Everyday scientists across the globe try their best to come up with a drug to treat the deadly coronavirus.
Previous research in March 2020 pinpointed the ACE2 receptor on cell surfaces as the reason why SARS-CoV-2 spreads so easily and is able to impact so much more than the lungs.
Even as scientists and health professionals from different countries are inching closer to get hold of an effective Covid-19 vaccine, a team of scientists from the University of Melbourne has devised a portable low cost nasal swab test method for Coronavirus testing that is providing substantially accurate results in less than 20 minutes time. "We have developed an alternative COVID-19 molecular test that can be readily deployed in settings where access to standard laboratory testing is limited or where ultra-rapid result turnaround times are needed", Stinear said.
Researchers also suspected that the Covid-19 infection has caused increased C-reactive protein (248 mg/L) - substance produced by the liver in response to inflammation - and decreased lymphocyte count (7·7 per cent) - a kind of white blood cells in the blood samples. "We have developed a drug discovery pipeline that identified several candidates".
"It is clear that some individuals respond better than others to the same SARS-CoV-2 virus. Our drug discovery pipeline can help". He generated machine learning models for each of the human proteins.
"These models are trained to identify new small molecule inhibitors and activators - the ligands - simply from their 3-D structures", Kowalewski notes.
Kowalewski and Ray were thus able to create a database of chemicals whose structures were predicted as interactors of the 65 protein targets.
"The 65 protein targets are quite diverse and are implicated in many additional diseases as well, including cancers", Kowalewski says. The title of the paper is "Predicting novel drugs for Sars-CoV-2 using machine learning from a greater than 10 million chemical space". Besides the ongoing attempts to repurpose drugs against these targets, we were also interested in discovering new chemicals that are not now well studied. Then, among the molecules that "hit" for any one of the 65 proteins, researchers looked for compounds that have already been approved by the FDA. According to a new study, however, there certainly isn't a shortage of possibilities. They also used the machine learning models to compute toxicity, which helped them reject potentially toxic candidates.
In all, more than 10 million (from a database of over 200 million) commercially available small molecules were screened by the machine learning models.