<![CDATA[<!-- ********************************************************************* -->
<!-- AGAVE - Architecture for Genomic Annotation, Visualization and -->
<!-- Exchange -->
<!-- -->
<!-- AGAVE is designed to offer the life sciences community a -->
<!-- comprehensive, extensible and open format for sharing genomic -->
<!-- annotations. Information on AGAVE can be found at -->
<!-- http://www.agavexml.org. -->
<!-- -->
<!-- Copyright (c) 2001. DoubleTwist, Inc. All Rights Reserved. AGAVE is -->
<!-- a trademark of DoubleTwist, Inc. -->
<!-- -->
<!-- Use of the Architecture for Genomic Annotation, Visualization and -->
<!-- Exchange (AGAVE) XML Document Type Definition (DTD), or any copies -->
<!-- thereof by you (either an individual or a single entity) is subject -->
<!-- to these Terms of Use ("Terms of Use"). Using the AGAVE XML DTD -->
<!-- constitutes your acceptance of these Terms of Use. -->
<!-- -->
<!-- CONDITIONS FOR USE -->
<!-- Redistribution and use of AGAVE in source and binary forms, with or -->
<!-- without modification, are permitted provided that the following -->
<!-- conditions are met: -->
<!-- -->
<!-- 1. Redistributions of source code must retain the above copyright -->
<!-- notice, this list of conditions and the following disclaimer. -->
<!-- -->
<!-- 2. Redistributions in binary form must reproduce the above copyright -->
<!-- notice, this list of conditions and the following disclaimer in -->
<!-- the documentation and/or other materials provided with the -->
<!-- distribution. -->
<!-- -->
<!-- 3. Redistributions of any form whatsoever must retain the following -->
<!-- acknowledgment: -->
<!-- "This product includes software developed by DoubleTwist, Inc. -->
<!-- (http://www.doubletwist.com)" -->
<!-- -->
<!-- 4. The names "AGAVE" and "DoubleTwist" must not be used to endorse -->
<!-- or promote products derived from this software without prior -->
<!-- written permission. For written permission, please contact -->
<!-- info@agavexml.org. -->
<!-- -->
<!-- 5. Products derived from this software may not be called "AGAVE", -->
<!-- nor may "AGAVE" appear in their name, without prior written -->
<!-- permission of DoubleTwist, Inc. -->
<!-- -->
<!-- NO WARRANTIES -->
<!-- Because the AGAVE XML DTD and documentation are licensed free of -->
<!-- charge, there is no warranty for the AGAVE XML DTD and documentation. -->
<!-- THE AGAVE XML DTD IS PROVIDED "AS IS" WITHOUT WARRANTY OF ANY KIND, -->
<!-- EITHER EXPRESS OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED -->
<!-- WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -->
<!-- AND NON-INFRINGEMENT. SHOULD THE AGAVE XML DTD PROVE DEFECTIVE, YOU -->
<!-- ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR, OR CORRECTION -->
<!-- RESULTING FROM SUCH DEFECT. -->
<!-- -->
<!-- LIMITATION OF LIABILITY -->
<!-- IN NO EVENT WILL DOUBLETWIST BE LIABLE TO YOU FOR ANY DAMAGES OF ANY -->
<!-- KIND, INCLUDING WITHOUT LIMITATION ANY GENERAL, DIRECT, SPECIAL, -->
<!-- INCIDENTAL OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, -->
<!-- LOSS OF DATA, DATA RENDERED INACCURATE, OR LOSSES SUSTAINED BY YOU OR -->
<!-- THIRD PARTIES, OR A FAILURE OF THE AGAVE XML DTD TO OPERATE WITH -->
<!-- AGAVE-VALID XML FILES), HOWEVER CAUSED AND ON ANY THEORY OF -->
<!-- LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING -->
<!-- NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS -->
<!-- SOFTWARE EVEN IF DOUBLETWIST HAS BEEN ADVISED OF THE POSSIBILITY OF -->
<!-- SUCH DAMAGES. -->
<!-- -->
<!-- INDEMNIFICATION -->
<!-- You agree to indemnify and hold DoubleTwist, its officers, employees -->
<!-- and its suppliers harmless from any claim or demand, including -->
<!-- reasonable attorneys' fees, made by any third party due to or arising -->
<!-- out of your use of the AGAVE XML DTD or breach of these Terms of Use -->
<!-- or violation of any rights of another. -->
<!-- -->
<!-- GENERAL -->
<!-- You agree to access and use the AGAVE XML DTD in accordance with all -->
<!-- applicable law and regulations, including, without limitation, state -->
<!-- and federal laws and regulations. User agrees not to use the Service -->
