Researchers at the Indian Institute of Technology Madras have developed an artificial intelligence tool that can identify cancer-causing genes.
The AI tool, “Pivot”, can predict cancer-causing genes in an individual thus assisting in not only reducing the side-effects of drugs but also in better recovery for patients.
The researchers have used prediction models for breast invasive carcinoma, colony adenocarcinoma and lung adenocarcinoma. They plan to extend it to other cancers. The aim is to find ways to provide personalised cancer treatment strategies.
The model uses information on gene mutations, gene expressions and number variations in genes and perturbations in the biological network owing to an altered gene expression.
Chemical engineering professor Raghunathan Rengaswamy led the research. D. Karthik Raman, associate professor, Bhupat and Jyoti Mehta School of Biosciences in the institute and Malavika Sudhakar, research scholar, were on the team.
Their findings were published in the journal Frontier in Genetics.
The tool is based on machine learning model that classifies genes as tumour suppressor, neutral or oncogenes. It could predict both the existing oncogenes and tumour suppressor genes besides certain new cancer-related genes, the researchers said.
According to them, the study is the first to use supervised learning and takes into account the functional impact of mutations while making predictions.
The team is working on a list of personalised cancer-causing genes that can help in identifying suitable drug for patients based on their personalised cancer profile.