Integration of machine learning with computational drug discovery for identifying potential inhibitors against pathogens – A case study with HIV and E. coli.

Diseases, characterized by specific symptoms and bodily function alterations, exert a profound impact on society, affecting public health and economies. Pathogens such as viruses and bacteria are the causative agents responsible for many diseases. Escherichia coli (E. coli), a common bacterium, continues to cause foodborne illnesses in 2023, with antibiotics serving as treatments, but antibiotic resistance remains a growing concern, which nullifies the effect of antibiotics. Global incidence of E. coli was estimated to be 2.8 million cases per year. HIV remains a global concern, where approximately 39.0 million people were living with HIV at the end of year 2022, despite the discovery of many antiretroviral drugs. Present limitations of these drugs such as drug resistance still poses as major challenge for society. Conventional Drug Discovery (CDD) suffer from time, cost, and success rate limitations, prompting a shift towards a new innovative approach for designing novel, effective and safe drugs against pathogens. Machine Learning (ML) is applied to analyze vast biological and chemical datasets and further predict potential drug candidates against E. coli and HIV. The capacity of ML to process big data offers an efficient means of streamlining drug discovery. Present study proposes novel and effective ML framework to accelerate CDD and discover novel, effective and safe drugs against E. coli and HIV.