25.4 Use of Artificial Intelligence (AI) in Drug Designing
Organic Synthesis
The past few decades have seen the development of very few new antibiotics. Those which have been developed are only slightly different from the existing ones. The methods which are currently used to develop new drugs are very costly, time consuming and are usually limited to a narrow spectrum of chemical activity. We are also facing growing number of cases whereby the prevalent antibiotics become resistant to existing pathogens.
In order to find out a solution to this problem the researchers at MIT (Massachusetts Institute of Technology) designed a machine-learning algorithm to look for chemical features that make molecules effective at killing E. coli bacteria. To do so, they applied the model on 2500 molecules and a set of 800 natural products with different structures and a wide range of bioactivities. Once the computer model was applied to these compounds, it picked out one molecule that was predicted to have antibacterial properties with a molecular structure different from the existing antibiotics.