PIVOT: AI-based tool to detect Cancer

July 11, 2022

An Artificial Intelligence-based tool called ‘PIVOT’ has been developed by researchers at the Indian institute of Technology Madras (IIT Madras).

About PIVOT

PIVOT is capable of predicting cancer-causing genes in patients.
This AI-based tool will help in formulating strategies for personalized cancer treatment.
PIVOT has been designed to predict genes which are responsible for causing cancer.

On which model was PIVOT developed?

The PIVOT tool was developed on the basis of a machine learning model, which divides genes as tumour oncogenes, suppressor genes, or neutral genes. It successfully predicted the oncogenes as well as tumour-suppressor genes such as TP53, and PIK3CA. This tool is also capable to foresee new cancer-related genes such as PRKCA, SOX9 and PSMD4.

Working Mechanism

PIVOT is a machine learning tool. It uses different data, including mutation & gene expression, to foresee the cancer-causing genes. These genes are called driver genes. It helps in formulating personalised cancer treatment strategies. firstly, it uses supervised model learns (ML) algorithms from known driver genes in patient. Patient data and corresponding personalised driver genes are unknown. Secondly, this tool makes use of models on multiple data types, considering the expression data, mutation data, and combination of all types of data.

How is it different than other existing tools?

In traditional methods, usually those tools are used that foresee driver genes by inspecting multiple samples from same cancer type to identify genes, which are responsible for progression of tumours for particular cancer type. Rare driver genes are not identified in these methods.