IIT Madras develops machine learning tool to detect brain tumour

Called GBMDriver (GlioBlastoma Mutiforme Drivers), this tool was developed to identify driver mutations and passenger mutations (passenger mutations are neutral mutations) in Glioblastoma, a fast growing tumour in the brain and spinal cord. 

Indian Institute of Technology (IIT) Madras researchers have developed a machine learning-based computational tool for better detection of cancer-causing tumours in the brain and spinal cord. Called ‘GBMDriver’ (GlioBlastoma Mutiforme Drivers), this tool is available online. 

Glioblastoma is a fast growing tumour in the brain and spinal cord. The GBMDriver was developed specifically to identify driver mutations and passenger mutations (passenger mutations are neutral mutations) in Glioblastoma. GBMDriver can be accessed using the following link – web.iitm.ac.in/bioinfo2/GBMDriver/index.html. 

In order to develop this web server, a variety of factors such as amino acid properties, di- and tri-peptide motifs, conservation scores, and position specific scoring matrices (PSSM) were taken into account. 

In this study, 9,386 driver mutations and 8,728 passenger mutations in glioblastoma were analysed. Driver mutations in glioblastoma were identified with an accuracy of 81.99 per cent, in a blind set of 1809 mutants, which is better than existing computational methods. This method is completely dependent on protein sequence. 

The research was led by Prof M Michael Gromiha, Department of Biotechnology, IIT Madras. 

Explaining the key findings of the research, Prof M Michael Gromiha, Department of Biotechnology, IIT Madras, said, “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. We hope that this tool (GBMDriver) could help to prioritise driver mutations in glioblastoma and assist in identifying potential therapeutic targets, thus helping to develop drug design strategies.” 

Key Applications of the research 

•   The methodology and features are portable to apply for other diseases. 
•   This method could serve as one of the important criteria for disease prognosis. 
•   Valuable resource to identify mutation-specific drug targets to design therapeutic strategies. 

Read more: 

• MHT CET Admit Card 2023 to release soon
• HP PAT registration 2023 ends tomorrow, apply on hptechboard.com
• COMEDK UGET 2023 Application Edit Window closes today