Fortanix and Nvidia enhance AI model accuracy in drug discovery with Xeureka

A brand new report out today from Intel Corp.-backed multicloud security firm Fortanix Inc. details how Xeureka Inc., a subsidiary of Mitsui & Co. Ltd., has leveraged Fortanix’s Confidential Computing technology to boost artificial intelligence model accuracy and reduce drug discovery time and costs.

Since rapidly taking off in 2022 with the discharge of OpenAI’s ChatGPT, AI has offered great promise across various areas and drug research is one in every of them. By harnessing the facility of AI, pharmaceutical corporations can analyze vast datasets with speed and accuracy, potentially resulting in the invention of latest drugs at a small fraction of the normal cost and time.

Xeureka goals to make use of computer technology across all points of drug development to enhance the efficiency and effectiveness of latest drug research. Using AI technologies is claimed to be core to its mission, requiring extensive data sets to power the AI models. Nonetheless, the information utilized in pharmaceutical research often includes highly confidential, sensitive and personally identifiable data, while stakeholders must comply with various global privacy regulations.

To tackle the information use issue, Xeureka has partnered with Fortanix and Nvidia Corp. to reveal the power to integrate disparate datasets from multiple sources while maintaining the safety and confidentiality of the unique sources. Through the partnership, Fortanix provides a control plane to enable security policy management and orchestrate the usage of highly confidential data in a secure environment.

Fortanix’s Confidential Computing capabilities include policy management and orchestration of highly confidential data in a secure environment. Additionally they include data sharing and access control for fast and collaborative data processing that ensures privacy for multiple parties without revealing sensitive information.

Modern key management provides unified encryption regardless of information location across hybrid multi-cloud environments and workflow management defines, manages and tracks the information collaboration process flow to make sure privacy and security guardrails are maintained.

Nvidia’s contribution includes secure enclaves and confidential computing graphics processing units for the execution environment. Within the environment, data, algorithms and AI models are run to ensure that highly sensitive data assets remain secure and personal while in use.

Through the partnership with Nvidia and Fortanix to enable confidential data collaboration, Xeureka has improved AI model accuracy from 65% to 74%, reducing the time and costs related to drug discovery. Fortanix also notes that it’s also a proof point for a way AI can enhance the effectiveness and efficiency of latest drug development while improving the lives of tens of millions of individuals across the globe.

“This can be a perfect example of the facility of confidential computing — rapidly processing extremely large volumes of real patient data required by AI models with the best level of privacy and security possible,” said Anand Kashyap, co-founder and chief executive of Fortanix.

Image: Fortanix