Scientists at Klick Applied Sciences have created an artificial intelligence framework that can rapidly identify new use cases for existing therapeutics, according to findings presented Friday at the NeurIPS conference that could greatly improve the drug repurposing process and transform the pharmaceutical industry.
The team debuted their algorithm, called LOVENet, a Large Optimized Vector Embeddings Network which integrates two cutting-edge AI technologies: large language model (LLM), and structured knowledge graph technology, which mathematically represents the relationships between drugs and diseases to offer a fresh perspective on new potential therapeutic applications.
Drug repurposing, the practice of identifying new therapeutic indications for existing drugs, has long been an area of interest due to the time and cost constraints associated with traditional drug development. Some reports estimate about 30 to 40 percent of new drugs and biologics approved by the US Food and Drug Administration (FDA) can be considered repurposed or repositioned products.
Jouhyun Jeon, lead scientist and principal investigator at Klick Applied Sciences, said LOVENet is designed to address these challenges by seamlessly integrating advanced machine-learning methods with extensive biological and clinical datasets. Her team found LOVENet to be successful in highlighting drug associations with other disease states already confirmed by scientific literature. One example they cited was a drug initially approved to treat heart rhythm disturbances that has also been shown to be helpful in treating seizures.
The usual path for developing new medicines can take more than a decade. By using AI to speed up the repurposing process, we hope to shave years off current timelines, identify more uses for existing drugs, and ultimately provide physicians and patients with more treatment options across a wide range of therapeutic areas."
Jouhyun Jeon, lead scientist and principal investigator at Klick Applied Sciences
Klick's EVP of Data Science Alfred Whitehead said, "LOVENet is an important first step in a new era of drug discovery. We think it holds amazing promise to lower development costs, while increasing time efficiency and risk mitigation. It could also greatly assist in streamlining regulatory pathways, expanding market opportunities, while addressing unmet medical needs."
Today's news is the latest glimpse into how Klick has been embracing AI and machine learning in a number of innovative ways. Earlier this week, the company announced the Klick Prize, an internal challenge team members who contribute the best AI ideas for life sciences clients. In October, it announced groundbreaking research in Mayo Clinic Proceedings: Digital Health around the AI model it created to detect Type 2 diabetes using 10 seconds of voice. The agency also recently launched the first ChatGPT plugin for life sciences companies in the U.S. and announced an exclusive North American partnership with AI pioneer Rainbird Technologies.
Antibiotic activity altered by interaction with nanoplastics, new research shows