Download - II-PIC 2017: Product Presentation ChemAxon
Markush Techology and Chemical Data
Curation
Surojit Sadhu
1st International Indian Patent Information Conférence
Bangalore, 2-3 Nov, 2017
Outline
• The ‘Naming’ Family
• ChemCurator
• Markush Technology
THE ‘NAMING’ FAMILY
The ‘Naming’ Family
• Convert Structures to IUPAC and Common Names (Structure to Name )
• Convert Names to Structures (Name to Structure )
• Extract Structures from Documents (Document to Structure)
• Display Documents in a web browser (Document Annotator)
• Extract and Index structures in Shared drives and Folders (ChemLocator)
Supported Languages: English, Chinese & Japanese
Inbuilt Chemical OCR error correction feature
Structure <> Name
Document to Structure
• Detects and extracts Chemical Structures
• Supports PDF, MS office docs, txt, html, xml, etc
• Process a whole document or a single page or a paragraph
• API available.
Document Annotator
Input: HTML, XML, Text or PDF
Output: HTML, with Chemical structures highlighted
Chemical Indexing and Searching
Documents Structure Database
Marvin JS Search ResultsHTML Annotated Document
Document Annotator
D2S JChem
JChem
ChemLocator
Discover the hidden
chemical knowledge in
documents, regardless
whether they are located
on local computer, network
share or in the Cloud
(Google Drive, OneDrive,
DropBox, SharePoint
Online, Office 365).
CHEMCURATOR
ChemCurator
● Computer assisted document curation and analysis
● Extract compounds, Markush structures and related
assay data.
● Simply drag-and-drop recognized structures and fragments to populate R-
groups, and quickly re-assemble the Markush structures according to the
claim
● Use extracted exemplified structures for Markush validation
Compounds extraction view
Compound listCompound listProject explorerProject explorer
Annotated documentAnnotated document
Selected structuresSelected structures
Markush extraction view
Markush editorMarkush editor
Example structuresExample structures
Annotated documentAnnotated document
Selected structuresSelected structures
Structure checkerStructure checker
General document curation
● Files (XML, PDF, HTML)
● Google Patents
● IFI CLAIMS
● Images (CLiDE & OSRA)
MARKUSH TECHNOLOGY
● R-groups
● Atom lists
● Bond lists
● Position variations
● Link nodes
● Repeating units
● Homology groups
Markush Representation
Markush technologies
● Search
● Enumeration
● Hit visualization
● Non-hit visualization
● Overlap
● Composer
Automatic Markush generation
Applications
• patent drafting
• combinatorial libraries:
representation & analysis
Automatic Markush generation
Task
• generate Markush from a list of
compounds
• it should represent:
• all input molecules
• other similar molecules
(structural combinations)
Example for Markush generation
ChemAxon provides solutions for:
• Naming Technology
• Data Curation from Patents and other documents
• Markush Technology
• Data Management tools.
Summary
THANK YOU