<!-- for any illegal or wrongful purposes. You shall be solely -->
<!-- responsible for your compliance with all applicable United States and -->
<!-- foreign laws and regulations and international treaties with respect -->
<!-- to the export or import or use of the AGAVE XML DTD and -->
<!-- documentation. -->
<!-- -->
<!-- These Terms of Use shall be governed by and construed in accordance -->
<!-- with the laws of the State of California, United States of America, -->
<!-- without regard to or application of choice of law rules or -->
<!-- principles. User hereby consents to the personal and exclusive -->
<!-- jurisdiction and venue of the Northern District of California federal -->
<!-- and state courts, as applicable. -->
<!-- -->
<!-- If any provision of these Terms of Use is held by a court of -->
<!-- competent jurisdiction to be invalid, such provision shall be -->
<!-- reformed to as nearly as possible approximate the intent of the -->
<!-- parties and all other provisions shall remain in full force and -->
<!-- effect. DoubleTwist's failure to exercise or enforce any right or -->
<!-- provision of these Terms of Use shall not constitute a waiver of such -->
<!-- right or provision. -->
<!-- -->
<!-- These Terms of Use constitute the parties' final, exclusive and -->
<!-- complete understanding and agreement with respect to the subject -->
<!-- matter hereof and supersedes all prior and contemporaneous -->
<!-- understandings and agreements between the parties. -->
<!-- -->
<!-- The AGAVE XML DTD is an evolving specification; please obtain the -->
<!-- latest AGAVE XML DTD and documentation from www.agavexml.org. -->
<!-- DoubleTwist reserves the right to change, without notice, the AGAVE -->
<!-- XML DTD and documentation. -->
<!-- -->
<!-- -->
<!-- History: -->
<!-- -->
<!-- Jun. 30, 2000 version 2.0 Released with Prophecy 1.0 -->
<!-- Aug. 25, 2000 version 2.1 Released with Prophecy 1.1.2 -->
<!-- Nov. 13, 2000 version 2.2 Released with Prophecy 2.0 -->
<!-- Jul. 3, 2001 version 2.3 Released with Propehcy 3.0 -->
<!-- -->
<!-- ********************************************************************* -->
<!-- -->
<!-- sciobj - The XML document root. -->
<!-- -->
<!-- The version is incremented when an incompatible change is made. -->
<!-- The release changes to indicate compatible changes within a -->
<!-- version. An incompatible change causes a "fatal error" in an XML -->
<!-- compliant parser when parsing data files formatted to a previous -->
<!-- version of the DTD. Compatible changes may cause non-fatal errors -->
<!-- or warnings. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- version: incremented to indicate incompatible changes. -->
<!-- release: incremented to indicate compatible changes. -->
<!-- date: The date this document was created. The date does not -->
<!-- specify when the data in the document was created, only -->
<!-- when the data was assembled into this document. The date -->
<!-- format is YYYY-MM-DD on the Gregorian calendar, as -->
<!-- specified in W3C technical report -->
<!-- http://www.w3.org/TR/NOTE-datetime-970915 -->
<!-- -->
<!ELEMENT sciobj (bio_sequence* , contig* , computation* , chromosome*)>
<!ATTLIST sciobj version NMTOKEN "2"
release NMTOKEN "3"
date CDATA #IMPLIED >
<!-- ********************************************************************* -->
<!-- Basic elements -->
<!-- -->
<!-- ********************************************************************* -->
<!-- -->
<!-- db_id is an identifier for an object in its source database. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- id: a data identifier such as GenBank accession or PID. -->
<!-- db_code: a code for the data source, e.g. GenBank is "gb". -->
<!-- version: version of the associated data. -->
<!-- -->
<!ELEMENT db_id EMPTY>
<!ATTLIST db_id id CDATA #REQUIRED
version CDATA #IMPLIED
db_code CDATA #REQUIRED >
<!-- -->
<!-- element_id contains an IDREF. Use when need to have an IDREF in an -->
<!-- ELEMENT content model. Useful for alternation of db_id or -->
<!-- element_id -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- id: the XML ID of another ELEMENT -->
<!-- -->
<!ELEMENT element_id EMPTY>
<!ATTLIST element_id id IDREF #REQUIRED >
<!-- -->
<!-- A user added note. -->
<!-- -->
<!ELEMENT note (#PCDATA )>
<!-- -->
<!-- A dataset name and version that identifies a set of annotations, -->
<!-- for example -->
<!-- -->
<!-- dataset name="Prophecy" version="1.1.1" -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- name: a dataset name -->
<!-- version: version of the dataset -->
<!-- -->
<!ELEMENT dataset EMPTY>
<!ATTLIST dataset name CDATA #REQUIRED
version NMTOKEN #REQUIRED >
<!-- -->
<!-- related_annot relates sequence annotations and specifies the -->
<!-- relationship type. This allows relationships other than -->
<!-- containment. For example, a link between overlapping features can -->
<!-- be created. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- rel: a relationship type name -->
<!-- score: a score representing the strength of the relationship. Score -->
<!-- is scaled to an integer from 0-100 -->
<!-- -->
<!-- Content: -->
<!-- -->
<!-- element_id: A reference to a comp_result or seq_feature in the same -->
<!-- document. Multiple references can be used because -->
<!-- more than one annotation may be in the same -->
<!-- relationship. -->
<!-- property: A property of the relationship such as a score or -->
<!-- a description. -->
<!-- -->
<!-- -->
<!ELEMENT related_annot (element_id+, sci_property*)>
<!ATTLIST related_annot rel CDATA #REQUIRED
score CDATA #IMPLIED>
<!-- -->
<!-- sci_property is a name-value pair. -->
<!-- -->
<!-- We use SQL types to specify the data_type because they are a well -->
<!-- established standard. Using a diffent datatype set such as Java -->
<!-- datatypes would be equally valid. -->
<!-- -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- prop_type: The type of the property -->
<!-- data_type: indicates if the content should be interpreted as a -->
<!-- number or a string -->
<!-- -->
<!ELEMENT sci_property (#PCDATA )>
<!ATTLIST sci_property prop_type CDATA #REQUIRED
data_type (NUMBER | VARCHAR | LONG ) 'NUMBER' >
<!-- -->
<!-- An assignment of type from a classification system. For example, -->
<!-- an element may be classified as a "gene" with id "BCHE" which is a -->
<!-- concept in the HUGO classifcation system. This would be written as -->
<!-- -->
<!-- classification code="HUGO" -->
<!-- id="BCHE" -->
<!-- type="gene" -->
<!-- assigned_by="locuslink" -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- system: the classification system, e.g. "HUGO" -->
<!-- id: the type id in the classification system. For example, a -->
<!-- gene label. -->
<!-- type: a type assignment such as "gene". -->
<!-- -->
<!-- assiged_by: person, organization, or algorithm who determined the -->
<!-- classification. -->
<!-- -->
<!-- -->
<!ELEMENT classification (description? , id_alias* , evidence? )>
<!ATTLIST classification system CDATA #REQUIRED
id CDATA #REQUIRED
type CDATA #REQUIRED
assigned_by CDATA #IMPLIED >
<!-- -->
<!-- alternate ids in a classification -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- id: a type id in the classification system. -->
<!-- type: The reason for the alias, such as "withdrawn", "misspelling", -->
<!-- "former". -->
<!-- -->
<!ELEMENT id_alias EMPTY>
<!ATTLIST id_alias id CDATA #REQUIRED
type CDATA #IMPLIED >
<!-- -->
<!-- Description. -->
<!-- -->
<!ELEMENT description (#PCDATA )>
<!-- -->
<!-- A view is the range in a chromosome or contig which contains all -->
<!-- available annotations. Since the number of annotations in a -->
<!-- chromosome or contig may be large, we have views to allow the -->
<!-- annotations to be divided among different documents. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- start: the start position in the container's coordinate system. -->
<!-- Must be an integer. -->
<!-- length: The length of the view. -->
<!-- -->
<!ELEMENT view EMPTY>
<!ATTLIST view start CDATA #REQUIRED
length CDATA #REQUIRED >
<!-- ********************************************************************* -->
<!-- Computational results elements. -->
<!-- -->
<!-- ********************************************************************* -->
<!-- -->
<!-- a computation element represents a particular run of an analysis -->
