </s:biomobyparser>
  </s:processor>
  <s:link source="fasta_sequence_2" sink="String_2:value" />
  <s:link source="Parse_Moby_Data_b64_encoded_jpeg:image_'content'" sink="Decode_base64_to_byte:base64" />
  <s:link source="StringArticleName:value" sink="String_1:article name" />
  <s:link source="fasta_sequence_1" sink="String_1:value" />
  <s:link source="StringArticleName:value" sink="String_2:article name" />
  <s:link source="String_1:mobyData" sink="FASTA_NA_1:String(content)" />
  <s:link source="String_2:mobyData" sink="FASTA_NA_2:String(content)" />
  <s:link source="identifier_1" sink="FASTA_NA_1:id" />
  <s:link source="identifier_2" sink="FASTA_NA_2:id" />
  <s:link source="namespace" sink="FASTA_NA_1:namespace" />
  <s:link source="namespace" sink="FASTA_NA_2:namespace" />
  <s:link source="FASTA_NA_1:mobyData" sink="fromFASTAToDNASequence_1:FASTA_NA(sequence)" />
  <s:link source="FASTA_NA_2:mobyData" sink="fromFASTAToDNASequence_2:FASTA_NA(sequence)" />
  <s:link source="fromFASTAToDNASequence_1:DNASequence(sequence)" sink="runSGP2GFF:DNASequence(sequence)" />
  <s:link source="fromFASTAToDNASequence_1:DNASequence(sequence)" sink="runWUTBlastx_2Seqs:NucleotideSequence(sequence)" />
  <s:link source="fromFASTAToDNASequence_1:DNASequence(sequence)" sink="translateGeneIDGFFPredictions:DNASequence(sequence)" />
  <s:link source="fromFASTAToDNASequence_2:DNASequence(sequence)" sink="runWUTBlastx_2Seqs:NucleotideSequence(database)" />
  <s:link source="runGFF2JPEG:b64_encoded_jpeg(image)" sink="Parse_Moby_Data_b64_encoded_jpeg:mobyData('b64_encoded_jpeg')" />
  <s:link source="runGFF2JPEG:b64_encoded_jpeg(image)" sink="Parse_Moby_Data_b64_encoded_jpeg:mobyData('b64_encoded_jpeg')" />
  <s:link source="runSGP2GFF:GFF(geneid_predictions)" sink="runGFF2JPEG:GFF(Collection - 'maps')" />
  <s:link source="runSGP2GFF:GFF(geneid_predictions)" sink="translateGeneIDGFFPredictions:GFF(geneid_predictions)" />
  <s:link source="Decode_base64_to_byte:bytes" sink="gff_map" />
  <s:link source="Parse_Moby_Data_FASTA:sequences_'content'" sink="peptide_sequences" />
  <s:link source="fromGenericSequenceCollectionToFASTA:FASTA(sequences)" sink="Parse_Moby_Data_FASTA:mobyData('FASTA')" />
  <s:link source="runSGP2GFF:GFF(geneid_predictions)" sink="Parse_Moby_Data_GFF:mobyData('GFF')" />
  <s:link source="runWUTBlastx_2Seqs:BLAST-Text(wutblastx_report)" sink="Parse_Moby_Data_BLAST_Text:mobyData('BLAST-Text')" />
  <s:link source="runWUTBlastx_2Seqs:BLAST-Text(wutblastx_report)" sink="runSGP2GFF:BLAST-Text(tblastx_report)" />
  <s:link source="Parse_Moby_Data_BLAST_Text:wutblastx_report_'content'" sink="tblastx_report" />
  <s:link source="Parse_Moby_Data_GFF:geneid_predictions_'content'" sink="geneid_gff" />
  <s:link source="translateGeneIDGFFPredictions:AminoAcidSequence(Collection - 'peptides')" sink="fromGenericSequenceCollectionToFASTA:GenericSequence(Collection - 'sequences')" />
  <s:source name="namespace" />
  <s:source name="fasta_sequence_1" />
  <s:source name="identifier_1" />
  <s:source name="fasta_sequence_2" />
  <s:source name="identifier_2" />
  <s:sink name="geneid_gff" />
  <s:sink name="tblastx_report" />
  <s:sink name="gff_map">
    <s:metadata>
      <s:mimeTypes>
        <s:mimeType>image/*</s:mimeType>
      </s:mimeTypes>
    </s:metadata>
  </s:sink>
  <s:sink name="peptide_sequences">
    <s:metadata>
      <s:mimeTypes>
        <s:mimeType>text/xml</s:mimeType>
      </s:mimeTypes>
    </s:metadata>
  </s:sink>
</s:scufl>

