University of Cambridge > Talks.cam > Theory - Chemistry Research Interest Group > Designing an Advanced Cancer Therapeutic Protein (GABPA Binding Inhibitor) Using an Artificial Intelligence-based DNA Binding Protein Design system.

Designing an Advanced Cancer Therapeutic Protein (GABPA Binding Inhibitor) Using an Artificial Intelligence-based DNA Binding Protein Design system.

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Lisa Masters.

https://zoom.us/j/96081156517?pwd=dmVGcVdDMXYvcVljdjVUQVIrd3F3QT09 Meeting ID: 960 8115 6517 Passcode: 135523

First Year PhD Report: Transcription factors (TF) are DNA binding proteins that regulate the gene expression mechanism. Different combinations of TF that are bound at the DNA promotor (transcription initiation region in a gene) determine whether a gene is switched on or off. Many complex diseases and organ development are related to the transcription factor machinery. Our ambitious goal is to design novel functional protein folds to interrupt gene switch mechanisms. Thus, we could develop advanced treatments for different kinds of diseases, including cancer, and in tissue regenerative applications.

We are developing an artificial intelligence-based protein designing system. In the first step, we have developed a method to translate a 3D geometry of a protein structure into a 1D structural language sequence that represents the 3D protein structure. The sequence could be used as input to a special type of RNN (Recurrent Neural Network) to learn how to build a novel fold using a fragment library guided own variational protein set. To test the system, we have designed a highly specific cancer therapeutic protein structure.

The system development is ongoing. We will optimise the designed protein using a self-learning RNN .

This talk is part of the Theory - Chemistry Research Interest Group series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2022 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity