Develop tools that use genetic data to better classify complex human diseases

ongoing

Many common diseases are highly heterogeneous, meaning that two individuals can be diagnosed with the same disease but have very different progressions or respond very differently to the same medication. These heterogeneous diseases affect a sizeable proportion of the population. For example, approximately one in four people will develop a heterogeneous brain disorder (e.g., a neurological condition such as epilepsy or Parkinson’s Disease, or a psychiatric condition such as depression or schizophrenia) To effectively treat a patient with a heterogeneous disease, it is necessary to quickly and accurately identify their subtype. At present, patient subtypes are decided using only clinical observations, and the process is highly suboptimal. For example, the available subtypes are often incomplete or poorly-defined, meaning that many patients are wrongly classified or can not be classified at all. Previous research indicates that for many heterogeneous diseases, the classification of patients can be improved by incorporating genetic information. However, for this to become a reality, requires statistical tools that do not yet exist. My project will develop novel statistical tools for classifying heterogeneous diseases based on genetic information. My project will prioritize classification of two heterogeneous diseases: epilepsy and schizophrenia. However, I will ensure that my new tools are general, freely available and easy-to-use, so that other groups can construct classification models for many other diseases. Overall, my project has the potential to revolutionize how patients with heterogeneous diseases are treated, and to facilitate more widespread use of precision medicine.