Generative AI predicts and assembles cell drug responses like Lego blocks

Controlling the state of a cell in a desired direction is one of the major challenges in life sciences, including drug development, cancer treatment, and regenerative medicine. However, it is extremely difficult to identify the right drug or genetic target for this purpose.

To address this problem, KAIST researchers mathematically modeled the interaction between cells and drugs like a modular “Lego block” – breaking them down and recombining them – to develop new AI technology capable of predicting not only new, never-before-tested cell-drug reactions, but also the effects of arbitrary genetic disruptions.

A research team led by Professor Kwang-Hyun Cho from the Department of Biotechnology and Brain Engineering has developed generative AI-based technology capable of identifying drugs and genetic targets that can guide cells toward a desired state. Their work is published in the journal Cellular systems.

“Latent space” is an invisible mathematical map used by image-generating AI to organize the essential features of objects or cells. The research team successfully separated representations of cell states and drug effects within this space, then recombined them to predict reactions of previously untested cell-drug combinations. They then extended this principle to show that the model can also predict how a cell’s state would change when a specific gene is regulated.

The team validated this approach using real experimental data. As a result, AI identified molecular targets capable of returning colorectal cancer cells to a normal state, which the team then confirmed through cellular experiments.

This finding demonstrates that the method is not limited to cancer treatment: it serves as a general platform capable of predicting various cellular state transitions and untrained drug responses. In other words, the technology not only determines whether a drug works or not, but also reveals how it works inside the cell, making this achievement particularly significant.

The research provides a powerful tool for designing methods to induce desired changes in cellular state. It is expected to have broad applications in drug discovery, cancer treatment and regenerative medicine, such as restoring damaged cells to a healthy state.

Professor Kwang-Hyun Cho said: “Inspired by image generation AI, we applied the concept of “direction vector”, an idea that allows us to transform cells in a desired direction. He added: “This technology enables quantitative analysis of how specific drugs or genes affect cells and even predicts previously unknown reactions, making it a highly generalizable AI framework. »