Owkin open sources AI software Substra, releases two AI innovations at NeurIPS

The company is also releasing two open source AI innovations at NeurIPS 2022, the world's most prestigious machine learning conference.

The move marks the launch of a commitment to open science, through which Owkin intends to help universities, hospitals and pharmaceutical companies to benefit from its privacy-preserving, secure and collaborative AI technologies.

Owkin is open sourcing Substra, its federated learning (FL) software, to allow researchers and developers to collaboratively train ML models without the data leaving its source, powering scientific breakthroughs by overcoming data privacy and security barriers. The move will enable users to leverage a cutting-edge AI technology that has already proven its ability to improve the performance of ML models. Substra is hosted by the Linux Foundation, the largest open source foundation in the world. The LF AI & Data Foundation provides a neutral home for Substra based on open governance principles.

Substra underpinned the MELLODDY project, an unprecedented AI drug discovery collaboration uniting 10 pharmaceutical companies that demonstrated for the first time that collaborating in AI for drug discovery is possible at industrial scale. Substra is also powering the HealthChain consortium, a project enabling hospitals to develop collaborative AI models on diseases without the data leaving hospital firewalls. It is also being used in a landmark project to establish the human voice as a routine biomarker used to diagnose and treat diseases.

Owkin is also releasing two open sourced innovations tackling real-world machine learning problems, which have been accepted for publication at NeurIPS 2022. FLamby is the world’s largest open-source FL-ready dataset designed to help researchers conduct initial experiments on different data modalities and find the most effective approaches before deploying models on real data. Created by Owkin in collaboration with nine world-leading FL experts, FLamby is intended to help build a collaborative community that accelerates the use of FL in healthcare. FLamby is available on GitHub and will be presented at NeurIPS at 2:30pm on Friday, November 30th.

The second is SecureFedYJ – a solution to help normalize real-world healthcare data distributed across multiple data centres in a federated manner, without compromising on data privacy or security. Experiments on real healthcare data demonstrate that SecureFedYJ drives the same quality improvements as if the data was pooled in a central server. SecureFedYJ is available as a paper, which will be presented at NeurIPS at 9:30am on Thursday, November 29th.

‍

Mathieu Galtier, Chief Data Officer at Owkin, said:

The future of medical research is collaborative. By open sourcing Substra and releasing two landmark federated innovations to researchers, we hope to unleash a wave of collaborative research that will spur on the development of the next generation of treatments.

Owkin is committed to unlocking the vast potential held within patient data by developing technologies that overcome the privacy and security challenges that until now impacted research.

Ibrahim Haddad PhD, General Manager of the LF AI & Data Foundation, part of the Linux Foundation, said:

Innovation thrives in collaboration, not in isolation – and the open sourcing of Substra is a landmark moment in the use of collaborative AI in medical research. Researchers can now leverage privacy-preserving and secure federated learning software to drive cutting-edge collaborative medical research. Open source is undoubtedly the future of AI research.