Skip to main content
Premium Trial:

Request an Annual Quote

WUSTL, PercayAI to Seek COVID-19 Treatments Via AI, Deep Learning

NEW YORK – The Washington University School of Medicine in St. Louis is teaming with WUSTL spinout PercayAI to apply deep learning and augmented intelligence to multiomic data in pursuit of COVID-19 treatments.

Under a research collaboration announced Tuesday, PercayAI will run a pilot project to analyze genomic and clinical data from WUSTL's Institute for Informatics and the university's McDonnell Genome Institute in hopes of identifying drug combinations that might be effective against COVID-19 in specific populations. Researchers from the two institutes will work alongside PercayAI bioinformaticians to review the results of the analysis, then propose future studies and perhaps clinical trials.

"As COVID-19 continues to spread globally, augmented intelligence and machine learning can play a key role in helping us address this crisis," Philip Payne, director of the WUSTL Institute for Informatics, said in a statement. "Machine learning technology enables computers to simulate human intelligence and analyze massive amounts of data quickly to identify patterns that could steer us toward promising drug combinations against COVID-19."

PercayAI spun out of the Genome Technology Access Center at the McDonnell Genome Institute and codeveloped its software with the genome technology center. The St. Louis-based firm emerged from stealth mode a year ago this month.

The company's CompBio product applies artificial intelligence and contextual language processing to help researchers identify relationships within multiomic datasets to inform drug discovery.

"We are pleased to be extending our collaboration with Washington University School of Medicine to leverage our collective expertise and resources in big data, genomics, and AI, helping to identify targeted treatment options that may be effective for COVID-19 patients," PercayAI Chief Commercial Officer Preston Keller said.

The Scan

Study Examines Insights Gained by Adjunct Trio RNA Sequencing in Complex Pediatric Disease Cases

Researchers in AJHG explore the diagnostic utility of adding parent-child RNA-seq to genome sequencing in dozens of families with complex, undiagnosed genetic disease.

Clinical Genomic Lab Survey Looks at Workforce Needs

Investigators use a survey approach in Genetics in Medicine Open to assess technologist applications, retention, and workforce gaps at molecular genetics and clinical cytogenetics labs in the US.

Study Considers Gene Regulatory Features Available by Sequence-Based Modeling

Investigators in Genome Biology set sequence-based models against observational and perturbation assay data, finding distal enhancer models lag behind promoter predictions.

Genetic Testing Approach Explores Origins of Blastocyst Aneuploidy

Investigators in AJHG distinguish between aneuploidy events related to meiotic missegregation in haploid cells and those involving post-zygotic mitotic errors and mosaicism.