taxonomies crossing boundaries: thomson reuters life sciences taxonomy use cases
TRANSCRIPT
THOMSON REUTERSLife Sciences Taxonomy Software Solutions
November 2015
AGENDA• Thomson Reuters Life Sciences annotation services
and use cases• Taxonomy Management System – Synaptica KMS
2
THOMSON REUTERSThe world's leading source of intelligent information for businesses and professionals
Tax & Accounting
Financial & Risk
Thomson Reuters Tax & Accounting is the leading global provider of integrated tax compliance and accounting information, software and services for professionals in accounting firms, corporations, law firms and government.
Intellectual Property & Science
Legal
Thomson Reuters Intellectual Property & Science is the leading provider of comprehensive intellectual property (IP) and scientific information, decision support tools, and services that enable pharmaceutical companies, governments, academia, publishers, corporations and law firms to discover, develop and deliver innovations.
Thomson Reuters Legal is the leading provider of critical information, decision support tools, software and services to legal, investigation, business and government professionals around the world. We offer a broad range of online services that utilize our databases of legal, regulatory, news and business information.
Thomson Reuters Financial & Risk is the leading provider of regulatory and operational risk management solutions. These solutions deliver critical news, information and analytics, enable transactions, and bring together communities that allow trading, investing, financial and corporate professionals to connect.
Reuters News2,800 journalists reporting in 20 languages from bureaus around the world
Reuters is the world’s largest international news organization
INTELLECTUAL PROPERTY & SCIENCESupporting the R&D community
SCIENTIFIC & SCHOLARLY RESEARCH
LIFE SCIENCES
IP SOLUTIONS
Our Mission: Helping Our Customers Bring Ideas and Innovations to the World
Reliable content, analytics and services that improve Pharma R&D productivity
World-class solutions to manage, protect and capitalize on IP assets
Research data and tools to identify, evaluate and
promote the best research
15,000 Customers representing over 20 Million users
LIFE SCIENCES-Supporting the R&D community
CO
NTE
NT
TEC
HN
OLO
GY
EXPE
RTI
SE
We are trusted for the decisions that matter most, empowering decision-makers to act with confidence in a complex world
THOMSON REUTERS LIFE SCIENCES SERVICES- Annotation services• Thomson Reuters provides manual and automated
searches for our customers:– Biomedical literature– Customer documents– Databases– Websites
6
Sources of relevant information. Search and annotation manually or with automated technologies
or
THOMSON REUTERS LIFE SCIENCES SERVICES- Automated annotation• Thomson Reuters automated annotation services
are powered by taxonomies, custom algorithms and domain experts.
7
Taxonomies Rules and Algorithms Domain experts
©20
12 T
hom
son
Reu
ters
.
Thomson Reuters annotation services- Use cases
8
THOMSON REUTERS ANNOTATION SERVICE- Use cases• Product use monitoring• Competitive intelligence• Adverse Event monitoring• Portfolio management
9
Customer terminology
Public terminology Custom
terminology
Final terminology
Secure storage of taxonomies
Edit taxonomies
Map taxonomies
Automated access to taxonomies
Domain specific terminology
PRODUCT USE AND ADVERSE EVENT MONITORING USE CASE
10
Data Approach Results• Monitoring of 50 products using
automated approaches• Indexing includes: indication,
dose, adverse effects, demographics, hot topics
• Output in client’s terminology to match their in-house library database
• Thomson Reuters literature collection
• Customer drug list• Customer
taxonomy
Goal: Due to growth in number of articles and products marketed, an innovative solution to literature monitoring for in-house database maintenance is needed.
• Automated search and indexing of the biomedical literature.
• Map customer thesaurus to public and Thomson Reuters’ taxonomies for a more robust final text-mining ontology source.
• Identify unique terms not found in the client’s taxonomy and recommend to the client.
Manual
Mixed
Text Mining
$$Time and volume
Client taxonomy
Public taxonomy
Thomson Reuters’
taxonomy
Unique terms
PORTFOLIO MANAGEMENT USE CASE
11
Data Approach Results
Automated search of the biomedical literature. Link genes/protein terms to immunoassay terms.
Article counts per month for gene/protein used in a specific immunoassay.
Monthly report with month-to-month analytics
Raw data
>2 million gene/protein and synonym terms +
immunoassay and synonym terms
Goal: Monitor >70,000 human, mouse and rat genes/proteins in the biomedical literature linked to immunoassays to confirm a current portfolio content, as well as identify the new up-and-coming needs for a life sciences reagent company.
Confidence score based on natural language, complexity, case, context clues (‘anti-’), proximity of terms
Tumor protein p53
p53
TP53
BCC7
LFS1
Cellular tumor antigen p53
Phosphoprotein p53
Antigen NY-CO-13
©20
12 T
hom
son
Reu
ters
.
How Synaptica KMS Enables THOMSON REUTERS Annotation Services
12
How Synaptica KMS Enables THOMSON REUTERS Annotation Services
13
Customer terminology
Public terminology Custom
terminology
Final terminology
Secure storage of taxonomies
Edit taxonomies
Map taxonomies
Automated access to taxonomies
Domain specific terminology
Review of Thomson Reuters Use Cases
Collaboration, Import, Linked Data, and Term Creation
14
Customer terminology
Public terminology
Custom terminology
Domain specific terminology
• Collaborative Work Spaces allow for team effort development
• Public and Enterprise term sets may be imported via various source formats (CSV, TXT, XLSX, XML)
• Linked Data technologies provide access to public and private resources across organizations throughout the world (Coming Soon)
• Enable the customer to create new controlled vocabularies, metadata fields, and new terms on the fly and on demand
Taxonomy Management, Mapping and Distribution
15
Final terminology
Secure storage of taxonomies
Edit taxonomies
Map taxonomies
Automated access to taxonomies
• Provide interface for editing new and existing terms along with their governance and lifecycle characteristics.
• Both automated and manual mapping features to provide alignment between public, internal, and external controlled vocabularies.
APIs and Web Services for direct integration with external applications
16
APIs / Web Services
Synaptica GUICloud Based orLocally Hosted
Editors
Administrators / Modelers
Reviewers / Stakeholders
End Users
Database – Data and Model
Database APIStored Procedures
3rd Party Applications
Vocabulary Distributionvia Scheduled Export
Import / Export FilesFull and Incremental
via WebService
via ScheduledDB Job
For More Information Please Contact Us!
17
Elizabeth Sweeney, PhDSenior Research ScientistThomson Reuters
Jim SweeneyProduct ManagerSynaptica, LLC