BenevolentAI & Helix Group at Stanford University Announce AI Collaboration

Scientific researchers are generating more data than ever before. There is an immediate need to extract information from this data to discover better medicines, faster. Our partnership with BenevolentAI aims to represent this information more precisely, to enhance the downstream target and drug predictions made by machine learning models, and ultimately help scientists translate algorithmic advances into medical breakthroughs.

Prof. Russ Altman, Professor of Bioengineering, Genetics, & Medicine at Stanford and Director of The Helix Group

BenevolentAI and Helix Group at Stanford University have announced an AI research collaboration. The partnership aims to discover more effective methods to extract knowledge from biological and clinical information and extend the potential of AI to help scientists discover and develop better medicines. BenevolentAI and Stanford University are leaders in using AI to tackle the biggest challenges in biology and medicine. By pooling their collective experience they hope to advance state-of-the-art research.

Collaboration Highlights

• The AI research partnership looks at the role of context in information extraction, with an emphasis on more granular, precise and high-resolution representations of biomedical information 
• The researchers have observed the importance of modeling biological context to refine/extract more nuanced and accurate PPI networks/interactions
• Moving forward, the two teams will expand the scope of the collaboration to include document-level features and create context-specific networks

Both BenevolentAI and Stanford have a strong track record in using AI to tackle some of the biggest challenges in biology and medicine. Through this partnership, researchers from the two organisations have pooled their expertise in AI, natural language processing and creating knowledge graphs to reason about drug discovery, with the aim of finding more effective methods to extract knowledge from biological and clinical information. The research focuses on the role of context in information extraction, and aims to represent information more precisely in order to enhance the downstream target and drug predictions made by machine learning models.

The Helix Group uses data at all scales to understand the drug response. They study drugs acting alone and in combination with other drugs. At the molecular level they study protein 3D structure and chemical interactions. At the cellular level they study expression and cellular interaction networks. At the organism level they study the human response to medications in clinical and research setting. They also leverage population-level data to look for large-scale trends in drug response.

The Helix Group at Stanford University

Using AI to Improve Drug Discovery

Using AI in Drug Discovery has great potential and many challenges. AI can extract information from literature and data, in the form of relationships between biomedical entities such as genes, chemicals and diseases. The characteristics of these relationships, often appear contradictory. This may be because the relationships are contingent on the biological context in which they occur.

BenevolentAI and Stanford will focus their research on the role of context in information extraction. The teams are planning to develop a state of the art context extraction model, which will add more confidence and accuracy to machine learning models used to identify novel drug targets and therapeutics. They plan to develop a state of the art context extraction model. They will use this to create context-specific regulatory networks across the entire PubMed biomedical manuscript collection which will add more confidence and accuracy to machine learning models used downstream in the drug discovery process.

BenevolentAI Pipeline

BenevolentAI has a growing in-house pipeline of over 20 drug programs spanning from target discovery to clinical studies and maintains commercial collaborations with leading pharma companies. BenevolentAI also identified Eli Lilly's baricitinib as a repurposing drug candidate for COVID-19, which has been authorised for emergency use by the FDA. BenevolentAI is headquartered in London, with a research facility in Cambridge, and offices in New York.

Subscribe and Comment

I'm interested in your feedback - please leave your comments. To subscribe please click subscribe at the top of this article.

Copyright © 2022 Margaretta Colangelo. All Rights Reserved.

This article was written by Margaretta Colangelo. Margaretta is Co-founder of Jthereum. She serves on the advisory board of the AI Precision Health Institute at the University of Hawaiʻi Cancer Center. She's based in San Francisco 

Twitter @realmargaretta