AI-based algorithm developed to track cancer-causing mutations

Researchers around the world are developing AI as a tool to improve the healthcare ecosystem. Aligning with this, researchers at the Indian Institute of Technology (IIT), Madras have achieved a stunning breakthrough by developing an Artificial Intelligence (AI) based mathematical model which intends to identify cancer-causing alterations in cells.

Artificial Intelligence (AI) driven algorithm uses a technique that probes into DNA composition to pinpoint genetic alterations that are held responsible for cancer progression.

*Understanding the Underlying mechanism*

According to the researchers of IIT Madras, usually, major challenges faced by cancer researchers involve the differentiation between the relatively small number of driver mutations that enable the cancer cells to grow and the large number of passenger mutations that do not have any effect on the progression of the disease. Hence, the practical implication of the study aims to have computational prioritization of cancer driver mutations as an active area of research.

To overcome this challenge, the researchers decided to look at this issue from a different perspective. The main goal was discovering patterns in the DNA sequences that are made up of four letters, or bases namely A, T, G and C surrounding a particular site of alteration.

To keep the focus on the study of mutations, the underlying hypothesis indicated that these patterns would be unique to individual types of mutations, that is, drivers and passengers, and therefore they could be modelled mathematically. Through this model, researchers could distinguish between well-studied drivers and passenger mutations from cancer genes with an accuracy of 89% significantly outperforming existing models.

*Target to be achieved*

With the aim to come up with the most accurate treatment strategy for cancer patients, the Artificial Intelligence-based Mathematical Model attempts for an easy-to-use web interface that will help cancer researchers. In turn, this mathematical model will also make further studies on mutations smooth. The study will also be a part of the broader cancer genomic sequence analysis. Ultimately, with this model, the end result is to discover the “right drug for the right person at the right time.”

*Next-Generation Sequencing*

Cancer is a group of diseases that is caused by changes in DNA that alter cell behaviour. The abnormalities caused by the change in DNA take up many forms, including DNA mutations, rearrangements, deletions, amplification, and the addition or removal of chemical marks. In turn, the abnormalities cause cells to produce unusual amounts of particular proteins that do not function as they should. Oftentimes, such combinations of several genomic alterations are responsible for promoting cancer.

Cancer Genomics is a relatively new area or field of research that takes advantage of recent technological advances and artificial intelligence to study the human genome, meaning studying the full set of DNA. By sequencing the DNA and RNA of cancer cells and making due comparisons of the sequences to normal tissue such as blood, scientists and researchers identify genetic differences that may cause cancer. This approach is called structural genomics. This could also be used to measure the activity of genes encoded in our DNA to understand which proteins are abnormally active or silenced in cancer cells. Once cancer-causing alterations in cells are identified, scientists can gain a better understanding of the molecular basis of cancer growth and drug resistance.