Owkin, a French-American startup developing federated learning and AI technologies to advance medicine, this week launched the Covid-19 Open AI Consortium (COAI), with the aim of advancing collaborative research and accelerating clinical development of effective treatments for patients infected with the coronavirus. COAI will unite academic institutions, researchers, data scientists and industrial partners to fight the Covid-19 pandemic. All of it’s findings will be shared with the global medical and scientific community.
The first live research area will explore cardiovascular complications in Covid-19 patients in partnership with Capacity Covid, an international registry working with over 50 centers worldwide to generate open-access and license-free results. Other planned areas of research include other organ complications, patient outcomes and triage and prediction and characterization of immune response.
Pharma companies can get involved by sponsoring COIA’s research, by contributing their expertise in immunology or by supplying data, says Dr. Sanjay Budhdeo, Owkin’s Pharmaceutical Business Development Director.
While pharma companies normally like to safeguard their intellectual property and data,Budhdeo says the pandemic is prompting “ an openness from many actors within the health and tech ecosystem. It is not business as usual, the focus is on the speed of working rather than on protecting assets that companies would normally guard more closely.”
That said Budhdeo says COAI “equally recognizes that there may be concerns and we are flexible in our ways of working.”
Owkin’s technology powers the blockchain-based Machine Learning Ledger Orchestration for Drug Discovery (MELLODDY),an EU-grant funded project which trains machine learning on chemical libraries from ten pharma companies including Amgen, AstraZeneca, GlaxoSmithKline, Janssen, Merck and Novartis. Owkin is using federated learning to accelerate the drug discovery process by making it easier to identify promising compounds without having to pool data and while still preserving each company’s intellectual property, privacy, and control.
The Owkin Federated Learning technology used in the MELLODDY project could be deployed for other consortia. “Equally we see ways of working using cloud access to try and accelerate how we do things as long as biopharma companie and academic institutions are also open to that,” he says.
Budhdeo says there is an exciting opportunity to apply machine learning to finding not just an effective treatment for COVID-19 but to improve medical research in general.
Owkin is applying its technology to empower researchers in hospitals, universities, and pharmaceutical companies to understand why drug efficacy varies from patient to patient,enhance the drug development process, and identify the best drug for the right patient to improve treatment outcomes. Its proprietary platform, OWKIN Studio, uses machine learning technology to integrate biomedical images, genomics and clinical data to discover biomarkers and mechanisms associated with diseases and treatment outcomes.
The company, which was co-founded in 2016 by Dr. Thomas Clozel, a clinical research doctor and former assistant professor in clinical hematology and Gilles Wainrib, PhD, a pioneer in the field of artificial intelligence in biology, has raised $30 million in venture capital. It provides AI technologies to several of the largest cancer centers and pharmaceutical companies in Europe and in the U.S. It competes with Imagia on its federated learning offering, nference on Real World Access and with Tempus on AI and machine learning solutions.
You can access more of The Innovator’s Startup Of The Week articles here.