By Dr Francesca Properzi, PhD. Research Manager, Centre for Health Solutions
Next week at the 2019 Global Financial Times Pharmaceutical and Biotechnology conference in London, we will formally launch the second in our series of reports on how artificial intelligence (AI) is driving the digital transformation of biopharma. This second report, Intelligent drug discovery: Powered by AI, explores the rise of ‘disruptive AI for drug discovery’ companies and the challenges and opportunities for biopharma in using AI technologies to help find new, more precise, targeted treatments.1 This blog highlights the key takeaways from our report.
Accelerating drug discovery
Drug discovery is the process of identifying new medicines for treating or curing human diseases. While drug discovery has led to many life-saving and life-enhancing clinical treatments, historically the process has also been long, expensive, and often unsuccessful, with many areas of unmet need still to be addressed.
The majority of drugs discovered during the 20th century were chemically synthesised small molecules, which still make up 90 per cent of drugs on the market today. Their advantages include simpler manufacturing and administration routes. They also have low specificity and a stable shelf life, meaning they are safe and effective for large groups of people. However, low specificity can also lead to side effects, reducing the chances of success in clinical trials.
Since the 1990s, scientific and technological advances have led to the discovery of larger, more complex, biological therapeutics (biologics), which are highly specific to their target. Biologics have invoked high levels of media and investor interest due to their innovative techniques and potential to cure previously untreatable diseases. In 2018, 17 of the 59 drugs approved by Food and Drug Administration (FDA) were biologics.
Despite the increasing pace of innovation seen over the past decade, the discovery and development of modern drugs remains long, expensive and largely unsuccessful. The average time to bring a molecule to launch is still 10-12 years (with 5-6 years accounted for by the preclinical, drug discovery process). In addition, the average cost of R&D for the top 12 biopharma companies in 2018 was $2.168 billion per drug – double the $1.188 billion calculated in 2010. At the same time, the average forecast peak sales per late-stage asset has declined to $407 million in 2018, less than half the 2010 value of $816 million. Consequently, the expected return on investment has declined from 10.1 per cent in 2010 to 1.9 per cent in 2018.
Finding new ways of improving the efficiency and cost-effectiveness of R&D is critical for the industry. One way to achieve this is by improving the accuracy, predictability and speed of drug discovery, which currently accounts for around a third of the above costs. Of the 10,000 molecules initially screened, only 10 make it to clinical trials. Moreover, the chance of success for a compound entering phase I trials, the first phase of clinical testing, is slightly under 10 per cent and has not increased in a decade. Given the growing cost of bringing a drug to market, a ten per cent improvement in the accuracy of predictions could save billions of dollars spent on drug development.
The rise of AI drug discovery disruptors
A number of AI-enabled solutions are emerging which are crucial for accelerating drug discovery. While these focus mostly on transforming the process of small molecule research, they are also showing potential in the identification of new biologics such as therapeutic antibodies against cancer, fibrosis and other diseases.
The potential of AI to improve the understanding of structures and specificity to the target molecules is due largely to the increasing amounts of structured and unstructured scientific data now available. The report includes a number of case studies that illustrate the five main challenges that AI for drug discovery companies are focusing their efforts:
- finding new diseases-associated targets
- screening of small molecule libraries to identify new drug candidates
- de novo design of new drug candidates
- drug optimisation and repurposing
- preclinical testing.
Key considerations for biopharma’s adoption of AI
AI algorithms extract concepts and relationships from data, and learn independently from data patterns, augmenting what humans do. AI also helps cross-referencing published scientific literature with alternative information sources, including clinical trials information, conference abstracts, public databanks and unpublished datasets. By mining such data, AI applications in drug discovery have already delivered new candidate medicines, in some cases in months rather than years.
If adopted at the drug discovery stage, AI solutions have the potential to kick-start the productivity of the entire R&D process. Biopharma companies should therefore develop robust strategies to integrate AI solutions into traditional processes. We have identified five key considerations to help the strategic adoption of innovation by biopharma companies (see Figure 1).
Figure 1. Five key considerations for the adoption of AI solutions
Source: Deloitte analysis.
The future of drug discovery: delivering ‘4P’ medicine
We believe that AI and other innovative technologies using data from multiple sources can enable more precise, targeted treatments that will help shift the health ecosystem towards a future where medicine is personalised, predictive, preventative and participatory (see Figure 2). This will also lead to new, more efficient and effective models of care. Over the next decade, these shifts will have a significant impact on treatments and on patient outcomes, particularly in areas of unmet need.
As the number of compounds identified using AI increases, drugs capable of treating specific pathologies will become available. This transition will open a new future for the health industry, as a higher level of knowledge on disease mechanisms increases the number of treatments available and, in many cases, cures diseases that have not previously had effective treatments.
To thrive, biopharma companies need strong AI divisions and a strategy for acquiring or collaborating with the best AI start-ups. Leaders with digital knowledge will need to integrate new strategies into research units. Agility and effective communication between departments with interdisciplinary skills in both business and technology will be a strategic asset.
Figure 2. Intelligent drug discovery to deliver ‘4P’ medicine
Source: Deloitte analysis.
By 2030, an increasing proportion of drug discovery will be done in silico and in collaboration with academia. The timings from screening to preclinical testing will be reduced to a few months and new potential drug candidates identified at increasingly lower costs, a transition that has already begun today.
Significant advances in the techniques used for drug discovery will evolve to provide the framework for precision medicine to become mainstream. Over the next decade, patients can expect these developments to have a significant impact on the effectiveness of their treatment options and on disease outcomes, particularly in areas currently with no treatments available.
1 Francesca Properzi, et al., Intelligent drug discovery: Powered by AI, https://www2.deloitte.com/us/en/insights/industry/life-sciences/artificial-intelligence-biopharma-intelligent-drug-discovery.html, accessed 7 November 2019.