Written By: Debjani Arora | Published : October 4, 2018 9:45 AM IST
Scientists find new computer algorithm to check on existing drugs. © Shutterstock
Recently a group of scientist stumbled upon a computer algorithm that will make discovery of new drugs much easier. This computer algorithm reduces the chances of simply rediscovering known compounds. The algorithm was discovered while they were trying to discover new antibiotic and cancer drugs. The study, published in the journal Nature Communications, found a new means of searching vast repositories of compounds produced by microbes.
Researchers, including those from the Carnegie Mellon University in the US, were able to identify known compounds within the repository and eliminate them from further analysis. This reduces the repetition of finding the same drug and improving one's knowledge about drugs. Once they could eliminate the known compounds within the repository they focussed on the unknown variants that might potentially be better or more efficient antibiotics, anticancer drugs or other pharmaceuticals.
In just a week, running on 100 computers, the algorithm, called Dereplicator+, identified over 5,000 promising, unknown compounds that merit further investigation, said Hosein Mohimani reportedly, an assistant professor at Carnegie Mellon University.
In the past, mass spectrometry data repositories have been underused as it was difficult to search through them and this had led to high rates of the rediscovery of known compounds, researchers said. But this new computer algorithm just makes things easier. Mohimani in fact, expressing astonishment said that rediscovery happens all too often and it is unbelievable how many times people have rediscovered penicillin.
Analysing the compounds' mass spectra essentially, a measurement of the masses within a sample that has been ionised is a relatively inexpensive way of identifying possible new pharmaceuticals. However, existing techniques were largely limited to peptides, which have simple structures such as chains and loops.
To analyse the larger number of complex compounds that have entangled structures and numerous loops and branches, the researchers developed a method for predicting how a mass spectrometer would break apart the molecules. Using 5,000 known compounds and their mass spectra, they trained a computer model that could then be used to predict how other compounds would break down.
Mohimani said Dereplicator+ not only can identify known compounds that don't need to be investigated further, but it can also find less common variants of the known compounds that likely would go undetected within a sample.
