Xiaowen Wang
Tongji University
14 Papers
12 Citations
Xiaowen Wang is an academic researcher from Tongji University. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 2, co-authored 6 publications.
Chat about Author
Papers
PRODeepSyn: predicting anticancer synergistic drug combinations by embedding cell lines with protein–protein interaction network
Xiaowen Wang,Hongming Zhu,Yizhi Jiang,Yulong Li,Chen Tang,Xiaohan Chen,Yunjie Li,Qi Li,Qin Liu +8 more
TL;DR: This study proposes a novel deep learning method, termed PRODeepSyn, for predicting anticancer synergistic drug combinations using the protein–protein interaction network with omics data and builds a deep neural network with the Batch Normalization mechanism to predict synergy scores using the cell line embeddings and drug features.
Semi-supervised heterogeneous graph contrastive learning for drug-target interaction prediction.
TL;DR: SHGCL-DTI as mentioned in this paper proposes a self-supervised contrastive learning module for predicting drug-target interactions (DTIs), which is independent of labeled DTIs, which can mitigate the impact of the problem.
16
Patent
A data fusion method and device for a knowledge graph
Liu Tao,Hongming Zhu,Gu Jiang,Yizhi Jiang,Xiaowen Wang,Zhou You +5 more
- 10 May 2019
TL;DR: In this article, a data fusion method and device for a knowledge graph is presented, which comprises a data platform configured with a unified access interface, and the method comprises the following steps: processing data from different data sources, converting the processed data into a triple format, storing the processed information into the data platform through the unified access interfaces, and receiving graph data index information returned by the data platforms; according to the graph index information, dividing an entity stored in the platform into one or more sub-partitions according to attributes, performing similarity calculation on the candidate entity pairs divided into
7
FTRLIM: Distributed Instance Matching Framework for Large-Scale Knowledge Graph Fusion.
TL;DR: Follow-the-Regular-Leader Instance Matching (FTRLIM) as discussed by the authors constructs indexes for instances based on the Ordered Joint of Multiple Objects' features to limit the number of candidate instance pairs.
5
•Proceedings Article
Modeling Relation Path for Knowledge Graph via Dynamic Projection.
Hongming Zhu,Yizhi Jiang,Xiaowen Wang,Hongfei Fan,Qin Liu,Bowen Du +5 more
- 01 Jan 2020
TL;DR: This paper embeds entities and relations in the knowledge graph into different semantic spaces, and project the embedding results to the same space dynamically, while maintaining the consistency of the relation path between entities.
2