<!-- algorithm. A computation contains comp_input, comp_results, and -->
<!-- possible comp_error if the computation fails. -->
<!-- -->
<!-- comp_results can contain sub comp_results in a result_group. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- element_id: an XML ID for this ELEMENT -->
<!-- computation_id: a unique key for database storage -->
<!-- algorithm: Algorithm/program type -->
<!-- algorithm_version: The algorithm/program version -->
<!-- parameters: Parameters that were used to run the program. -->
<!-- target_database: Database type that was used to perform -->
<!-- computation -->
<!-- -->
<!-- -->
<!ELEMENT computation (comp_input? , dataset? , (comp_error | result_group | results)*)>
<!ATTLIST computation element_id ID #IMPLIED
computation_id NMTOKEN #IMPLIED
algorithm CDATA #REQUIRED
algorithm_version CDATA #IMPLIED
parameters CDATA #IMPLIED
target_database CDATA #IMPLIED >
<!-- -->
<!-- Computational Input element -->
<!-- -->
<!-- This takes one or more db_ids or biosequences as input. -->
<!-- Biosequences could be used when we want to include more info other -->
<!-- than the identifier (e.g. species or the sequence itself). -->
<!-- -->
<!ELEMENT comp_input (db_id | bio_sequence)+>
<!-- -->
<!-- For storing error messages from programs -->
<!-- The error message is the contents of the comp_error tag -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- program: name of program called -->
<!-- arguments: arguments of program -->
<!-- errno: formal error number (if available) -->
<!-- returncode: OS return code (if available) -->
<!-- source: source of error (for multi-layer reporting) -->
<!-- time: time of error -->
<!-- -->
<!ELEMENT comp_error (#PCDATA)>
<!ATTLIST comp_error program CDATA #IMPLIED
arguments CDATA #IMPLIED
errorno CDATA #IMPLIED
returncode CDATA #IMPLIED
source CDATA #IMPLIED
time CDATA #IMPLIED>
<!-- -->
<!-- comp_result contains result alignments, scores, and other -->
<!-- properties. comp_results can be nested using a result_group -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- element_id: an XML ID for this ELEMENT -->
<!-- result_id: a unique key for database storage -->
<!-- group_order: is the order of a result when it appears inside a -->
<!-- group. The group_order is only needed as a database -->
<!-- storage id. -->
<!-- result_type: a result type code, for example grail_exon for a -->
<!-- Grail predicted Exon -->
<!-- feature_type: an assignment of the computed result_type to a -->
<!-- GenBank feature type. Use "*alignment" for -->
<!-- feature_type if the result is an alignment not -->
<!-- interpreted as a feature. -->
<!-- -->
<!-- on_complement_strand: true when match is on complementary strand -->
<!-- -->
<!-- confidence: an integer in the range 0-100. It expresses the -->
<!-- confidence in the result, and is usually a rough -->
<!-- summary of the algorithm scores. Applications can use -->
<!-- the confidence score for filtering, querying, and -->
<!-- sorting. We use an integer rather than a floating -->
<!-- point because as a rough estimate there is no useful -->
<!-- difference between an integral and a fractional score -->
<!-- in this range. -->
<!-- -->
<!-- align_length: the length of the alignment in the alignment units -->
<!-- align_units: the alignment length units -->
<!-- -->
<!ELEMENT comp_result (note? , match_desc? , match_align? , query_region? ,
match_region? , result_property* , result_group* ,
related_annot*)>
<!ATTLIST comp_result element_id ID #IMPLIED
result_id NMTOKEN #IMPLIED
group_order NMTOKEN #IMPLIED
result_type CDATA #REQUIRED
feature_type CDATA #IMPLIED
on_complement_strand (true | false ) 'false'
confidence NMTOKEN #IMPLIED
align_length NMTOKEN #IMPLIED
align_units (bp | AA) #IMPLIED >
<!-- -->
<!-- result_group is an association class that holds the group_id -->
<!-- of a group of comp_results -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- group_order: a unique key for database storage -->
<!-- -->
<!ELEMENT result_group (comp_result+ )>
<!ATTLIST result_group group_order NMTOKEN '0' >
<!-- -->
<!-- results contain comp_results that are not grouped. -->
<!-- -->
