The Future of Drug Development: How AI and Data are Revolutionising the Pharmaceutical Industry

We’re thrilled to share insights from Dr. Zahra Rattray, Senior Lecturer in Translational Pharmaceutics at the University of Strathclyde. In this guest blog, Dr. Rattray explores how AI and big data are transforming the pharmaceutical industry, speeding up drug discovery, and enabling personalised treatments. From improving preclinical development to enhancing clinical trials, AI is paving the way for more efficient and effective drug development. Join us as we dive into the future of medicine and the role technology plays in shaping it.

The healthcare sector, particularly the pharmaceutical industry, is experiencing a seismic shift in the speed at which new lifesaving treatments are discovered. Since the advent of the Human Genome Project at the turn of the millennium, vast quantities of clinical and drug-related data have been captured. These large, information-rich datasets are gold mines for understanding patterns of health and disease, and the design rules that define what makes a safe and effective new medicine.

The integration of artificial intelligence (AI) and data analytics has not only accelerated drug development, but has also made the dream of safe and effective individualised medicines a reality. In this blog, I will explore examples illustrating how AI and big data are being harnessed to develop the next generation of medicines, from discovery to clinical trials and beyond.

The Power of Big Data in Drug Discovery

Traditionally, drug discovery has been a time-consuming (>10 years) and multi-billion-dollar process. Pharmaceutical companies have captured decades of know-how and internal data on successes and failures from their pipelines in the form of chemical libraries and clinical trial data. AI is changing the drug discovery paradigm by enabling academic and industrial researchers to analyse patterns from these vast datasets at unprecedented speed, so that they can predict and identify promising new drug candidates. This data-driven approach is also being used to identify patterns and correlations in the manufacture of medicines, enabling rapid process design, and the streamlined and continuous manufacture of medicines.

For example, AlphaFold is an AI-based tool developed by DeepMind that predicts the structure of proteins with high accuracy, which are common candidates as targets for drug development. These predictions allow researchers to simulate how potential drug candidates will interact with target proteins, significantly reducing the need for experiments in the laboratory and speeding up the discovery process.

“Data science and AI are transforming R&D, helping us turn science into medicine more quickly and with a higher probability of success. We are applying AI throughout the discovery and development process, from target identification to clinical trials, to uncover new insights to guide our drug discovery and development.” – Jim Weatherall, Chief Data Scientist, BioPharmaceuticals R&D, AstraZeneca

Enhancing Preclinical Development

Once promising drug candidates are identified, they must undergo rigorous testing before clinical trials to assess their safety and efficacy.

In this space, AI models have been used to predict how a drug will behave in the human body based on data from animal studies. These models help researchers understand potential side effects and optimise the design of medicines before progressing to clinical trials.

For example, AI algorithms for toxicity prediction can interpret chemical structures and biological data to predict the toxicity of new compounds, helping to identify and eliminate potentially harmful drugs early in the development process, thereby saving time and resources

Personalised Medicine

One of the most exciting advancements in drug development is the shift towards personalised medicine. By leveraging AI and big data, researchers can harness genetic, molecular, and lifestyle data from population level trends to design medicines tailored to individual patients.

Since 2006, the UK Biobank, a large-scale biomedical research resource with genetic and health information has collected biological and medical data from 500,000 UK participants aged 40-69. This database is regularly updated with additional data, and is accessible to researchers

AI can analyse the genetic makeup of patients to identify genetic mutations and patterns associated with specific disease types. This information can be used to develop targeted therapies that are more effective in certain patient populations with a particular genetic makeup. For example, researchers at Columbia University developed an AI tool called the General Expression Transformer (GET). This AI tool predicts how genes inside cells influence their behaviour, which has been successfully validated in genes associated with childhood leukaemia. Information from this study can now be used to develop new gene therapies for patients with leukaemia.

Another component of personalised medicine in which AI has been implemented, is optimising the dose of a drug for individual patients based on their genetic makeup, age, weight, and other factors. This application is particularly important to ensure that patients receive the most effective dose of a drug with minimal side effects.

From Bench to Bedside

Clinical trials are one of the most critical and expensive stages of drug development. AI and data analytics are streamlining this process, making it more efficient and effective.

AI can be used to analyse patient data to identify suitable candidates for clinical trials, ensuring that trials are designed appropriately with the right participants who will benefit most from the trial medicine. This not only speeds up the recruitment process but also improves the quality of collected data and trial success.

Adaptive trial designs can be implemented where the trial protocol is modified based on interim findings from the clinical trial. This flexibility allows researchers to make data-driven decisions in real-time, potentially reducing the duration and cost of clinical trials.

Summary and future perspectives

AI and big data are revolutionising the pharmaceutical industry, offering ways to discover, develop, and deliver drugs more efficiently and effectively. From accelerating discovery to personalising treatments, these technologies are transforming the development of next-generation medicines. AI and big data in drug development are beginning to deliver on their promise, with six companies leading the race to deliver AI-designed medicines, which are undergoing clinical trial evaluation. While these successes highlight the potential for AI, no AI-designed drug has yet completed the entire regulatory approval process. To remain viable and sustainable in the long-term, the use of AI in drug development raises several challenges, all of which require careful consideration.

Ethical questions surrounding data privacy and ownership of health-related data exist, and how these data could be exploited by privatised healthcare firms. Moreover, disparities in access to data-based technologies in developing nations and a lack of ethnically-diverse clinical data, increase the risk of bias resulting from AI implementation in drug development. Most clinical trials are conducted in healthy young adult males, which may lack relevance to female, paediatric, and geriatric patient groups. Such biases in drug discovery and clinical trial design could risk drug development efforts lacking real-world relevance to the global population, driving further health inequalities. The effectiveness of AI and data-based approaches is dependent on the quality and comprehensiveness of input data. Therefore, ensuring accurate, integrated, and standardised data has never been so important.

Interested in taking a deeper dive into Data, AI and Life Sciences? The Data Lab and The Scottish Universities Life Sciences Alliance (SULSA) are teaming up to deliver a programme of activity bringing together Life Sciences with Data & AI for the month of April. The programme aims to provide insights into cutting-edge research at the intersection of life sciences and data science being undertaken in Scotland. Creating an opportunity for industry, academics, students and staff in the SULSA network and TDL Community to make new connections. At the end of the programme SULSA and The Data Lab will launch our first joint Innovation Seed to support collaboration between industry and academia.

Events coming up in April: