Harnessing Preference Optimisation in Protein LMs for Hit Maturation in Cell Therapy
This work addresses the resource-intensive and high-failure-rate process of developing cell therapies like CARs for diseases such as cancer, though it is incremental as it builds on existing protein language models.
The researchers tackled the challenge of applying machine learning to immunotherapy development by fine-tuning protein language models on high-throughput experimental data, demonstrating that preference-optimized models show correlations with biological assays and can be used for few-shot hit maturation in CARs.
Cell and immunotherapy offer transformative potential for treating diseases like cancer and autoimmune disorders by modulating the immune system. The development of these therapies is resource-intensive, with the majority of drug candidates failing to progress beyond laboratory testing. While recent advances in machine learning have revolutionised areas such as protein engineering, applications in immunotherapy remain limited due to the scarcity of large-scale, standardised datasets and the complexity of cellular systems. In this work, we address these challenges by leveraging a high-throughput experimental platform to generate data suitable for fine-tuning protein language models. We demonstrate how models fine-tuned using a preference task show surprising correlations to biological assays, and how they can be leveraged for few-shot hit maturation in CARs. This proof-of-concept presents a novel pathway for applying ML to immunotherapy and could generalise to other therapeutic modalities.