Drug discovery (DD) and development is currently a time consuming and expensive process with many small molecules in development failing in the later stages due to lack of efficacy or to toxicity. More complex mechanisms of action and stricter regulation have resulted in a drastic drop in pharmaceutical R&D productivity over the past 60 years. Only 11% of drug candidates that enter clinical phases make it to approval. As a result, it takes on average €1.9 billion to bring one successful drug to the market. This trend is unsustainable and requires innovative solutions.
The pharmaceutical industry is embracing the virtualization of parts of DD processes through Machine Learning (ML) as a promising approach to improve time and cost efficiency. The expected efficiency gains in DD critically depend on the predictive performance and chemical applicability domain of models that predict the biological activities of small molecules.
MELLODDY demonstrates how the pharmaceutical industry can better leverage its data assets to virtualize the DD process with ML technologies in answer to the challenges and stricter regulatory requirements it is facing. The lack of a tested, secure and privacy-preserving platform for federated ML that enables pharmaceutical partners to extract DD-relevant information from all types of, not only their own but even each other’s competitive data, without mutual disclosure of the chemistry and biology each partner has worked on, has previously held back such demonstration, to the detriment of patients in the EU and beyond.
At the end of our 3 year collaboration, MELLODDY has reached its overall project objectives of
● building a flexible, scalable, and secure platform for FL
● performing audit, stress-test, and an evaluation of the platform
● demonstrating sufficient privacy preservation to allow platform usage with sensitive/ competitive data
● demonstrating predictive performance improvement of models trained with FL
● demonstrating chemical applicability domain expansion of models trained with FL
The first period of the project was devoted to reaching the intermediate project objectives namely building, testing and auditing the platform. The second part of the project focused on demonstrating superior performance. By the end of year 3, we have demonstrated federated model superiority, further enhancing predictive performance in the final run through revising data inclusion criteria, and through platform and hyperparameter optimization.
The successful demonstration of the predictive benefits from unlocking the joint data volume of 10 pharmaceutical partners, while strictly preserving the privacy of all underlying data and the resulting predictive models, will shape best practices and translate into substantial efficiency gains in the DD process, and in the future, drug development. Finally, MELLODDY will prepare and exploit a service-for-fee vehicle to ensure the MELLODDY technologies are available to the rest of the pharmaceutical sector.
