IIT Madras Researchers Develops Machine Learning Tool To Detect Brain and Spinal Cord Tumours; Check Details Here

Content Curator

IT Madras Researchers Develops Machine Learning Tool To Detect Brain and Spinal Cord Tumours

New Delhi: A computational tool based on machine learning has been developed by researchers at the Indian Institute of Technology, Madras (IIT Madras) for improved detection of cancerous tumours in the brain and spinal cord. This tool, known as "GBMDriver" (GlioBlastoma Mutiforme Drivers) is publicly available online.

A publicly available online server called the GBMDriver was created primarily to find driver mutations and passenger mutations (neutral mutations) in glioblastoma, a brain and spinal cord tumour that spreads quickly and aggressively, as well as in other cancers. The project's principal investigator was Prof. M. Michael Gromiha of the Department of Biotechnology at IIT Madras.

In addition to this, two IIT Madras alumni, Dr. P. Anoosha, who is currently at The Ohio State University in Columbus, Ohio, and Dr. Dhanusha Yesudhas, who is currently with the National Institutes of Health in the US, the study team also includes Medha Pandey, an IIT Madras PhD student.

The construction of this web server took into account a number of factors, such as amino acid properties, di- and tri-peptide motifs, conservation scores, and Position Specific Scoring Matrices (PSSM). The research looked at 8728 passenger mutations and 9386 driver mutations in glioblastoma. In a blind set of 1809 mutants, driver mutations in glioblastoma were detected with an accuracy of 81.99%, which is superior to current computational techniques. The only variable on which this approach depends is the protein sequence.

According to Prof. Gromiha, the key findings of their study were that they had discovered the essential amino acid traits that set cancer-causing mutations apart and had achieved the highest level of accuracy for identifying driver and neutral mutations. “We anticipate that our tool (GBMDriver) will help in identifying the prospective therapeutic targets and the prioritisation of driver mutations in glioblastoma, to assist in the development of drug design methods,” Prof. Gromiha added.

Although the glioblastoma tumour has been the subject of extensive research in the past, there are currently only a limited number of treatment options, and the expected survival time upon diagnosis is less than two years. Medha Pandey, a PhD Student at IIT Madras, said, “We anticipate that the current approach will help discover treatment targets and aid to prioritise driver mutations in glioblastoma”.

Read More: