<!--
###################################################################################################################### 

    tigrxml.dtd
    DTD for XML format presented by TIGR to release the genome annotation data
    to the scientific community.

    Brian Haas 02/13/2001

    This DTD continues to be under development.  The current formatting described will be retained in future versions of this DTD.  
    Future additions to the DTD will be made to extend the information content and will be specified below.

   -update (bhaas)
            -Revamped the CDNA_SUPPORT section to include ESTs as well as fl-cdnas, including the status of the incorporation and any associated comments.


    -update 01212003
            -ACCESSION attribute of SEQ_ELEMENT was changed from type NMTOKEN to CDATA to allow '|' in accession.


    -update 07202002 
             -PUB_LOCUS added as an optional element under MODEL; allows for the exact identification of alternative splicing isoforms of a single gene (TU).
	     -URL element added to gene to link to the gene report page.  This URL element has just have a single attribute URLNAME providing a token identifier and it provides the complete URL to a page associated with that token.


    -update 07/15/2002
            -CDNA_SUPPORT added as a sub-element to MODEL, indicating which complete cDNA supports the annotated CDS structure, hence the protein sequence.

    -update 05/29/2002 (bsuh)
            -MODEL_ATTRIBUTE element (new!) added to MODEL
            -ATTRIBUTE_TYPE element (new!) added to MODEL_ATTRIBUTE
            -added description of XML representation of MODEL_ATTRIBUTEs: SignalP and TMHMM

    -update 04/30/2002 (bsuh)
            -FUNCT_ANNOT_EVIDENCE element added to GENE_INFO
            -TYPE attribute added to FUNCT_ANNOT_EVIDENCE
            -ASSIGN_TYPE attribute removed from ASSIGN_ACC

    -update 04/28/2002 (bsuh)
             -MODEL_EVIDENCE element added to MODEL
             -COMMENT element (from ident.comment) added to GENE_INFO
             -ASSIGN_METHOD attribute added to ASSIGN_ACC
             -Various small changes to DTD syntax

    -update 12/19/2001
             -PUB_LOCUS element added to the RNA genes. (optional).
	     -ROLE_INFO becomes deprecated due to Gene Ontology.  
	     -GENE_ONTOLOGY added to GENE_INFO.

    -update 08/09/2001
             -ALT_LOCUS added under GENE_INFO to identify alternate bac-based identifiers for a gene.
	     -FROM_OVERLAP_TYPE and TO_OVERLAP_TYPE added under TILING_PATH to describe the quality of the overlaps between adjacent assemblies in the tiling path.
	     -SEQ_LAST_TOUCHED added as an element under HEADER to identify the date in which the assembly sequence was last manipulated.  

    -update 06/11/2001 (began tracking updates).
             -CLONE_NAME added as an attribute of ASMBL_ID, LEFT_ASMBL, RIGHT_ASMBL.  It preexists as an element under HEADER, and that will remain.
	     -GENE_SYNONYM and CHROMO_LINK added as an element under TU and MODEL.
	     -TRANSCRIPT_SEQUENCE (as well as CDS_SEQUENCE and PROTEIN_SEQUENCE) are optional.


######################################################################################################################
-->


<!-- 
   Root element for XML is TIGR.  TIGR contains at least one ASSEMBLY element.
-->

<!ELEMENT TIGR (PSEUDOCHROMOSOME | ASSEMBLY)* >

<!ELEMENT PSEUDOCHROMOSOME (SCAFFOLD, ASSEMBLY) >

<!--
   The ASSEMBLY element is the parent element referring to an individual nucleotide assembly.
   Often, the nucleotide assembly represents a single BAC (bacterial artificial chromosome) sequence.
   This element houses the annotation for the sequence unit.

   The unique index to the TIGR annotation database is the ASMBL_ID.
   CLONE_ID is for TIGR's tracking purposes only.
   DATABASE references the TIGR annotation database name.  ie. ATH1:Arabidopsis, OSA1:Rice.
   CURRENT_DATE : the date the xml was created.
   COORDSET: represents the coordinates for which information is provided for the assembly.  If the
   entire assembly is described, then the coordset will be from position 1 to the length of the assembly.

-->

<!ELEMENT ASSEMBLY ( ASMBL_ID, COORDSET, HEADER, TILING_PATH?, GENE_LIST, MISC_INFO?, REPEAT_LIST?, ASSEMBLY_SEQUENCE ) >


<!ATTLIST ASSEMBLY CLONE_ID        NMTOKEN    #REQUIRED >
<!ATTLIST ASSEMBLY DATABASE        NMTOKEN    #REQUIRED >
<!ATTLIST ASSEMBLY CHROMOSOME      NMTOKEN    #IMPLIED  >
<!ATTLIST ASSEMBLY CURRENT_DATE    CDATA      #REQUIRED >

<!ELEMENT ASMBL_ID (#PCDATA) >
<!ATTLIST ASMBL_ID  CLONE_NAME     CDATA  #IMPLIED>


<!--
   GENE_LIST contains all gene features broken down into two parent nodes: the protein coding
   genes and the RNA genes.
-->

<!ELEMENT GENE_LIST (PROTEIN_CODING, RNA_GENES)>


<!--
    Element RNA_GENES contains each of the non-protein coding genes that TIGR may provide annotation for.
    These include tRNAs (see PRE-TRNA), small nuclear RNAs (see SNRNA), small nucleolar RNAs (see SNORNA), 
    and ribosomal RNAs (see RRNA).
--> 

<!ELEMENT RNA_GENES (PRE-TRNA*, SNRNA*, SNORNA*, RRNA*) >


<!-- 
    FEAT_NAME represents a temporary identifier assigned to each gene component.  The only stable reference
    to a gene is the LOCUS or PUB_LOCUS (see GENE_INFO).
-->

<!ELEMENT FEAT_NAME (#PCDATA) >


<!--
    DATE represents the date in which a feature was created or modified.  This element is useful for synchronization
    of the annotation data with external databases.
-->

<!ELEMENT DATE (#PCDATA) >


<!--
    PROTEIN_CODING genes are represented by at least four components: TU, MODEL, EXON, CDS. 
    The TU represents the transcriptional unit and is the highest order component of the gene.
    A TU can encode multiple gene MODELs only in cases where alternative splicing exists.
    A gene MODEL encapsulates all of the coding and non-coding structures of an individual splicing isoform.
    Each gene MODEL can encode several mRNA EXONS and represent the spliced, intronless portions of the gene.
    An mRNA EXON may only partially code for a protein; exactly the case where upstream or downstream untranslated
    regions exist.  The protein coding portion of an individual EXON is represented by the CDS element.  The CDS element
    will also encode the stop codon.  The gene components are not ordered based on their coordinates.
    For regions in which untranslated regions exist, UTR(s) will present.  UTR(s) represent the non-protein-coding portions
    of the RNA EXON(s).  UTRs are not currently supported TIGR data types outside of this DTD and they exist here only
    to facilitate external data analysis.

    Each gene component has a coordinate set associated with it (see COORDS).  The following illustration should clarify
    the role of each element and its coordinates:

    TU        {=============================================================================}
              |                                                                             |
    MODEL     |       {============================================================}        |
              |       |                                                            |        |
    EXON(s)   {=============}        {========================}    {========================}
              |      ||              |                        |    |               ||       |
    CDS(s)    |      |{=====}        {========================}    {===============}|       |
              |      |                                                              |       |
    UTR(s)    {======}                                                              {=======}

-->
    

<!ELEMENT PROTEIN_CODING (TU*) >

<!ELEMENT TU (FEAT_NAME, GENE_SYNONYM*, CHROMO_LINK*, DATE, GENE_INFO, COORDSET, MODEL+, TRANSCRIPT_SEQUENCE?, GENE_EVIDENCE?, URL*) >

<!ELEMENT MODEL (FEAT_NAME, PUB_LOCUS?, CDNA_SUPPORT?, GENE_SYNONYM*, CHROMO_LINK*, DATE, COORDSET, MODEL_ATTRIBUTE?, MODEL_EVIDENCE?, EXON+, CDS_SEQUENCE?, PROTEIN_SEQUENCE?) >
<!ATTLIST MODEL CURATED          NMTOKEN    #IMPLIED >  <!-- flag indicates a TIGR curator has approved the gene structure, or supported by a full-length cDNA  -->
<!ATTLIST MODEL COMMENT          CDATA      #IMPLIED >


<!ELEMENT EXON (FEAT_NAME, DATE, COORDSET, CDS?, UTRS?) >

<!ELEMENT CDS  (FEAT_NAME, DATE, COORDSET) >

<!--
     MODEL_ATTRIBUTE provides annotation info regarding the "attributes" of a model.
     Some sample attributes are Molecular Weight, PI, Cellular Localization, Transmembrane Domains, etc.
     Listed below are the specifics/examples for some important attributes...

     *) Transmembrane domains
          <ATTRIBUTE_TYPE METHOD="TMHMM2.0">	                    (Prediction via TMHMM version 2.0)
               <ATT_SCORE DESC="count">2</ATT_SCORE>                (Number of predicted helices, in this case 2)
               <ATT_SCORE DESC="coords">182:201,265:287</ATT_SCORE> (Coordinates of predicted helices, in this case 182-201 and 265-287)
          </ATTRIBUTE_TYPE>

     *) Signal Peptide (3 cases with different ATT_SCORE tags)
          <ATTRIBUTE_TYPE METHOD="signalP&#x2D;2.0 HMM">                        (Prediction via SignalP HMM ver 2.0)
               <ATT_SCORE DESC="HMM&#x2D;prediction">Signal peptide</ATT_SCORE> (Prediction = Signal peptide)
               <ATT_SCORE DESC="HMM&#x2D;position">20</ATT_SCORE>               (Predicted cleavage site)
               <ATT_SCORE DESC="HMM&#x2D;SPprob">0.874</ATT_SCORE>              (Signal peptide probability)
          </ATTRIBUTE_TYPE>

          <ATTRIBUTE_TYPE METHOD="signalP&#x2D;2.0 HMM">                                    (Prediction via SignalP HMM ver 2.0)
               <ATT_SCORE DESC="HMM&#x2D;prediction">Non&#x2D;secretory protein</ATT_SCORE> (Prediction = Non-secretory protein)
          </ATTRIBUTE_TYPE>

          <ATTRIBUTE_TYPE METHOD="signalP&#x2D;2.0 HMM">                       (Prediction via SignalP HMM ver 2.0)
               <ATT_SCORE DESC="HMM&#x2D;prediction">Signal anchor</ATT_SCORE> (Prediction = Signal anchor)
               <ATT_SCORE DESC="HMM&#x2D;SAprob">0.768</ATT_SCORE>             (Signal anchor probability)
          </ATTRIBUTE_TYPE>
     
-->

<!ELEMENT MODEL_ATTRIBUTE (ATTRIBUTE_TYPE*)>
<!ELEMENT ATTRIBUTE_TYPE (ATT_SCORE*)>
<!ATTLIST ATTRIBUTE_TYPE METHOD CDATA #REQUIRED>

<!ELEMENT ATT_SCORE (#PCDATA)>
<!ATTLIST ATT_SCORE DESC CDATA #REQUIRED>


<!-- CDNA_SUPPORT provides the accessions (mostly gi-numbers) of complete cDNAs which support the annotated 
     CDS structure for the gene model, and hence the annotated protein sequence.
-->

<!ELEMENT CDNA_SUPPORT (ACCESSION+) >
<!ELEMENT ACCESSION (#PCDATA)> <!-- pcdata now holds comments -->
<!ATTLIST ACCESSION DBXREF CDATA #IMPLIED> <!-- contains genbank accession for fl-cdna or est -->
<!ATTLIST ACCESSION IS_FLI NMTOKEN #IMPLIED> <!-- flag 1=full-length, 0=not full-length (ie. est) -->
<!ATTLIST ACCESSION UNIQUE_TO_ISOFORM NMTOKEN #IMPLIED> <!-- flag 1=unique, 0=shared between isoforms  -->
<!ATTLIST ACCESSION ANNOT_INCORP NMTOKEN #IMPLIED> <!-- flag 1=incorporated into gene model verified, 0=incorporation not verified  -->


<!-- 
     GENE_EVIDENCE provides all annotation data that may support the gene structure for the corresponding transcriptional unit (TU) 
-->


<!ELEMENT GENE_EVIDENCE (EVIDENCE_TYPE)>

<!ELEMENT MODEL_EVIDENCE (EVIDENCE_TYPE)>

<!ELEMENT EVIDENCE_TYPE (SEQUENCE_DB_MATCH*,  COMPUT_PREDICTION*)>

<!ELEMENT SEQUENCE_DB_MATCH (SEARCH_DB*)>

<!ELEMENT SEARCH_DB (SEQ_ELEMENT*)>
<!ATTLIST SEARCH_DB  DB_NAME CDATA  #REQUIRED>
<!ATTLIST SEARCH_DB  DB_TYPE CDATA  #REQUIRED>

<!ELEMENT COMPUT_PREDICTION (PREDICTION_SET*)>

<!ELEMENT PREDICTION_SET (SEQ_ELEMENT*) >
<!ATTLIST PREDICTION_SET PREDICTION_TOOL CDATA #REQUIRED>
<!ATTLIST PREDICTION_SET PREDICTION_TYPE CDATA #REQUIRED>

<!-- 
     SEQ_ELEMENT(s) represent features that provide evidence for the existing annotation and can include gene predictions,
     splice site predictions, or database matches.  Each match segment or predicted exon is considered an individual
     sequence element and has a pair of coordinates referential to the parent nucleotide assembly (ASMBL_COORDS)
     or to the element itself (MATCH_COORDS).
-->
     

