Skip to main content

Rx Data News: Impact of Advanced Data Technologies on Pharma R&D

Originally published in Rx Data News

Author: Jane Reed

Published: 19th June 2019

Jane Z. Reed, Ph.D, is the Linguamatics’ head of life science strategy and responsible for developing the strategic vision for Linguamatics’ growing product portfolio and business development in the life science market.

In his 2017 book “The Fourth Industrial Revolution,” Klaus Schwab describes how the fourth revolution is fundamentally different from the previous three. Each previous Industrial Revolution (IR) was characterised by advances in technology: iron and textile industries for the first, electricity-fuelled innovations for the second, digital technology for the third. 4IR builds on the digital revolution, embedding technology more deeply in society.

Schwab reasons that the underlying basis for 4IR is advances in connectivity and communication - and these advances are having significant impact on all industries, including pharma and healthcare. Access to huge amounts of varied data and the ability to connect, integrate, query and analyse these vast volumes is enabling radical changes in how we envisage drug discovery and delivery in the clinic.

If we take a step back and reflect, the pace of change we are seeing is amazing. For example, our understanding of the human genome has grown immensely over the past few decades. The first human chromosome was sequenced in 1999; the human genome published in draft in 2001.

Now across the globe there are national genome projects, such as the UK 100k Genomes project, the China 100k Genomes Project, the US “All of Us” research program, and more. These are all sequencing large numbers of whole genomes, aiming to connect the genomic data to other data types - clinical, wearable, scientific - in order to fuel innovations around health, wellness, and precision medicine.

Key components for these innovations include data integration and data analysis. In order to develop new therapeutics for the revolution promised by precision medicine, pharma companies need to be able to join up genomic data with clinical information, plus the landscape of knowledge around the natural history of a particular disease from scientific papers.

Tools and processes for data interoperability are critical; examples include use of standard ontologies to map data to suitable identifiers, the FAIR principles, and the increased adoption of cloud-based technologies, enabling research groups to access the most relevant and efficient technology.

As well as data integration, advanced analytics technologies are impacting R&D. We now have more data than the human brain could interpret in a lifetime, and are turning to AI technologies, applying algorithms and machine learning models to search for patterns and significant links. AI in early research isn’t new. Algorithms for sequence manipulation (BLAST, Clustal), methods in computational chemistry and QSAR, these have all been used for years.

But with the increase in genomic and clinical data, researchers can now start to develop models to investigate genotype-phenotype associations, cluster symptoms to understand rare disease, and correlate sequence and clinical data to pinpoint small patient populations where specific focused treatments will be effective.

It’s important to remember that each significant leap forward is actually composed of many tiny steps rather than a single major revolution. Using specific technologies to bring benefits in particular areas can move a particular drug project forward, or make an organization more efficient in work processes. Natural language processing (NLP) can assist in extracting the key data from unstructured text, and thus provide critical decision support. Within development (e.g., clinical, regulatory or safety), robotic process automation (RPA) can integrate into the daily lives of employees, reducing the burden of repetitive tasks, such as receiving, checking and filing case forms. So, connecting the data, communicating across teams, tailoring the analytics to the problem in hand, and taking small, but significant, steps in the right direction are all essential to ensure pharma can really benefit from 4IR.