Researchers at Colorado State University have determined how to use artificial intelligence to modify antibodies so they act as lightbulbs, enabling scientists to better see inside living cells to track errors in gene expression that can lead to cancer and other disorders.
AI-assisted protein design to convert antibody sequences to intrabodies
This section elaborates on the application of AI techniques, specifically Google DeepMind's AlphaFold2 and ProteinMPNN software, to revolutionize the design of antibody-based probes. The CSU team leveraged these tools to efficiently convert antibody sequences into stable intrabodies, drastically reducing the development time and increasing the success rate from a mere 5-10% to approximately 70%. This accelerated process allows researchers to rapidly generate functional probes for observing cellular activity, with insights gained from both successful and unsuccessful designs contributing to the refinement of AI algorithms. The potential of this method is immense, given the vast number of publicly available antibody structures and sequences that could be similarly transformed into useful intrabodies.
Future work to create intrabodies against viruses like West Nile
The research findings present significant potential for future applications, particularly in the field of virology. Professor Brian Geiss's team plans to utilize these newly developed intrabody probes, re-engineered from virus-specific antibodies, to study viral replication and its impact on infected cells, such as those affected by West Nile virus. Unlike traditional microscopy which offers only static snapshots, this approach will enable real-time tracking of individual viral proteins, providing an unprecedented dynamic view of the infection process from initiation to maturation. Furthermore, the robust and temperature-stable nature of these probes opens doors for diagnostic work, offering a promising new tool for both understanding and detecting viral diseases.
