11-Big Data Application in Biomedical Research and Health Care.pptx

Big Data Application in
Biomedical Research and Health
Care
Prof.Dr.H. Hami OZ
Citation: Luo et al. Big Data Application in Biomedical Research and Health Care:
A Literature Review. Biomedical Informatics Insights 2016:8 1–10 doi: 10.4137/BII.S31559.

Volume of data
 ProteomicsDB 8 covers 92% (18,097
of 19,629) of known human genes that
are annotated in the Swiss-Prot
database.
 ProteomicsDB has a data volume of
5.17 TB

Volume of data
 Data from millions of patients have
already been collected and stored in
an electronic format, and these
accumulated data could potentially
enhance health-care services and
increase research opportunities.10,11
 Visible Human Project, which has
archived 39 GB of female datasets.12

variety of data types and
structures.
 For example, sequencing technologies
produce “omics” data systematically at
almost all levels of cellular components,
from genomics, proteomics, and metabo-
lomics to protein interaction and
phenomics.13
 Much of the data that are
unstructured14 (eg, notes from
EHRs,15,16 clinical trial results,17,18
medical images,19 and medical sensors)
provide many opportunities and a unique
challenge to formulate new
investigations.

velocity
 refers to producing and processing data.
 The new generation of sequencing
technologies enables the production of
billions of DNA sequence data each day
at a relatively low cost.
 Because faster speeds are required for
gene sequencing,1,20 big data
technologies will be tailored to match the
speed of producing data, as is required
to process them

Veracity
 Veracity is important for big data as, for example,
personal health records may contain typographical
errors, abbreviations, and cryptic notes.
 Ambulatory measurements are sometimes taken within
less reliable, uncontrolled environments compared to
clinical data, which are collected by trained practi-
tioners.
 The use of spontaneous unmanaged data, such as
those from social media, can lead to wrong predictions
as the data context is not always known.
 Furthermore, sources are of-ten biased toward those
young, internet savvy, and expressive online.

value
 Last but not least, real value to both patients and
healthcare systems can only be realized if challenges to
analyze big data can be addressed in a coherent
fashion.
 It should be noted that many of the underlying principles
of big data have been explored by the research
community for years in other domains.
 Nevertheless, new theories and approaches are
needed for analyzing big health data.
 The total projected healthcare spending in the UK by
2021 will make 6.4% of the gross domestic product
(GDP) whilst the total projected healthcare share of the
GDP in the United States is expected to reach 19.9%
by 2022 [4].

Big Data Technologies
 In most of the cases reported, we
found multiple technologies that were
used together, such as artificial
intelligence (AI), along with
Hadoop®,24 and data mining tools.

Parallel computing
 In recent years, novel parallel computing models, such
as MapReduce25 by Google, have been proposed for a
new big data infrastructure.
 More recently, an open-source MapReduce package
called Hadoop24 was released by Apache for distributed
data management.
 The Hadoop Distributed File System (HDFS)
supports concurrent data access to clustered machines.
 Hadoop-based services can also be viewed as cloud-
computing platforms, which allow for centralized data
storage as well as remote access across the Internet.

cloud computing
 cloud computing is a novel model for
sharing con-figurable computational
resources over the network26 and can
serve as an infrastructure, platform,
and/or software for providing an
integrated solution

Big Data Applications
 Bioinformatics applications
 This section classifies big data
technologies/tools into four categories:
 (1) data storage and retrieval,
 (2) error identification,
 (3) data analysis, and
 (4) platform integration deployment

Data storage and retrieval.
 Nowadays, a sequencing machine can produce millions
of short DNA sequencing data during one run.
 The sequencing data need to be mapped to specific
reference genomes in order to be used for additional
analysis, such as genotype and expression variation -
analysis.
 CloudBurst30 is a parallel computing model that
facilitates the genome mapping process.
 CloudBurst parallelizes the short-read mapping
process to improve the scalability of reading large
sequencing dat

CloudBurst30
 The CloudBurst model was evaluated using a
25-core cluster, and the results indicate that the
speed to process seven million short-reads was
almost 24 times faster than a single-core
machine.
 The CloudBurst team have developed new tools
based on CloudBurst to support
 biomedical research, such as
 Contrail31 for assembling large genomes and
 Crossbow32 for identifying single nucleotide
 polymorphisms (SNPs) from sequencing data.

