93
Research… this time it’s Personal! ilkinson, PI Bioinformatics, Heart + Lung Institute @ St. Paul’s Ho Vancouver, BC, Canada

Research - this time it's personal

Embed Size (px)

DESCRIPTION

Final version of my presentation to BioIT World Congress, Boston MA, April 22, 2010. Describes how we're using the SADI Semantic Web Service framework to begin personalizing medical research.

Citation preview

Page 1: Research - this time it's personal

Research… this time it’s Personal!

Mark Wilkinson, PI Bioinformatics, Heart + Lung Institute @ St. Paul’s HospitalVancouver, BC, Canada

Page 2: Research - this time it's personal

DEMO

...to give you incentive to listen to the rest of the presentation

;-)

Page 3: Research - this time it's personal

Show me patients with elevated creatinine along with their latest BUN and creatinine levels

PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> PREFIX patients: <http://sadiframework.org/ontologies/patients.owl#> PREFIX pred: <http://sadiframework.org/ontologies/predicates.owl#> SELECT ?patient ?bun ?creatFROM <http://sadiframework.org/ontologies/patients.rdf>WHERE {

?patient rdf:type patients:ElevatedCreatininePatient .?patient pred:latestBUN ?bun . ?patient pred:latestCreatinine ?creat .

}

Page 4: Research - this time it's personal

VOILA!

Page 5: Research - this time it's personal

There was no database...

There was no patient data anywhere annotated as

“Elevated Creatinine Patient”

Page 6: Research - this time it's personal

How did I answer a question where the required data didn’t exist?

(...no, I didn’t just make it up! LOL!)

Page 7: Research - this time it's personal

The story begins...

Page 8: Research - this time it's personal

This is going to hurt...

Page 9: Research - this time it's personal

Web Services

vs.

Semantic Web

Page 10: Research - this time it's personal

Web Servicesare not “connected” to

the Semantic Web

Why?

Page 11: Research - this time it's personal

Web ServicesXML + XML Schema

Semantic WebRDF + OWL

Page 12: Research - this time it's personal

Web ServicesPOST of SOAP-XML

Semantic WebGET of RDF-XML

Page 13: Research - this time it's personal

Web ServicesNo (rigorous) semantics

Semantic WebRich, flexible semantics

Page 14: Research - this time it's personal

Web Services&

Semantic Web

Fundamentally and deeply different Web technologies!

Page 15: Research - this time it's personal
Page 16: Research - this time it's personal

>1000 X more data in the “Deep Web” than in Web pages

Page 17: Research - this time it's personal

Accessing these databases and

analytical algorithms “transparently”,

based on an individual researcher’s

ideas, beliefs, and preferences

will help us personalize

medical research

Page 18: Research - this time it's personal

Mark Butler (2003) Is the semantic web hype? Hewlett Packard laboratories presentation at MMU, 2003-03-12

Page 19: Research - this time it's personal

Semantic Web?(my definition)

An information system where machines can receive information from one source, re-interpret it, and correctly use it for a purpose that the source had

not anticipated.

Page 20: Research - this time it's personal

Re-interpretation

Correct re-use

Both are critical to

the personalization

of research

Page 21: Research - this time it's personal

Building a

personalized Semantic Web…

Step-by-step…

Page 22: Research - this time it's personal

Founding partner

Semantic Automated Discovery and Integrationhttp://sadiframework.org

(open source)MicrosoftResearch

Page 23: Research - this time it's personal

SADI

“best-practices” for Semantic Web Service provision

Page 24: Research - this time it's personal

standards-compliant

Page 25: Research - this time it's personal

Lightweight(only 2 “rules”)

Page 26: Research - this time it's personal

Rules come from observations:

Page 27: Research - this time it's personal

SADI Observation #1:

Web Services in Bioinformatics create implicit biological relationships

between their input and output

Page 28: Research - this time it's personal

SADI Observation #1:

Page 29: Research - this time it's personal

SADI Best Practice #1

Make the implicit explicit…

A Web Service should create “triples” linking the input data to the output data, thus explicitly describing the semantic

relationship between them

Page 30: Research - this time it's personal

SADI Best Practice #1

This is what bioinformatics Web Services implicitly do anyway!

Easy to implement this as a best-practice

Page 31: Research - this time it's personal

SADI Observation #2:HTTP GET and POST

GET guarantees the response relates to the request URI

in a very precise and predictable way

POST does not…

Page 32: Research - this time it's personal

SADI Observation #2:GET and POST

That’s why Web Services have a fundamentally different behaviour than the Semantic Web

Page 33: Research - this time it's personal

SADI Observation #2:GET and POST

We can fix that!

