AI tools speed development of antibody probes to see activity inside living cells
Peer-Reviewed Publication
Updates every hour. Last Updated: 14-Jan-2026 03:11 ET (14-Jan-2026 08:11 GMT/UTC)
Researchers used Google DeepMind’s AlphaFold2 and ProteinMPNN to speed development of antibody-based probes that can be used to see key functions and chemical changes inside living cells as they happen. This AI-driven method is significantly faster than previous manual testing and development approaches, allowing the CSU team to rapidly create and test 19 new potential probes. The work enables continuous imaging of living cells, which may help researchers better understand errors in genetic expression that can lead to cancer and other disorders.
Key Study Highlights:
Demonstrates how dual-purpose therapeutic targets may address both hepatocellular carcinoma progression and cellular senescence, supporting emerging strategies that link disease treatment with aging biology
Identifies PRPF19 and MAPK9 as targets that suppress tumor cell proliferation while reducing senescence-associated signaling in relevant cellular models
Provides evidence of senomorphic activity, reducing harmful senescence-associated secretory phenotype (SASP) signaling without marked cytotoxicity
Illustrates the effectiveness of integrating AI-driven target discovery, multi-omic human datasets, and experimental validation to prioritize biologically relevant and translationally promising targets
Reinforces Insilico’s broader AI-guided discovery approach for uncovering shared mechanisms across disease and aging
A new machine-learning-based approach to mapping real-time tumor metabolism in brain cancer patients, developed at the University of Michigan, could help doctors discover which treatment strategies are most likely to be effective against individual cases of glioma. The team verified the accuracy of the model by comparing it against human patient data and running mouse experiments.