<!ELEMENT SEQ_ELEMENT (ASMBL_COORDS?, MATCH_COORDS?, RELATIVE_COORDS?)>
<!ATTLIST SEQ_ELEMENT  FEAT_TYPE      NMTOKEN    #REQUIRED>
<!ATTLIST SEQ_ELEMENT  METHOD         CDATA      #IMPLIED>
<!ATTLIST SEQ_ELEMENT  ACCESSION      CDATA      #IMPLIED>
<!ATTLIST SEQ_ELEMENT  DESCRIPTION    CDATA      #IMPLIED>
<!ATTLIST SEQ_ELEMENT  PER_ID         NMTOKEN    #IMPLIED>
<!ATTLIST SEQ_ELEMENT  SCORE          CDATA      #IMPLIED>
<!ATTLIST SEQ_ELEMENT  E_VALUE        NMTOKEN    #IMPLIED>
<!ATTLIST SEQ_ELEMENT  ELEMENT_NUM    NMTOKEN    #IMPLIED>


<!-- describe the coordinates within the ASSEMBLY (also the default behaviour for the COORDSET element)-->
<!ELEMENT ASMBL_COORDS (COORDSET)>


<!-- describe the coordinates within the search database sequence -->
<!ELEMENT MATCH_COORDS (COORDSET)>


<!-- describe the coordinates relative to the sequence being analysed; protein or nucleotide sequence of an annotated gene.-->
<!ELEMENT RELATIVE_COORDS (COORDSET)>


<!-- GENE_SYNONYM explained:
     Within the overlapping regions of bacs, a gene may exist  either compeletely or partially on both bacs, 
     and represent the single canonical gene only after a merging operation has taken place.  For the purpose 
     of generating a non-redundant gene set, all gene synonyms are merged with their sibling gene synonyms.  
-->

<!ELEMENT GENE_SYNONYM (#PCDATA) >


<!-- CHROMO_LINK explained:
     Pseudo-chromosomes are constructed based on the tiling path containing individual bacs.  The annotation along the
     bac sequences are propagated from the bac to the pseudochromosome.  The genes on the pseudo-chromosome are given
     new temporary feat_name identifiers that differ from the bac genes from which they were derived.  The CHROMO_LINK
     provides a link between the temporary feat_name of the pseudochromosome gene set to the feat_names of the genes
     along the bacs.
-->


<!ELEMENT CHROMO_LINK (#PCDATA) >


<!-- 
    UTRS specify each UTR or untranslated region.
    There can be more than one if it's a single exon gene: ie. 
              5'                                                  3'
     EXON:      {===============================================}
     CDS :      |   |{============================}|            |
     LEFT_UTR:  {===}                              |            |
     RIGHT_UTR:                                    {============}
            
     
     If no portion of the EXON is translated, then we have an EXTENDED_UTR, which
     is includes the full length of the EXON.


-->

<!ELEMENT UTRS (LEFT_UTR | RIGHT_UTR | EXTENDED_UTR)* >

<!ELEMENT LEFT_UTR (COORDSET) >

<!ELEMENT RIGHT_UTR (COORDSET) >

<!ELEMENT EXTENDED_UTR (COORDSET) >


<!-- 
    Gene Sequences Described:
    TRANSCRIPT_SEQUENCE: provides the unspliced genomic nucleotide sequence representing the entire transcribed
    region of the gene.
    CDS_SEQUENCE: The nucleotide sequence which encodes the protein sequence directly.
    PROTEIN_SEQUENCE: the peptide sequence representing the translation of the CDS_SEQUENCE.
-->

<!ELEMENT TRANSCRIPT_SEQUENCE (#PCDATA) >

<!ELEMENT CDS_SEQUENCE (#PCDATA) >

<!ELEMENT PROTEIN_SEQUENCE (#PCDATA) >


<!--
    COORDSET contains child elements END5 and END3 and provides the sequence-based (see ASSEMBLY_SEQUENCE) coordinates for all elements
    containing it. The sequence begins at position 1.  END5 and END3 represent the exact coordinates of the feature within the
    sequence provided (positive orientation).  If END5 < END3, then the positive strand orientation is specified; therefore, 
    if END5 > END3, the negative strand orientation is referenced.
    
-->

<!ELEMENT COORDSET (END5, END3) >

<!ELEMENT END5 (#PCDATA)>

<!ELEMENT END3 (#PCDATA)>


<!--
    GENE_INFO contains the gene name, locus, and functional category role assignment information.  The LOCUS in many
    instances represents the assembly (ie. BAC)-based gene identifier.  The PUB_LOCUS represents a publication-based
    locus; possibly representing a chromosomal locus identifier.  In overlapping regions of assembly tiling paths, the
    same gene may be represented on both overlapping assemblies with different LOCUS values but identical PUB_LOCUS values.
    In chromosome-based data sets, this gene in overlapping assemblies will be represented singly under the PUB_LOCUS identifier, 
    the LOCUS identifiers from the derived genes are presented in the LOCUS and ALT_LOCUS fields for the chromosomal gene.