(without breaking any existing rules or standards!)

Page 34: Research - this time it's personal

SADI Best Practice #2

SUBJECT URI of the output graph (triples) is the same

as the SUBJECT URI of the input graph (triples)

(the output is “about” the input... Now explicitly!)

Page 35: Research - this time it's personal

Consequence

The “Semantics” of our interaction with the Web Service are now

explicit and identical to the “Semantics” of GET

Page 36: Research - this time it's personal

SADI Web Service Interfaces

Service Interfaces defined by two OWL classes:

Page 37: Research - this time it's personal

SADI Web Service Interfaces

OWL Class #1: My Input Class

Page 38: Research - this time it's personal

SADI Web Service Interfaces

OWL Class #2: My Output Class

Page 39: Research - this time it's personal

SADI Web Service Interfaces

My Service consumes OWL Individuals of Class #1

and returns OWL Individuals of Class #2

…but the URI of those two individuals is the same!(see best practice #2)

Page 40: Research - this time it's personal

How do we discover services?

Since input and output are about the same “thing”,

we can automatically determine

what a service does

by comparing

the Input and Output OWL classes

Page 41: Research - this time it's personal

Automatically index services in a registry based

on what properties (predicates) Services add to

their respective input data

How do we discover services?

Page 42: Research - this time it's personal

EXAMPLE

Input Data: BRCA1 rdf:type Gene ID

Output Data: BRCA1 hasDNASequence AGCTTAGCCA…

Registry Index: Service provides “hasDNASequence” property to Gene IDs

Page 43: Research - this time it's personal

Now we can answer questions like

“what is the DNA sequence of BRCA1?”

Discover a SADI Web Service that generates the

DNA Sequence property for gene identifiers

Page 44: Research - this time it's personal

Okay, enough tech gobbledygook

What will this do for ME?

Page 45: Research - this time it's personal

Demo #1

Page 46: Research - this time it's personal

Imagine there is a “virtual database” containing all of the data from all of the databases,together with the output of

every conceivable analysis

Page 47: Research - this time it's personal

How do we query that database?

Page 48: Research - this time it's personal

“SHARE”

Semantic Health And Research Environment

SADI client application

Page 49: Research - this time it's personal
Page 50: Research - this time it's personal

What pathways does UniProt protein P47989 belong to?

PREFIX pred: <http://sadiframework.org/ontologies/predicates.owl#>PREFIX ont: <http://ontology.dumontierlab.com/>PREFIX uniprot: <http://lsrn.org/UniProt:>SELECT ?gene ?pathway WHERE {

uniprot:P47989 pred:isEncodedBy ?gene . ?gene ont:isParticipantIn ?pathway .

}

Page 51: Research - this time it's personal
Page 52: Research - this time it's personal
Page 53: Research - this time it's personal
Page 54: Research - this time it's personal

Recapwhat we just saw

A standard SPARQL query was entered into SHARE, a SADI-aware query engine

Page 55: Research - this time it's personal

Recapwhat we just saw

The query was interpreted to extract the properties being queried and these were passed to SADI for Web Service discovery

Page 56: Research - this time it's personal

Recapwhat we just saw

SADI searched-for, found, and accessed all databases and/or analytical tools capable

of generating those properties

Page 57: Research - this time it's personal

Recapwhat we just saw

We posed, and answered a complex database query

WITHOUT A DATABASE

(in fact, the data didn’t even have to exist...)

Page 58: Research - this time it's personal

Cool!

Page 59: Research - this time it's personal

…but I’m supposed to be personalizing research…

Let’s make this a little more personal by bringing in Ontologies

Page 60: Research - this time it's personal

My Definition of Ontology (for this talk)

Ontologies explicitly define the things that exist in “the world”

based on what properties each kind of thing must have

Page 61: Research - this time it's personal

Ontology Spectrum

Catalog/ID

SelectedLogical

Constraints(disjointness,

inverse, …)

Terms/glossary

Thesauri“narrowerterm”relation

Formalis-a

Frames(Properties)

Informalis-a

Formalinstance

Value Restrs.

GeneralLogical

constraints

Page 62: Research - this time it's personal

Demo #2Discover instances of OWL classes

from data that doesn’t exist…

Page 63: Research - this time it's personal

Show me patients with elevated creatinine along with their latest BUN and creatinine levels

PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> PREFIX patients: <http://sadiframework.org/ontologies/patients.owl#> PREFIX pred: <http://sadiframework.org/ontologies/predicates.owl#> SELECT ?patient ?bun ?creatFROM <http://sadiframework.org/ontologies/patients.rdf>WHERE {

?patient rdf:type patients:ElevatedCreatininePatient .?patient pred:latestBUN ?bun . ?patient pred:latestCreatinine ?creat .