DistMap33
 DistMap33 is a toolkit for distributed short-read mapping on a
Hadoop cluster.
 DistMap aims to increase the support of different types of mappers
to cover a wider range of sequenc-ing applications.
 The nine supported mapper types include BWA, Bowtie, Bowtie2,
GSNAP, SOAP, STAR, Bismark, BSMAP, and TopHat.
 A mapping workflow is integrated into DistMap, which can be
operated with simple commands.
 For example, an evaluation test was done using a 13-node cluster,
making it an effective application for mapping short-read data. The
BWA mapper can perform 500 million read pairs (247 GB) in about
six hours using DistMap, which is 13 times faster than a single-node
mapper.

SeqWare3
 SeqWare34 is a query engine built on the Apache
HBase35 database to help bioinformatics researchers
access large-scale whole-genome datasets.
 The SeqWare team created an interactive interface to
integrate genome browsers and tools. In a prototyping
analysis, the U87MG and 1102GBM tumor databases
were loaded, and the team used this engine to compare
the Berkeley DB and HBase back end for loading and
export-ing variant data capabilities.
 The results show that the Berkeley DB solution is faster
when reading 6M variants, while the HBase solution is
faster when reading more than 6M variants.

Read Annotation
Pipeline®36
 The Read Annotation Pipeline®36 by the DNA Data Bank of
Japan (DDBJ) is a cloud-based pipeline for high-throughput
analysis of next-generation sequencing data.
 DDBJ initiated this cloud-computing system to support sequencing
analysis.
 It offers a user-friendly interface to process sequencing data-sets,
which supports two levels of analysis:
 (1) the basic-level tools accept FASTQ format data and preprocess
them to trim low-quality bases and
 (2) during the second analysis, the data are mapped to genome
references or assembled on supercomputers.
 This pipeline uses the Galaxy interface for advanced analysis, such
as SNP detection, RNA-sequencing (RNA-seq) analysis, and ChIP-
seq analysis. In a benchmark testing, DDBJ finished mapping 34.7
million sequencing reads to a 383-MB reference genome in 6.5
hours.

Hydra37
 Hydra37 is a scalable proteomic search engine that
uses the Hadoop-distributed computing framework.
 Hydra is a software package for processing large
peptide and spectra databases, implementing a
distributed computing environ-ment that supports the
scalable searching of massive amounts of spectrometry
data.
 The proteomic search in Hydra is divided into two steps:
 (1) generating a peptide database and
 (2) scoring the spectra and retrieving the data.
 The system is capable of performing 27 billion peptide
scorings in about 40 minutes on a 43-node Hadoop
cluster.

Error identification
 Error identification. A number of tools have been
devel-oped to identify errors in sequencing data;
 SAMQA38 identifies such errors and ensures that large-
scale genomic data meet the minimum quality
standards. Originally built for the National Institutes of
Health Cancer Genome Atlas to automatically identify
and report errors, SAMQA includes a set of technical
tests to find data abnormalities (eg, sequence
alignment/map [SAM] format error, invalid CIGAR
value) that contain empty reads.
 A comparison of Hadoop, which was tested on a
cluster, with SAMQA, which was tested on a single-core
server, shows that the Hadoop cluster processed a 23-
GB sample nearly 80 times faster (18.25 hours).

ART
 ART 39 provides simulation data for
sequencing analysis for three major
sequencing platforms:
 454 Sequencing™, Illumina, and
SOLiD.
 ART has built-in profiles of read error
and read length and can identify three
types of sequencing errors: base
substitutions, insertions, and deletions.

