Whenever you share your personal data with a platform or service (e.g. Facebook), there are at least two risks regarding data loss or exposure:
An attacker could explore and exploit technical vulnerabilities of the platform, gain access to your personal data, and steal it.
An attacker could explore and exploit publicly shared data to gain insights into your life.
In the MELLODDY project, we have very similar risks.
The MELLODDY project provides a unique platform for federated learning in drug discovery. Several pharma companies are contributing to its development, both to provide training data for the global model and to evaluate if the global model performs better than the one built solely on their data. As is common with machine learning models, the more data is fed into the platform, the better the global models tend to be. As a result, we decided to include an extra data source from the public domain which would augment the entire chemical space seen by the platform. This public dataset would also be relevant for development and testing purposes since it can be easily shared among the partners as opposed to proprietary chemical datasets.
In MELLODDY, several of the world’s largest pharmaceutical companies aim to leverage each other’s data by jointly training a multi-task machine learning model for drug discovery without compromising data privacy (or confidentiality). In this blog post, we are going to explain how this data is safeguarded.
MELLODDY is a unique project that aims at bringing together structure-activity data of ten pharma companies in a partnership to build a machine learning model aimed at accelerating R&D research without compromising intellectual property. The idea is based on the underlying concept of “big data”: If we can train models on larger volumes of data, the resulting models can become more complex and can achieve a higher predictivity.
One of the pillars of modern drug discovery is data-driven bioactivity modelling because it allows selecting potent and safe drug candidates. Additionally, even for a complicated disease where the exact mechanism is unknown researchers can use the bioactivity models to identify causally related pathways and proteins.
The 3-year Machine Learning Ledger Orchestration for Drug Discovery (MELLODDY) project Janssen is proud to co-lead, now a good year into execution, passed a critical milestone today: the launch of a first federated and privacy-preserving machine learning run across massive data sets from 10 major pharmaceutical companies, demonstrating technical feasibility. In anticipation of the results of the run, some have started wondering how this ambitious project came to life; the consortium recently received several questions about this. So let’s go five years back in time.
The MELLODDY consortium brings together 17 partner organizations of different types, working towards a common goal, in multiple countries with different cultures. The project is fully remote, with various businesses and technicals skills brought in by the partners. How does one develop transversality to a project in this context? How to create a common way of working in such an innovative and new collaboration endeavor? That is what Substra Foundation is trying to contribute to...
