New Machine Learning Tool to Detect Brain Tumor

New machine learning (ML)-based tool developed by researchers helps detect cancer-causing tumors in the brain and spinal cord. Glioblastoma is a fast and aggressively growing tumor in the brain and spinal cord.

Although there has been research undertaken to understand this tumor, therapeutic options remain limited with an expected survival rate of less than two years from the initial diagnosis.

Driver mutations are usually defined as mutations that induce cell proliferation and tumor growth, while passenger or 'hitchhiker' mutations, which represent approximately 97 percent of all cancerous mutations, do not.

Brain Tumor Detection Using Machine Learning

"We have identified the important amino acid features for identifying cancer-causing mutations and achieved the highest accuracy for distinguishing between driver and neutral mutations," said Prof. M. Michael Gromiha, Department of Biotechnology at IIT Madras, in a statement.

To develop this web server, the team analysed 9,386 driver mutations and 8,728 passenger mutations in glioblastoma. Driver mutations in glioblastoma were identified with an accuracy of 81.99 percent, in a blind set of 1809 mutants, which is better than existing computational methods. This method is completely dependent on protein sequence.

Their findings were published in the peer-reviewed journal Briefings in Bioinformatics.

The ML tool can also be applied for other diseases. The method could serve as one of the important criteria for disease prognosis. AIt is a valuable resource to identify mutation-specific drug targets to design therapeutic strategies.

Advertisement

"We envisage that the method is helpful to prioritize driver mutations in glioblastoma and assist in identifying therapeutic targets," said Medha Pandey, a PhD Student at IIT Madras.

Source-IANS