<!ELEMENT results (comp_result+ )>
<!-- -->
<!-- result_property holds result values such as blast P scores -->
<!-- -->
<!-- We use SQL types to specify the data_type because they are a well -->
<!-- established standard. Using a diffent datatype set such as Java -->
<!-- datatypes would be equally valid. -->
<!-- -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- prop_type: The type of the property -->
<!-- data_type: indicates if the content should be interpreted as a -->
<!-- number or a string -->
<!-- -->
<!ELEMENT result_property (#PCDATA )>
<!ATTLIST result_property prop_type CDATA #REQUIRED
data_type (NUMBER | VARCHAR | LONG ) 'NUMBER' >
<!-- description of an alignment -->
<!-- -->
<!ELEMENT match_desc (#PCDATA )>
<!-- the text representation of an alignment -->
<!-- -->
<!ELEMENT match_align (#PCDATA )>
<!-- query_region is the region of the query sequence described by a -->
<!-- comp_result. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- start: start point on the query sequence -->
<!-- end: end point on the query sequence -->
<!-- -->
<!ELEMENT query_region (db_id? )>
<!ATTLIST query_region start CDATA #REQUIRED
end CDATA #REQUIRED >
<!-- match_region is the region of the match or hit sequence described -->
<!-- by a comp_result. The match can be identified by db_id, an -->
<!-- element_id containing an IDREF to a bio_sequence, or the -->
<!-- match_region can contain a bio_sequence that represents the match. -->
<!-- -->
<!-- Note that the IDREF should refer to a bio_sequence defined earlier -->
<!-- the document to make it easy to use a SAX parser. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- start: start point on the match sequence -->
<!-- end: end point on the match sequence -->
<!-- -->
<!ELEMENT match_region (db_id | element_id | bio_sequence)? >
<!ATTLIST match_region start CDATA #REQUIRED
end CDATA #REQUIRED >
<!-- ********************************************************************* -->
<!-- Sequence related elements. -->
<!-- -->
<!-- ********************************************************************* -->
<!-- -->
<!-- The chromosome element contains sub-assemblies of DNA such as -->
<!-- contigs or BACs. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- number: The chromosome identifier, for example, "1", "2", "X". -->
<!-- length: THe base pair length of the chromosome -->
<!-- view_start: The view_start and view_length specify the range of -->
<!-- contig annotations that are included in this document. -->
<!-- The view coordinates define a window on the contig -->
<!-- data. -->
<!-- view_length: length of the view from view_start -->
<!-- -->
<!-- Content: -->
<!-- -->
<!-- view: the range of the chromosome in which all available -->
<!-- annotations are included in this document. -->
<!-- contig: an assembled DNA sequence. -->
<!-- -->
<!ELEMENT chromosome (view? , contig*)>
<!ATTLIST chromosome number CDATA #IMPLIED
length NMTOKEN #IMPLIED >
<!-- -->
<!-- A bio_sequence represents a linear molecule such as DNA, RNA, -->
<!-- or a protein. The bio_sequence element contains a primary identifier, -->
<!-- sequence, alternate identifiers, and cross references. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- element_id: an XML ID for this ELEMENT -->
<!-- sequence_id: a unique key for database storage -->
<!-- seq_length: The length of the sequence -->
<!-- molecule_type: The sequence molecule type -->
<!-- organism_name: The organism name in form Genus Species -->
<!-- taxon_id: NCBI Taxonomy database identifier -->
<!-- clone_id: Identifier of the clone from which this sequence was -->
<!-- derived -->
<!-- clone_library: the clone library -->
<!-- chromosome: the chromosome name -->
<!-- map_position: Cytogenetic Map position where sequence comes from -->
<!-- ec_number: The Enzyme commision number which serves to -->
<!-- characterize the enzymatic activity of proteins -->
<!-- using a hierarchical classification scheme -->
<!-- create_date: The date that the sequence was "created" or placed -->
<!-- in the original source database. Not currently used. -->
<!-- update_date: date that sequence or annotation was updated. Not -->
<!-- currently used. -->
<!-- -->
