Data visualization has a long history. During the Crimean War in the 19th century, Florence Nightingale worked with a medical statistician to use data to create a polar area chart that showed many more soldiers were dying from preventable diseases than from battle wounds. Nightingale’s use of statistics and visual diagrams helped to change health policies and practices for military hospitals from the 1850s onward.
Today, data visualization plays a crucial role in many fields, from agriculture to financial management. In drug discovery, data visualization can help to reveal hidden patterns and trends. It can also support collaboration, increase transparency, and create narratives around scientific information that can communicate important facts to a wider audience, including the general public.
Here are some of the benefits of data visualization in drug discovery, including small molecule design:
Identifying patterns and trends
Data visualization can reveal patterns in data that are hidden using traditional methods. Using machine learning (ML) and other technologies, early drug discovery teams can use data visualization for lead discovery and optimization. Computer-assisted drug design (CADD) and in-silico processes would not be possible without data visualization tools.
Since the mid-2000s, various biopharma businesses and government organizations have used data mining and data visualizations to uncover adverse drug reactions (ADRs). Data visualization can benefit in-silico models of potential ADRs.
In the past, this type of data monitoring uncovered problems with the diet drug fenfluramine-phentermine (fenphen), resulting in its removal from the marketplace. In the public sector, data mining of public forums and social media can uncover early instances of ADRs. The power of contemporary data mining and visualization can speed the process and save lives.
Knowledge graphs can help teams who work in different groups located in different areas around the globe to visualize connections between their work. For example, the Clinical Knowledge Graph (CKG) is an open-source platform that illustrates about 220 million relationships covering relevant experimental data.
The CKG uses a flexible data model that incorporates statistical and machine learning algorithms to create data visualizations that support broad international collaboration and cooperation in the biosciences.
Sophisticated data visualization and collaboration tools can create trusted collaborative environments (TCEs) which support the essential concepts of transparency, data security, and an audit trail. TCEs provide protection for proprietary algorithms and for proprietary data and processes while enabling collaboration and advancement of individual team progress and the benefits of collaborative and cooperative research and investigation.
Increasing trust and transparency
Have you heard the phrase, “a picture is worth a thousand words?” Drug discovery is a highly technical process filled with numbers and terminology that members of the general public are unlikely to understand. Data visualization can help to communicate important concepts to the public in an understandable, transparent way.
In the United Kingdom, the Association of the British Pharmaceutical Industry (ABPI) is formally launching an initiative to use data visualization to show the public how pharmaceutical companies are committed to being transparent and responsive to the public’s needs.
Helping researchers to tell a story
Companies can harness the power of data visualization to tell the story of their drug discovery process. Peter Chobanian, the director of Marketing Analytics at Ogilvy Health, told PharmaVoice that he uses data visualization to create compelling data stories that involve people. Data visualization can help your business to identify and present the data about your drug discovery processes that will resonate the most with the public, investors, or business partners.
How You Can Use Data Visualization In Your Research
Today’s fast-paced scientific research environments are far from the early pen-and-paper methods of 19th century healthcare pioneers like Florence Nightingale. Today’s biopharma professionals work with millions of data points.
Data visualization in the drug discovery sector seems here to stay, and the growing challenges we face see us dealing with more data than ever before. Despite this, techniques are constantly evolving and improving, helping not just scientists and researchers but all stakeholders in the broader drug discovery ecosystem visualize data like never before.