Pu Tian

The paper characterizes cross-family conserved fragments, showing their structural and biophysical properties and their role in folding and stability.

ProDive detects cross-family local conservation using a pHMM-based framework, identifying 318,289 high confidence segment correspondences across 25,545 Pfam families.

The paper develops scalable algorithms for accurate multiple sequence alignment of ultramassive genome sets, achieving significant speedup and improved accuracy over MAFFT.

This paper introduces a computational graph framework for free energy optimization in molecular systems, achieving efficient and accurate protein structure refinement.

This paper introduces a hierarchical clustering algorithm that avoids record comparison, achieving linear time complexity for high-dimensional data with strong nonlinear correlations.

This paper introduces a non-parametric global sequence comparison method using sorted composition vectors to efficiently classify and compare large protein sequence datasets.

The paper introduces a context convolutional neural network for protein secondary structure prediction and shows it achieves competitive accuracy compared to existing methods.