CloudRS40
 CloudRS40 is an error- correction
algorithm of high-throughput sequencing
data based on a parallel, scalable
framework.
 This method is developed based on the
RS algorithm.41 The CloudRS team
evaluated the system on six different
datasets using the GAGE benchmarks,42
and the results show that CloudRS has a
higher precision rate compared with the
Reptile43 method.

Data analysis
 In addition to the described frameworks and toolkits for
sequencing data analysis, the Genome Analysis Toolkit
(GATK)20,44 is a MapReduce-based programing framework
designed to support large-scale DNA sequence analysis.
 GATK supports many data formats, including SAM files,
binary alignment/map (BAM), HapMap, and dbSNP.
 With GATK, “traversal” modules prepare and read
sequencing data into the system and thus provide associated
references to the data, such as ordering data by loci.
 The “walker” module consumes the data and provides
analytics outcomes. GATK has been used in the Cancer
Genome Atlas and 1000 Genomes Projects.

ArrayExpress Archive of
Functional Genomics
 The ArrayExpress Archive of Functional Genomics data
repository45,46 is an international collaboration for integrating
high-throughput genomics data.
 The repository contains 30,000 experiments and more than
one million assays.
 About 80% of the data were extracted from the GEO data
repository, and the rest 20% were directly submitted to
ArrayExpress by its users.
 Each day, the platform is visited by more than 1,000 different
users, and more than 50 GB of data are downloaded.
 The platform also connects with R and GenomeSpace to
support data transition and analysis.

BlueSNP
 BlueSNP 47 is an R package for genome-wide
associa-tion studies (GWAS) analysis, focusing
on statistical tests (eg, P-value) to find intensive
associations between large geno-type–
phenotype datasets.
 BlueSNP operates on the Hadoop platform,
which reduces barriers and improves the
efficiency of running GWAS analyses on
clustered machines.
 On a 40-node cluster, BlueSNP analyzed 1,000
phenotypes on 106 SNPs in 104 individuals within
34 minutes.

Myrna48
 Myrna48 is a cloud-based computing pipeline that calculates the
differences of gene expression in large RNA-seq datasets.
 RNA-seq data are m-sequencing reads derived from mRNA
molecules.
 Myrna supports several functions for RNA-seq analysis, including
reads alignment, normalization, and statistical modeling in an
integrated pipeline.
 Myrna returns differential expression of genes into the form of P-
value and q-value.
 This system was tested on the Amazon Elastic Compute Cloud
(Amazon EC2) using 1.1 billion RNA-seq reads, and the results
show that Myrna can process data in less than two hours; the cost
of the test task was around $66

Eoulsan package49
 The Eoulsan package49 implanted a pipeline for
analyzing the differential transcript expressions,
including data imports from sequencer reads, data
mapping to reference genomes, alignment filters,
transcription expression calculations, expression
normalizations using edgeR, and detection of
differential expressions.
 Eoulsan can be run under three modes: stand-alone,
local cluster, and cloud on Amazon Elastic
MapReduce.

 Eoulsan was tested on Amazon EC2 using eight mouse
samples of 188 million reads. The cost for processing
the data was $18–$66, and the total time ranged from
109 to 822 minutes.

SparkSeq50
 SparkSeq50 is a fast, scalable, cloud-
ready software pack-age for
interactive genomic data analysis with
nucleotide pre-cision.
 SparkSeq provides interactive queries
for RNA/DNA studies, and the project
is implemented on Apache Spark
using the Hadoop-BAM library for
processing bioinformatics files.

Platform integration
deployment
 Platform integration deployment. The
use of big data platforms usually requires
a strong grasp of distributed computing
and networking knowledge.
 To help biomedical researchers embrace
big data technology, novel methods are
needed to integrate existing big data
technologies with user-friendly
operations.
 The following systems have been
developed to help achieve this goal.

SeqPig51
 SeqPig51 reduces the need for bioinformaticians to
obtain the technological skills needed to use
MapReduce.
 The SeqPig project extends the Apache Pig scripts to
provide feature-rich sequence processing functions.
 With the help of Hadoop-BAM,52 SeqPig solves the
problem of reading large BAM files to feed analysis
applications.
 SeqPig supports commonly used sequencing formats,
such as FASTQ , SAM, BAM, and QSeq.
 It further sustains commonly used processing tools,
such as Pileup, base frequency count, read coverage,
and distribution.