    This is confusing, so here's an illustration:
	    
           (gene on BAC-1)                                                                                 Chromosome
	   pub_locus = At1g1                                                                              pub_locus = At1g1
           locus = A                                                                                      locus = A
           {====}                                                                                         alt_locus = B
    ________________________                                                                               {====}
           ______________________________         In the assembled chromosome sequence:       _________________________________
	   {====}
           (gene on BAC-2)
	   pub_locus = At1g1
	   locus = B


    EC_NUM provides an enzyme commission number.
    GENE_SYM provides the gene symbol conventionally given by experimentalists; ie. alcohol dehydrogenase: ADH
    COM_NAME represents the gene name. IS_PSEUDOGENE is a toggle to indicate whether or not the gene is a pseudogene{1=true|0=false}

-->

<!ELEMENT GENE_INFO (LOCUS, ALT_LOCUS?, PUB_LOCUS?, COM_NAME, COMMENT?, PUB_COMMENT?, EC_NUM?, GENE_SYM?, IS_PSEUDOGENE, FUNCT_ANNOT_EVIDENCE*, DATE, GENE_ONTOLOGY?, ROLE_LIST?) >

<!ELEMENT LOCUS (#PCDATA) >

<!ELEMENT PUB_LOCUS (#PCDATA) >

<!ELEMENT ALT_LOCUS (#PCDATA) >

<!ELEMENT COM_NAME (#PCDATA) >
<!ATTLIST COM_NAME CURATED NMTOKEN #IMPLIED> <!-- flag indicates a TIGR curator has approved the gene name -->

<!ELEMENT COMMENT (#PCDATA) >

<!ELEMENT PUB_COMMENT (#PCDATA) >

<!ELEMENT EC_NUM (#PCDATA) >

<!ELEMENT GENE_SYM (#PCDATA) >

<!ELEMENT IS_PSEUDOGENE (#PCDATA) >

<!--
       FUNCT_ANNOT_EVIDENCE describes the information from which the functional assignment (aka com_name) for a TU is based upon.
       Attribute TYPE indicates the type of assignment made: manually curated (CURATED) or automatically assigned (AUTO)

       Element ASSIGN_ACC cites the database accession used
           The format of the accession is: db:id_num:desc
               where db is the database id (GP = GenPept, EGAD = TIGR EGAD, etc)
               where id is the id number of the accession
               where desc is the description of the accession
       Attribute ASSIGN_METHOD indicates the method used. Some possibilities include BER, autoBYOB.
--> 

<!ELEMENT FUNCT_ANNOT_EVIDENCE (ASSIGN_ACC*) >
<!ATTLIST FUNCT_ANNOT_EVIDENCE  TYPE  NMTOKEN  #REQUIRED >

<!ELEMENT ASSIGN_ACC (#PCDATA) >
<!ATTLIST ASSIGN_ACC  ASSIGN_METHOD  NMTOKEN  #REQUIRED >

<!--
   ROLE_LIST contains each of the functional role category assignments for the gene.
   COMPARTMENT indicates the role assignment class being used; examples include microbial, plant, GO (gene ontology), etc.
   The roles are classifications that become more specific via the SUBROLE_* elements.
-->

<!ELEMENT ROLE_LIST (ROLE_INFO+) >  <!-- ROLE_INFO has been deprecated.  Gene Ontology assignments are now employed. -->

<!ELEMENT ROLE_INFO (COMPARTMENT, DATE, MAIN_ROLE,  SUBROLE_1?, SUBROLE_2?, SUBROLE_3?, SUBROLE_4?) >

<!ELEMENT COMPARTMENT (#PCDATA) >

<!ELEMENT MAIN_ROLE (#PCDATA) >

<!ELEMENT SUBROLE_1 (#PCDATA) >

<!ELEMENT SUBROLE_2 (#PCDATA) >

<!ELEMENT SUBROLE_3 (#PCDATA) >

<!ELEMENT SUBROLE_4 (#PCDATA) >


<!-- GENE_ONTOLOGY The controlled nomenclature for classifying genes.  Please visit http://www.geneontology.org
 
-->     
<!ELEMENT GENE_ONTOLOGY (GO_ID*)>

<!-- 
GO_ID is the identifier of a particular molecular function, biological process or cellular component that describes a gene product.

