Transcript Life Sciences Integrated Demo

Life Sciences Integrated
Demo
Joyce Peng
Senior Product Manager, Life Sciences
Oracle Corporation
[email protected]
Informatics Challenges
Access
heterogeneous
data
Integrate
a variety
of data
types
Manage
vast
quantities of
data
Find Patterns
and
insights
Collaborate
securely
Access
heterogeneous
Data
Oracle Life Sciences Platform
Transparent Gateways
Fast access using Oracle OCI
e.g.
PubMed
MySQL
GenBank
e.g.
Distributed Queries
Perform searches across domains
External Tables
Generic Gateways
Ability to index and
query external files
Access any data using ODBC
Real Application Clusters
Oracle Portal
Build personalized portals
Application Server
Provide scalability for the
middle tier
e.g.
SwissProt
SP-ML
SQL Loader
High performance data loader
Web Services
Standard communication
between applications
Merge/Upsert
Enabling update and insert
in one step
Linear scalability
XML DB
Security
Flexibly manage data
Enforce security
interMedia
Auditing
Collaboration Suite
Collaborate securely
iFS/Files
UltraSearch
Search external sites
& repositories
MySQL Toolkit
Easily move MySQL
data into Oracle
Store & manage images Create audit trail to facilitate Share documents
FDA compliance
Workflow
Extensibility
Framework
O
Cl
Cl
(Data cartridges), manage
complex scientific data
LOBs
Manage unstructured data
Text
Index & query text,
e.g. literature
searches
Data Mining
Automate laboratory
Discover patterns & insights
& business processes
BLAST
Sequence similarity search
Network Model
Pathways Modeling
Statistics
Transportable
Tablespaces
Rapidly exchange tables
Oracle Streams
Perform basic statistics
subscription for
Table FunctionsRule-based
information sharing
Implement complex algorithms
OLAP & Discoverer
Interactive query & drill-down
Platform Features Highlighted
Transparent Gateways
Fast access using Oracle OCI
e.g.
PubMed
MySQL
GenBank
e.g.
Distributed Queries
Perform searches across domains
External Tables
Generic Gateways
Ability to index and
query external files
Access any data using ODBC
Real Application Clusters
Oracle Portal
Build personalized portals
Application Server
Provide scalability for the
middle tier
e.g.
SwissProt
SP-ML
SQL Loader
High performance data loader
Web Services
Standard communication
between applications
Merge/Upsert
Enabling update and insert
in one step
Linear scalability
XML DB
Security
Flexibly manage data
Enforce security
interMedia
Collaboration Suite
Collaborate securely
iFS/Files
Auditing
Store & manage images Create audit trail to facilitate
FDA compliance
Workflow
Extensibility
Framework
O
Cl
(Data cartridges), manage
complex scientific data
LOBs
Manage unstructured data
Index & query text,
e.g. literature
searches
Search external sites
& repositories
MySQL Toolkit
Easily move MySQL
data into Oracle
Share documents
Data Mining
Automate laboratory
Discover patterns & insights
& business processes
Cl
Text
UltraSearch
BLAST
Sequence similarity search
Network Model
Pathways Modeling
Statistics
Transportable
Tablespaces
Rapidly exchange tables
Oracle Streams
Perform basic statistics
subscription for
Table FunctionsRule-based
information sharing
Implement complex algorithms
OLAP & Discoverer
Interactive query & drill-down
BioOracle Project
We are scientists at a life
sciences company
looking to find a cure for
Lymphoma
BioOracle Portal
Integrated data view
and Single-Sign-On
to many applications
Find a Cure for Lymphoma








Literature search on Lymphoma
Set up a project workspace
Set up a meeting
Check lab protocols
Store cell histology images
Analyze gene expression results
Study the markers
Find a lead
Literature Search
Search document
content.
Extract Document Themes
Generate the Gist
Categorize Documents
Text Mining
Find a Cure for Lymphoma








Literature search on Lymphoma
Set up a project workspace
Set up a meeting
Check lab protocols
Store cell histology images
Analyze gene expression results
Study the markers
Find a lead
BioOracle Project In Oracle Files
Lymphoma project
workspace after adding
documents
BioOracle Project in Oracle Files
Support revision control
BioOracle Project in Oracle Files
Associate metadata
(Categories) to a
document.
BioOracle Project in Oracle Files
Advanced
Search
Approval Workflow
Approval Workflow
BioOracle Project in Oracle Files
Access Control
BioOracle Project in Oracle Files
Support
• HTTP/WebDAV(Web)
• SMB (Windows)
• NFS (UNIX)
• AFP (Apple Mac)
• FTP protocols
Wireless Access
Highly Scalable, Worldwide Access
Find a Cure for Lymphoma








Literature search on Lymphoma
Set up a project workspace
Set up a meeting
Check lab protocols
Store cell histology images
Analyze gene expression results
Study the markers
Find a lead
Calendar
Use calendar in
Collaboration Suite to
schedule meetings
with collaborators
Internet Meeting
Protocol Sharing
Find a Cure for Lymphoma








Literature search on Lymphoma
Set up a project workspace
Set up a meeting
Check lab protocols
Store cell histology images
Analyze gene expression results
Study the markers
Find a lead
BioOracle Image Management
Use interMedia to
manage and query
Lymphoma
histology data
BioOracle Image Management
Generate image
thumbnails
BioOracle Image Management
Integrated search across
relational data and
image attributes
extracted
DLBC
Follicular
Gene Expression Analysis
for Lymphoma
Biopsies
Samples
Instruments
Filtering
and PreProcessing
SQL, XML,
Java
Feature
Selection
Interpretation
of Results
SQL
Molecular
Pattern
Recognition
Oracle Data
Mining
Oracle Data
Mining
Reports
Feature
Selection
Bayesian
Classifier
Java Servlets
Discoverer
Portals
Affymetrix
Microarray
Use analytical pipeline to
identify the patterns that
differentiate DLBC from
Dataset from Golub et al Science
286:531-537.
Follicular
Lymphoma
Prediction:
DLBC
Follicular
Find a Cure for Lymphoma








Literature search on Lymphoma
Set up a project workspace
Set up a meeting
Check lab protocols
Store cell histology images
Analyze gene expression results
Study the markers
Find a lead
Oracle Data Mining
Classification of Cancer Subtypes
(DLBC versus Follicular)
Oracle provides wizards to
guide analysts through data
mining model creation
Oracle Data Mining
Build a classification
model
Oracle Data Mining
Select the target field,
e.g. DLBC or Follicular
Lymphoma
Oracle Data Mining
Select the
classification model
Oracle Data Mining
Test the model on the
data set of interest
Naïve Bayes has built a model
that distinguishes DLBC from
Folicular with 77% accuracy
The confusion matrix shows the
number of times the model’s
predictions are accurate
Oracle Data Mining
See if the Adaptive Bayes
Network algorithm can
build a better model
Oracle Data Mining
Use wizards to define
parameters for
building a model
Oracle Data Mining
Adaptive Bayes Network
algorithm can predict
Lymphoma subtype with
84% accuracy
Oracle Data Mining
Adaptive Bayes Network
algorithm generates rules
for model interpretation
Oracle Data Mining in JDeveloper
Automatically create the Java
code needed to build analytical
pipelines inside the database