<!-- Content: -->
<!-- -->
<!-- xrefs: cross-references to other sequences or annotations. -->
<!-- map_location: location of the sequence within a larger sequence -->
<!-- such as a chromosome or contig. -->
<!-- -->
<!ELEMENT bio_sequence (db_id , note? , description?, keyword*, sequence? ,
alt_ids? , xrefs? , sequence_map*, map_location* ,
classification*)>
<!ATTLIST bio_sequence element_id ID #IMPLIED
sequence_id NMTOKEN #IMPLIED
seq_length NMTOKEN #IMPLIED
molecule_type (DNA | mRNA | rRNA | tRNA | cDNA | AA ) #IMPLIED
organism_name CDATA #IMPLIED
taxon_id CDATA #IMPLIED
clone_id CDATA #IMPLIED
clone_library CDATA #IMPLIED
chromosome CDATA #IMPLIED
map_position CDATA #IMPLIED
ec_number CDATA #IMPLIED
create_date CDATA #IMPLIED
update_date CDATA #IMPLIED >
<!-- -->
<!-- seq_location contains a sequence location in GenBank format -->
<!-- -->
<!-- the location format is defined on the NCBI web site. The location -->
<!-- may have ambiguous start and end points, and it may be a join of -->
<!-- many intervals. For convenience applications may parse out the -->
<!-- least start point and greatest end point and store them in the -->
<!-- seq_location attributes. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- is_on_complement: true when feature is on complementary strand -->
<!-- -->
<!-- least_start: the smallest start point of the location. For -->
<!-- example, the least_start of "(<25.50)..100" is 25. -->
<!-- greatest_end: the greatest end point of the location. The -->
<!-- greatest_end of "50..(100.110)" is 110. -->
<!-- -->
<!ELEMENT seq_location (#PCDATA )>
<!ATTLIST seq_location is_on_complement (true | false ) #IMPLIED
least_start NMTOKEN #IMPLIED
greatest_end NMTOKEN #IMPLIED >
<!-- -->
<!-- A keyword. Used in bio_sequence. -->
<!-- -->
<!ELEMENT keyword (#PCDATA )>
<!-- -->
<!-- A sequence of symbols representing a linear molecule such as DNA or -->
<!-- a protein. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- start: index of the first symbol in the sequence when the sequence -->
<!-- is partial. This is used in case there is a partial -->
<!-- sequence, such as sequence data within a view. -->
<!-- -->
<!ELEMENT sequence (#PCDATA )>
<!ATTLIST sequence start NMTOKEN #IMPLIED>
<!-- -->
<!-- Alternate identifiers. Used in bio_sequence. -->
<!-- -->
<!ELEMENT alt_ids (db_id+ )>
<!-- -->
<!-- A list of cross references. -->
<!-- -->
<!ELEMENT xrefs (db_id | xref)+>
<!-- -->
<!-- xref is a cross reference. It optionally includes a relationship -->
<!-- descriptor, e.g. protein, and a list of properties. -->
<!-- -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- relationship: The relationship between the cross-referenced -->
<!-- bio_sequences -->
<!-- -->
<!ELEMENT xref (db_id, xref_property*)>
<!ATTLIST xref relationship CDATA #IMPLIED>
<!-- -->
<!-- xref_property holds any data related to a cross reference -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- prop_type: The type of the property -->
<!-- data_type: indicates if the content should be interpreted as a -->
<!-- number or a string -->
<!-- -->
<!ELEMENT xref_property (#PCDATA )>
<!ATTLIST xref_property prop_type CDATA #REQUIRED
data_type (NUMBER | VARCHAR | LONG ) 'VARCHAR' >
<!-- -->
<!-- The seq_feature element describes a feature of a bio_sequence region. -->
<!-- -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- element_id: an XML ID for this ELEMENT -->
<!-- feature_type: The type of the feature. Usually a GenBank feature -->
<!-- type such as "exon". -->
<!-- label: a descriptive name used to refer to the feature. -->
<!-- Usually corresponds to a GenBank /gene or /label -->
<!-- qualifier. Can be assigned by the user. -->
<!-- Content: -->
<!-- -->
<!-- xrefs: cross-references to annotations. -->
<!-- -->
<!ELEMENT seq_feature (classification* , note? , seq_location , xrefs? ,
evidence? , qualifier* , seq_feature* , related_annot*)>
<!ATTLIST seq_feature element_id ID #IMPLIED
feature_type CDATA #REQUIRED
label CDATA #IMPLIED >
<!-- -->
<!-- The gene element inherits the content and attributes of a seq_feature -->
<!-- and adds classifications and transcripts. -->
<!-- -->
<!-- -->
<!-- Content: -->
<!-- -->