--> 
<!ELEMENT GO_ID (DATE, GO_TERM, GO_TYPE, GO_EVIDENCE*)>
<!ATTLIST GO_ID  ASSIGNMENT     CDATA  #REQUIRED>

<!ELEMENT GO_TERM (#PCDATA) > <!-- The term associated with the go_id -->
<!ELEMENT GO_TYPE (#PCDATA) > <!-- Process, Function, or Component -->


<!-- 
     GO_EVIDENCE is a reference (usually to a database entry) that supports the assignment of the GO ID. 
     EV_CODE is a three-letter code that represents the type of evidence being cited as supporting the assignment of the GO ID.
     WITH_EV is the entity with which the gene product interacts. 
--> 

<!ELEMENT GO_EVIDENCE (EV_CODE, EVIDENCE, WITH_EV?)>
<!ELEMENT EV_CODE  EMPTY>
<!ATTLIST EV_CODE CODE NMTOKEN #REQUIRED> 

<!ELEMENT EVIDENCE (#PCDATA) >
<!ELEMENT WITH_EV  (#PCDATA) >


<!--
    URL provides a complete URL to information about a topic specified in the XML document.
    The URLNAME attribute provides a simple token to establish the class of the URL.
-->

<!ELEMENT URL (#PCDATA) >
<!ATTLIST URL URLNAME NMTOKEN #REQUIRED>


<!--
    REPEAT_LIST contains REPEAT elements.  A repeat is a repetitive nucleotide sequence and could represent
    simple repeats (AT-rich regions) to complex repeats (retroelements, rRNA sequences).  Currently, rRNA
    sequences are being specified here.  Eventually, they will be specified in the RRNA element (see RRNA).
-->

<!ELEMENT REPEAT_LIST (REPEAT*) >

<!ELEMENT REPEAT (FEAT_NAME, DATE, COORDSET, REPEAT_TYPE) >

<!ELEMENT REPEAT_TYPE (#PCDATA) >


<!--
   RRNA encompasses ribosomal RNA genes.
-->

<!ELEMENT RRNA (PUB_LOCUS?, FEAT_NAME, DATE, COORDSET, COM_NAME) >


<!--
   SNRNA encompasses small nuclear RNA genes.
-->

<!ELEMENT SNRNA (PUB_LOCUS?, FEAT_NAME, DATE, COORDSET, COM_NAME) >


<!--
    SNORNA encompasses small nucleolar RNA genes.
-->

<!ELEMENT SNORNA (PUB_LOCUS?, FEAT_NAME, DATE, COORDSET, COM_NAME) >


<!--
    TRNA genes are represented by multiple components.  The structure is analogous to that 
    provided for protein coding genes (see PROTEIN_CODING).  The major difference is the lack
    of a CDS, since no protein is encoded by tRNA genes.
    The analogies are presented as follows:
        PRE-TRNA ~ TU
	TRNA ~ MODEL
	RNA-EXON ~ EXON

-->

<!ELEMENT PRE-TRNA (PUB_LOCUS?, FEAT_NAME, DATE, COORDSET, TRNA) >

<!ELEMENT TRNA (FEAT_NAME, DATE, COORDSET, COM_NAME, RNA-EXON+) >
<!ATTLIST TRNA ANTICODON         NMTOKEN    #REQUIRED >


<!ELEMENT RNA-EXON (FEAT_NAME, DATE, COORDSET)>


<!--
    TILING_PATH provides all of the information required to position the current ASSEMBLY in the 
    context of it's neighboring ASSEMBLY(s).  Each element and attribute is described as follows:
    ORIENTATION : [+|-] the strand orientation in the pseudo-chromosome.
    LEFT_ASMBL : identifies the ASMBL_ID (see ASSEMBLY) of the preceding neighbor in the tiling path.
    RIGHT_ASMBL : identifies the ASMBL_ID of the succeeding neighbor in the tiling path.
    FROM_CONNECT : [1|0] toggle which identifies if there is a sequence joining between the preceding sequence and current sequence.
    TO_CONNECT : [1|0] toggle ... analogous to FROM_CONNECT except that it refers to the joining of the current assemlby and the succeeding one.
    FROM_OVERLAP_SIZE : indicates the number of nucleotides that the current bac overlaps with the preceding bac.
    FROM_OVERHANG_SIZE : indicates the sequence length of non-overlapping sequence of the current sequence with the preceding sequence.
    TO_OVERHANG_SIZE : indicates the length of non-overlapping sequence of the current bac with the preceding bac.
    FROM_OVERLAP_TYPE and TO_OVERLAP_TYPE : describes the quality of the overlap between the adjacent assemblies.


    Interpretation of this data:  The data presented above is essentialy a single node in a linked list.  To build the 
    pseudo-chromosome, the first step is to identify the head-asmbl_id which should have a FROM_OVERLAP = 0.  From that 
    element, you can identify the TO_ASMBL that overlaps it.
    Once an overlapping assembly is identified, prior to doing anything else, you must flip the assembly to the proper orientation (+).
    Then, you can align the assembly to the previous one via the overlap information.

