Project Details
Project Description
Relinquished due to COVID-19 travel restrictions
In this project, we will conduct a joint study on the development of scalable and accurate computational methods for analyzing somatic mutations, which are critical signatures in the genesis, progression and treatment of cancers. Although many studies have been done on computational analysis of somatic mutations, existing methods typically use small training datasets of fewer than 5,000 variants and also limited numbers of cancer types, thereby limiting the application areas and scalability of the developed methods. In this joint project, we will develop a scalable, accurate and next-generation computational method using hybrid deep learning techniques, to characterize important and contributing heterogeneous features within each cancer type and significantly improve the predictive capability of the method across a range of cancer types.
In this project, we will conduct a joint study on the development of scalable and accurate computational methods for analyzing somatic mutations, which are critical signatures in the genesis, progression and treatment of cancers. Although many studies have been done on computational analysis of somatic mutations, existing methods typically use small training datasets of fewer than 5,000 variants and also limited numbers of cancer types, thereby limiting the application areas and scalability of the developed methods. In this joint project, we will develop a scalable, accurate and next-generation computational method using hybrid deep learning techniques, to characterize important and contributing heterogeneous features within each cancer type and significantly improve the predictive capability of the method across a range of cancer types.
| Status | Not started |
|---|