Hongzhi Wen

Hongzhi Wen

Auto-generated profile, based on publicly available information

Hongzhi Wen

Michigan State University

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
5 October 2023 in bioRxiv
Verified
Preprint
Open access
PDF file
HWHongzhi Wen
Hongzhi Wen
WTWenzhuo Tang
Wenzhuo Tang
XDXinnan Dai
Xinnan Dai
JDJiayuan Ding
Jiayuan Ding
WJWei Jin
Wei Jin
JTJiliang Tang
Jiliang Tang
The current state-of-the-art single-cell pre-trained models are greatly inspired by the success of large language models. They trained transformers by treating genes as tokens and cells as sentences. However, three fundamental differences between single-cell data and natural language data are overlooked: (1) scRNA-seq data are presented as bag-of-genes instead of sequences of RNAs; (2) Cell-cell relations are more intricate and important than inter-sentence relations; and (3) The quantity of single-cell data is considerably inferior to text data, and they are very noisy. In light of these characteristics, we propose a new pre-trained model CellPLM , which takes cells as tokens and tissues as sentences. In addition, we leverage spatially-resolved transcriptomic data in pre-training to facilitate learning cell-cell relationships and introduce a Gaussian mixture prior distribution as an additional inductive bias to overcome data limitation. CellPLM is the first single-cell pre-trained transformer that encodes cell-cell relations and it consistently outperforms existing pre-trained and non-pre-trained models in diverse downstream tasks, with 100x times higher inference speed compared to existing pre-trained models.

29 March 2024 in ACM Transactions on Intelligent Systems and Technology
Verified
Journal Article
Open access
DMDylan Molho
Dylan Molho
JDJiayuan Ding
Jiayuan Ding
WTWenzhuo Tang
Wenzhuo Tang
ZLZhaoheng Li
Zhaoheng Li
HWHongzhi Wen
Hongzhi Wen
JTJiliang Tang
Jiliang Tang
Single-cell technologies are revolutionizing the entire field of biology. The large volumes of data generated by single-cell technologies are high dimensional, sparse, and heterogeneous and have complicated dependency structures, making analyses using conventional machine learning approaches challenging and impractical. In tackling these challenges, deep learning often demonstrates superior performance compared to traditional machine learning methods. In this work, we give a comprehensive survey on deep learning in single-cell analysis. We first introduce background on single-cell technologies and their development, as well as fundamental concepts of deep learning including the most popular deep architectures. We present an overview of the single-cell analytic pipeline pursued in research applications while noting divergences due to data sources or specific applications. We then review seven popular tasks spanning different stages of the single-cell analysis pipeline, including multimodal integration, imputation, clustering, spatial domain identification, cell-type deconvolution, cell segmentation, and cell-type annotation. Under each task, we describe the most recent developments in classical and deep learning methods and discuss their advantages and disadvantages. Deep learning tools and benchmark datasets are also summarized for each task. Finally, we discuss the future directions and the most recent challenges. This survey will serve as a reference for biologists and computer scientists, encouraging collaborations.

21 October 2023 in Proceedings of SPIE
Verified
Conference Paper
Open access
WTWenzhuo Tang
Wenzhuo Tang
HWHongzhi Wen
Hongzhi Wen
RLRenming Liu
Renming Liu
JDJiayuan Ding
Jiayuan Ding
WJWei Jin
Wei Jin
JTJiliang Tang
Jiliang Tang
The recent development of multimodal single-cell technology has made the possibility of acquiring multiple omics data from individual cells, thereby enabling a deeper understanding of cellular states and dynamics. Nevertheless, the proliferation of multimodal single-cell data also introduces tremendous challenges in modeling the complex interactions among different modalities. The recently advanced methods focus on constructing static interaction graphs and applying graph neural networks (GNNs) to learn from multimodal data. However, such static graphs can be suboptimal as they do not take advantage of the downstream task information; meanwhile GNNs also have some inherent limitations when deeply stacking GNN layers. To tackle these issues, in this work, we investigate how to leverage transformers for multimodal single-cell data in an end-to-end manner while exploiting downstream task information. In particular, we propose a scMoFormer framework which can readily incorporate external domain knowledge and model the interactions within each modality and cross modalities. Extensive experiments demonstrate that scMoFormer achieves superior performance on various benchmark datasets. Remarkably, scMoFormer won a Kaggle silver medal with the rank of 24/1221 (Top 2%) without ensemble in a NeurIPS 2022 competition1. Our implementation is publicly available at Github2.

2 July 2024
Verified
Book Chapter
Closed access
PDF file
KYKaiqi Yang
Kaiqi Yang
YCYucheng Chu
Yucheng Chu
TDTaylor Darwin
Taylor Darwin
AHAhreum Han
Ahreum Han
HLHang Li
Hang Li
HLHui Liu
Hui Liu

1 January 2024
Verified
Conference Paper
Open access
PDF file
KYKaiqi Yang
Kaiqi Yang
HLHang Li
Hang Li
HWHongzhi Wen
Hongzhi Wen
TPTai-Quan Peng
Tai-Quan Peng
JTJiliang Tang
Jiliang Tang
HLHui Liu
Hui Liu
Kaiqi Yang, Hang Li, Hongzhi Wen, Tai-Quan Peng, Jiliang Tang, Hui Liu. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

24 August 2024
Verified
Conference Paper
Open access
KGKai Guo
Kai Guo
HWHongzhi Wen
Hongzhi Wen
WJWei Jin
Wei Jin
YGYaming Guo
Yaming Guo
JTJiliang Tang
Jiliang Tang
YCYi Chang
Yi Chang
Graph neural networks (GNNs) have exhibited remarkable performance under the assumption that test data comes from the same distribution of training data. However, in real-world scenarios, this assumption may not always be valid. Consequently, there is a growing focus on exploring the Out-of-Distribution (OOD) problem in the context of graphs. Most existing efforts have primarily concentrated on improving graph OOD generalization from two model-agnostic perspectives: data-driven methods and strategy-based learning. However, there has been limited attention dedicated to investigating the impact of well-known GNN model architectures on graph OOD generalization, which is orthogonal to existing research. In this work, we provide the first comprehensive investigation of OOD generalization on graphs from an architecture perspective, by examining the common building blocks of modern GNNs. Through extensive experiments, we reveal that both the graph self-attention mechanism and the decoupled architecture contribute positively to graph OOD generalization. In contrast, we observe that the linear classification layer tends to compromise graph OOD generalization capability. Furthermore, we provide in-depth theoretical insights and discussions to underpin these discoveries. These insights have empowered us to develop a novel GNN backbone model, DGat, designed to harness the robust properties of both graph self-attention mechanism and the decoupled architecture. Extensive experimental results demonstrate the effectiveness of our model under graph OOD, exhibiting substantial and consistent enhancements across various training strategies. Our codes are available at https://github.com/KaiGuo20/DGAT **REMOVE 2nd URL**://github.com/KaiGuo20/DGAT.