A Canadian non-profit drug discovery organization called Conscience, which was launched last year with catalytic funding from the Canadian government to pioneer a new “open-science” approach to drug discovery, has announced that its first scientific competition has resulted in the identification of seven promising molecules, or “hits,” that show potential for new, more effective drugs for familial Parkinson’s disease.
The Michael J. Fox Foundation funded this initial CACHE (Critical Assessment of Computational Hit-Finding Experiments) Challenge, and the Structural Genomics Consortium at the University of Toronto evaluated the (mostly) AI-predicted small molecules in the lab to assess for their action against the CACHE Challenge’s target protein, which is linked to Parkinson’s disease.
Parkinson’s disease, which affects 8.5 million people, can cause tremor, slowness, stiffness, and walking and balance problems among its symptoms. Current treatments offer symptom relief but do not halt its advance or offer a cure. Contributing factors include a combination of genetic and environmental factors.
Conscience is attempting to enable global drug discovery and development for emerging, rare or complex diseases – ones for which the pharmaceutical industry/market has failed to provide drugs for patients. A prominent example is with inquiries into Parkinson’s disease and the application of artificial intelligence to scrutinise large and complex drug-related data sets.
From the study, all data from the challenge will be public. This will include the entire experimental data set from this CACHE Challenge, including the chemical structures of all the molecules tested and associated computational methods.
These data will be made available on the basis of open science and patent-drive approaches Conscience are committed to an “open science” approach to drug discovery, as opposed to a patent-driven approach where scientists work in competition with their peers from other laboratories.
It is hoped that the data released will enable better drug-discovery AI algorithms. By comparing dozens of computational methods against the same target protein, the CACHE Challenge provides a consistent benchmark and sheds light on the most effective AI-generated, hit-finding algorithms.
By analysing large datasets of drug and patient data, AI algorithms seek to identify potential side effects of existing drugs that may have therapeutic value for other diseases. This may include the use of an existing drug used to treat a particular condition may have side effects that could be useful in treating a different disease.