CloVR
 Current bioinformatics platform also incorporates
a virtual machine. CloVR53 is a sequencing
analysis package that is distributed through a
virtual machine.
 By reducing the technical barriers for analyzing
large sequencing datasets, CloVR supports both
local desktop and cloud systems to enable high-
throughput data processing.
 Several automated bioinformatics
workflows/pipelines are integrated into the virtual
machine, including whole-genome, metagenome,
and 16S rRNA-sequencing analysis.

CloVR
 The CloVR team tested the portability of the
system on a local machine (4 CPU, 8 GB
RAM) and on the Amazon EC2 cloud platform
(80 CPU), and the results show that CloVR is
portable on both platforms, while the EC2
instance runs about five times faster.
 Similarly, CloudBio Linux54 is a virtual
machine solution that provides more than 135
bioinformatics packages for sequencing
analysis, includ-ing preconfigured tools (eg,
GATK, Bowtie, Velvet, FASTX) and
programing libraries (eg, BioJava, R,
Bioconductor).

CloudDOE
 CloudDOE is a software package that provides a
simple interface for deploying the Hadoop cloud
because the Hadoop platform is often too complex for
scientists without computer science expertise and/or
similar technical skills.
 CloudDOE55 is a user-friendly tool for analyzing high-
throughput sequencing data with MapReduce,
encapsulating the complicated procedures for
configuring the Hadoop cloud for bioinformatics
researchers.
 Several packages are integrated with the CloudDOE
package (CloudBurst, CloudBrush, and CloudRS),
and its operation is further simplified by wizards and
graphic user interfaces.

Clinical informatics
applications
 Clinical informatics focuses on the application
of information technology in the health-care
domain. It includes
 activity-based research,
 analysis of relationship between patient main
diagnosis (MD) and underlying cause of
death (UCD),
 and storage of data from EHRs and other
sources (eg, electrophysiological [such as
EEG] data).

Clinical informatics
applications
 In this section, we classified big data technolo-gies/tools
into four categories:
 (2) interactive data retrieval for data sharing,
 (3) data security, and
 (4) data analysis.
 Compared with bioinformatics, clini-cal informatics does
not offer many tools for error identifica-tion but pays
more attention to data-sharing and data security
issues.
 Its data analysis method is very different from bioin-
formatics, as clinical informatics works with both
structured and unstructured data, develops specific
ontologies, and uses natural language processing
extensively.

 Data storage and retrieval. It is critical to
discuss the ways in which big data
techniques (eg, Hadoop, NoSQL database)
are used for storing EHRs.
 The efficient storage of data is especially
important when working with clinical real-time
stream data.56 Dutta et al evaluated the
potential of using Hadoop and HBase35 as
data warehouses for storing EEG data and
discussed their high-performance
characteristics. Jin et al.57 analyzed the
potential of using Hadoop HDFS and HBase
for distributed EHRs.

 Cloudwave, uses Hadoop-based data
processing modules to store clinical data, and
by leveraging the processing power of
Hadoop, they developed a web-based
interface for real-time data visualization
and retrieval.
 The Cloudwave team evaluated a dataset of
77-GB EEG signal data and compared
Cloudwave with a stand-alone system; the
results show that Cloudwave processed five
EEG studies in 1 minute, while the stand-
alone system took more than 20 minutes.

NoSQL
 Compared with a traditional relational
database that handles structured data
well, the novel NoSQL is a great
prospect for storing unstructured data.
 It combines both relational and
multidimensional technologies with
NoSQL repositories to enable data
mining techniques and provide
flexibility and speed in data -
processing.

