Image: Cancer vaccine using AI technology with handprint and survivor ribbon / Nicole Bean Biospace
Immunotherapies have become a key therapeutic area within oncology. The global market size for this type of treatment was estimated at $118.9 billion in 2023, and is expected to double in the next decade. Many large pharma companies that own immunotherapies are now looking for combination therapies to enhance their efficacy, giving them an edge in a highly competitive space. This has led some companies to explore cancer vaccines, in combination with immunotherapies, to create more targeted therapies that enhance or enhance the immune response to cancer cells compared to immunotherapy alone. are
This approach has been aided by the rise of artificial intelligence and machine learning, which can digest data from cancer biopsies to design vaccines that target patient-specific mutations. The ability to target specific mutations for individual patients is not new. Targeted cancer drugs, such as anti-HER2 therapies and CDK4/6 inhibitors, have become big sellers for the industry. However, AI's ability to identify neoantigens from each patient's biopsy that are likely to prove an effective target for a therapeutic vaccine adds a layer of specificity and complexity to the process.
Development with AI
The use of AI has become a major talking point in many industries, and pharma is no exception. When combined with advances in tumor and blood biopsies, this has allowed cancer vaccine developers to home in on specific neoantigens as targets. Neoantigens are new proteins that appear on cancer cells when certain mutations occur in tumor DNA.
Merck and Moderna are working on an advanced cancer vaccine in the clinic, which they are investigating in conjunction with the immunotherapy Keytruda. “Mutations [detected in patient biopsies] can be fed into an algorithm that will predict which mutations are most immunogenic,” said Scott Ebbinghaus, vice president of clinical research at Merck. Biospace. “From there, we can synthesize an RNA designed to encode each mutated cancer gene, which can then be made into a protein and presented to the immune system. would be very close to unique for
Unlike treatments that are developed against a single, fixed antigen, the AI system being used by Moderna will try to optimize its selection of neoantigens. The algorithm examines the genetic mutations present in a patient's tumor and predicts which of the 34 neoantigens are most likely to trigger an immune response, Kyle Hollin, head of development, therapeutics and oncology at Moderna, explained in an email. of Biospace. “The algorithm has the potential to learn over time by combining clinical and immunogenicity data and will hopefully get better at selecting the most clinically active neoantigens,” Hollin said.
Ebbinghaus noted that certain neoantigens are likely to elicit stronger responses and therefore feature in individualized vaccines for more patients. This presented some challenges to Moderna and Merck when designing clinical trials, as it would not be possible to track the efficacy of an AI system and a cancer vaccine that was constantly changing as it learned from incoming data. To mitigate this problem, the algorithm was “locked down” before the start of clinical studies to prevent any changes to its calculations during the trials, Hollin said. Intense biotech.
Another company using an AI approach is Transgene, which has partnered with NEC Corporation to design an individualized treatment cancer vaccine. Instead of mRNA vaccines, transgenes are working with viral vectors to educate patients' immune systems against specific cancer targets. said Alessandro Riva, CEO of Transgene Biospace via email that NEC's AI-enabled neoantigen selection tool allows the company to identify the most immunogenic peptides for a given patient.
“Finding immunogenic mutations in a tumor is like finding a needle in a haystack. AI enables us to analyze an incredible amount of data. Screen more than 10 parameters, such as HLA binding, antigen processing or RNA expression. ; adjust their weights based on the data and suggest a list of relevant neoantigens in a very short time,” explained Reva. “The beauty of this approach is that it can be applied to most solid tumors, as long as they show meaningful mutations.”
Transgene is responsible for selecting the “most suitable” neoantigens discovered by NEC's tool before developing patient-specific genetic cassettes, Reva said. Transgene enrolled the first patient in the second part of a Phase I/II trial for its lead therapeutic vaccine, TG4050, in early June, with the final patient expected to enroll by Q4 2025. An additional Phase I trial has also been scheduled. Launch for another, undisclosed signal in 2025, Reva added.
Communication with regulators
With cancer vaccines now reaching later-stage trials, one of the challenges is managing potential products. The FDA has prioritized some of the discussions in this area by issuing a guidance document on the topic of clinical considerations for cancer vaccines. One area covered in the document is multi-antigen vaccines; The agency says that each component of these jobs does not need to be individually tested for safety and performance. However, the document says it will be “considered on a case-by-case basis.”
An FDA spokesperson provided an emailed statement. Biospace About the agency's work on AI approaches to new treatments. “The FDA recognizes the potential of AI/ML to enhance the development of personalized treatment approaches. While we cannot predict future developments, AI/ML can be used to learn from real-world feedback and data analytics. The capabilities of ML software are an important component of scientific advances that can lead to the development of new products across a wide range of treatments,” the spokesperson said.
When asked about the regulatory process for a potential transgene cancer vaccine, Reva responded that it would be similar to the FDA's guidance on cell and gene therapy. He added that the expectation is that approval would be based on a process that would be applied to all patients rather than a single, immutable product.
Moderna declined to comment on regulatory expectations for its cancer vaccine. First, Hollin said Intense biotech that the company expects to submit its algorithm to the FDA as part of the approval process; Merck and Moderna's cancer vaccine, mRNA-4137 (V940), has entered Phase III studies and has been granted Breakthrough Therapy designation by the FDA, so regulation of such individualized treatments remains open. Questions will need answers soon.
Ben Hargreaves is a freelance science journalist based in Tosse, France. Reach out to her on LinkedIn.