Chennai, NFAPost: A team of researchers from the Indian Institute of Technology Madras has created a computational tool called GBMDriver that uses machine learning to improve the detection of cancerous tumours in the brain and spinal cord. This tool is freely accessible and has been designed specifically to detect driver mutations and passenger mutations in glioblastoma, a fast-growing tumour.
To develop the web server, the researchers analyzed 9386 driver mutations and 8728 passenger mutations in glioblastoma, taking into account various factors such as amino acid characteristics, di- and tri-peptide motifs, conservation scores, and Position Specific Scoring Matrices (PSSM).
According to the researchers, GBMDriver can detect driver mutations in glioblastoma with an accuracy of 81.99%, which is better than existing computational techniques. The approach relies solely on protein sequences, and the study identified the essential amino acid characteristics that distinguish cancer-causing mutations.
The researchers hope that GBMDriver will help prioritize driver mutations in glioblastoma and identify potential therapeutic targets, thereby aiding in drug design strategies. Currently, there are few therapeutic options available for glioblastoma, and patients have a predicted survival rate of less than two years after diagnosis.
PhD student Medha Pandey, who worked on the project, believes that GBMDriver could be useful in identifying therapeutic targets and prioritizing driver mutations in glioblastoma. She also thinks that the development of this tool has the potential to uncover novel therapeutic targets and improve the prognosis for patients with glioblastoma.