the crusade for big data in the aal domain

48
The crusade for Big Data in the AAL domain Femke Ongenae

Upload: aalforum

Post on 21-Jan-2017

168 views

Category:

Healthcare


0 download

TRANSCRIPT

Page 1: The crusade for big data in the AAL domain

The crusade for Big Data in the AAL domainFemke Ongenae

Page 2: The crusade for big data in the AAL domain

22

Session organizers – Hi!

Femke OngenaeKnowledge Engineer

IBCN, UGent - iMinds

Femke De BackereeCare Researcher

IBCN, UGent - iMinds

Griet VerhennemanLegal ResearcherICRI, KULeuven -

iMinds

Julie DoyleResearch Fellow

CASALA

Page 3: The crusade for big data in the AAL domain

33

Ambient-Assisted Living

Trend towards more personalized & context-aware healthcare services

Page 4: The crusade for big data in the AAL domain

44

FallRisk

Social-aware and context-aware multi-sensor fall detection platform

Page 5: The crusade for big data in the AAL domain

5

Page 6: The crusade for big data in the AAL domain

66

Enable the collection of (near) real-life profile and context data

Page 7: The crusade for big data in the AAL domain

77

Closing the gap...

DevelopersResearchers

Page 8: The crusade for big data in the AAL domain

Keynote by Dr. GrayFemke Ongenae

Page 9: The crusade for big data in the AAL domain

Data Integration in a Big Data ContextOpen PHACTS Case StudyAlasdair J G [email protected]@gray_alasdair

Page 10: The crusade for big data in the AAL domain

11

Big Data

@gray_alasdair Big Data Integration

Volume Velocity

Variety Veracity

http

://i.k

inja

-img.

com

/gaw

ker-m

edia

/imag

e/up

load

/lvzm

0afp

8kik

5dct

xiya

.jpg

Page 11: The crusade for big data in the AAL domain

Open PHACTS Use Case

“Let me compare MW, logP and PSA for launched inhibitors of human & mouse oxidoreductases”

Chemical Properties (Chemspider) Launched drugs (Drugbank) Human => Mouse (Homologene) Protein Families (Enzyme) Bioactivty Data (ChEMBL) … other info (Uniprot/Entrez etc.)

“Let me compare MW, logP and PSA for launched inhibitors of human & mouse oxidoreductases”

@gray_alasdair Big Data Integration 12

Page 12: The crusade for big data in the AAL domain

13

Open PHACTS Mission: Integrate Multiple Research Biomedical Data Resources

Into A Single Open & FreeAccess Point

@gray_alasdair Big Data Integration

Page 13: The crusade for big data in the AAL domain

14

LiteraturePubChem

GenbankPatents Databases

Downloads

Data Integration Data Analysis Firewalled Databases

Repeat @ each companyx

A single, shared solution.

Funded under• IMI: 2011-14• ENSO: 2014-16

Pre-competitive Data

@gray_alasdair Big Data Integration

Page 14: The crusade for big data in the AAL domain

15

http://dx.doi.org/10.1016/j.websem.2014.03.003

• Cloud-Based “Production” Level System.

• Secure & Private

• Guided By Business Questions

• Uses Semantic Web Technology

• Provides REST-ful API

http://dx.doi.org/10.1016/j.drudis.2013.05.008

Discovery Platform

@gray_alasdair Big Data Integration

Page 15: The crusade for big data in the AAL domain

16

Scientific Results

http://ceur-ws.org/Vol-1114/Demo_Dunlop.pdf

http://dx.doi.org/10.1016/j.drudis.2014.11.006 http://dx.doi.org/10.1002/minf.v31.8

http://dx.doi.org/10.1371/journal.pone.0115460

@gray_alasdair Big Data Integration

Page 16: The crusade for big data in the AAL domain

OPS Discovery Platform

@gray_alasdair Big Data Integration 17

Drug Discovery Platform

Apps

Domain API

Interactive responses

Production qualityintegration platform

MethodCalls

Standard Web Technologies

Page 17: The crusade for big data in the AAL domain

18

App Ecosystem

@gray_alasdair

An “App Store”?

