Achilles Therapeutics plc says its newly developed AI application, trained with proprietary real-world data, outperformed current AI and non-AI methods for prediction of neoantigen immunogenicity in a recent analysis, enabling the identification of the most efficacious clonal neoantigens for existing cancer therapies. personalized.
Further details of the company’s AI-powered PELEUS bioinformatics platform are expected to be presented at an upcoming scientific meeting.
Of the large number of neoantigens initially identified in patient tumors, only a minority will elicit a T-cell response that is of clinical benefit. Achilles says it has developed an AI tool to enable the prospective identification of the most potent neoantigens. Newly trained and validated PELEUS neoantigen immunogenicity rating module with data from over 10,000 neoantigens from in-silico identification through extension and characterization of actual T cell clones.
With this new tool, the PELEUS platform can accurately predict which neoantigens are most likely to elicit a robust T-cell response, supporting the potential implementation of the platform into ongoing TIL-based clinical programs in advanced non-small cell lung cancer (NSCLC). and melanoma, and other modalities including clonal neoantigen cancer vaccines.
Personalized neoantigen approach
“We believe our “Target-to-T Cell” approach will be fundamental to unlocking the precision therapy potential of moving from our own T-cell approach with TIL-based neoantigen-reactive clonal T cells (cNeT) to a personalized neoantigen approach. We believe the key to accurate predictions, and thus the best neoantigens and related products, is to train your AI system on the highest quality data sets,” said Sergio Quezada, chief scientific officer of Achilles Therapeutics.
“The advantage of our patent-protected PELEUS platform in predicting clinically relevant clonal neoantigens with this new AI module has transformational potential, as a focus on the most potent antigens will drive long-term durable responses with multiple precision treatment modalities.”
Analysis conducted by the Bioinformatics & Data Science Team at Achilles shows that the PELEUS platform provides significantly improved rating performance when compared to currently used methods as measured by “Receiver Operating Characteristic Area Under the Curve” (ROC AUC). ROC AUC evaluates the performance of machine learning models to predict in vivo confirmed neoantigens.
The PELEUS AI immunogenicity rating tool was developed and trained using proprietary real-world data from patient material from the Achilles Material Acquisition Program (MAP), the ongoing CHIRON trial in patients with advanced NSCLC, and the THETIS trial in patients with recurrent or metastatic melanoma. AI methods are currently trained on publicly available data from sources such as the Immune Epitope Database (IEDB), a freely available resource funded by the National Institute of Allergy and Infectious Disease (NIAID).
Late last year, Achilles was awarded a US patent for the treatment of patients with immunotherapies, including vaccines, antibodies, and an autologous T-cell therapy approach, targeting clonal neoantigens identified using the Achilles Clonality Engine (ACE).