FEATURE

Drowning in data?

David Wang gives his view on how modern laboratories can leverage data to provide maximum value

Big data is revolutionising science and medicine and underpinning some of medical research’s most exciting trends, including translational research, precision medicine and immunotherapy. But researchers today are drowning in data. Despite advancements in big data and the benefits that it offers, researchers are still struggling to leverage the information effectively.

This is because leveraging big data is a complex process which requires collection, processing and analysis of massive amounts of structured and unstructured content, including data from next-generation sequencing, high throughput and phenotypic screening, drug and protein interactions, and clinical trials. Much of this research is in disintegrated technologies, from hard drives to the cloud, clinical reports to lab notes, and PubMed reports that continue to double every 3.5 years – making it extremely hard for researchers to gain insights to see the complete picture.

While the landscape of available technologies from vendors offering cloud capabilities, analysis tools, and software-as-a-service has increased and improved dramatically in recent years, the scope and variety of these offerings has made it hard for researchers to choose a data analysis tool that supports their needs.

Although it may be difficult, there is hope that researchers and lab managers can successfully choose the correct data analysis tool if they know what to look for in their big data technology.  Here are four high-value characteristics to look for when making decisions on which technologies and tools to implement. 

Boundary-less collaboration

Research is increasingly collaborative across organisational and geographical borders, which means scientists need quick, easy ways to share data.

At the same time, backed by initiatives like Cancer Moonshot and the Vivli Center for Global Research Data, public data sharing and clinical trial reporting networks are becoming more common.

This is beneficial to scientists because new data streams can enhance and accelerate clinical trials. They also improve the probability of patient success, as the selection of biomarkers increases and becomes more accurate.

But while such collaborations and data-sharing initiatives improve access to a diverse data set, they require a data management system with advanced algorithms that are scalable, efficient, effective and simple enough to deliver the right data at the right time.

Seamless data-to-decisions

More efficiency equals time and cost savings. A single system with a user-friendly workflow can help researchers work faster and more productively, allowing them to spend more time making new discoveries. 

Cloud-enabled systems meet this need because they have the scalability to accommodate larger datasets and workloads on demand. The cloud also enables researchers to access and share their data no matter where they are. 

Easy queries and visualisation

In today’s on-demand, uber-economy, we have the capability to call a car service or place an order for food delivery with the click of a button, giving more convenience and control to the end user. That experience should be no different when it comes to enterprise data software and technology, and researchers are beginning to demand the same level of control and convenience at work, as at home. Self-service data enables researchers to find and modify data sets, while the visualisation helps tell the data story and provides insights, which can help accelerate discovery. 

Enhanced security and compliance

Given the data-intensive nature of medical research, and an overall rise in data piracy attempts, privacy and security of life sciences data becomes critical. And while researchers and life scientists prioritise innovation as they develop new therapies and treatment, a KPMG report finds that they’re becoming more susceptible to cybersecurity risks.

The integrity and security of medical research data is an important component of industry’s responsibility to ensure the safety, efficacy and quality of drugs, and the Food and Drug Administration’s ability to protect the public health.

Life sciences organisations need to be able to assess the risk of their software and devices, and associated networks that they interact with, and ensure the integrity of their data.

Big data offers several benefits across medical research and drug discovery. But we need to be able to understand and manage it properly. By providing researchers with the right tools and technology, we can enable them to better explore and analyse data sets and deliver on the promise of translational research, precision medicine and immunotherapy. 

Other tags: 
Feature

Robert Roe explores the role of maintenance in ensuring HPC systems run at optimal performance

Feature

Robert Roe speaks with Dr Maria Girone, Chief Technology Officer at CERN openlab.

Feature

Dr Keren Bergman, Professor of Electrical Engineering at the School of Engineering and Applied Science, Columbia University discusses her keynote on the development of silicon photonics for HPC ahead of her keynote presentation at ISC High Performance 2018 

Feature

Sophia Ktori explores the use of informatics software in the first of two articles covering the use of laboratory informatics software in regulated industries

Feature

Robert Roe discusses the role of Pistoia Alliance in creating the lab of the future with Pistoia’s Nick Lynch