1st science competition’s ‘hits’ may treat familial Parkinson’s disease
7 molecules ID'd in Canadian nonprofit's new approach to drug discovery
In a new approach to drug discovery, seven molecules, or “hits,” that may treat familial Parkinson’s disease were identified in the first open science competition run by the Canadian nonprofit Conscience.
Launched with support from the global public-private partnership Structural Genomics Consortium (SGC) and a grant from the Canadian government, Conscience advances infrastructure to make artificial intelligence (AI) a viable tool for drug discovery. Its open-science approach refers to the practice of openly sharing data, information, tools, and research results without the constraints imposed by patents.
“Today’s results are a win for open science, for collaboration in drug discovery, as opposed to a patent-driven approach where scientists work in isolation from competing laboratories,” Ryan Merkley, CEO of Conscience, said in a press release.
“We can also celebrate the emergence of AI as a promising new tool for drug discovery. That’s what makes these findings – even if preliminary – so exciting,” Merkley said.
The CACHE Challenge series — fully, the Critical Assessment of Computational Hit-Finding Experiments — is Conscience’s first competition and is funded by The Michael J. Fox Foundation for Parkinson’s Research (MJFF). Participants in the competition use their computer-based methods to predict molecules that may treat disease, which are then tested experimentally by CACHE.
“We celebrate today the scientific achievements of CACHE participants around the world and experimentalists at the Structural Genomics Consortium who together discovered new chemical starting points for drug discovery,” said CACHE lead scientist Matthieu Schapira, PhD, from the SGC at the University of Toronto, in Canada. “These compounds have an entirely novel mode of action and may help explore new therapeutic strategies against Parkinson’s disease.”
CACHE Challenge aims to make AI a tool for drug discovery
Parkinson’s is a progressive neurological disorder that can cause slowness of movement, tremors, and walking and balance problems. It also is associated with depression, memory problems, and various other nonmotor symptoms. While approved therapies can relieve symptoms, they do not slow or halt disease progression or offer a cure.
Thus, finding treatments that can address the causes of the disease is a major goal for researchers — and especially, for people with familial Parkinson’s, in which patients have a family history of the disorder.
Mutations in the LRRK2 gene, which encodes a protein of the same name, are the most common genetic cause of familial Parkinson’s. Here, CACHE participants were invited to submit molecules that bind strongly to LRRK2 — and of the 2000 molecules submitted, seven were validated experimentally at the SGC.
An independent “hit evaluation committee” from companies then assessed the data to find the most convincing results. The procedure, which included a second round of predictions and experimental validations, took two years. Six of the winning molecules were submitted by laboratories at universities, and one came from a pharmaceutical company.
“Core to our mission is to accelerate discoveries that lead to meaningful new treatments for people living with Parkinson’s disease,” said Brian Fiske, co-chief scientific officer at MJFF.
“Working with partners like Conscience and their CACHE Challenge model is one way we have been able to tackle complex biology with innovative solutions,” Fiske said.
In an era where new therapies for many diseases have been scarce despite substantial investment, the CACHE Challenge provides an alternative, collaborative model for drug development.
Conscience also has made the entire dataset of the CACHE Challenge available to the public. Included are the chemical structures of all the molecules evaluated, as well as the applied computer-based methods. This transparency, the nonprofit notes, will allow the entire scientific community to benefit from the data and advance therapeutic development without being hindered by patents or proprietary limitations.
Further, this approach may improve the efficiency and cost-effectiveness of the drug discovery and development process, which can take years or even decades, Conscience noted in its release.
“The application of artificial intelligence within a collaborative open science model is bearing fruit,” said François-Philippe Champagne, Canada’s Minister of Innovation, Science and Industry, adding that “these principles have successfully yielded a promising discovery in the treatment of Parkinson’s disease.”
“We applaud Conscience’s commitment to this pioneering approach,” Champagne said.
Canada’s government in October awarded CA $49 million (about $36.5 million) in funding to Conscience.
In addition to Parkinson’s, four CACHE Challenges are underway for other conditions. Two are focusing on COVID-19, a third on cancer, and the fourth on obesity.
“In an era where new therapies for many diseases have been scarce despite substantial investment, the CACHE Challenge provides an alternative, collaborative model for drug development,” Merkley said.
An inaugural CACHE Symposium will be held March 6 and 7 in Toronto. Specialists in computer-based chemistry and AI will come together to share experiences about open science collaborations and developing AI tools for drug discovery.