    Here's an illustration:
                                           ASMBL_ID 23

                               \__________________________________/
		    ___________________
		                       \
		         ASMBL_ID 1
  

               properties of ASMBL_ID 1 (ORIENTATION = '+', FROM_CONNECT = 0, TO_CONNECT = 1, RIGHT_ASMBL = 23, TO_OVERHANG_SIZE = 50).
	       properties of ASMBL_ID 23 (ORIENTATION = '+', FROM_CONNECT = 1, FROM_OVERHANG_SIZE = 120, FROM_OVERLAP_SIZE = 1000, TO_OVERHANG_SIZE = 140)

	       The FROM_OVERHANG_SIZE indicates the (\) portion of ASMBL_ID 23 in which non-overlapping sequence exists (ie. untrimmed vector).
	       The FROM_OVERLAP_SIZE indicates that 1000 nt's overlap ASMBL_ID 1.  Summing up both pieces of information for ASMBL_ID 23, coordinates 1 to 120
	       do not overlap, coordinates 121 to 1121 do overlap ASMBL_ID 1.
	       If size N = length (ASMBL_ID 1), then ASMBL_ID 23 overlaps ASMBL_ID 1 between (N-50-1000) to (N-50), taking into account 
	       the non-overlapping sequence of ASMBL_ID 1.

	       If either assembly was in the reverse orientation (ORIENTATION = '-'), then the first step would be to reverse complement the sequence.  The
	       remainder of the protocol remains identical.

	       MOST OF THE TIME, the non-overlapping end sequences OVERHANG_SIZE(s) will be = 0 because the assemblies should be trimmed of vector prior 
	       to entering either genbank or TIGR's annotation database.  Although, there may be some exceptions, and this specification prepares for it.

-->


<!ELEMENT TILING_PATH (LEFT_ASMBL, RIGHT_ASMBL, FROM_CONNECT, TO_CONNECT, ORIENTATION, FROM_OVERLAP_SIZE, FROM_OVERHANG_SIZE, TO_OVERHANG_SIZE, FROM_OVERLAP_TYPE, TO_OVERLAP_TYPE, DATE) >


<!ELEMENT LEFT_ASMBL (#PCDATA) >
<!ATTLIST LEFT_ASMBL CLONE_NAME     CDATA  #IMPLIED>

<!ELEMENT RIGHT_ASMBL (#PCDATA) >
<!ATTLIST RIGHT_ASMBL CLONE_NAME    CDATA  #IMPLIED>

<!ELEMENT FROM_CONNECT (#PCDATA)>

<!ELEMENT ORIENTATION (#PCDATA) >

<!ELEMENT TO_CONNECT (#PCDATA) >

<!ELEMENT FROM_OVERLAP_SIZE (#PCDATA) >

<!ELEMENT FROM_OVERHANG_SIZE (#PCDATA) >

<!ELEMENT TO_OVERHANG_SIZE (#PCDATA) >

<!ELEMENT FROM_OVERLAP_TYPE (#PCDATA) >

<!ELEMENT TO_OVERLAP_TYPE (#PCDATA) >


<!--
    SCAFFOLD is composed of SCAFFOLD_COMPONENT(s).  Each SCAFFOLD_COMPONENT indicates the portion of a given nucleotide 
    assembly (ie. BAC) from which a segment of the pseudochromosome was constructed.  By joining each of the SCAFFOLD_COMPONENT(s),
    the entire pseudo-chromosome nucleotide sequence can be constructed.

-->


<!ELEMENT SCAFFOLD (SCAFFOLD_COMPONENT*) >

<!ELEMENT SCAFFOLD_COMPONENT (ASMBL_ID, CHR_LEFT_COORD, CHR_RIGHT_COORD, ASMBL_LEFT_COORD, ASMBL_RIGHT_COORD, ORIENTATION, DATE) >

<!ELEMENT CHR_LEFT_COORD (#PCDATA) >

<!ELEMENT CHR_RIGHT_COORD (#PCDATA) >

<!ELEMENT ASMBL_LEFT_COORD (#PCDATA) >

<!ELEMENT ASMBL_RIGHT_COORD (#PCDATA) >


<!-- 

   MISC_INFO is the component in which we can store any comments regarding the ASSEMBLY.  The FEATURE_DESC element
   contains the feature description text, and a COORDSET element identifies the position the comment is referring to.
-->

<!ELEMENT MISC_INFO ( MISC_FEATURE+ ) >

<!ELEMENT MISC_FEATURE (COORDSET, DATE, FEATURE_DESC) >

<!ELEMENT FEATURE_DESC (#PCDATA) >


<!--
    The HEADER element contains some basic attributes of the nucleotide assembly, including the identity of the
    organism from which it was derived, the lineage, the group that sequenced the assembly, and information that is
    provided to genbank within TIGR's annotation submissions.
    The SEQ_LAST_TOUCHED field contains the date in which this sequence was last manipulated, which may or may not 
    include actual sequence changes.

