Hongyan Wu

Hongyan Wu


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 November 2022 in Nature Machine Intelligence
Verified
Journal Article
Open access
PDF file
JZJie Zhang
Jie Zhang
YDYishan Du
Yishan Du
PZPengfei Zhou
Pengfei Zhou
JDJinru Ding
Jinru Ding
XSXia Shuai
Xia Shuai
SZShaoting Zhang
Shaoting Zhang
Most natural and synthetic antibodies are ‘unseen’. That is, the demonstration of their neutralization effects with any antigen requires laborious and costly wet-lab experiments. The existing methods that learn antibody representations from known antibody–antigen interactions are unsuitable for unseen antibodies owing to the absence of interaction instances. The DeepAAI method proposed herein learns unseen antibody representations by constructing two adaptive relation graphs among antibodies and antigens and applying Laplacian smoothing between unseen and seen antibodies’ representations. Rather than using static protein descriptors, DeepAAI learns representations and relation graphs ‘dynamically’, optimized towards the downstream tasks of neutralization prediction and 50% inhibition concentration estimation. The performance of DeepAAI is demonstrated on human immunodeficiency virus, severe acute respiratory syndrome coronavirus 2, influenza and dengue. Moreover, the relation graphs have rich interpretability. The antibody relation graph implies similarity in antibody neutralization reactions, and the antigen relation graph indicates the relation among a virus’s different variants. We accordingly recommend probable broad-spectrum antibodies against new variants of these viruses.

3 May 2019 in International Journal of Distributed Sensor Networks
Verified
Journal Article
Open access
PDF file
LCLi Chen
Li Chen
DLDongxin Lu
Dongxin Lu
MZMenghao Zhu
Menghao Zhu
MMMuhammad Muzammal
Muhammad Muzammal
Oluwarotimi Williams SamuelOluwarotimi Williams Samuel
Oluwarotimi Williams Samuel
HWHongyan Wu
Hongyan Wu
Millions of adults have diabetes across the globe and the overall cost for managing diabetic patients has reached up to approximately 250 million. A major constraint in existing ontology-based systems for diagnosing and treating diabetes is the presence of semantic inconsistencies and lack of a comprehensive clinical approach primarily due to consideration of a limited number of classes in the model. In this research, we are focused on building an ontology-based model for diabetic patients by collecting detailed diabetic knowledge of subjects for further diagnosis and treatment. The concept of semantic resources to electronic health record standards is an essential factor for semantic interoperability in remote health monitoring. This study applies semantic web ontology language for developing ontology-based model for diabetic patients to aid doctors in reaching an efficient diagnostic decision about the status of diabetes by applying Semantic Web Rule Language. A total of 766 medical records from clinical environment were selected in this study, and 269 of them were known for developing diabetes. The experimental results suggest that the proposed solution is more accurate in managing diabetes compared to other medical applications. The performance analysis of the ontology-based model for diabetic patients regarding the accuracy of disease prediction, diagnosing diabetes, and recommending medicine is 95%, 98%, and 85%, respectively.

31 December 2018 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
YWYingying Wang
Yingying Wang
HWHongyan Wu
Hongyan Wu
YCYunpeng Cai
Yunpeng Cai
Protein sequence alignment analyses have become a crucial step for many bioinformatics studies during the past decades. Multiple sequence alignment (MSA) and pair-wise sequence alignment (PSA) are two major approaches in sequence alignment. Former benchmark studies revealed drawbacks of MSA methods on nucleotide sequence alignments. To test whether similar drawbacks also influence protein sequence alignment analyses, we propose a new benchmark framework for protein clustering based on cluster validity. This new framework directly reflects the biological ground truth of the application scenarios that adopt sequence alignments, and evaluates the alignment quality according to the achievement of the biological goal, rather than the comparison on sequence level only, which averts the biases introduced by alignment scores or manual alignment templates. Compared with former studies, we calculate the cluster validity score based on sequence distances instead of clustering results. This strategy could avoid the influence brought by different clustering methods thus make results more dependable. Results showed that PSA methods performed better than MSA methods on most of the BAliBASE benchmark datasets. Analyses on the 80 re-sampled benchmark datasets constructed by randomly choosing 90% of each dataset 10 times showed similar results. These results validated that the drawbacks of MSA methods revealed in nucleotide level also existed in protein sequence alignment analyses and affect the accuracy of results.

28 February 2025 in Interdisciplinary Sciences: Computational Life Sciences
Verified
Journal Article
Closed access
PDF file
SASaba Aslam
Saba Aslam
Abdur RasoolAbdur Rasool
Abdur Rasool
XLXiaoli Li
Xiaoli Li
HWHongyan Wu
Hongyan Wu

14 September 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Open access
CJChaojie Ji
Chaojie Ji
YZYijia Zheng
Yijia Zheng
RWRuxin Wang
Ruxin Wang
YCYunpeng Cai
Yunpeng Cai
HWHongyan Wu
Hongyan Wu
Molecular optimization, which transforms a given input molecule X into another Y with desired properties, is essential in molecular drug discovery. The traditional approaches either suffer from sample-inefficient learning or ignore information that can be captured with the supervised learning of optimized molecule pairs. In this study, we present a novel molecular optimization paradigm, Graph Polish. In this paradigm, with the guidance of the source and target molecule pairs of the desired properties, a heuristic optimization solution can be derived: given an input molecule, we first predict which atom can be viewed as the optimization center, and then the nearby regions are optimized around this center. We then propose an effective and efficient learning framework, Teacher and Student polish, to capture the dependencies in the optimization steps. A teacher component automatically identifies and annotates the optimization centers and the preservation, removal, and addition of some parts of the molecules; a student component learns these knowledges and applies them to a new molecule. The proposed paradigm can offer an intuitive interpretation for the molecular optimization result. Experiments with multiple optimization tasks are conducted on several benchmark datasets. The proposed approach achieves a significant advantage over the six state-of-the-art baseline methods. Also, extensive studies are conducted to validate the effectiveness, explainability, and time savings of the novel optimization paradigm.

24 March 2023 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
JZJie Zhang
Jie Zhang
PZPengfei Zhou
Pengfei Zhou
YZYijia Zheng
Yijia Zheng
HWHongyan Wu
Hongyan Wu