1 code implementation • 28 Oct 2023 • JunJie Wee, Jiahui Chen, Kelin Xia, Guo-Wei Wei
The Transformer, pretrained with hunderds of millions of protein sequences, embeds wild-type and mutant sequences, while persistent Laplacians track the topological invariant change and homotopic shape evolution induced by mutations in 3D protein structures, which are rendered from AlphaFold2.
no code implementations • 25 Oct 2023 • See Hian Lee, Feng Ji, Kelin Xia, Wee Peng Tay
Traditionally, graph neural networks have been trained using a single observed graph.
1 code implementation • 23 Jun 2023 • Cong Shen, Xiang Liu, Jiawei Luo, Kelin Xia
This demonstrates that analytic torsion is a highly efficient topological invariant in the characterization of graph structures and can significantly boost the performance of GNNs.
1 code implementation • 23 Jun 2023 • Cong Shen, Pingjian Ding, JunJie Wee, Jialin Bi, Jiawei Luo, Kelin Xia
The results from the simulated data show that our CGCN model is superior to the traditional GCN models regardless of the positive-to-negativecurvature ratios, network densities, and network sizes (when larger than 500).
1 code implementation • 22 Jun 2023 • Cong Shen, Jiawei Luo, Kelin Xia
This demonstrates the great potential of novel molecular representations beyond the de facto standard of covalent-bond-based molecular graphs.
no code implementations • 5 Feb 2023 • JunJie Wee, Ginestra Bianconi, Kelin Xia
A series of physical persistent attributes, which characterize the spectrum of the Dirac matrices across a filtration, are proposed and used as efficient molecular fingerprints.
1 code implementation • 20 Nov 2020 • JunJie Wee, Kelin Xia
Persistence and variation of Ollivier Ricci curvatures on these nested graphs are defined as Ollivier persistent Ricci curvature.
no code implementations • 3 Feb 2020 • Zhenyu Meng, Kelin Xia
In this paper, we propose persistent spectral based machine learning (PerSpect ML) models for drug design.
no code implementations • 1 Nov 2018 • Chi Seng Pun, Kelin Xia, Si Xian Lee
A suitable feature representation that can both preserve the data intrinsic information and reduce data complexity and dimensionality is key to the performance of machine learning models.
Algebraic Topology
no code implementations • 4 Oct 2015 • Zixuan Cang, Lin Mu, Kedi Wu, Kristopher Opron, Kelin Xia, Guo-Wei Wei
However prediction of protein function and dynamics from its sequence and structure is still a fundamental challenge in molecular biology.
Biomolecules