NoSQL
 A prototype system for storing clinical signal data,
where the time series data of clinical sensors are
stored within HBase in a way that the row key serves
as the time stamp of a single value, and the column
stores patient physiological values that correspond
with the row key time stamp.
 To improve the accessibility and read-ability of the
HBase data schema, the metadata are stored in
MongoDB,62 which is a document-based NoSQL
database.
 Google Web Toolkit is incorporated into the system to
visual-ize the clinical signal data.

Interactive data retrieval for
data sharing
 Interactive data retrieval for data
sharing. Interactive medical information
retrieval is expected to play an important
role in sharing medical knowledge and
integrating data.
 To handle huge amounts of online heart
disease data analyses in China, Wang et
al.68 used a hybrid XML database and
the Hadoop/HBase infrastructure to
design the “Clinical Data Managing and
Analyzing System.”

Data security.
 MedCloud , a model that leverages the Hadoop
eco-system to consider compliance issues with
HIPAA when accessing patient data.
 Home-Diagnosis, a cloud-based framework to
address challenges with privacy protection,
ensure highly concurrent and scalable medical
record retrieval, and conduct data analysis in a
self-caring setting.
 To solve these major challenges, a Lucene-
based dis-tributed search cluster was used in
Home -Diagnosis, while a Hadoop cluster was
employed to speed up the process overall.

Data analysis
 Data analysis. Predicting disease risk and progression
over time can be very useful for clinical decision
support, and building computational models for clinical
prediction requires a complex pipeline.
 PARAMO as a predictive modeling platform for
analyzing electronic health data.
 PARAMO supports the generation and reuse of a
clinical data analysis pipeline for different modeling
purposes.
 To efficiently process parallel tasks, PARAMO supports
MapReduce, which analyzes data for an immense
amount of medical data that can be processed in a
reasonable time.

PARAMO
 Medical terminology ontologies (eg,
ICD, UMLS) were inte-grated into the
PARAMO system, and the analysis
was tested on a set of EHR data from
5,000 to 300,000 patients using a
Hadoop cluster; the concurrent task
varies from 10 to 160. Results show
that on this large dataset, 160
concurrent tasks are 72 times faster
than running on 10 concurrent tasks.

Imaging informatics
applications.
 In this section, we classified big data
technologies/tools into three
categories:
 (2) data sharing, and
 (3) data analysis..

Data storage and retrieval
Imaging informatics is pre-dominantly used for
improving the efficiency of image processing
workflows, such as storage, retrieval, and
interoperation.
PACS are popular for delivering images to local
display work-stations, which is accomplished
primarily through DICOM protocols in radiology
departments.
Many web-based medical applications have been
developed to access PACS, and greater use of big
data technology has been improving their
performance

Data storage and retrieval
 A massive Hadoop-based was
developed medical image retrieval
system that extracted the
characteristics of medical images
using a Brushlet transform and a local
binary pattern algorithm.
 Then, the HDFS stored the image
features, followed by the imple-
mentation of MapReduce.

Data and workflow sharing
 PACS primarily provide image data
archiving and analysis workflow at
single sites.
 Radiology groups operating under a
disparate delivery model (ie, different
services offered by different vendors
to complete a single radiology task)
face significant challenges in a data-
sharing infrastructure.

Super PACS,
 Super PACS, a system that enables a
radiology group that serves multiple sites and
has disparate PACS, RIS, reporting, and
other relevant IT systems to view these sites
virtually from one site and to use one virtual
desktop to efficiently complete all radiology
work and reporting.
 SuperPACS provides two approaches:
 (1) the federated approach, in which all
patient data stay local, and
 (2) the consolidated approach, in which the
data are stored centrally by a single agent

Super PACS
 The agent is able to
 (1) provide an interface for DICOM, HL7, HTTP, and
XDS standard and nonstandardized data;
 (2) synchronize metadata on local PACS and RIS;
 (3) cache images and data received from local PACS,
RIS, any input tool, or another agent;
 (4) archive image data with compression and multitier
storage, backup, disaster recovery, and image and data
life cycle management;
 (5) provide worklists, folders, routing logic, and
mechanisms for image and nonimage data;
 (6) distribute image data through a web server,
including compres-sion and streaming; and
 (7) access local and remote data from a SuperPACS
web client.

