Transcript Delivering the integration promise

The Discovery Informatics
Framework
Delivering the Integration Promise
Pat Rougeau
President and CEO
MDL Information Systems, Inc.
American Chemical Society Meeting
San Francisco, CA
March 27, 2000
1
Integrating informatics into the
Discovery process
Targets
Inventory
Candidates
Standard Test Set
Lead
And
Repeat
Repeat
Proof
XXX
Early Validation
safe
effective
economical
2
new
X
X
X
Descriptors (chem., physicochem. etc.)
Proposals
Information sources for the
Discovery process
DB
Targets
Journals
DB
DB
Inventory
Candidates
Standard Test Set
Lead
Proof
DB
XXX
Journals
Early Validation
safe
effective
economical
Journals
3
new
DB
X
X
X
Descriptors (chem., physicochem. etc.)
Proposals
Journals
Prioprietary information is
exploding
High Throughput Screening
Combinatorial Chemistry
Genomics
Partnerships and Outsourcing
Mergers
4
Public information is more
accessible
Globalized research
Globalized publishing
Electronic media
World Wide Web
Patent literature
5
Turn data into information assets
Drive
up capability
Drive
out cost
6
Information
Innovate
Educate
Application
Globalize
Integrate
IT infrastructure
Standardize
Reduce costs
Turn information assets into
actionable decisions & knowledge
Provide workflow tools that help ensure
quality data
Provide access tools that give the right
data at the right time
Provide analysis tools that help turn
information into action
Capture the knowledge derived from this
process for future use
7
Workflow tools: Assay Explorer
8
Access Tools
R1
A
OH
OH
9
Analysis Tools
Humans are the best decision makers
Informatics must
 Aid the human ability to recognize
patterns through easy to manipulate
visualizations of data
 Improve UI’s to be more natural
10
Spotfire
11
Going beyond analysis to
decision support
A truly effective decision support
environment is build on an open
informatics framework to
 Access all of the information available, in
context
 Visualize and analyze against all or subsets of
the information
 Access tools for calculating and predicting
properties and predicting properties based on
existing data
12
Going beyond analysis to
decision support
Discover in silica predictive models
Test those models against existing data
Validate those models through
additional screening
Result: Provide new leads more quickly,
with fewer discovery cycles
13
Interoperating informatics
solutions for Discovery
Targets
SMART
Compound
Reagent Selector
Selection
Inventory
Assay Explorer
CL Tools
Candidates
Standard Test Set
Central Lib
Lead
Compound
Proof
Toxicity
Early Validation
EcoPharm
safe
effective
economical
14
new
XXX
Warehouse
Analysis
Visualization
X
X
X
Proposals
Descriptors (chem., physicochem. etc.)
Accessing disparate data sources
Compound Warehouse
Beilstein
DB
MDL
DBs
Enterprise
DB
Project
DB
3rd Party
DB’s
Beilstein’s
MDL’s
Your
Your
3rd Party
Application Application Application Application Application
15
Provide access to data anywhere:
Compound Warehouse and LitLink
One query access to
multiple databases
Compound Warehouse
Beilstein
MDL
Enterprise Project
LitLink Server
3rd Party
3rd Party
Native
Application
One click access from
multiple databases
16
Facilitating interoperability
Query
CW Result
Decision Support
Procurement
17
Drill down
Database Browser
Interoperability requires software
and database resources
Compound
Locator
Decision
Support
Content
Database
Browser
18
Experimental
Workflow
Your
Application
Technology
Procurement
Knowledge Extraction
Knowledge—what scientists create
Recognizing and generalize patterns
Differentiating causality from
coincidence
Recording conclusions in papers and
reports, supported by data
20
Knowledge capture is key
In Discovery, capturing knowledge
means capturing




21
Decisions
Analysis methodology
Supporting data
Context (e.g., experimental protocol)
Knowledge mining today
Today’s technology can help the
scientist
 Search disparate sources
 Review the results
 Navigate between the sources
Recreate the knowledge
22
Knowledge extraction
progress is being made
Automating knowledge base creation
 Intelligent indexing
 Automatic thesaurus construction
Mining the knowledge base
 Relevance based retrieval
 Natural language searching
23
Creative Science on a Systems
Engineering Framework
Creative science is
 ad hoc
 interactive
 intuitive
Systems engineering is
 disciplined
 ordered
 structural
24
Creative Science on a Systems
Engineering Framework
Change is a constant
Transitions require management
Take into account




25
strategy
pace
values
culture
Link business and scientific
concerns
People
Science
26
Business
Thank You
27