bde sc1 workshop 3 - iasis (guillermo palma)

Integration and analysis of heterogeneous big data for precision medicine and suggested treatments for different types of patients.

SC1-PM-18-2016: Big Data supporting Public Health policies

iASiS: Big Data to Support Precision

Medicine and Public Health Policy

Sören Auer, Guillermo Palma, Maria-Esther VidalFarah Karim, Kemele Endris, Samaneh Jozashoori,

Scientific Data Management Group 13.12.2017

Big Data Europe: 3rd Workshop on Big Data in Health

1

http://project-iasis.eu

@Project_IASIS

Agenda

1. iASiS: Big Data to Support Precision Medicine and Public Health Policy

2. The iASiS Architecture3. iASiS Big Data Analytics and Pattern Discovery

2

iASiS: Vision and Objectives

3

iASiS Vision:

Turn clinical, pharmacogenomics, and other Big Data into actionable knowledge for personalized medicine and health policy-making

iASiS Objectives:

• Integrate automated unstructured and structured data analysis,image analysis, and sequence analysis into a Big Data framework

• Use the iASiS framework to support personalized diagnosis andtreatment

Pilot 1: Lung Cancer

4

Motivation:

• Lung cancer among the most• common and deadly diseases • costly cancers

• Lung cancer is a heterogeneousdisease. Characteristics differ among• patients• tumor regions

iASiS will enable:

• Discovery of correlations among tumor spread, prognosis, response to treatment

• Unraveling molecular mechanisms that predict response to different tumor types (signatures)

Pilot 2: Alzheimer's Disease

Motivation:

• Approximately, 10% of people over 65 suffer from Alzheimer’s

• Heterogeneity of the symptoms impedes accurate diagnosis and treatments

iASiS will enable:

• Discovery of patterns associated withprognosis, outcomes, and response to treatments

• Association of medical and lifestyleadvice to Alzheimer’s risk and stages of severity

The iASiS Pipeline

6

Big Data in the Lung Cancer Pilot

• Pharmacological knowledge extractedfrom publicly available datasets

• Biomedical ontologies and taxonomies• terminology standardization• semantically describing the EHRs

• EHRs in Spanish

• PET/CT Images

• Genomic Data/Liquid Biopsy Samples

• EHRs in English

• MRI Brain Images

• Genomic Data

• Pharmacological knowledge extractedfrom publicly available datasets

• Biomedical ontologies and taxonomies• terminology standardization• semantically describing the EHRs

Big Data in the Alzheimer's Disease Pilot

The iASiS Pipeline

9

Clinical Big Data Analytics

Clinical Notes NLP

Data Preprocessing

Medical Images

Deep Learning Predictive Models

Medical Vocabularies

Knowledge

Data Mining

Knowledge Graph

Genomic Big Data Analytics

Identification of RNAs regulated

by RBP

Comparison with available information

Integration with transcriptomic

data

Hospital-derived data

Knowledge Graph

Identification of key genes and

interactions

Open Big Data Analytics

• Heterogeneous open data

• Semantic indexing of the data via ontologies and thesauri

• Knowledge extraction from the data• NLP and network analysis technologies

The iASiS Pipeline

13

The iASiS Schema

14

http://vocol.iais.fraunhofer.de/iasis/ Powered by VolCol

The iASiS Pipeline

15

The iASiS Architecture

16

Knowledge GraphCentral Node

Node@Partner1Node@Partner2

The iASiS Architecture

17

Knowledge Graph

The iASiS Architecture

18

Knowledge GraphCentral Node

Node@Partner1

The iASiS Architecture

19

Knowledge GraphCentral Node

Node@Partner1Node@Partner2

Big Data Analytics and Pattern Discovery

20

Pragmatics

ContextSemanticsDrug Similarity

TargetSimilarity

DetectingPatterns

PredictingInteractions

Computing Similarity

Pattern Detection Prediction Principle

Network of

Drugs, Targets,

and interactions

Patterns of

similar Drugs,

similar Targets,

and their

interactions

Discovered

Drug-Target

Interactions

ChEBI Ontology

Patterns between Drug-Protein Interactions

21

Predicted Interactions between Drugs and Proteins

Patterns between Drug and Side Effects

22

Predicted Interactions between Drugs and Side Effects

Conclusions and Future Work

23

The iASiS Pipeline

The iASiS Architecture Big Data Analytics and Pattern Discovery

Conclusions and Future Work

24

The iASiS Pipeline

The iASiS Architecture Big Data Analytics and Pattern Discovery

Next Steps:● Ingest Big Data● Extract Knowledge from Big Data sources● Create the iASiS Knowledge Graph● Enforce Data Access and Privacy Policies● Big Data Processing and Analytics

The iASiS Partners

25

The iASiS Team

26

Scientific Data Management Group at TIB

27

Guillermo

Palma

Guillermo Betancourt Yerson Roa Kemele

Endris

Farah

Karim

Bachelor StudentsPhD StudentsPostDoc

Maria-Esther Vidal

Samaneh

Jozashoori

Many thanks for your attention!

Questions?

28