<!-- BlastLikeDataSetCollection DTD - attempts to provide a           
     unified model for the output from the following pieces of        
     bioinformatics sequence similarity search sofware:               
                o BLAST                (NCBI)                         
                o WU-BLAST             (Washington University)        
                o HMMER                (Washington University)        
                o DBA                  (Sanger Center)                
                                                                      
     NB This DTD covers output from the above software, when run      
     in modes such that the detailed output is based around           
     pairwise alignments.          

     This is as opposed to other output formats such as ASN.1

     The root element is a BlastLikeDataSetCollection.  This is
     described towards the end of the DTD.
     ================================================================ 
     This DTD is Copyright 1999, 2000, 2001 Cambridge Antibody Technology   
     Group plc (CAT). All Rights Reserved.                            
                                                                      
     Version 1.02

     Author List:                                                     
       Primary Author: Simon Brocklehurst (CAT)                       
       Other Authors:  Colin H. Hardman   (CAT)                       
                       Stuart Johnson     (CAT)                       
                       Tim Dilks          (CAT)                       
                       Keith James        (Sanger Center)
     ================================================================ -->

<!-- PARAMETER ENTITY DECLARATIONS 
     ============================= -->

<!ENTITY % strandType    "(plus|minus)">

<!ENTITY % frameNumber   "(minus3|minus2|minus1|plus1|plus2|plus3)">

<!ENTITY % alignmentType "(internal|end)">

<!ENTITY % sequenceType  "(dna|rna|protein|profile)">

<!ENTITY % querySequenceType   "querySequenceType %sequenceType; ">
<!ENTITY % hitSequenceType     "hitSequenceType   %sequenceType; ">

<!ENTITY % queryStrand   "queryStrand %strandType;">
<!ENTITY % hitStrand     "hitStrand   %strandType;">

<!ENTITY % queryFrame    "queryFrame  %frameNumber;">
<!ENTITY % hitFrame      "hitFrame    %frameNumber;">

<!-- HMMER sequence and model alignment types - i.e. local or global      -->

<!ENTITY % startPositionOfSequence "startPositionOfSequence %alignmentType; ">
<!ENTITY % endPositionOfSequence   "endPositionOfSequence   %alignmentType; ">
<!ENTITY % startPositionOfModel    "startPositionOfModel    %alignmentType; ">
<!ENTITY % endPositionOfModel      "endPositionOfModel      %alignmentType; ">

<!-- ELEMENT DECLARATIONS
     ==================== -->

<!-- ================================================================ -->
<!-- Elements used in more than one section of the data set.          -->
<!-- For example, in both Summary and Detail sections                 -->

<!ELEMENT biojava:HitDescription (#PCDATA)>
<!ELEMENT biojava:HitId EMPTY>
<!ATTLIST biojava:HitId
                     id                  CDATA #REQUIRED
                     metaData            CDATA #REQUIRED >

<!-- The RawOutput element is used to represent sections of the
     output from programs "as is".  This enables information from
     software to be represented, without being parsed in detail.
                                                                      -->
<!ELEMENT biojava:RawOutput (#PCDATA)>
<!ATTLIST biojava:RawOutput
                     xml:space       (default|preserve) #IMPLIED >

<!-- ================================================================ -->
<!-- Header section related information                               -->


<!ELEMENT biojava:QueryId EMPTY>
<!ATTLIST biojava:QueryId
                    id             CDATA #REQUIRED 
                    metaData       CDATA #REQUIRED >

<!ELEMENT biojava:DatabaseId EMPTY>
<!ATTLIST biojava:DatabaseId
                    id             CDATA #REQUIRED 
                    metaData       CDATA #REQUIRED >

<!ELEMENT biojava:Header (biojava:RawOutput, QueryId?, DatabaseId? )>

<!-- ================================================================ -->
<!-- Summary section related information                              -->

<!ELEMENT biojava:HitSummary (biojava:HitId, biojava:QueryId?,
                              biojava:HitDescription?)>
<!ATTLIST biojava:HitSummary
                score                    CDATA #REQUIRED
                expectValue              CDATA #IMPLIED
                numberOfHSPs             CDATA #IMPLIED
                numberOfContributingHSPs CDATA #IMPLIED
                smallestSumProbability   CDATA #IMPLIED
                readingFrame             CDATA #IMPLIED 
                numberOfMatches          CDATA #IMPLIED >

