Texas researchers train ML on zoonotic pathogens

A team of biomedical researchers, comprising scientists from the Southwest Research Institute (SwRI), the University of Texas at San Antonio (UTSA), and the Texas Biomedical Research Institute (Texas Biomed), have developed a machine learning (ML) algorithm with the capacity to identify efficacious treatments for diseases caused by emerging zoonotic pathogens, which are capable of transmitting from animal hosts to humans. Rhodium software, developed by SwRI, was utilised to screen and rank over 40 million compounds for the treatment of bat-borne Nipah and Hendra henipaviruses, which have the potential to cause life-threatening infections in humans. This process led to the identification of 30 viral inhibitors with the potential to be effective. The results of the study were presented at the International Henipavirus Hendra@30 Conference in Melbourne, Australia. The potential of ML to swiftly identify antiviral candidates for highly pathogenic viruses that are challenging to study due to biosafety restrictions was emphasised. This statement was made by Dr. Jonathan Bohmann, a researcher at SwRI. The study of such infectious diseases demands adherence to rigorous safety standards and access to a BSL-4-certified high-containment laboratory. The utilisation of virtual screening methodologies enables researchers to achieve substantial savings in terms of time and resources, while concurrently ensuring the safety of their research practices.