Exai Bio Announces Publication in Nature Communications Highlighting its Generative AI Liquid Biopsy Platform

Exai’s AI platform surpasses commonly used machine learning methods in overall lung cancer detection performance

Exai Bio Announces Publication in Nature Communications Highlighting its Generative AI Liquid Biopsy Platform

Kim Maxwell Brown
kimb@exai.bio
Phone: 650-262-4516

Exai Bio, a next-generation oncRNA- and generative AI-based liquid biopsy company, today announced a peer-reviewed publication about its generative AI model in Nature Communications. The paper entitled “Deep generative AI models analyzing circulating orphan non-coding RNAs enable detection of early-stage lung cancer” demonstrates that Exai’s generative AI model surpasses commonly used machine learning methods in overall lung cancer detection performance. Exai’s platform achieved higher overall sensitivity and specificity for cancer detection across all stages, beating the performance of other methods on held-out validation datasets by 30%.

“The publication of our study in a preeminent journal like Nature Communications demonstrates the power of Exai’s Bio’s generative AI platform and its ability to surpass the performance of other commonly used methods in liquid biopsy,” stated Dave Daly, Chief Executive Officer of Exai Bio. “Harnessing our unique advantages in generative AI as well as novel RNA biomarkers will be integral to our next generation liquid biopsy tests that will truly deliver on the promise of early cancer detection.”

In a study of 1050 individuals diagnosed with non-small cell lung cancer plus non-cancer controls, Exai’s deep generative AI model demonstrated superior performance compared to commonly used machine learning methods. These methods include the support vector machine classifier, ElasticNet, and XGBoost. Exai’s model not only excelled in overall performance but also showed better generalizability to held-out datasets and improved analytical properties.

“This publication underscores the importance of leveraging generative AI and assessing its performance and robustness relative to traditional machine learning methods in the context of liquid biopsy,” stated Babak Alipanahi, Chief Scientific Officer of Exai Bio. “Our platform is poised to play a central role in the next generation of liquid biopsy applications.”

Exai’s liquid biopsy platform uses RNA sequencing to identify a novel category of cancer-associated, small non-coding RNAs, termed orphan non-coding RNAs (oncRNAs). oncRNAs are actively secreted from living cancer cells and are abundant in the blood. When combined with proprietary artificial intelligence technology, oncRNAs have multiple advantages over tests that utilize circulating tumor DNA, including superior sensitivity and specificity, low cost of goods, as well as the ability to reveal dynamic changes in the biology of a patient’s tumor over time.

About Exai Bio

Exai Bio is a next-generation liquid biopsy company. Its mission is to enable a world where cancer can be detected early, diagnosed accurately, treated in a personalized and targeted way, and ultimately cured. The company’s proprietary oncRNA- and AI-based liquid biopsy technology delivers clinical insights into cancer biology to enable the earliest, most accurate diagnosis of cancer. For more information, please visit us on www.exai.bio and follow us on Twitter and LinkedIn.