Data analysis.
 Data analysis. Seeking to overcome the
challenges brought by large -scale (terabytes
or petabytes) data derived from path-ological
images,
 Hadoop-GIS, an effi-cient and cost-effective
parallel system. Here, GIS refers to spatially
derived data management applications,
which enable real-time spatial queries with
the Real-time Spatial Query Engine, and
integrates both MapReduce-based spatial
query processing and Hive-based feature
query processing.

Hadoop-GIS
 The Hadoop-GIS system also offers an easier
SQL-like declarative query language that is
supported by Hive.
 In the performance study,
 (1) a small-sized cluster for prototype tests
and
 (2) a medium-sized cluster for scalability tests
on real-world data were used.
 The results show that Hadoop-GIS increased
query efficiency and decreased loading and
query time.

Hadoop-GIS
 Hadoop was used to establish a cluster of computing
nodes and MapReduce to speed up the process.
 Three cases of use were analyzed:
 (1) parameter opti-mization for lung texture
classification using support vector machines (SVMs),
 (2) content-based medical image indexing, and
 (3) three-dimensional directional wavelet analysis for
solid texture classification.
 Test results in a parallel grid search for optimal SVM
parameters showed that using concurrent map tasks
reduced the total runtime from 50 hours to 9 hours 15
minutes – a significant improvement in computing effi-
ciency while maintaining a good classification
performance.

Public health information
 public health has three core functions:

 (1)assessment,
 (2) policy development, and
 (3) assurance.
 Assessment primarily involves collecting and analyzing
data to track and monitor public health status, thereby
providing evidence for decision making and policy
development.
 Assurance is used to validate whether the services
offered by health institutions have achieved their initial
target goals for increasing public health outcomes;

Public health information
 This section focuses on four areas:

 (1) infectious disease surveillance,
 (2) population health man-agement,
 (3) mental health management, and
 (4) chronic dis-ease management.

Infectious disease
surveillance
 Using big data for global infectious disease surveillance.
 A system was developed that provides real-time risk
monitoring on map, pointing out that machine learning and
crowdsourcing have opened new possibilities for devel-oping
a continually updated atlas for disease monitoring.
 Online social media combined with epidemiological
information is a valuable new data source for facilitating
public health surveillance.
 The use of social media for disease monitoring was
demonstrated in which 553,186,016 tweets were collected
and extracted more than 9,800 with HIV risk-related keywords
(eg, sexual behaviors and drug use) and geographic
annotations.
 There is a significant positive correlation (P , 0.01) between
HIV-related tweets and HIV cases based on prevalence
analysis, illustrating the importance of social media

Population health
management
 The independent association of patient MD and UCD
was analyzed.
 The MD was identified by ICD10 code, while the UCD
was extracted from a death registry.
 If MD and UCD were different events, then those events
were found to be independent.
 Using health insur-ance data, information from 421,460
deceased patients was extracted from 2008 to 2009.
 The results show that 8.5% of inhospital deaths and
19.5% of out-of-hospital deaths were independent
events and that independent death was more common
in elderly patients.
 The results demonstrate that large-scale data analysis
can be used to effectively analyze the association of
medical events.

Mental health management
 Messages posted on social media could be used to screen
for and potentially detect depression.
 Their analysis is based on previous research of the
association between depressive dis-orders and repetitive
thoughts/ruminating behavior.
 Big data analytics tools play an important role in their work by
mining hidden behavioral and emotional patterns in
messages, or “tweets,” posted on Twitter.
 Within these tweets, a disease-related emotion pattern,
which is a previously hidden symptom may be detected .
 Future research could delve deeper into the conversations of
the depressed users to understand more about their hidden
emotions and sentiments.
 The effectiveness of their model against a dataset of 89,840
patients were analyzed, and the results show that they can
achieve an overall accuracy of 82.35% for all conditions.

