A pretrained unified model enables cellular functional profile prediction and multi-objective virtual drug screening
Cells are characterized by molecular states, coordinated molecular interactions, regulatory programs, and responses to perturbations. Systematic mapping of these cellular functional profiles across biological contexts remains experimentally costly and fragmented. Here we present InsilicoCell, a pretrained multi-modal, multi-task model that unifies prediction of cellular functional profiles…
A new artificial intelligence model called InsilicoCell has the potential to revolutionize the way we understand and predict cellular behavior. By learning from over 88 million measurements, InsilicoCell can predict various cellular functional profiles, including molecular states, interactions, and responses to perturbations. This unified model outperforms specialized models and can be applied to a wide range of biological contexts, including patient tissues, spatial data, and single-cell samples.
InsilicoCell's versatility extends to drug discovery, as it can identify potential new compounds for various conditions, such as c-Myc activity inhibitors, antifibrotic agents, and stemness-inducing compounds. The model's success in virtual screening and candidate identification demonstrates its capacity to accelerate therapeutic discovery. By providing a scalable framework for predictive cellular biology, InsilicoCell represents a significant step forward in our ability to understand and manipulate cellular function.
Written by urgent.news from bioRxiv's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
