- In the absence of a SARS-CoV-2 vaccine, scientists are turning towards the development of other Covid-19 treatments
- Finding suitable treatments is key to reducing Covid-19 deaths as a vaccine could still be months away
- Through machine learning, scientists have been able to screen millions of chemicals to help identify suitable drugs
As vaccine candidates are still in various stages of testing, medical experts are relying on developing other treatments to help eliminate Covid-19 deaths.
Now, scientists from the University of California have identified a way to screen millions of chemicals in an attempt to find suitable Covid-19 treatment drugs – all through machine learning.
The full research was published in the journal Heliyon.
"There is an urgent need to identify effective drugs that treat or prevent Covid-19," said Anandasankar Ray, a professor of molecular, cell, and systems biology, in a news release. "We have developed a drug discovery pipeline that identified several candidates,” stated Ray, who led this research.
How machine learning works to identify potential treatment drugs
In an effort to help discover drugs that can potentially treat Covid-19, the researchers have used a type of computational strategy linked to artificial intelligence. This works through a computer algorithm which can predict activity over time, through trial and error – i.e. a drug discovery pipeline.
"As a result, drug candidate pipelines, such as the one we developed, are extremely important to pursue as a first step toward the systematic discovery of new drugs for treating Covid-19," Ray stated in the release.
"Existing FDA-approved drugs that target one or more human proteins important for viral entry and replication are currently high priority for repurposing as new Covid-19 drugs. The demand is high for additional drugs or small molecules that can interfere with both entry and replication of SARS-CoV-2 in the body. Our drug discovery pipeline can help."
More than 10 million commercially available chemicals screened
Joel Kowalewski, who collaborated with Ray, determined in the laboratory how at least 65 human proteins interact with the proteins of SARS-CoV-2. Machine learning models were then generated for each of the models.
Kowalewski and Ray then created a database from which chemicals that could potentially be interactors for the 65 targets could be identified, while also evaluating them for safety.
"The 65 protein targets are quite diverse and are implicated in many additional diseases as well, including cancers," Kowalewski said. "Apart from drug-repurposing efforts ongoing against these targets, we were also interested in identifying novel chemicals that are currently not well studied."
Ray and Kowalewski used their machine learning models to screen more than 10 million commercially available small molecules from a database comprised of 200 million chemicals, and identified the best-in-class hits for the 65 human proteins that interact with SARS-CoV-2 proteins.
Machine learning was used to identify compounds that were already FDA approved, and also to compute the toxicity of various chemicals. This method helped them to eliminate toxic chemicals, but prioritise those chemicals that could potentially target SARS-CoV-2.
"Compounds I am most excited to pursue are those predicted to be volatile, setting up the unusual possibility of inhaled therapeutics," Ray said.
"Historically, disease treatments become increasingly more complex as we develop a better understanding of the disease and how individual genetic variability contributes to the progression and severity of symptoms," Kowalewski said. "Machine learning approaches like ours can play a role in anticipating the evolving treatment landscape by providing researchers with additional possibilities for further study. While the approach crucially depends on experimental data, virtual screening may help researchers ask new questions or find new insight."
"Our database can serve as a resource for rapidly identifying and testing novel, safe treatment strategies for Covid-19 and other diseases where the same 65 target proteins are relevant," he said. "While the Covid-19 pandemic was what motivated us, we expect our predictions from more than 10 million chemicals will accelerate drug discovery in the fight against not only Covid-19 but also a number of other diseases."
Image credit: Getty Images