-->

<!ELEMENT HEADER ( CLONE_NAME, SEQ_LAST_TOUCHED, GB_ACCESSION, ORGANISM, LINEAGE, SEQ_GROUP, KEYWORDS*, GB_DESCRIPTION*, GB_COMMENT*, AUTHOR_LIST ) >

<!ELEMENT CLONE_NAME (#PCDATA) >

<!ELEMENT SEQ_LAST_TOUCHED (DATE) >

<!ELEMENT GB_ACCESSION (#PCDATA) >

<!ELEMENT ORGANISM (#PCDATA) >

<!ELEMENT LINEAGE (#PCDATA) >

<!ELEMENT SEQ_GROUP (#PCDATA)>

<!ELEMENT KEYWORDS (#PCDATA) >

<!ELEMENT GB_DESCRIPTION (#PCDATA) >

<!ELEMENT GB_COMMENT (#PCDATA) >

<!ELEMENT AUTHOR_LIST ( AUTHOR*) >
<!ATTLIST AUTHOR_LIST CONTACT      CDATA    #IMPLIED >

<!ELEMENT AUTHOR EMPTY>
<!ATTLIST AUTHOR FNAME      CDATA      #IMPLIED >
<!ATTLIST AUTHOR LNAME      CDATA      #REQUIRED >
<!ATTLIST AUTHOR MNAME      CDATA      #IMPLIED >
<!ATTLIST AUTHOR SUFFIX     CDATA      #IMPLIED >


<!-- 
    ASSEMBLY_SEQUENCE contains the entire nucleotide sequence of the ASSEMBLY.  The sequence begins at position 1 in our coordinate space and is
    assumed to exist in the positive strand orientation.  No whitespace should interrupt the sequence; it should exist
    as one loooooooong string.
-->

<!ELEMENT ASSEMBLY_SEQUENCE (#PCDATA) >


<!-- Added ATTLIST for TIGR ID'ed XML -->

<!ATTLIST TIGR xmlns:xlink CDATA #IMPLIED>
<!ATTLIST TIGR xmlns CDATA #IMPLIED>

<!ATTLIST TU id CDATA #IMPLIED>

<!-- Added ATTLIST for TIGR skeleton XML -->

<!ATTLIST TIGR xmlns:xlink CDATA #IMPLIED>
<!ATTLIST TIGR xmlns:tigr CDATA #IMPLIED>
<!ATTLIST TIGR xmlns CDATA #IMPLIED>

<!ATTLIST TU xlink:type CDATA #IMPLIED>
<!ATTLIST TU xlink:show CDATA #IMPLIED>
<!ATTLIST TU xlink:href CDATA #IMPLIED>
<!ATTLIST TU xlink:role CDATA #IMPLIED>

<!ATTLIST MISC_INFO xlink:type CDATA #IMPLIED>
<!ATTLIST MISC_INFO xlink:show CDATA #IMPLIED>
<!ATTLIST MISC_INFO xlink:href CDATA #IMPLIED>
<!ATTLIST MISC_INFO xlink:role CDATA #IMPLIED>

<!ATTLIST ASSEMBLY_SEQUENCE xlink:type CDATA #IMPLIED>
<!ATTLIST ASSEMBLY_SEQUENCE xlink:show CDATA #IMPLIED>
<!ATTLIST ASSEMBLY_SEQUENCE xlink:href CDATA #IMPLIED>
<!ATTLIST ASSEMBLY_SEQUENCE xlink:role CDATA #IMPLIED>

<!ATTLIST TILING_PATH xlink:type CDATA #IMPLIED>
<!ATTLIST TILING_PATH xlink:show CDATA #IMPLIED>
<!ATTLIST TILING_PATH xlink:href CDATA #IMPLIED>
<!ATTLIST TILING_PATH xlink:role CDATA #IMPLIED>

<!ATTLIST RNA_GENES xlink:type CDATA #IMPLIED>
<!ATTLIST RNA_GENES xlink:show CDATA #IMPLIED>
<!ATTLIST RNA_GENES xlink:href CDATA #IMPLIED>
<!ATTLIST RNA_GENES xlink:role CDATA #IMPLIED>

<!ATTLIST REPEAT_LIST xlink:type CDATA #IMPLIED>
<!ATTLIST REPEAT_LIST xlink:show CDATA #IMPLIED>
<!ATTLIST REPEAT_LIST xlink:href CDATA #IMPLIED>
<!ATTLIST REPEAT_LIST xlink:role CDATA #IMPLIED>

<!ATTLIST SCAFFOLD xlink:type CDATA #IMPLIED>
<!ATTLIST SCAFFOLD xlink:show CDATA #IMPLIED>
<!ATTLIST SCAFFOLD xlink:href CDATA #IMPLIED>
<!ATTLIST SCAFFOLD xlink:role CDATA #IMPLIED>