G
Guo-Wei Wei
Researcher at Michigan State University
Publications - 328
Citations - 16850
Guo-Wei Wei is an academic researcher from Michigan State University. The author has contributed to research in topics: Persistent homology & Solvation. The author has an hindex of 63, co-authored 320 publications receiving 12992 citations. Previous affiliations of Guo-Wei Wei include University of British Columbia & University of Houston System.
Papers
More filters
Journal ArticleDOI
MathDL: mathematical deep learning for D3R Grand Challenge 4
TL;DR: In the D3R Grand Challenge 4 (GC4), Wang et al. as discussed by the authors presented the performances of their mathematical deep learning (MathDL) models for pose prediction, affinity ranking, and free energy estimation for beta secretase 1 (BACE) as well as affinity ranking for Cathepsin S (CatS).
Posted Content
A topological approach for protein classification
TL;DR: The present study establishes computational topology as an independent and effective alternative for protein classification as well as proposing a molecular topological fingerprint based support vector machine (MTF-SVM) classifier.
Journal ArticleDOI
Boosting Tree-Assisted Multitask Deep Learning for Small Scientific Datasets.
TL;DR: It is found that the proposed BTAMDL models outperform the current state-of-the-art methods in various applications involving small datasets, including toxicity, partition coefficient, solubility and solvation.
Journal ArticleDOI
Discrete Singular Convolution-Finite Subdomain Method for the Solution of Incompressible Viscous Flows
TL;DR: The utility of the DSC?FSM approach is illustrated by two other benchmark problems, viz., the flow over a backward-facing step and the laminar flow past a square prism, which compare well with the numerical and experimental data available in the literature.
Journal ArticleDOI
TopP-S: Persistent homology-based multi-task deep neural networks for simultaneous predictions of partition coefficient and aqueous solubility.
TL;DR: In this article, an algebraic topology-based method, called element-specific persistent homology (ESPH), is introduced to describe molecular properties in terms of multiscale and multicomponent topological invariants.