Post on 13-Apr-2017
AnalyzeGenomes.com: When time matters…
Dr. –Ing. Matthieu-P. Schapranow Festival of Genomics, London, UK
Jan 31, 2017
What is the Hasso Plattner Institute, Potsdam, Germany?
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
2
From Raw Genome Data to Analysis
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
■ DNA Sequencing: Transformation of analogues DNA into digital format
■ Alignment: Reconstruction of complete genome with snippets
■ Variant Calling: Identification of genetic variants
■ Data Annotation: Linking genetic variants with research findings
3
■ Purpose: Transformation of analogous DNA into digital format (A/D converter)
■ Input: Chunks of DNA
■ Output: DNA reads in digital form, e.g. in FASTQ format
1. DNA Sequencing
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
4 4peaks.app
■ FASTQ format used for further processing
■ One read is a quart-tuple of:
1. Sequence identifier / description
2. Raw sequence
3. Strand / direction
4. Quality values per sequenced base
1. Output of Sequencing
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
5
■ Purpose: Mapping of DNA reads to a reference
■ Input:
□ DNA reads := Sequence of nucleotides with a length of 100 bp up to some 1 kbp
□ Reference genome := Blueprint for alignment of DNA reads
■ Output: Mapped DNA reads
■ Bear in mind:
□ Less fraction in DNA reads, i.e. longer reads, allows more precise alignment
□ Reference from same origin improves mapping quality
2. Alignment Overview
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
6
■ Purpose: Variant Calling := Detect variations within a genome
■ Input:
□ Mapped DNA reads, i.e. output of alignment process
□ Reference genome
■ Output: List of variants
■ Bear in mind:
□ Read depth at posi:= Number of nucleotides storing information about pos i
3. Variant Calling Overview
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
7
■ Purpose:
□ Assess impact of genetic changes
□ Understand gene function and possible medical therapy options
■ Input: List of genetic variants
■ Output: Details about certain genetic locus
4. Genetic Annotations
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
8
CHROM POS ID REF ALT QUAL FILTER INFO FORMAT SAMPLE
chr7 140753336 rs113488022 T A 61 PASS NS=1 GT 0/1
■ Manual, time-consuming Internet search, e.g. publications, annotations, guidelines
■ International consortiums provide fragmented information
■ Missing linkage across individual data sources
■ Annotations vary in completeness and correctness
4. Challenges Today
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
9
■ https://www.ncbi.nlm.nih.gov/projects/SNP/snp_ref.cgi?rs=rs113488022
4. Interpretation of Annotations: BRAF Gene dbSNP
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
10
4. Interpretation of Annotations: BRAF Gene Kegg
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
11
4. Interpretation of Annotations: BRAF gene GeneCards
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
12
4. Interpretation of Annotations: BRAF Gene PubMed
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
13
Simplified Clinical Oncology Process (1/2)
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
14
Simplified Clinical Oncology Process (1/2)
Simplified Clinical Oncology Process (1/2)
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
15
Simplified Clinical Oncology Process (2/2)
■ Can we enable clinicians to take their therapy decisions:
□ Incorporating all available patient specifics,
□ Referencing latest lab results and worldwide medical knowledge, and
□ In an interactive manner during their ward round?
Our Motivation Turn Precision Medicine Into Clinical Routine
When time matters...
16
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
Use Case: Precision Oncology Identification of Best Treatment Option for Cancer Patient
■ Patient: 48 years, female, non-smoker, smoke-free environment
■ Diagnosis: Non-Small Cell Lung Cancer (NSCLC), stage IV
■ Markers: KRAS, EGFR, BRAF, NRAS, (ERBB2)
1. Remove tumor through surgery
2. Send tumor sample to laboratory for DNA extraction
3. Sequence complete DNA of sample results in 750 GB of raw genome data
4. Process raw genome data, e.g. alignment, variant calling, and annotate
5. Identify relevant variants using international medical knowledge
6. Support decision making, e.g. link to de-identified historic cases Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
17
Our Vision Medical Board Incorporating Latest Medical Knowledge
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
19
The Challenge Distributed Heterogeneous Data Sources
20
Human genome/biological data 600GB per full genome 15PB+ in databases of leading institutes
Prescription data 1.5B records from 10,000 doctors and 10M Patients (100 GB)
Clinical trials Currently more than 30k recruiting on ClinicalTrials.gov
Human proteome 160M data points (2.4GB) per sample >3TB raw proteome data in ProteomicsDB
PubMed database >23M articles
Hospital information systems Often more than 50GB
Medical sensor data Scan of a single organ in 1s creates 10GB of raw data Cancer patient records
>160k records at NCT
When time matters...