Successful applications of personalized medicine in cancer
 Successful applications of personalized
medicine in cancer include three drugs that
have been identified and used in specific groups
of patients.
 Patients with melanoma and the BRAF muta-
tion V600E can be treated with dabrafenib [52],
 patients with breast cancer and the amplification
or overexpression of the gene encoding
Her2/Neu can be treated with a targeted therapy
using trastuzumab [53]
 and different types of tumor that contain the
fusion protein BCR-ABL can be treated with
imatinib [54].

Chronic disease
management
 Cardiovascular Health in Ambulatory Care Research
Team (CANHEART), a unique, population-based -
observational research initiative aimed at measuring and
improving cardio-vascular health and the quality of
ambulatory cardiovascular care provided in Ontario, Canada.
 It included data from 9.8 million Ontario adults aged $20
years.
 Data were assembled by linking multiple databases, such as
electronic surveys, health administration, clinical, laboratory,
drug, and electronic medical record databases using encoded
personal identifiers.
 Follow-up clinical events were collected through record link-
ages to comprehensive hospitalization, emergency
department, and vital statistics administrative databases.

Conclusion
 (1) integrating different sources of information enables
clinicians to depict a new view of patient care processes
that consider a patient’s holistic health status, from
genome to behavior;
 (2) the avail-ability of novel mobile health technologies
facilitates real-time data gathering with more accuracy;
 (3) the implementation of distributed platforms enables
data archiving and analysis, which will further be
developed for decision support; and
 (4) the inclusion of geographical and environmental
informa-tion may further increase the ability to interpret
gathered data and extract new knowledge.

Conclusion
 While big data holds significant promise for improving
 health care, there are several common challenges facing all
the four fields in using big data technology; the most
significant problem is the integration of various databases.
 For example, the VHA’s database, VISTA, is not a single
system; it is a set of 128 interlinked systems.
 This becomes even more complicated when databases
contain different data types (eg, integrating an imaging
database or a laboratory test results database into existing
systems), thereby limiting a system’s ability to make queries
against all databases to acquire all patient data.
 The lack of standardization for laboratory protocols and
values also creates challenges for data integration.

Conclusion
 For example, image data can suffer from
technological batch effects when they come
from different laboratories under different
proto-cols.
 Efforts are made to normalize data when there is
a batch effect; this may be easier for image data,
but it is intrinsically more difficult to normalize
laboratory test data.
 Security and privacy concerns also remain as
hurdles to big data integra-tion and usage in all
the four fields, and thus, secure platforms with
better communication standards and protocols
are greatly needed.

 Example of companies and institutions
that provide solutions to generate,
interperet and visualize combined
omics and health clinical data

Examples of companies and institutions that provide solutions to generate, interpret and visualize combined omics and health
clinical data
Company or institution Type of solution Website
Appistry High-performance big data platform that combines self-organizing computational http://www.appistry.com
storage with optimized and distributed high-performance computing to provide secure,
HIPAA-complaint accurate on-demand analysis of omics data in association with clinical
information
Beijing Genome Institute This solution serves as a solid foundation for large-scale bioinformatics processing. The http://www.genomics.cn/en
computing platform is an integrated service comprising versatile software and powerful
hardware applied to life sciences
CLC Bio Utilizes proprietary algorithms, based on published methods, to accelerate successfully http://www.clcbio.com
data calculations to achieve remarkable improvements in big data analytics
Context Matters Provides a comprehensive tool that empowers pharmaceutical and biotechnology http://www.contextmattersinc.com
companies to make better strategic decisions using web-based applications, and
easy-to-use interface and visualization tools to deal with complex data sets
DNAnexus Provides solutions for NGS by using cloud computing infrastructure with scalable http://www.dnanexus.com
systems and advanced bioinformatics in a web-based platform to solve data
management and the challenges in analysis that are common in unified systems.
Genome International Genome International Corporation (GIC) is a research-driven company that provides http://www.genome.com
Corporation innovative bioinformatics products and custom research solutions for corporate,
government, and academic laboratories in life sciences
GNS Healthcare A big data analytics company that has developed a scalable approach to deal with big http://www.gnshealthcare.com
data solutions that could be applied across the healthcare industry
NextBio Big data technology that enables users to integrate and interpret systematically public http://www.nextbio.com
and proprietary molecular data and clinical information from individual patients,
population studies and model organisms applying omics data in useful ways both in
research and in the clinic
Pathfinder Develops customized software applications, providing solutions in different sectors, http://www.pathfindersoftware.com
including healthcare and omics, offering technologies that enable business
breakthroughs and competitive advantages
Reviews
INFORMATICS

