Indian Institute of Technology researchers develop AI tool to identify cancer-causing genes
Researchers from the Indian Institute of Technology in Madras have come up with a new AI prediction tool that can detect cancer-causing genes in individuals.
WHAT IT DOES
Dubbed PIVOT, the predictive model-based AI tool uses information about mutations, gene expression, and copy number variation in genes and disturbances in biological networks due to impaired gene expression. change.
Machine learning models can classify these genes as tumor suppressor genes, oncogenes or neutral genes.
In one researchWith their findings published in the peer-reviewed journal Frontier in Genetics, PIVOT has been found to successfully predict both oncogenes and tumor suppressor genes such as TP53 and PIK3CA, and related genes. new cancers, such as PRKCA, SOX9 and PSMD4.
Researchers have so far developed AI predictive models for three types of cancer: invasive breast carcinoma, colon carcinoma, and lung adenocarcinoma. According to a press release, they plan to build more models for other types of cancer.
Additionally, the team is building lists of oncogenes to help identify the right drugs for patients based on their cancer profiles.
WHY IT IMPORTANT
The uncontrolled growth of cells that lead to cancer occurs due to mutations in oncogenes or tumor suppressor genes, or both. However, not all mutations necessarily lead to cancer, according to the IIT-Madras researchers.
They say identifying the genes responsible for the onset and progression of cancer in patients helps identify the right combination of drugs and therapies for recovery.
Dr Karthik Raman, research team member and associate professor at IIT-Madras Bhupat and Jyoti Mehta School of Biological Sciences, commented: “As cancer treatment increasingly moves towards personalized medicine, Such models are built to accurately identify patient differences.
While there are tools available that can also identify cancer genes, they use unsupervised learning and base their predictions on the presence and absence of mutations in those genes.
According to the team, the IIT-Madras study on PIVOT is the first to use supervised learning and take into account the functional impact of mutations in making predictions.
SNAPSHOT . MARKET
There have been recent efforts across Asia Pacific to detect and predict cancer using AI technology. Last month, cancer care platform Karkinos Health Care partnered with US oncology company C2i Genomics to promote AI-powered cancer surveillance in India. The second method provides a diagnostic test that uses AI to determine the trace amount of cancer that has recurred.
IT supplier Fujitsu is working on a research project with Southern Tohoku General Hospital, Japan to develop an AI solution that detects pancreatic cancer from CT scans at an early stage.
Two years ago, a research group at National University of Singapore came up with a cancer scorecard, a panel of 29 selected genes, that help detect cancer. It was developed using big data and predictive analysis of more than 30,000 biopsies taken from patients.
“The field of precision medicine is still in its infancy,” said Malvika Sudhakar, team member and research scholar at IIT-Madras.