AI Tool Reveals Hidden Cellular Responses to Cancer Treatment

New AI-powered tool scNET peels back the noise in single-cell data to reveal how immune cells respond to cancer treatments, unlocking a clearer path to precision therapies and medical breakthroughs.

Research: scNET: learning context-specific gene and cell embeddings by integrating single-cell gene expression data with protein–protein interactions. Image Credit: unoL / Shutterstock

Researchers from Tel Aviv University have developed an innovative method that can help us better understand how cells behave in changing biological environments, such as those found within a cancerous tumor.

The new system, called scNET, combines information on gene expression at the single-cell level with information on gene interactions, enabling the identification of important biological patterns such as responses to drug treatments.

The scientific article published in the journal Nature Methods journal explains how scNET may improve medical research and assist in the development of treatments for diseases. The study was led by PhD student Ron Sheinin under the supervision of Prof. Asaf Madi, from the Faculty of Medicine, and Prof. Roded Sharan, head of the School of Computer Science and AI at Tel Aviv University.

Today, advanced sequencing technologies allow the measurement of gene expression at the single-cell level and, for the first time, researchers can investigate the gene expression profiles of different cell populations within a biological sample and discover their effects on the functional behavior of each cell type. One fascinating example is understanding the impact of cancer treatments – not only on the cancer cells themselves but also on the pro-cancer supporting cells or, alternatively, anti-cancer cell populations, such as some immune system cells surrounding the tumor.

Despite the amazing resolution, these measurements are characterized by high noise levels, making it difficult to identify precise changes in genetic programs that underlie vital cellular functions. This is where scNET comes into play.

Ron Sheinin: "scNET integrates single-cell sequencing data with networks that describe possible gene interactions, much like a social network, providing a map of how different genes might influence and interact with each other. scNET enables more accurate identification of existing cell populations in the sample. Thus, it is possible to investigate the common behavior of genes under different conditions and to expose the complex mechanisms that characterize the healthy state or response to treatments."

Prof. Asaf Madi: "In this research, we focused on a population of T cells, immune cells known for their power to fight cancerous tumors. scNET revealed the effects of treatments on these T cells and how they became more active in their cytotoxic activity against the tumor, something that was not possible to discover before due to the high level of noise in the original data."

Prof. Roded Sharan: "This is an excellent example of how artificial intelligence tools can help decipher biological and medical data, allowing us to gain new and significant insights. The idea is to provide biomedical researchers with computational tools that will aid in understanding how the body's cells function, thereby identifying new ways to improve our health."

In conclusion, scNET demonstrates how combining AI with biomedical research could lead to the development of new therapeutic approaches, reveal hidden mechanisms in diseases, and propose new treatment options.