<?xml version="1.0" encoding="UTF-8"?>
<!--Annex II of ST.26, Document Type Definition (DTD) for Sequence Listing

This entity may be identified by the PUBLIC identifier:
********************************************************************************************
PUBLIC "-//WIPO//DTD SEQUENCE LISTING 1.0//EN" "ST26SequenceListing_V1_0.dtd"
********************************************************************************************

* PUBLIC DTD URL

* http://www.wipo.int/standards/DTD/ST26SequenceListing_V1_0.dtd
********************************************************************************

Recommended Standard for the presentation of nucleotide and amino acid sequence listings using XML (eXtensible Markup Language)

********************************************************************************
* CONTACTS
********************************************************************************

xml.standards@wipo.int


Date draft created: 2014-03-11

********************************************************************************
* NOTES
********************************************************************************
The sequence data part is a subset of the complete INSDC DTD that only covers
the requirements of WIPO Standard ST.26.

*******************************************************************************
* REVISION HISTORY
********************************************************************************
2014-03-11

Final draft for adoption.
*******************************************************************************

ST26SequenceListing
*******************************************************************************
* ROOT ELEMENT
*******************************************************************************
-->
<!ELEMENT ST26SequenceListing  ((ApplicantFileReference | (
               ApplicationIdentification,ApplicantFileReference?)),
               EarliestPriorityApplicationIdentification?,(ApplicantName,
               ApplicantNameLatin?)?,(InventorName,InventorNameLatin?)?,
               InventionTitle+,SequenceTotalQuantity,SequenceData+) >

<!--The elements ApplicantName and InventorName are optional in this DTD to facilitate
the conversion between various encoding schemes-->
<!ATTLIST ST26SequenceListing
               dtdVersion  CDATA    #REQUIRED 
               fileName  CDATA    #IMPLIED 
               softwareName  CDATA    #IMPLIED 
               softwareVersion  CDATA    #IMPLIED 
               productionDate  CDATA    #IMPLIED  >

<!--ApplicantFileReference
Applicant's or agent's file reference, mandatory if application identification not provided.
-->
<!ELEMENT ApplicantFileReference  (#PCDATA) >

<!--ApplicationIdentification
Application identification for which the sequence listing is submitted, when available.
-->
<!ELEMENT ApplicationIdentification  (IPOfficeCode?,ApplicationNumberText,
               FilingDate?) >

<!--EarliestPriorityApplicationIdentification
Application identification of the earliest claimed priority, which Contains IPOfficeCode, ApplicationNumberText and FilingDate elements. 
-->
<!ELEMENT EarliestPriorityApplicationIdentification  (IPOfficeCode?,
               ApplicationNumberText,FilingDate?) >

<!--ApplicantName
The name of the first mentioned applicant in characters set forth in paragraph 40 a) of the ST.26 main body document.
-->
<!--languageCode: Appropriate language code from ISO 639-1 – Codes for the representation of names of languages - Part 1: Alpha-2
-->
<!ELEMENT ApplicantName  (#PCDATA) >
<!ATTLIST ApplicantName
               languageCode  CDATA    #REQUIRED  >

<!--ApplicantNameLatin
Where ApplicantName is typed in characters other than those as set forth in paragraph 40 b), a translation or transliteration of the name of the first mentioned applicant must also be typed in characters as set forth in paragraph 40 b).
-->
<!ELEMENT ApplicantNameLatin  (#PCDATA) >

<!--InventorName
Name of the first mentioned inventor typed in the characters as set forth in paragraph 40 a).-->
<!--languageCode: Appropriate language code from ISO 639-1 – Codes for the representation of names of languages - Part 1: Alpha-2
-->
<!ELEMENT InventorName  (#PCDATA) >
<!ATTLIST InventorName
               languageCode  CDATA    #REQUIRED  >

<!--InventorNameLatin
Where InventorName is typed in characters other than those as set forth in paragraph 40 b), a translation or transliteration of the first mentioned inventor may also be typed in characters as set forth in paragraph 40 b).
-->
<!ELEMENT InventorNameLatin  (#PCDATA) >

<!--InventionTitle
Title of the invention typed in the characters as set forth in paragraph 40 a) in the language of filing. A translation of the title of the invention into additional languages may be typed in the characters as set forth in paragraph 40 a) using additional InventionTitle elements. Preferably two to seven words.
-->
<!--languageCode: Appropriate language code from ISO 639-1 - Codes
for the representation of names of languages - Part 1: Alpha-2
-->
<!ELEMENT InventionTitle  (#PCDATA) >
<!ATTLIST InventionTitle
               languageCode  CDATA    #REQUIRED  >

<!--SequenceTotalQuantity
Indicates the total number of sequences in the document.
Its purpose is to be quickly accessible for automatic processing.
-->
<!ELEMENT SequenceTotalQuantity  (#PCDATA) >