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
■ Requirements
□ Managed services
□ Reproducibility
□ Real-time data analysis
■ Restrictions
□ Data privacy
□ Data locality
□ Volume of big medical data
Software Requirements in Life Sciences
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
21
http://stevedempsen.blogspot.de/2013/08/agile-software-requirements-comic.html
Project Time Line
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
22
2009 2010 2011 2012 2013 2014 2015
SAP HANA launched Oncolyzer SORMAS
Drug Response Analysis
Enterprise Software
Medical Knowledge
Cockpit
Analyze Genomes Platform
IMDB Research
2016 2017 A R
T +
T R A M
S + S
M
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
Our Approach: AnalyzeGenomes.com In-Memory Computing Platform for Big Medical Data
23
In-Memory Database
When time matters...
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
Our Approach: AnalyzeGenomes.com In-Memory Computing Platform for Big Medical Data
24
In-Memory Database
Combined and Linked Data
Genome Data
Cellular Pathways
Genome Metadata
Research Publications
Pipeline and Analysis Models
Drugs and Interactions
When time matters...
Indexed Sources
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
Our Approach: AnalyzeGenomes.com In-Memory Computing Platform for Big Medical Data
25
In-Memory Database
Extensions for Life Sciences
Data Exchange, App Store
Access Control, Data Protection
Fair Use
Statistical Tools
Real-time Analysis
App-spanning User Profiles
Combined and Linked Data
Genome Data
Cellular Pathways
Genome Metadata
Research Publications
Pipeline and Analysis Models
Drugs and Interactions
When time matters...
Indexed Sources
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
Our Approach: AnalyzeGenomes.com In-Memory Computing Platform for Big Medical Data
26
In-Memory Database
Extensions for Life Sciences
Data Exchange, App Store
Access Control, Data Protection
Fair Use
Statistical Tools
Real-time Analysis
App-spanning User Profiles
Combined and Linked Data
Genome Data
Cellular Pathways
Genome Metadata
Research Publications
Pipeline and Analysis Models
Drugs and Interactions
When time matters...
Drug Response Analysis
Pathway Topology Analysis
Medical Knowledge Cockpit Oncolyzer
Clinical Trial Recruitment
Cohort Analysis
...
Indexed Sources
Combined column and row store
Map/Reduce Single and multi-tenancy
Lightweight compression
Insert only for time travel
Real-time replication
Working on integers
SQL interface on columns and rows
Active/passive data store
Minimal projections
Group key Reduction of software layers
Dynamic multi-threading
Bulk load of data
Object-relational mapping
Text retrieval and extraction engine
No aggregate tables
Data partitioning Any attribute as index
No disk
On-the-fly extensibility
Analytics on historical data
Multi-core/ parallelization
Real-Time Data Analysis In-Memory Database Technology
+
+++
+
P
v
+++t
SQL
xx
T
disk
27
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
Managed Services provided by Federated In-Memory Database System (FIMDB)
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
28
Node i
Worker Worker Worker
IMDB
Node j
Worker Worker Worker
IMDB
Node k
Worker Worker Worker
IMDB
Scheduler
Node m
Worker Worker Worker
IMDB
Relay
Node n
Worker Worker Worker
IMDB ...
Cloud Service Provider (Shared Algorithms and Public Reference Data)
Hospital or Research Department (Sensitive/Patient Data)
VPN
UDP TCP
Shared File System (Pool) Shared File System (Pool)
...
Shared File System (Global)
From Raw Genome Data to Analysis
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
■ DNA Sequencing: Transformation of analogues DNA into digital format
■ Alignment: Reconstruction of complete genome with snippets
■ Variant Calling: Identification of genetic variants
■ Data Annotation: Linking genetic variants with research findings
29
Reproducibility Modeling of Data Analysis Pipelines 1. Design time (researcher, process expert)
□ Definition of parameterized process model
□ Uses graphical editor and jobs from repository
2. Configuration time (researcher, lab assistant)
□ Select model and specify parameters, e.g. aln opts
□ Results in model instance stored in repository
3. Execution time (researcher)
□ Select model instance
□ Specify execution parameters, e.g. input files
When time matters...
Dr. Schapranow, Festival of Genomics, Jan 31, 2017 30
App Example: Cloud-based Services for Processing of DNA Data
■ Control center for processing of raw DNA data, such as FASTQ, SAM, and VCF
■ Personal user profile guarantees privacy of uploaded and processed data
■ Supports reproducible research process by storing all relevant process parameters
■ Implements prioritized data processing and fair use, e.g. per department or per institute
■ Supports additional service, such as data annotations, billing, and sharing for all Analyze Genomes services
■ Honored by the 2014 European Life Science Award
When time matters...
Standardized Modeling and runtime environment for
analysis pipelines
31
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
Real-time Data Analysis and Interactive Exploration
App Example: Identification of Optimal Chemotherapy
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
Smoking status, tumor classification
and age (1MB - 100MB)
Raw DNA data and genetic variants
(100MB - 1TB)
Medication efficiency and wet lab results
(10MB - 1GB)
32
Patient-specific Data
Tumor-specific Data
Compound Interaction Data
■ Honored by the 2015 PerMediCon Award
Showcase
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
34 Calculating Drug Response… Predict Drug Response
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
When time matters...
35 cetuximab might be more
beneficial for the current case
■ Query-oriented search interface
■ Seamless integration of patient specifics, e.g. from EMR
■ Parallel search in international knowledge bases, e.g. for biomarkers, literature, cellular pathway, and clinical trials
App Example: Medical Knowledge Cockpit for Patients and Clinicians
When time matters...
36
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
Medical Knowledge Cockpit for Patients and Clinicians Pathway Topology Analysis
■ Search in pathways is limited to “is a certain element contained” today
■ Integrated >1,5k pathways from international sources, e.g. KEGG, HumanCyc, and WikiPathways, into HANA
■ Implemented graph-based topology exploration and ranking based on patient specifics
■ Enables interactive identification of possible dysfunctions affecting the course of a therapy before its start
When time matters...
Unified access to multiple formerly disjoint data sources
Pathway analysis of genetic variants with graph engine
37
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
■ Interactively explore relevant publications, e.g. PDFs
■ Improved ease of exploration, e.g. by highlighted medical terms and relevant concepts
Medical Knowledge Cockpit for Patients and Clinicians Publications
When time matters...
38
Real-time Assessment of Clinical Trial Candidates
■ Switch from trial-centric to patient-centric clinical trials
■ Real-time matching and clustering of patients and clinical trial inclusion/exclusion criteria
■ No manual pre-screening of patients for months: In-memory technology enables interactive pre-screening process
■ Reassessment of already screened or already participating patient reduces recruitment costs
When time matters... Assessment of patients
preconditions for clinical trials
39
Dr. Schapranow, Festival of Genomics, Jan 31, 2017
■ For patients
□ Identify relevant clinical trials and medical experts
□ Become an informed patient
■ For clinicians
□ Identify pharmacokinetic correlations
□ Scan for similar patient cases, e.g. to evaluate therapy efficiency
■ For researchers
□ Enable real-time analysis of medical data, e.g. assess pathways to identify impact of detected variants
□ Combined mining in structured and unstructured data, e.g. publications, diagnosis, and EMR data
What to Take Home? Learn more and test-drive it yourself: AnalyzeGenomes.com
Dr. Schapranow, Festival of Genomics, Jan 31, 2017 40
When time matters...