MIT researchers used a large language model to optimize the genetic sequences of proteins manufactured by yeast, reducing production costs. The new model predicted which codons would work best for manufacturing six different proteins, including human growth hormone and a monoclonal antibody, with successful results.
A new mathematical framework has been created to study fitness landscapes of regulatory DNA, enabling the prediction of gene expression changes. The framework uses a neural network model trained on millions of experimental measurements to decipher the evolutionary past and future of non-coding sequences.
Scientists at MIT have developed a screening method to study protein-protein interactions, which are crucial in understanding disease mechanisms. The researchers created a synthetic molecule that binds tightly to a protein implicated in cancer metastasis, providing a potential tool for disrupting disease-causing interactions.
Researchers found that certain T cells stop working before entering the tumor due to changes in gene expression, making ICB therapies less effective. Combining ICB with other forms of immunotherapy targeting different aspects of T cell function may improve response rates for non-small cell lung cancer patients.
Scientists devised a method to analyze the NPC directly inside cells, capturing its true size and structure. The results showed that the pore had a wider central channel than previously thought, emphasizing the importance of analyzing complex molecules in their native environments.