<!--SequenceData
Data for individual Sequence.
For intentionally skipped sequences see the ST.26 main body document.
-->
<!ELEMENT SequenceData  (INSDSeq) >
<!ATTLIST SequenceData
               sequenceIDNumber  CDATA    #REQUIRED  >

<!--IPOfficeCode
ST.3 code. For example, if the application identification is PCT/IB2013/099999, then IPOfficeCode value will be IB.
-->
<!ELEMENT IPOfficeCode  (#PCDATA) >

<!--ApplicationNumberText
The application identification as provided by the office of filing (eg. PCT/IB2013/099999)
-->
<!ELEMENT ApplicationNumberText  (#PCDATA) >

<!--FilingDate
The date of filing of the patent application for which the sequence listing is submitted ST.2 format (paragraphs 7 (a) and 11) "CCYY-MM-DD", using a 4-digit calendar year, a 2-digit calendar month and a 2-digit day within the calendar month, e.g., 2015-01-31
-->
<!ELEMENT FilingDate  (#PCDATA) >

<!--*******************************************************************************
* INSD Part
*******************************************************************************

The purpose of the INSD part of this DTD is to define a customized DTD for sequence listings to support the work of IP offices while facilitating the data exchange with the public repositories.

The INSD part is subset of the INSD DTD v1.4 and as such can only be used to generate an XML instance as it will not support the complete INSD structure.

This part is based on:

The International Nucleotide Sequence Database (INSD) collaboration.

INSDSeq provides the elements of a sequence as presented in the GenBank/EMBL/DDBJ-style flatfile formats. Not all elements are used here.
-->

<!--INSDSeq
Sequence data.
-->
<!ELEMENT INSDSeq  (INSDSeq_length,INSDSeq_moltype,INSDSeq_division,
               INSDSeq_other-seqids?,INSDSeq_feature-table?,INSDSeq_sequence) >

<!--INSDSeq_length
-->
<!ELEMENT INSDSeq_length  (#PCDATA) >

<!--INSDSeq_moltype
Admissible values: DNA, RNA, AA
-->
<!ELEMENT INSDSeq_moltype  (#PCDATA) >

<!--INSDSeq_division
Indication that a sequence is related to a patent application. Must be populated with the value PAT.
-->
<!ELEMENT INSDSeq_division  (#PCDATA) >

<!--INSDSeq_other-seqids
In the context of data exchange with database providers, the Patent Offices should populate for each sequence the element INSDSeq_other-seqids with one INSDSeqid containing a reference to the corresponding published patent and the sequence identification.
-->
<!ELEMENT INSDSeq_other-seqids  (INSDSeqid?) >

<!--INSDSeq_feature-table
Information on the location and roles of various regions within a particular sequence. Whenever the element INSDSeq_feature-table is used, it must contain at least one feature.
-->
<!ELEMENT INSDSeq_feature-table  (INSDFeature+) >

<!--INSDSeq_sequence
The residues of the sequence. The sequence must not contain numbers, punctuation or whitespace characters.
-->
<!ELEMENT INSDSeq_sequence  (#PCDATA) >

<!--INSDSeqid
Intended for the use of Patent Offices in data exchange only.

Format:
pat|{office code}|{publication number}|{document kind code}|{Sequence identification number}

where office code is the code of the IP office publishing the patent document, publication number is the publication number of the application or patent, document kind code is the letter codes to distinguish patent documents as defined in ST.16 and Sequence identification number is the number of the sequence in that application or patent

Example:
pat|WO|2013999999|A1|123456

This represents the 123456th sequence from WO patent publication No. 2013999999 (A1)
-->
<!ELEMENT INSDSeqid  (#PCDATA) >

<!--INSDFeature
Description of one feature.
-->
<!ELEMENT INSDFeature  (INSDFeature_key,INSDFeature_location,INSDFeature_quals?) >

<!--INSDFeature_key
A word or abbreviation indicating a feature.
-->
<!ELEMENT INSDFeature_key  (#PCDATA) >

<!--INSDFeature_location
Region of the presented sequence which corresponds to the feature.
-->
<!ELEMENT INSDFeature_location  (#PCDATA) >

<!--INSDFeature_quals
List of qualifiers containing auxiliary information about a feature.
-->
<!ELEMENT INSDFeature_quals  (INSDQualifier*) >

<!--INSDQualifier
Additional information about a feature.
For coding sequences and variants see the ST.26 main body document.
-->
<!ELEMENT INSDQualifier  (INSDQualifier_name,INSDQualifier_value?) >

<!--INSDQualifier_name
Name of the qualifier.
-->
<!ELEMENT INSDQualifier_name  (#PCDATA) >

<!--INSDQualifier_value
Value of the qualifier.
-->
<!ELEMENT INSDQualifier_value  (#PCDATA) >