}

Page 64: Research - this time it's personal

Start burrowing through the OWL class find that we need aregression model OWL class

Page 65: Research - this time it's personal

Regression models have features like slopes and intercepts… and so onThe class is completely decomposed until a set of required Services are discoveredcapable of creating all these necessary properties

Page 66: Research - this time it's personal

Successful decomposition of the OWL class to discover the need for a LinearRegression Web Service, and so on

Page 67: Research - this time it's personal

VOILA!

Page 68: Research - this time it's personal

OWL Class restrictions converted into workflows

SPARQL queries converted into workflows

Reasoning happening in parallel with query execution

Data fulfilling OWL models is discovered,

or generated through running analytical tools

SADI and CardioSHARE

Page 69: Research - this time it's personal

I still don’t seewhy this is“Personal”

??

Page 70: Research - this time it's personal

Show me patients whose creatinine level is increasing over time, along with their latest BUN and creatinine

SELECT ?patient ?bun ?creatFROM <http://sadiframework.org/ontologies/patients.rdf>WHERE {

?patient rdf:type patients:ElevatedCreatininePatient .?patient pred:latestBUN ?bun . ?patient pred:latestCreatinine ?creat .

}

Page 71: Research - this time it's personal

I created a small ontologydescribing my definition of

an Elevated Creatinine Patient

Page 72: Research - this time it's personal

… it was MY ontology!

Page 73: Research - this time it's personal

I can re-use it

Page 74: Research - this time it's personal

I can modify it as I change my world-view

Page 75: Research - this time it's personal

I can publish it for others to use

Page 76: Research - this time it's personal

Others can modify it to fit THEIR world-view

Page 77: Research - this time it's personal
Page 78: Research - this time it's personal

My personal world-view is being dynamically resolved against

global data and knowledge

Page 79: Research - this time it's personal

…but it’s bigger than that…

Page 80: Research - this time it's personal

“Elevated Creatinine Patient”

Page 81: Research - this time it's personal

I made that up! It came out of my head!

Page 82: Research - this time it's personal

What’s a fancy word for a world-view that you make-up?

Hypothesis

Page 83: Research - this time it's personal

Current Research

We believe that ontologies and hypotheses are, in some ways, the same “thing”…

…simply assertions about individuals that may or may not exist

Future SADI client applications will supportdata-driven hypothesis generation and resolution

Page 84: Research - this time it's personal

Recap

SADI Semantic Web Services generate triples; the predicates of those triples are indexed... Period.

For a given query, determine which properties are available, and which need to be

discovered/generated

Find services that generate the properties we need

Page 85: Research - this time it's personal

Semantic Web

An information system where machines can receive information from one source, re-interpret it, and correctly use it for a purpose that the source had

not anticipated.

My Purpose!!

Page 86: Research - this time it's personal

What SADI + SHARE supports

Re-interpretation

We constantly compare the collection of properties, gathered from third-parties worldwide, to whatever world-model (query/ontology) we wish to view it

through.

MY world model

Page 87: Research - this time it's personal

Novel re-use

There is no way for the provider to dictate how their data should be used, or how it should be interpreted. They simply add

their properties into the “data cloud” and those properties are used in whatever

way is appropriate for ME.

What SADI + SHARE supports

Page 88: Research - this time it's personal

And all this because SADI simply requires

that the input URI

is the same

as the output URI

Page 89: Research - this time it's personal

Semi-automated SADI service writing and deployment

Taverna

Semantically-guided SADI service discovery and pipelining

SADI Plug-ins

Page 90: Research - this time it's personal

Simple and Open WINS!Join us!

We have recently received funding from CANARIEto assist and train service providers

in deploying their own SADI Semantic Web Services

Come join us – we’re having a lot of fun!!

http://sadiframework.orghttp://twitter.com/sadiframework

Page 91: Research - this time it's personal

Fin

This presentation available on SlideShare: keywords ‘wilkinson’ ‘BioIT-2010’

Page 92: Research - this time it's personal

C r e d i t s

B e n j a m i n V a n d e r V a l k ( S A D I & C a r d i o S H A R E )

L u k e M c C a r t h y ( S A D I & C a r d i o S H A R E )

S o r o u s h S a m a d i a n ( C a r d i o S H A R E )

Page 93: Research - this time it's personal

Microsoft Research