The field of cell and gene therapy (CGT) has experienced significant advancements in recent years, witnessing a surge in both pipeline developments and approved products. Despite these strides, the CGT market encounters persistent challenges impeding its widespread adoption within the healthcare system. These challenges include limited comprehension of certain diseases, the intricate nature of therapies, and constraints in scaling up and optimizing manufacturing processes. In response to these hurdles, artificial intelligence (AI) and machine learning (ML) solutions are emerging, leveraging the progress in digital technologies and computing power. The objective is to analyze vast datasets, derive insights, and ultimately surmount obstacles hindering mainstream CGT adoption.
AI's potential impact on the pharmaceutical research and development (R&D) business model and investment strategy is expected to mirror its transformative influence on the traditional pharma industry, particularly in small molecule development and manufacturing.
The CGT ecosystem, encompassing major pharma, biotech companies, equipment manufacturers, software developers, and healthcare providers, has seen the rise of AI and ML technology vendors collaborating with CGT developers. These collaborations aim to address challenges through advanced data analytics and AI-based tools, offering new opportunities across the CGT value chain, from early R&D to post-commercialization.
One area where AI is poised to make a significant impact is in reshaping the pharma R&D business model. The historical paradigm of large pharma companies overseeing the costly and time-intensive end-to-end development of blockbuster drugs has evolved. Today, major innovation in drug discovery and early R&D is driven by smaller companies, while significant pharma players contribute investment and resources for clinical development and commercialization. This trend is observable in the CGT sector as well, with large pharma companies divesting early-stage R&D programs and partnering with or acquiring successful smaller entities. AI and ML are anticipated to accelerate early R&D, minimizing associated costs and risks. The integration of such technologies is crucial for small CGT developers seeking investment from risk-averse major pharma, fostering an increasing number of partnerships and expediting the development and commercialization of novel therapies.
Regulators play a vital role in responding to the rapid advancements in AI technologies within the CGT ecosystem. Major countries regulatory bodies have begun establishing guidelines and frameworks to safeguard against potential negative impacts of AI, such as protecting data privacy and preventing bias. Ongoing debates are expected to shape the evolution of AI-related laws and regulations, striking a balance between innovation and associated risks.
AI solutions can be applied across the entire CGT value chain, addressing challenges in early R&D, clinical trials, manufacturing and scale-up, operation, supply chain, and regulatory compliance. The potential applications of AI and ML in CGT are diverse, showcasing examples from the industry:
Acceleration of Early R&D:
AI and ML facilitate drug target discovery by efficiently handling complex molecular data. AstraZeneca, for instance, collaborated with an AI drug discovery company, BenevolentAI, to identify a novel target for idiopathic pulmonary fibrosis (IPF).
AI is also instrumental in optimizing delivery methods for gene therapies. Dyno Therapeutics, in collaboration with Google Research, developed an AI platform to design adeno-associated virus 2 (AAV2) variants with optimal immunity-evasion properties.
Acceleration and Facilitation of Clinical Trials:
AI aids in patient cohort identification for clinical trials, analyzing unstructured data from medical records. It can also generate synthetic control arms (SCAs) using statistical methods, reducing the time, costs, and ethical hurdles associated with control arms in clinical trials.
Optimization of Manufacturing and Scale-Up:
Digital twins and AI models simulate cellular and viral behavior in bioreactors, aiding in real-time optimization of manufacturing conditions. This approach enhances consistency in CGT products derived from living cells.
Optimization of Operation and Supply Chain:
Generative AI identifies inefficiencies in manufacturing processes and workflow by analyzing data related to process parameters, equipment settings, and product quality. AI also optimizes supply chain logistics, predicting disruptions and enabling contingency measures.
Supporting Regulatory Compliance:
AI accelerates regulatory submissions and time-to-market for novel therapies by automating document generation and extracting data from clinical trials. NLP and large language models semi-automate regulatory intelligence, reducing the manual effort required for compliance.
While AI holds tremendous potential for the CGT sector, challenges persist, necessitating ongoing exploration and adaptation. Stakeholders in the CGT space must recognize the advantages and opportunities AI presents, preparing comprehensive strategies for implementation, considering the transformative nature of adopting AI within organizational structures and operations. Subsequent articles will delve into the challenges that AI technologies in CGT still need to overcome.
