Drug Discovery and Trials Optimisation

Despite a concerted and sustained international research effort into developing and testing disease-modifying therapies for dementia-related neurodegenerative diseases, none have been identified. There are a small number of treatments for Alzheimer’s Disease that can produce short-term cognitive relief, but the disease continues unabated. This working group foresee interest in applying data science methods to clinical trial recruitment as well as computational drug discovery.

Clinical trials aim to recruit at-risk individuals who would potentially benefit from an experimental drug. Identifying the right people at the right time in a heterogeneous disease process for a clinical trial is a challenge well-suited to advanced statistical methods, using multimodal data from large cohort and population studies. Such approaches promise the precision that seems to have been thwarting clinical trials to date. Explicit opportunities for optimising clinical trials using data science and related methods include making more out of (publicly) available data, and improving the state of the art in precision understanding and forecasting of dementias. The former lends itself naturally to methods from traditional data science (e.g., gradient boosting for feature selection/weighting) and AI (e.g., feature generation from neuroimaging data). The latter is an active area of research that will benefit from large multidisciplinary collaborative initiatives leveraging available data. 

The application of computational biology and bioinformatic strategies for large scale data analysis also provides the potential to greatly advance CNS research into disease mechanisms, identification of new therapeutic targets in dementia and prediction of efficacy and safety of new and existing drugs. Early supportive evidence in human data of a therapeutic target may also mitigate the risk of a drug translating through to the clinic. Multimodal data from large cohort and population studies collated through a variety of sources, including from within the DEMON network, will be evaluated through cutting-edge bioinformatics technology and novel computational methodology to fulfil a global mission of identifying new or better therapies. By partnering with interdisciplinary organisations, the promise is to then facilitate a dynamic translation and validation of findings from in silico to in vitro and in vivo models.

By building a large network of collaboratively-minded scientists and clinicians having broad expertise across all facets of dementia research, the DEMON Network is well placed to have a significant impact upon clinical trials and drug discovery in dementia.