Published: 19th September 2022
IIIT Delhi research team creates software that detects cancer-causing elements in chemicals
The research on the AI-based software, named Metabokiller, has also been published in Nature Chemical Biology, informed the team
In what could be a boost for the pharma industry, researchers from the Indraprastha Institute of Information Technology Delhi (IIIT Delhi) have developed an Artificial Intelligence (AI)-based model to detect carcinogens (cancer-causing compounds) in chemical structures. Their research has the potential to help in the screening of new drugs.
The research on the software, named Metabokiller, has also been published in Nature Chemical Biology, which is one of the most reputed journals in the field of Chemical Biology, the researchers stated. Other clinical and research institutes such as IIT Ropar, Rajiv Gandhi Cancer Hospital and Research Centre and CSIR-Institute of Genomics and Integrative Biology, New Delhi, have also participated in the research, as per a PTI report.
"Our latest work builds an AI model that could recognise the carcinogens from the chemical structures. This model utilises a novel approach that specifically targets the biological and chemical properties associated with known carcinogens," said Gaurav Ahuja, Assistant Professor, Department of Computational Biology, IIIT Delhi. Ahuja, along with Dr Debarka Sengupta, has developed six independent Machine Learning-based models that precisely scan every query compound for carcinogen-associated properties. The former stated that Metabokiller has vast importance and utilization in the pharma industry for the screening of new drugs.
"Of note, in the last few decades, many FDA-approved drugs have been taken back from the market since they were found to cause cancer. It also has huge importance in the cosmetics and food industries," the Assistant Professor said. He also added that the software, unlike others, provides explainability. "Machine learning is a black box approach, where the cause or the reason for the prediction is largely obscure. Metabokiller predicts carcinogens and does provide the underlying, human interpretable reasoning for this prediction," he said, as per PTI.
Speaking about the future course of action, Ahuja said, "We are in advanced communication with multiple pharma companies to test our software in a real-world scenario. The research team is presently working on establishing a direct link between carcinogens and the mutations which they cause in the DNA, he informed. "Approximately 5 per cent of the cancer is heritable while around 95 per cent of the cancer is caused by exposure to carcinogens (compounds) in the environment," Ahuja explained, to emphasise the importance of the research.