<!-- classification: classification of the gene. Element order is not -->
<!-- significant. -->
<!-- -->
<!-- xrefs: cross-references to annotations. -->
<!-- transcript: alternate splice forms of the gene. The first -->
<!-- transcript is the primary transcript. The order of the -->
<!-- following transcripts is not significant. -->
<!-- -->
<!ELEMENT gene (classification* , note? , seq_location , xrefs? ,
evidence? , qualifier* , seq_feature* , related_annot* ,
transcript*)>
<!ATTLIST gene element_id ID #IMPLIED
label CDATA #IMPLIED >
<!-- -->
<!-- The transcript element is a subset of exons from a gene model along -->
<!-- with the possible translation of those exons into cds, mrna, and a -->
<!-- predicted_protein -->
<!-- -->
<!ELEMENT transcript (exons , cds? , mrna? , predicted_protein?)>
<!-- -->
<!-- The exons element contains a subset of exons from a gene model that -->
<!-- constitute a transcript. -->
<!-- -->
<!-- Content: -->
<!-- -->
<!-- Each element_id refers to an exon seq_feature within the same gene. -->
<!-- -->
<!ELEMENT exons (element_id+)>
<!-- -->
<!-- The cds element represents a CDS. We put bio_sequence here to support -->
<!-- annotation of the CDS. For example, the CDS could be annotated with -->
<!-- SNPs. -->
<!-- -->
<!ELEMENT cds (bio_sequence)>
<!-- -->
<!-- The mrna element represents an mRNA. The bio_sequence supports -->
<!-- annotation of the mRNA. For example, the mRNA could be annotated -->
<!-- to tell where cDNA starts and ends. -->
<!-- -->
<!ELEMENT mrna (bio_sequence)>
<!-- -->
<!-- The predicted_protein element contains the translation of a -->
<!-- transcript into a protein. The bio_sequence allows annotation -->
<!-- of the protein and cross references to known proteins. -->
<!-- -->
<!ELEMENT predicted_protein (bio_sequence)>
<!-- -->
<!-- A qualifier-value pair. Corresponds to GenBank feature qualifiers. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- qualifier_type: The type of the qualifier. Usually a GenBank -->
<!-- feature qualifier. -->
<!-- -->
<!-- data_type: indicates if the content should be interpreted as a -->
<!-- number or a string -->
<!-- -->
<!ELEMENT qualifier (#PCDATA )>
<!ATTLIST qualifier qualifier_type CDATA #REQUIRED
data_type (NUMBER | VARCHAR | LONG ) 'VARCHAR' >
<!-- -->
<!-- The evidence element contains comp_results. A computational result -->
<!-- may be the evidence for the existence of a feature. The evidence -->
<!-- element may contain other types of evidence later. -->
<!-- -->
<!ELEMENT evidence (element_id | comp_result)+>
<!-- ********************************************************************* -->
<!-- Sequence mapping elements -->
<!-- -->
<!-- ********************************************************************* -->
<!-- -->
<!-- A contig is an assembly of sequence fragments that may have come -->
<!-- from a contiguous source sequence. A contig may represent a -->
<!-- Bacterial Artificial Chromosome (BAC). contigs may be partially -->
<!-- ordered, so a contig contains ordered and unordered fragments. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- length: the length is the sum of the lengths of all the contained -->
<!-- sequences. -->
<!-- -->
<!-- Content: -->
<!-- -->
<!-- db_id: The identifier of the contig in its source database. -->
<!-- view: the range of the chromosome in which all available -->
<!-- annotations are included in this document. -->
<!-- note: A user added note. -->
<!-- -->
<!-- fragment_order: depreacted. Use assembly instead. -->
<!-- -->
<!-- unordered_fragments: deprecated. Use assembly instead. -->
<!-- -->
<!-- assembly: an assembly or ordering of segments such as BACs to -->
<!-- make up the contig. Use the bio_sequence -->
<!-- map_location to provide a position for the segments -->
<!-- within the contig. -->
<!-- -->
<!-- bio_sequence: sub-sequences of the contig. -->
<!-- -->
<!-- map_location: location of the sequence within a larger sequence -->
<!-- such as a chromosome or contig. -->
<!-- -->
<!ELEMENT contig (db_id , view? , note? , fragment_order* , unordered_fragments? , assembly? ,
sequence? , sequence_map* , map_location* )>
<!ATTLIST contig length NMTOKEN #REQUIRED >
