Tian Xia

Tian Xia is a Ph.D. student in the Department of Computer Science and Software Engineering at Auburn University. My research advisor is Dr. Wei-Shinn Ku.

Research interests: I am broadly interested in designing machine learning algorithms for solving real-world problems related to drug discovery, structural biology, and other related domains. My research seeks to develop novel machine learning models that can be incorporated into practical applications to improve robustness, efficiency, generalizability, and interpretability.

news

Nov 2, 2021	I am grateful for receiving AWS Cloud Credits for Research Program!
May 20, 2021	Grateful that our project has been accepted by the Oracle for Research program!
May 19, 2021	Our work “Geometric Graph Representation Learning on Protein Structure Prediction” is accepted in KDD 2021 (acceptance rate: 15.4%)!
Jan 15, 2016	Here we go!

selected publications

KDD2021

Geometric Graph Representation Learning on Protein Structure Prediction

Xia, Tian, and Ku, Wei-Shinn

In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining 2021

Abs HTML PDF

Determining a protein’s 3D from its sequences is one of the most challenging problems in biology. Recently, geometric deep learning has achieved great success on non-Euclidean domains including social networks, chemistry, and computer graphics. Although it is natural to present protein structures as 3D graphs, existing research has rarely studied protein structures as graphs directly. The present research explores the geometry deep learning of three-dimensional graphs on protein structures and proposes a graph neural network architecture to address these challenges. The proposed Protein Geometric Graph Neural Network (PG-GNN) models both distance geometric graph representation and dihedral geometric graph representation by geometric graph convolutions. This research shed new light on protein 3D structure studies. We investigated the effectiveness of graph neural networks over five real datasets. Our results demonstrate the potential of GNNs for 3D structure prediction.