The healthcare and biotechnology sectors are benefiting from remarkable developments through AI ranging from breakthrough applications in identifying high-risk heart patients through to protein structure prediction with DeepMind’s AlphaFold. Cell therapy stands out as a particularly promising field – AI can streamline research and development, enhance manufacturing processes, de-risk and de-cost regulatory testing and approval, and substantially reduce overall cell therapy development duration and costs.
Cell therapy offers hope for treating previously incurable conditions, but there are still several obstacles currently limiting its widespread adoption. Manufacturing faces significant challenges in scaling up production without compromising quality and consistency. There are also further constrains, like lengthy testing protocols for new therapeutic candidates and rigorous regulatory requirements. On top of that, there is a need for specialised infrastructure and advanced equipment that drives up the production expenses. This is clearly illustrated by Novartis’ Kymriah CAR T-cell therapy which was priced at $475,000 back in 2017, putting such a therapy out of reach for many who need it most. Future cell therapies are projected to cost much more.
AI could help address these challenges and reinvent cell therapy as an industry by transforming how we develop, produce, test, approve and deliver cell therapies.
AI is set to transform cell therapy
The unique benefits of using cells as drugs come from the fact that they are alive – cells can grow, migrate, change or perform diverse functions and locate targets within the body with exquisite precision, and in general perform sophisticated biological functions simply impossible to achieve with conventional drugs. This makes them singularly positioned to treat or potentially cure in entirely new ways complex conditions like cancer, autoimmune disorders and degenerative diseases that often resist conventional treatments. Yet these same properties can also create significant challenges. Understanding and controlling how cells behave, from their responses to different environments to their growth patterns and interactions with other cells, is crucial to developing reliable cell therapy productions. This is where AI steps in.
Firstly, traditionally cell therapy research is time-consuming and expensive, often taking years of laboratory research and substantial financial investment to find a viable candidate asset. AI can speed up this process dramatically by significantly accelerating and improving cell quality control and analytics leveraging large multimodal datasets, enabling to predict and optimise cell quality and behaviour, identifying novel approaches to therapeutic design, and helping automate and accelerate manual work.
In addition to this, the regulatory landscape for cell therapies requires extensive testing – often over many years. AI can track and organise massive amounts of data and can ensure traceability and compliance throughout manufacturing processes. Developing cell therapy generates massive amounts of multimodal information data and by leveraging AI, it could be possible to substantially derisk and reduce the time spent on regulatory submissions, testing and approval, and ultimately cut down on costs of resulting drugs.
AI can also help advance the development of personalised treatments. By analysing individual genetic profiles, medical histories, and molecular data, AI can help design highly targeted cell therapies tailored to specific patient characteristics or indeed cell therapies developed using a patient’s own cells. For example, AI could identify the most suitable matching cells to use for a particular patient, predict how a patient’s immune system might respond to certain therapies, and determine the best conditions for cell differentiation into pure, stable target cells, ensuring the therapy is not only effective but also minimally toxic and invasive.
By tailoring cell therapies to the unique needs of each patient, it could be possible to reduce the likelihood of adverse reactions and ensure that therapies are more likely to succeed and lead to long-lasting improvements. This personalised and precision approach could therefore significantly increase treatment efficacy and move definitively beyond the traditional one-size-fits-all approach.
Breaking down AI application barriers
Despite its huge potential, to fully harness AI’s benefits for cell therapy there are several challenges that must be overcome.
Integrating AI into existing biotech and pharma systems has proven to be complex. For companies not built with AI at the core, adoption can be slow as AI approaches often cannot directly be applied to existing data assets or processes and deliver immediate results and requires careful integration and adaptation.
This is particularly evident in large pharmaceutical companies, where established processes and legacy systems can make incorporating AI difficult. By contrast, startups and smaller biotech firms tends to have greater flexibility, allowing them to adopt AI easier and from the outset and embed it directly into their workflows. This difference highlights how organisational structure and agility play a critical role in successfully leveraging AI.
With the recent Nobel Prizes in Physics and Chemistry awarded for work in AI, there is a generational opportunity to reinvent the bio/healthcare industry as a whole and that is certainly the case for cell therapy. To do so the industry needs to embrace and proactively implement changes needed to fully capitalise on this opportunity, like upgrading or acquiring their high-performance computing infrastructure, improving and extending the quality, depth, curation, organisation and annotation of datasets to enable effective algorithm training and deployment and generation of enhanced predictive power and insights. In the case of cell therapy, such data is still only in its infancy, and tends to be scattered and disconnected, which creates roadblocks for AI systems to be effectively deployed.
Furthermore, scaling up cell therapy from research labs to clinical production will require the development of AI approaches that can enable and optimise scaling up processes. As production grows, many factors change – from manufacturing conditions to supply chains and patient populations. The goal will be to develop AI-powered strategies that are sophisticated enough to handle these changes while maintaining accuracy, robustness and optimality.
Finally, when it comes to regulation, using AI in healthcare requires thorough validation of the new technology. This is challenging given the speed at which AI is advancing, because the pace of regulatory updates may not always keep up. The ongoing development of regulatory frameworks may create transient uncertainty for companies integrating AI.
Last April, the UK’s MHRA released a white paper on strategic approach to AI for medical products, and in the US, last month the FDA issued the first draft guidance to support regulatory decisions on AI’s use to establish drugs and biological products’ safety, effectiveness and quality. These are both important steps towards establishing and understanding how to support and regulate AI-enabled medical products.
Both of these illustrate the active and pressing discussion taking place within regulatory agencies across the globe to both define a path ensuring that this new way of developing therapeutics meets robust scientific and regulatory standards while recognising and seeking to maximally embrace the potentially step-changing power of AI-enabled therapeutics.
A transformative future
AI and cell therapy are both revolutionising the bio/healthcare space and are poised to power an entirely new generation of breakthrough medical treatments. With AI’s help, we will be able to develop and produce cell therapies faster, better and more affordably, while simplifying the testing and approval processes, and ultimately deliver more medicines accessible to all to treat or potentially cure hitherto untreatable or incurable diseases.