<!-- -->
<!-- fragment_order is a container for fragments that have a relative -->
<!-- ordering. The ordering may have been determined computationally. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- group_id: a unique key for database storage -->
<!-- -->
<!-- Content: -->
<!-- -->
<!-- fragment_orientation is deprecated. Use of bio_sequence with a -->
<!-- map_location is more flexible. -->
<!-- -->
<!-- bio_sequence: a sequence fragment within the group of ordered -->
<!-- fragments. It can be positioned relative to the -->
<!-- group by its map_location. -->
<!-- -->
<!-- map_location: location of the fragment_order within a larger -->
<!-- sequence such as a contig. -->
<!-- -->
<!ELEMENT fragment_order ((fragment_orientation+ | bio_sequence+) , map_location?) >
<!ATTLIST fragment_order group_id CDATA #IMPLIED
length NMTOKEN #IMPLIED >
<!-- -->
<!-- unordered_fragments is a container for fragments that have no known -->
<!-- relative ordering, -->
<!-- -->
<!ELEMENT unordered_fragments (bio_sequence+ )>
<!-- -->
<!-- contains the assembled bio_sequences in a contig. Assembled -->
<!-- sequences are contiguous and positioned within the contig. -->
<!-- -->
<!ELEMENT assembly (bio_sequence | fragment_order)+ >
<!-- -->
<!-- fragment_orientation defines the orientation of a sequence fragment -->
<!-- within an ordering. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- on_complement_strand: true when match is on complementary strand -->
<!-- has_5prime_end: true if 5 prime end has BAC contamination -->
<!-- has_3prime_end: true if 3 prime end has BAC contamination -->
<!-- is_all_BAC_vect: true if the entire fragment is BAC -->
<!-- contamination. -->
<!-- -->
<!-- Content: -->
<!-- -->
<!-- -->
<!ELEMENT fragment_orientation (bio_sequence , map_location?)>
<!ATTLIST fragment_orientation on_complement_strand (true | false ) 'false'
has_5prime_end (true | false ) #IMPLIED
has_3prime_end (true | false ) #IMPLIED
is_all_BAC_vect (true | false ) #IMPLIED>
<!-- -->
<!-- A sequence_map is a set of annotations on a bio_sequence. An -->
<!-- annotation is a seq_feature or a comp_result. -->
<!-- -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- label: an identifying name for the map. Usually an algorithm name. -->
<!-- -->
<!ELEMENT sequence_map (note? , computation? , annotations? )>
<!ATTLIST sequence_map label CDATA #IMPLIED >
<!-- -->
<!-- annotations is a container for sequence annotations. -->
<!-- -->
<!ELEMENT annotations (seq_feature | gene | comp_result )+ >
<!-- -->
<!-- map_location is the location of a bio_sequence within a larger -->
<!-- sequence such as a chromosome. A location may be a single position -->
<!-- or a location within an interval. -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- map_type: map type such as cytogentic, RH, or physical -->
<!-- source: the source of the map, i.e. who made it -->
<!-- units: units of measurement for the contained position. -->
<!-- chromosome: chromosome assignment -->
<!-- -->
<!-- subseq_start: the start of the interval. For example, the -->
<!-- starting position on a BAC which makes up a contig. -->
<!-- Must be an integer. -->
<!-- -->
<!-- orientation: indicates the orientation within the larger sequence -->
<!-- -->
<!-- Content: -->
<!-- -->
<!-- map_position: a single position or the start of an interval -->
<!-- map_position?: the end of an interval -->
<!-- -->
<!ELEMENT map_location (map_position, map_position?)>
<!ATTLIST map_location map_type CDATA #REQUIRED
source CDATA #IMPLIED
units ( band | cR | cM | kb | bp ) #REQUIRED
chromosome CDATA #IMPLIED
subseq_start CDATA '1'
orientation ( forward | complement | none ) #IMPLIED >
<!-- -->
<!-- A position relative to a genomic sequence such as a contig or -->
<!-- chromosome -->
<!-- -->
<!-- Attributes: -->
<!-- -->
<!-- pos: map position such as "13.2" or "7q11" measured in the units of -->
<!-- the containing map_location -->
<!-- Content: -->
<!-- -->
<!-- db_id: reference to the object that this position is on. We allow -->
<!-- multiples for aliases of the same object. -->
<!-- -->
<!ELEMENT map_position (db_id*)>
<!ATTLIST map_position pos CDATA #REQUIRED>
]]>