1. In Silico Predictive Analytics: Accelerating Identification of Potential Diease-Modifying Compounds for Parkinson’s Disease

150 150 Techna Symposium

Chen 1, N. Visanji 2, A. Lacoste 3, S. Spangler 4, S. Ezell 5, C. Marras 2, L. Kalia 1,2
1 Krembil Research Institute, University Health Network, Toronto, Canada
2 Toronto Western Hospital, Morton and Gloria Shulman Movement Disorders Centre and Edmond J. Safra Program in Parkinson’s Disease, Toronto, Canada
3 IBM, IBM Watson Health, New York, USA
4 IBM, IBM Research, San Jose, USA
5 IBM, IBM Global Business Services, San Francisco, USA

To use IBM Watson for Drug Discovery (WDD) to identify compounds that may reduce α-synuclein (aSyn) oligomers and are amenable to drug repurposing for Parkinson’s disease (PD).

We developed a training set of 15 chemical compounds known to reduce aSyn oligomers in vitro and/or in vivo, and a candidate set composed of 620 individual active compounds in the Ontario Drug Benefit program (ODB) database. WDD analyzed hundreds of thousands of Medline abstracts to learn text patterns and develop a semantic fingerprint for each compound, then used machine learning to generate a predictive model to rank compounds from the candidate set based on semantic similarity to the training set.

Leave-one-out cross-validation demonstrated that each compound in the training set was highly ranked by the model, suggesting that highly ranked compounds from the candidate set have properties common to the training set. Following ranking of candidate compounds, PubMed searches and exploration using WDD applications for the top 52 compounds revealed: 9 compounds with existing evidence for inhibition of aSyn aggregation (4 of which have not yet been studied in human clinical trials or epidemiological studies of PD), and 12 compounds not previously associated with aSyn but with biologically plausible links to aSyn aggregation.

Our approach using WDD to rank compounds with potential to reduce aSyn oligomers is novel and promising. Future work will include validation studies in which prioritized compounds will be tested using in vitro and in vivo models of aSyn aggregation and toxicity. Specifically, compound efficacy in vitro will be evaluated using a cell-based protein fragment complementation assay of aSyn oligomer formation, and in vivo studies will measure aSyn-mediated motor dysfunction in Caenorhabditis elegans. Further work to validate WDD predictions will include epidemiologic studies using the ODB database to assess incidence and outcomes in PD.