صفحه 1:
صفحه 2:
Semantic Web Development in
Traditional Chinese Medicine
Huajun Chen
Zhejiang Unviersity
صفحه 3:
Semantic Web Development for Traditional
Chinese Medicine
What’s TCM
هه ۱۱۵/3
TCM Ontolo:
ام ا
95
3
TCM Semantic Search Engine (DartGrid System)
Semantic Graph Mining for biomedical network analysis
صفحه 4:
صفحه 5:
What’s TCM?
® Traditional Chinese Medicine (TCM) is an ancient
medical system that accounts for around 40% of
all health cares delivered in China.
© Preventive Medicine
Take medicine as like a daily nutrition supplement or part of
food to maintain the balance of the whole body system.
© Personalized Medicine
Treatment can be completely different for people with
respect to their gender, age, health condition although
they have very similar symptoms.
® Empirical Medicine
The effect of many TCM drugs are based on more one
thousand years of practices, whereas they do not know the
specific underlying mechanism.
صفحه 6:
TCM Knowledge
® TCM theories derive from many knowledge
sources including the theories of Yin-Yang,
Chinese five elements, the human body
channel system, Zang Fu organ theory,
holistic connections, mind-body
intervention, and many others.
® TCM practice includes diagnosis and
treatments theories such as herbal
medicine and , massage and cupping,
acupuncture and meridians.
صفحه 7:
TCM Semantic Web Project
A project in collaboration with China Academy of
Traditional Chinese Medicine.
صفحه 8:
The ultimate vision of the TCM
Semantic Web
Query&Search Analysis&Mining Navigation Workflow
صفحه 9:
The Subprojects
® TCM Ontology Engineering (2001-current).
© The DartGrid Data Integration System (first started in
2002)
® Integrating legacy relational database into Semantic Web
DartMapper: Visulized relational-2-RDF Mapper (2003-2005)
DartQuery: SPARQL2SQL Query Rewriter and a Form-based SPARQL
query builder (2003-2006)
DartSearch: Semantic Search. (2005-current)
® Semantic Data Analysis and Data Mining for Semantic
Web
® DartSpora: semantic data analysis engine (2007-current)
® Semantic Graph Mining for biomedical network analysis.
(2007- current)
صفحه 10:
صفحه 11:
TCM Ontology Engineering
جوجوو وج و
۱
HRS
الاق 5
۱ than
100 persons from over 30 TCM
research institutes located in
different parts of China
Scale
More than 20,000 classes and 100,000
instances defined in the current ontology
Service
Web APIs for ontology-based
applications.
صفحه 12:
The current TCM ontology contains 15.
major categories for each sub-domain.
Individuals
4939
86
11677
6516
10448,
1300
14804
21089
69
1647
1997
3624
1725
219
240
Concepts
65
948
158
308
1680
303
719
216
163
716
108
1572
3313
1352
217
Categories
Pathogeny and pathogenesis and diagnosis
Geography
Pharmacology of TCM medical formulae
Disease
Humanities
Health care management
Medicinal plant and animal
Informatics and philology
Prevention and life-cultivation
Acupuncture
‘Therapeutic principles and treatments
Traditional Chinese Drugs
‘The basic theory of TCM
‘The doctrines of TCM and relevant sciences
Natural science and physics
صفحه 13:
Ontology visualization and query
engine
۲5 46 مج = aa) aE) Com
صفحه 14:
TCM Semantic Search Engine
A semantic search engine build upon a lot of
relational databases.
صفحه 15:
صفحه 16:
Visualized Mapper
صفحه 17:
semantic Searcn Portal Version
صفحه 18:
Semantic Search Portal
Version 1
صفحه 19:
Semantic Data Analysis for TCM
What kinds of new connections can be
discovered or mined from this huge web of
data?
صفحه 20:
(۱ Tld
ل اناه
enter) al
لاع امنره© 3 ك3
Graph Mining 8
( Graph vs Semantic
Graph
erin 0
602 ۱ تشک
4
ككف
Cleweut
1 Semantic
صفحه 21:
An example.
A semantic graph can
connect data from different
sources and domains while
preserving the provenance
صفحه 22:
An example
©» Frequent Semantic Sub-graph Discovery
sema
ented رهم هدر
@ )086
© ور
‘ition مهعم ووم جد مور یه سیف
G, iff. there are r ub-
graphs in G with ‘teat ‘compose [a i is a user-specified
6 lie tha tatal numhar of
سا ماه
000
winize ation it 5
‘ion
sine
Giyoytizae
صفحه 23:
Semantic data analysis
® Semantic graph contains richer information
than normal graph.
® It is based upon the integration capability of
semantic web.
® Much more meaningful mining results:
® Discover the facts directly.
© Find more meaningful associations among
entities.
® Calculate the network parameters in a more
accurate way.
© Ontological reasoning can be leveraged to
further facilitate the mining process.
®We need good tools to help do so.
صفحه 24:
DartSpora: a interactive mining
engine for TCM
صفحه 25:
Summary
© A Web of Data means a lot to us.
® It can enable fancy ways of searching and
browsing the daunting online information
space.
® It can also finally unleash the potential
underlying disparate data sources to greatly
facilitate and advance the data mining and
knowledge discovery technology.
® But we need powerful tools to help us to
achieve the goal.
صفحه 26:
Summary:
Key Benefits of Semantic Web for TCM
© Fusion of data across many scientific discipline
® Easier recombination of data
® Querying of data at different levels of
granularity
© Capture provenance of data through
annotation
® Data can be assessed for inconsistencies
® Integrative knowledge discovery from large-
scale semantic graph formed by integrating
cross-institutional, cross-dispinaries data
sources.
صفحه 27:
Thanks for your time!