2. Getting started: While Adam talks:
1. Go to http://scienceonline.sagebase.org
2. Install the Sage R packages and
dependencies by following instructions on
the home page.
3. Create a Synapse account by following the
How-To Guide: “How to Create a Synapse
Account”.
2
3. Sage Bionetworks Mission
Sage Bionetworks is a non-profit organization with a vision to create a commons
where integrative bionetworks are evolved by contributor scientists with a shared vision
to accelerate the elimination of human disease
Building Disease Maps Data Repository
Commons Pilots
Discovery Platform
4. Synapse Platform and Repository Roadmap
Synapse Platform Functionality
Publicly Hosted Datasets Social Networking
& Attribution
Projects and Datasets Tool / Workflow Support
Networks and Models
Demo System Internal Alpha Invited External Beta Public Beta Full Production
Q1-2011 Q2-2011 Q3-2011 Q4-2011 Q1-2012 Q2-2012 Q3-2012 Q4-2012
Curation Pipeline
Statistical QC Pipeline Crowd-sourcing web tools
Bioconductor Analysis Packages
Coexpression Networks
Data Analysis Capabilities
7. Synapse workflows: reproducible research
1. Load feature data and phenotype data into R
objects.
2. Create matrix aggregating feature data
3.
Write
custom
predicBve
modeling
funcBon.
• Includes
parameter
selecBon
procedure.
• Will
also
do
first
example
with
a
modeling
funcBon
4.
Wrap
predicBve
model
in
cross-‐
that
we
provide
(i.e.
elasBc
net).
validaBon
procedure
for
performance
evaluaBon.
5.
Output
final
predicBve
model
(e.g.
biomarkers).
7
8. 1. Load feature data and phenotype data into R objects.
(Synapse workflow)
1. Load feature data and phenotype data into R
objects.
2. Create matrix aggregating feature data
3.
Write
custom
predicBve
modeling
funcBon.
• Includes
parameter
selecBon
procedure.
• Will
also
do
first
example
with
a
modeling
funcBon
4.
Wrap
predicBve
model
in
cross-‐
that
we
provide
(i.e.
elasBc
net).
validaBon
procedure
for
performance
evaluaBon.
5.
Output
final
predicBve
model
(e.g.
biomarkers).
8
10. 2. Create matrix aggregating feature data
(Synapse workflow)
1. Load feature data and phenotype data into R
objects.
2. Create matrix aggregating feature data
3.
Write
custom
predicBve
modeling
funcBon.
• Includes
parameter
selecBon
procedure.
• Will
also
do
first
example
with
a
modeling
funcBon
4.
Wrap
predicBve
model
in
cross-‐
that
we
provide
(i.e.
elasBc
net).
validaBon
procedure
for
performance
evaluaBon.
5.
Output
final
predicBve
model
(e.g.
biomarkers).
10
12. 3. Predictive modeling functions.
(Synapse workflow)
1. Load feature data and phenotype data into R
objects.
2. Create matrix aggregating feature data
3.
Write
custom
predicBve
modeling
funcBon.
• Includes
parameter
selecBon
procedure.
• Will
also
do
first
example
with
a
modeling
funcBon
4.
Wrap
predicBve
model
in
cross-‐
that
we
provide
(i.e.
elasBc
net).
validaBon
procedure
for
performance
evaluaBon.
5.
Output
final
predicBve
model
(e.g.
biomarkers).
12