<!-- DomainSummary and DomainHit elements are HMMER Specific -->

<!ELEMENT biojava:DomainHit EMPTY>
<!ATTLIST biojava:DomainHit
                modelId                  CDATA #REQUIRED
                domainPosition           CDATA #REQUIRED
                sequenceFrom             CDATA #REQUIRED
                sequenceTo               CDATA #REQUIRED
                hmmFrom                  CDATA #REQUIRED
                hmmTo                    CDATA #REQUIRED
                %startPositionOfSequence;      #IMPLIED
                %endPositionOfSequence;        #IMPLIED
                %startPositionOfModel;         #IMPLIED
                %endPositionOfModel;           #IMPLIED
                score                    CDATA #REQUIRED 
                expectValue              CDATA #REQUIRED >

<!ELEMENT biojava:DomainSummary (biojava:DomainHit*) >

<!-- End of DomainSummarySecion                                       -->

<!ELEMENT biojava:Summary (biojava:HitSummary*, biojava:DomainSummary?) >

<!-- ================================================================ -->
<!-- Mainly DetailSection related information                         -->

<!ELEMENT biojava:HSPSummary (biojava:RawOutput?)>
<!ATTLIST biojava:HSPSummary
                score               CDATA #REQUIRED
                bitScore            CDATA #IMPLIED
                expectValue         CDATA #REQUIRED
                numberOfIdentities  CDATA #REQUIRED
                alignmentSize       CDATA #REQUIRED
                percentageIdentity  CDATA #REQUIRED
                numberOfPositives   CDATA #IMPLIED
                percentagePositives CDATA #IMPLIED
                pValue              CDATA #IMPLIED
                sumPValues          CDATA #IMPLIED
                numberOfGaps        CDATA #IMPLIED
                %queryStrand;             #IMPLIED
                %hitStrand;               #IMPLIED
                %queryFrame;              #IMPLIED
                %hitFrame;                #IMPLIED 
                %querySequenceType;       #IMPLIED 
                %hitSequenceType;         #IMPLIED >

<!ELEMENT biojava:QuerySequence (#PCDATA)>
<!ATTLIST biojava:QuerySequence 
                startPosition       CDATA #REQUIRED
                stopPosition        CDATA #REQUIRED >


<!-- A MatchConsensus element represents the consensus information
     present in a pairwise alignment produced by Blast-like programs
     (i.e. the middle line of the alignment).                          -->

<!ELEMENT biojava:MatchConsensus (#PCDATA)>
<!ATTLIST biojava:MatchConsensus
                     xml:space       (default|preserve) #IMPLIED >


<!ELEMENT biojava:HitSequence (#PCDATA)>
<!ATTLIST biojava:HitSequence 
                startPosition       CDATA #REQUIRED
                stopPosition        CDATA #REQUIRED >

<!-- The BlastLikeAlignment elements represents information from the
     pairwise alignments produced by Blast-like programs. Rather than
     representing the alignment simply as preformatted raw text, it
     separates out the information into a QuerySequence, a HitSequence
     and a MatchConsensus.                                             -->

<!ELEMENT biojava:BlastLikeAlignment (biojava:QuerySequence,
                                      biojava:MatchConsensus,
                                      biojava:HitSequence) >

<!ELEMENT biojava:HSP (biojava:HSPSummary, biojava:BlastLikeAlignment)>

<!-- HSPCollections model related groups of HSPs. For example, this
     allows all plus strand HSPs to be grouped separated from all
     minus strand HSPs                                                 -->

<!ELEMENT biojava:HSPCollection (biojava:HSP+)>

<!ELEMENT biojava:Hit (biojava:HitId, biojava:QueryId?, 
                       biojava:HitDescription?,
                       biojava:HSPCollection+)>
<!ATTLIST biojava:Hit
                sequenceLength      CDATA #IMPLIED >

<!ELEMENT biojava:Detail (biojava:Hit*)>

<!-- ================================================================ -->
<!-- Mainly TailSection related information                           -->

<!ELEMENT biojava:Trailer (biojava:RawOutput)>

<!-- ================================================================ -->
<!-- Relating to overall results of searches                          -->

<!ELEMENT biojava:BlastLikeDataSet (biojava:Header,
                                    biojava:Summary?,
                                    biojava:Detail?,
                                    biojava:Trailer?)>
<!ATTLIST biojava:BlastLikeDataSet
                 program             CDATA #REQUIRED
                 version             CDATA #REQUIRED>

<!-- A BlastLikeDataSetCollection contains data from groups of results
     obtained from  bioinformatics software that produces Blast-like 
     output. For example, it can model the output from Blast run on 
     multiple sequences. Or it could be used to group together analyses
     on a single sequence obtained from multiple programs.             -->

<!ELEMENT biojava:BlastLikeDataSetCollection (biojava:BlastLikeDataSet+) >
<!ATTLIST biojava:BlastLikeDataSetCollection
                 xmlns               CDATA #FIXED ""
                 xmlns:biojava       CDATA #FIXED "http://www.biojava.org" >