Protein Classification and Dynamics

We work at the intersection of proteomics and deep learning

Proteins are responsible for most functions in our body. They form as an extended chain of amino acids and fold into a three-dimensional (3D) structure that governs their function. Determining proteins’ 3D structure is key to understanding how they work, why they cause diseases, and how researchers can design drugs to block or activate their functions. 

Efficient deep learning methods perform structural analysis tasks at large scale, ranging from the classification of experimentally determined proteins to the quality assessment and ranking of computationally generated protein models in the context of protein structure prediction. Yet, the literature discussing these methods does not usually interpret what the models learned from the training or identify specific data attributes that contribute to the classification or regression task.

While 3D and 2D CNNs have been widely used to deal with structural data, they have several limitations when applied to structural proteomics data. Graph-based convolutional neural networks (GCNNs) are an efficient alternative while producing results that are interpretable. They are able to learn effectively from simplistic graph representations of protein structures while providing the ability to interpret what the network learns during the training and how it applies it to perform its task.

GCNNs perform comparably to their 2D CNN counterparts in predictive performance and they are outperformed by them in training speeds. The graph-based data representation allows GCNNs to be a more efficient option over 3D CNNs when working with large-scale datasets as preprocessing costs and data storage requirements are negligible in comparison. [Read more]

Molecular Dynamics simulation of STING protein

This work, which is a collaboration with Prof. Masakatsu Watanabe and his students at Fort Hays State University, focuses on the stimulator of interferon genes (STING) protein. Recent studies have shown that STING plays a central role in the immune system by facilitating the production of Type I interferons in cells. Because of its central role in immunological research and drug discovery for cancer treatments, an understanding of the STING molecular pathway would help develop new effective strategies to combat cancer and immune diseases. STING’s pathway is activated once it binds to the ligand. However, due to the size and complexity of these biological systems, the details of the binding process and activation of the STING pathway at the atomic level are still unclear. Rachel ran molecular dynamics simulations on the Cori supercomputer to investigate structural and dynamic differences between wild-type and ligand-bound human STING proteins to shed some light on this pathway. Our results support the idea proposed by previous work which states that the CTD region of STING undergoes a 180 º rotation when bound to ISY ligand.