A Nigerian scientist, Gideon Gyebi, has highlighted how the application of artificial intelligence (AI) and machine learning could accelerate the discovery of new antibiotics and help counter the growing global threat of antimicrobial resistance (AMR).
Gyebi, a researcher in computational and systems biology, shared insights from his recent study during a presentation in Abuja on Tuesday.
Antimicrobial resistance (AMR) occurs when microbes like bacteria, viruses, fungi, and parasites found in the body resist drugs designed to kill them.
According to News Agency of Nigeria (NAN) report, his work, titled “Computational profiling of terpenoids for putative dual-target leads against Staphylococcus aureus Penicillin-Binding Protein 2a and Beta-Lactamase,” was recently showcased at the Durban University of Technology in South Africa.
Read Also: Lifelong learning may shield brain from Dementia, Study
The study demonstrates how computational technologies can fast-track the identification of effective drug candidates by simulating how potential compounds interact with bacterial proteins.
According to Gyebi, these emerging tools enable scientists to virtually test thousands of compounds in a fraction of the time required for traditional laboratory experiments.
“Computational biology is transforming the way we think about medicine,” he said. “By simulating how potential drugs interact with bacterial proteins, we can guide experiments more intelligently and make discoveries faster.”
Gyebi’s research focuses on Staphylococcus aureus, a bacterium linked to numerous hospital-acquired infections and a key contributor to the global AMR crisis.
He explained that methicillin-resistant Staphylococcus aureus (MRSA) has become particularly difficult to treat because it produces enzymes that break down antibiotics and modifies its protein targets to resist their effects.
To address this, his study explored natural compounds called terpenoids that could simultaneously inhibit two major bacterial defence mechanisms, the enzyme β-lactamase, which destroys β-lactam antibiotics, and Penicillin-Binding Protein 2a (PBP2a), which reduces the drugs’ effectiveness.
Gyebi explained that tackling both β-lactamase and PBP2a simultaneously provides a dual strategy that may help revive the effectiveness of widely used antibiotics.
He added that such an approach could play a crucial role in combating resistance and enhancing treatment success.
He noted that while computational tools cannot replace laboratory experiments, they play a crucial complementary role by narrowing down viable candidates for further testing.
The World Health Organisation (WHO) has warned that antimicrobial resistance is among the top ten global public health threats, with projections suggesting it could cause up to ten million deaths annually by 2050 if left unchecked.
With more than 70 scientific papers and over 1,000 citations, Gyebi is part of a new generation of African researchers leveraging technology to address complex health challenges.
He believes that integrating computational methods, AI, and biotechnology could reshape the antibiotic discovery pipeline and strengthen global efforts against drug-resistant infections.
