If you have an ACS member number, please enter it here so we can link this account to your membership. (optional)

ACS values your privacy. By submitting your information, you are gaining access to C&EN and subscribing to our weekly newsletter. We use the information you provide to make your reading experience better, and we will never sell your data to third party members.



Group targets a platform for collaborative data management in drug discovery

Drugmakers apply machine learning and blockchain technologies to a data access network

by Rick Mullin
June 4, 2019


Photograph of a man, Hugo Ceulemans, working at a copmuter in his office.
Credit: Janssen Pharmaceuticals
Hugo Ceulemans, scientific director for discovery data sciences at Janssen Pharmaceuticals, leads the Melloddy project.

A newly-formed consortium of pharmaceutical companies, academic researchers, and technology suppliers has announced a three-year, $20 million project that will apply machine learning methods and block-chain security techniques to data management in drug development. The Machine Learning Ledger Orchestration for Drug Discovery (Melloddy) project aims to facilitate sharing of data from chemical libraries among competitive drug firms.

“This project allows the pharma partners for the first time to collaborate in their core competitive space, invigorating discovery efforts through efficiency gains,” says Hugo Ceulemans, scientific director for discovery data sciences at Janssen Pharmaceuticals and Melloddy project leader.

With funding from the Innovative Medicines Initiative, a partnership between the European Union and the European Federation of Pharmaceutical Industries and Associations, the consortium plans to develop a machine learning model that will allow for the extraction of data from multiple databases without the creation of a common databank, an application of artificial intelligence known as federated learning.

The platform is also designed to prevent proprietary information from leaking from one data set or model to another.

Block-chain technology, which establishes an encrypted ledger managed collectively by partners in a network, will be used to ensure data security. The ledger is permanent and traceable. “The goal is to harness the collective knowledge of the consortium,” says Mathieu Galtier, a project manager at Owkin, the firm providing the block-chain software. The partners envision a collaborative platform for identifying the most effective compounds for drug development, “while protecting the intellectual property rights of the consortium contributors,” says Galtier.

The pharmaceutical companies partnering on Melloddy—Amgen, Astellas, AstraZeneca, Bayer, Boehringer Ingelheim, GSK, Janssen Pharmaceutica, Merck KGaA, Novartis, and Institut de Recherches Servier—are joined by academic partners KU Leuven and the Budapest University of Technology and Economics in the consortium. The five technology participants in the group include Owkin and Nvidia, a supplier of large scale artificial intelligence computers.

Another pharmaceutical industry consortium, the Machine Learning for Pharmaceutical Discovery and Synthesis, hosted by the Massachusetts Institute of Technology, has focused on artificial intelligence techniques for drug discovery. The group has developed machine learning based tools for retrosynthesis, tools and algorithms for property prediction, and tools for generating new molecules with desired profiles. Its members include Amgen, BASF, Bayer, Lilly, Novartis, Pfizer Sunovion and GlaxoSmithKline.



This article has been sent to the following recipient:

Chemistry matters. Join us to get the news you need.