Explorer Explorer2 ChemBioNavigator Target Dossier Pharmatrek Helium

MOE Collector Cytophacts Utopia Garfield SciBite

KNIME Mol. Data Sheets PipelinePilot scinav.it Taverna

Big Data Integration https://www.openphacts.org/2/sci/apps.html

Page 18: The crusade for big data in the AAL domain

Big Data Integration 19http://chembionavigator.com

ChemBioNavigator

@gray_alasdair

Page 19: The crusade for big data in the AAL domain

Big Data Integration 20@gray_alasdair

Page 20: The crusade for big data in the AAL domain

Big Data Integration 21@gray_alasdair

Page 21: The crusade for big data in the AAL domain

22

API Hits

@gray_alasdair Big Data Integration

Jan 2013

Feb 2013

Mar 2013

Apr 2013

May 2013

June 2013

July 2013

Aug 2013

Sept 2

013

Oct 2013

Nov 2013

Dec 2013

Jan 2014

Feb 2014

Mar 2014

Apr 2014

May 2014

June 2014

July 2014

Aug 2014

Sept 2

014

Oct 2014

Nov 2014

Dec 2014

Jan 2015

Feb 2015

Mar 2015

Apr 2015

May 2015

June 2015

0

10000000

20000000

30000000

40000000

50000000

60000000

Month

No

of H

its

Public launchof 1.2 API

1.3 API 1.4 API 1.5 API

Page 22: The crusade for big data in the AAL domain

23

OPS Discovery Platform

RDFNanopub

Db

VoID

Data Cache (Virtuoso Triple Store)

Semantic Workflow Engine

Linked Data API (RDF/XML, TTL, JSON)DomainSpecificServices

Identity Resolution

Service

Chemistry RegistrationNormalisation & Q/C

IdentifierManagement

Service

Indexing

Cor

e Pl

atfo

rm

P12374EC2.43.4

CS4532

“Adenosine receptor 2a”

RDF

VoID

Db

RDFNanopub

Db

VoID

RDF

Db

VoID

RDFNanopub

VoID

Public Content Commercial

Public Ontologies

User Annotations

Apps

@gray_alasdair Big Data Integration

Page 23: The crusade for big data in the AAL domain

24

Open PHACTS Data

@gray_alasdair Big Data Integration

Page 24: The crusade for big data in the AAL domain

John Wilbanks consulted for us

A framework built around STANDARD well-understood Creative Commons licences – and how they interoperate

Deal with the problems by:

Interoperable licences

Appropriate terms

Declare expectations to users and

data publishers

One size won‘t fit all requirements

Data Licensing (Or Lack Of!)

Page 25: The crusade for big data in the AAL domain

26

API: Complex Interactions

@gray_alasdair Big Data Integration

Disease

Tissue

Target

Compound

Pathway

Page 26: The crusade for big data in the AAL domain

27

STANDARD_TYPE   UNIT_COUNT---------------- -------AC50                  7 Activity         421 EC50                 39 IC50                 46 ID50                 42 Ki                   23 Log IC50             4 Log Ki               7 Potency              11 log IC50             0 

STANDARD_TYPE      STANDARD_UNITS     COUNT(*)------------------ ------------------ --------IC50               nM                   829448 IC50               ug.mL-1               41000 IC50                                     38521 IC50               ug/ml                  2038 IC50               ug ml-1                 509 IC50               mg kg-1                 295 IC50               molar ratio             178 IC50               ug                      117 IC50               %                       113 IC50               uM well-1                52 

~ 100 units>5000 types

Implemented using the Quantities, Units, Dimension, TypesOntology (http://www.qudt.org/)

Quantitative Data Challenges

@gray_alasdair Big Data Integration

Page 27: The crusade for big data in the AAL domain

28

Quality Assurance

@gray_alasdair Big Data Integration

Page 28: The crusade for big data in the AAL domain

Big Data Integration 29

P12047X31045 P12047

GB:29384RS_2353

Identity Mapping

@gray_alasdair

Andy Law's Third Law“The number of unique identifiers assigned to an individual is never less than the number of Institutions involved in the study”http://bioinformatics.roslin.ac.uk/lawslaws/

