The National Post reports in its Monday, Feb. 10, edition that scientists at Columbia University have developed a model called General Expression Transformer (GET) to predict how genes within a cell influence its behaviour. A Washington Post dispatch to the Post reports that GET could enhance our understanding of cancer and genetic diseases. GET uses an approach similar to that of Microsoft-backed OpenAI's ChatGPT, but instead of learning language, it understands gene expression -- the process of turning genes on or off and regulating protein production. GET may serve a role comparable to Alphafold2, which predicts protein structures. The regulation of genes and the structure of proteins both are fundamental to life, and problems in either can trigger disease. Raul Rabadan, one of the authors of a paper reporting the work last month in the journal Nature and director of the Program for Mathematical Genomics at Columbia says, "Biology is being transformed into something that is a predictive science. We're seeing a revolution in biology." The work described in the Nature paper "directly tackles one of biology's major challenges: understanding how the same genome can drive such diverse behaviours in different cell types."