University of Hong Kong Develops ClairS for Enhanced Cancer Mutation Detection
The University of Hong Kong's School of Computing and Data Science has developed ClairS, a deep-learning algorithm designed to improve the detection of cancer mutations using long-read sequencing. Led by Professor Ruibang Luo, the research team has tested ClairS on datasets from breast cancer, lung cancer, and melanoma, demonstrating high accuracy across various cancer types. ClairS addresses the limitations of existing methods that struggle with structurally complex regions of the human genome by utilizing long-read sequencing. This innovation allows for the generation of synthetic tumor-normal data, providing a virtually unlimited number of realistic training examples. ClairS has been integrated into Oxford Nanopore Technologies’ somatic variant-calling workflow, marking a significant advancement in clinical genomics.