Page 29: The crusade for big data in the AAL domain

Gleevec®: Imatinib Mesylate

@gray_alasdair Big Data Integration 30

DrugbankChemSpider PubChem

Imatinib

MesylateImatinib MesylateYLMAHDNUQAMNNX-UHFFFAOYSA-N

Page 30: The crusade for big data in the AAL domain

Gleevec®: Imatinib Mesylate

@gray_alasdair Big Data Integration 31

DrugbankChemSpider PubChem

Imatinib

MesylateImatinib MesylateYLMAHDNUQAMNNX-UHFFFAOYSA-N

Are these records the same?It depends upon your task!

Page 31: The crusade for big data in the AAL domain

Big Data Integration 32

skos:exactMatch(InChI)

Strict Relaxed

Analysing Browsing

Structure Lens

@gray_alasdair

I need to perform an analysis, give me details of the active compound in

Gleevec.

Page 32: The crusade for big data in the AAL domain

Big Data Integration 33

skos:closeMatch(Drug Name)

skos:closeMatch(Drug Name)

skos:exactMatch(InChI)

Strict Relaxed

Analysing Browsing

Name Lens

@gray_alasdair

Which targets are known to interact with Gleevec?

Page 33: The crusade for big data in the AAL domain

Big Data Integration 35

Data Provenance

@gray_alasdair

Page 34: The crusade for big data in the AAL domain

Big Data Integration 36

Data Provenance

@gray_alasdair

Page 35: The crusade for big data in the AAL domain

38

dev.openphacts.org

@gray_alasdair Big Data Integration

Page 36: The crusade for big data in the AAL domain
Page 37: The crusade for big data in the AAL domain

40

Open PHACTS Approach1. Know your audience

Web developers2. Understand your use cases

Prioritised business questions3. Identify access pathways

Identify dataIdentify connectionsImplement API

@gray_alasdair Big Data Integration

Page 38: The crusade for big data in the AAL domain

41

QuestionsAlasdair J G [email protected]@gray_alasdair

Open [email protected]@open_phacts

@gray_alasdair Big Data Integration

Page 39: The crusade for big data in the AAL domain

Brainstorm sessionFemke Ongenae

Page 40: The crusade for big data in the AAL domain

4343

How do we enable an infrastructure/platform that allows the user-

friendly and rapid sharing of Living Lab data?

Page 41: The crusade for big data in the AAL domain

4444

Brainstorm: 3 Steps

Generation of ideas

Selection of best ideas

Further detailing top ideashttp://www.flandersdc.be/gps

Page 42: The crusade for big data in the AAL domain

4545

Table 3Data Sharing Infrastructure

Table 4 Quality & Reliability of data

Table 5Data Usage

Results

Table 1Privacy &

Ethics

Table 2Business Models

Generating ideas

Page 43: The crusade for big data in the AAL domain

4646

Practical arrangements• Paper indicating table order

• Brainstorm round: +/- 15 minutes

• Moderators

Page 44: The crusade for big data in the AAL domain

4747

Some tips!

Page 45: The crusade for big data in the AAL domain

4848

Some tips!

Delay your judgementBe open to naive and crazy

ideas

Openess & enthusiasmUse associative thinking

Piggyback on ideas of others

Page 46: The crusade for big data in the AAL domain

4949

Selection of ideas• Summarize 3 key ideas

• How to select?– Keep the goal in mind! – Think in opportunities– What are you enthusiastic about?– Personal engagement– What is needed in the short term? – Most promising

Page 47: The crusade for big data in the AAL domain

5050

Selection of ideas• 5 Votes

• Put your name & e-mail on the sheet if you want to be involved in working out the idea!

Page 48: The crusade for big data in the AAL domain

THANK YOU FOR YOURTIME

Contact me @ [email protected]