Collage images sourced from unstplash.com, adobestock.com, and rawpixel.com
Stanford University researchers have developed a machine learning-based approach to engineers that are safer and more effective proteins for use in cell and gene therapy. The work focuses on using zinc fingers, a small naturally occurring human protein involved in gene regulation.
Xiaojing Gao, senior author of Stanford papers and assistant professor of chemical engineering, explained: “In this paper, why don't you design a treatment that avoids an immune response from the start? We try to predict that changes in proteins can trigger an immune response.
The team wanted to redesign the zinc fingers so that they could target specific genomic sites associated with the disease without developing the immune system. To do this, I used three machine learning tools:
First, the algorithm helped to identify zinc finger combinations that could bind to selected DNA sequences. However, they linked these proteins to extend their reach and introduced unnatural junctions that could become a potential red flag for immune cells. To address this, the team used Maria, a model originally developed to identify immunogenic regions for cancer vaccine design. Conversely: Predict and avoid sequences that can trigger an immune response.
Finally, a protein language model called ESM-IF1 proposed small target genetic adjustments to enhance protein function while maintaining low immunogenicity.
Ai-Optimized zinc fingers were tested in lab experiments and showed up to 6 times improvement in gene activation compared to unmodified proteins. Gao describes the work as “having zinc finger engineering in a place I've never visited before.”
Eric Walesberg, the lead author of the paper, added: “The most important part of our research is the developments in the design of zinc finger DNA binding domains that can target genomic sites of our choice, while maintaining the low predictive risk of triggering immune responses.”
It's not just about creating a great scientific journal and providing knowledge and quality content. It's also about packaging these in the right words, ensuring that someone is really inspired by the topic. My passion is to ensure that the author's expertise is presented as a seamless, enjoyable reading experience in print, digital and social media. I spent 14 years writing and editing features for scientific and manufacturing publications, making this content engaging and accessible without sacrificing scientific integrity. There's nothing better than a magazine with great content that you find great to read.
