Researchers at the Indian Institute of Technology Madras (IIT Madras) have created a tool called “PIVOT” that uses artificial intelligence to predict a person’s cancer-causing genes. Ultimately, this tool will aid in developing individualised cancer treatment plans.
Cancer is an unregulated cell growth that can be brought on by mutations in tumour suppressor genes, oncogenes, or both. Nevertheless, not all mutations inevitably lead to cancer. To create effective, individualised cancer treatment plans, it is crucial to identify the genes that are causing cancer.
Researchers at IIT Madras created “PIVOT,” which aims to identify genes that are likely to contribute to a person’s development of cancer. The prediction is supported by a model that makes use of data on gene expression, gene copy number variation, gene expression, mutations, and biological network disturbances brought on by changing gene expression.
Highlighting the significance of the Research, Dr. Karthik Raman, Core Member, RBCDSAI, IIT Madras, said, “Cancer, being a complex disease, cannot be dealt with in a one-treatment-fits-all fashion. As cancer treatment increasingly shifts towards personalized medicine, such models that build toward pinpointing differences between patients can be very useful.”
The tool classifies genes as tumour suppressors, oncogenes, or neutral genes using a machine learning algorithm. TP53, PIK3CA, and other tumor-suppressor genes as well as newly discovered cancer-related genes including PRKCA, SOX9, and PSMD4 were all correctly predicted by the algorithm.
Speaking on the importance of providing personalized cancer treatment, Ms. Malvika Sudhakar, Research Scholar, IIT Madras, said, “The research area of precision medicine is still at a nascent stage. PIVOT helps push these boundaries and presents prospects for experimental research based on the genes identified.”
The researchers have developed AI prediction models for three different cancer types—breast invasive carcinoma, colon adenocarcinoma, and lung adenocarcinoma. They intend to expand it to include a lot more cancer kinds. The team is also putting up a list of unique genes that cause cancer, which can be used to determine a patient’s best course of treatment based on their unique cancer profile.
The findings of the research have been published in a peer-reviewed journal Frontier in Genetics. Click here to view the study.