Examples of big corporations offering solutions and pipelines to store, analyze and deal with complex biomedical information
Company Solution(s) Website
Amazon Web Services Provides the necessary computing environment, including CPUs, storage, http://aws.amazon.com
memory (RAM), networking, and operating system, for a hardware
infrastructure as a service in the biomedical and scientific fields
Cisco Healthcare Solutions Offers different types of solution for the life sciences, including specific http://www.cisco.com/web/strategy/
hardware and cloud computing for reliable and highly secure health data healthcare/index.html
communication and sharing across the healthcare community
DELL Healthcare Solutions Connects researchers to the right technology and processes to create http://www.dell.com/Learn/us/en/70/
information-driven healthcare and accelerate innovation in life sciences healthcare-solutions?c=us&l=en&s=hea
with electronic medical record (EMR) solutions
GE Healthcare Life Sciences Provides expertise and tools for a wide range of applications, including basic http://www3.gehealthcare.com/en/
research of cells and proteins, drug discovery research, as well as tools to Global_Gateway
support large-scale manufacturing of biopharmaceuticals
IBM Healthcare and Provides healthcare solutions, technology and consulting that enable http://www-935.ibm.com/industries/
Life Sciences organizations to achieve greater efficiency within their operations, and healthcare
to collaborate to improve outcomes and integrate with new partners for
a more sustainable, personalized and patient-centric system
Intel Healthcare Currently builds frameworks with governments, healthcare organizations, http://www.intel.com/healthcare
and technology innovators worldwide to build the health IT tools and
services of tomorrow by combining different types of health information
Microsoft Life Sciences Provides innovative, world-class technologies to help customers nurture http://www.microsoft.com/health/en-us/
innovation, improve decision-making and streamline operations solutions/Pages/life-sciences.aspx
Oracle Life Sciences Delivers key functionalities built for pharmaceutical, biotechnology, clinical http://www.oracle.com/us/industries/
and medical device enterprises. Oracle maximizes the chances of life-sciences/overview/index.html
discovering and bringing to market products that will help in treating
specific diseases

Examples of companies that offer personalized genetics and omics solutions
Company Applications and/or services Website
23andme A DNA analysis service providing information and educational tools for individuals to http://www.23andme.com
learn and explore their DNA through personal genomics
Counsyl Offers tests for gene mutations and variations in more than 100 inherited rare genetic http://www.counsyl.com
disorders using a DNA biochip designed specifically to test for these disorders
Foundation Medicine A molecular information company at the forefront of bringing comprehensive cancer http://www.foundationmedicine.com
genomic analytics to routine clinical care
Knome Analyzes whole-genome data using software-based tests to examine and compare http://www.knome.com
simultaneously many genes, gene networks and genomes as well as integrate other
forms of molecular and nonmolecular data
Pathway Genomics Incorporates customized and scientifically validated technologies to generate http://www.pathway.com
personalized reports, which address a variety of medical issues, including an
individual’s propensity to develop certain diseases
Personalis A genome-scale diagnostics services company pioneering genome-guided medicine http://www.personalis.com
focused on producing the most accurate genetic sequence data from each sample,
using data analytics and proprietary content to draw accurate and reliable biomedical
interpretations
Examples of companies that offer personalized genetics and omics solutions

11-Big Data Application in Biomedical Research and Health Care.pptx

More Related Content

Similar to 11-Big Data Application in Biomedical Research and Health Care.pptx (20)

Recently uploaded (20)

11-Big Data Application in Biomedical Research and Health Care.pptx