The Medical University of South Carolina is making a new drug discovery program publicly available to researchers in an attempt to accelerate the search for effective therapies against COVID-19.
The program, co-developed with Hewlett Packard Enterprise, is called PharML. The software uses neural network architecture to estimate what drugs might be effective for specific diseases using a real-world data set containing millions of data points.
MUSC says PharML has a 98.3% accuracy rate of finding known drugs that could treat COVID-19 and other diseases.
“The smart move in the middle of a pandemic is to take a fast look at repurposing existing drugs, which we and many others are doing,” MUSC researcher Yuri Peterson said in a news release. “But what we really need, and where artificial intelligence like PharML can shine, is to get ahead of COVID-19 by finding the right drug — the perfect drug, if you will — that can limit this virus’s ability to survive, reproduce and continue to wreak havoc on our world.”
PharML is in its early phase, and Peterson and his team initially intended to test their predictions in a preclinical setting and publish their findings in an academic journal. The coronavirus pandemic accelerated their timeline, though, and they decided to release the code and training files under an open license rather than license and market the program.
Jacob Balma, an artificial intelligence engineering researcher with Hewlett Packard and part of the PharML team, said in the news release that he hopes making PharML publicly available makes it easier for the scientific community to find treatments for COVID-19.
“Making PharML widely available is an important step toward providing the world with true high-throughput, open-therapeutics technology,” Balma said. “The drug discovery pipeline, which this framework aims to accelerate, is currently the limiting factor in the time it takes to design and repurpose compounds to treat diseases.”o