Lei Huang

Lei Huang

Auto-generated profile, based on publicly available information

Lei Huang

Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
26 March 2024 in Nature Communications
Verified
Journal Article
Open access
PDF file
LHLei Huang
Lei Huang
TXTingyang Xu
Tingyang Xu
YYYang Yu
Yang Yu
PZPeilin Zhao
Peilin Zhao
XCXingjian Chen
Xingjian Chen
HZHengtong Zhang
Hengtong Zhang
Structure-based generative chemistry is essential in computer-aided drug discovery by exploring a vast chemical space to design ligands with high binding affinity for targets. However, traditional in silico methods are limited by computational inefficiency, while machine learning approaches face bottlenecks due to auto-regressive sampling. To address these concerns, we have developed a conditional deep generative model, PMDM, for 3D molecule generation fitting specified targets. PMDM consists of a conditional equivariant diffusion model with both local and global molecular dynamics, enabling PMDM to consider the conditioned protein information to generate molecules efficiently. The comprehensive experiments indicate that PMDM outperforms baseline models across multiple evaluation metrics. To evaluate the applications of PMDM under real drug design scenarios, we conduct lead compound optimization for SARS-CoV-2 main protease (Mpro) and Cyclin-dependent Kinase 2 (CDK2), respectively. The selected lead optimization molecules are synthesized and evaluated for their in-vitro activities against CDK2, displaying improved CDK2 activity.

10 February 2023 in Advanced Science
Verified
Journal Article
Open access
ZZZetian Zheng
Zetian Zheng
JCJunyi Chen
Junyi Chen
XCXingjian Chen
Xingjian Chen
LHLei Huang
Lei Huang
WXWeidun Xie
Weidun Xie
Ka-Chun WongKa-Chun Wong
Ka-Chun Wong
The single‐cell RNA sequencing (scRNA‐seq) quantifies the gene expression of individual cells, while the bulk RNA sequencing (bulk RNA‐seq) characterizes the mixed transcriptome of cells. The inference of drug sensitivities for individual cells can provide new insights to understand the mechanism of anti‐cancer response heterogeneity and drug resistance at the cellular resolution. However, pharmacogenomic information related to their corresponding scRNA‐Seq is often limited. Therefore, a transfer learning model is proposed to infer the drug sensitivities at single‐cell level. This framework learns bulk transcriptome profiles and pharmacogenomics information from population cell lines in a large public dataset and transfers the knowledge to infer drug efficacy of individual cells. The results suggest that it is suitable to learn knowledge from pre‐clinical cell lines to infer pre‐existing cell subpopulations with different drug sensitivities prior to drug exposure. In addition, the model offers a new perspective on drug combinations. It is observed that drug‐resistant subpopulation can be sensitive to other drugs (e.g., a subset of JHU006 is Vorinostat‐resistant while Gefitinib‐sensitive); such finding corroborates the previously reported drug combination (Gefitinib + Vorinostat) strategy in several cancer types. The identified drug sensitivity biomarkers reveal insights into the tumor heterogeneity and treatment at cellular resolution.

2 November 2021 in Aslib Journal of Information Management
Verified
Journal Article
Closed access
LHLei Huang
Lei Huang
JZJingyi Zhou
Jingyi Zhou
JLJiecong Lin
Jiecong Lin
SDShengli Deng
Shengli Deng
Purpose: In the era of big data, people are more likely to pay attention to privacy protection with facing the risk of personal information leakage while enjoying the convenience brought by big data technology. Furthermore, people’s views on personal information leakage and privacy protection are varied, playing an important role in the legal process of personal information protection. Therefore, this paper aims to propose a semi-qualitative method based framework to reveal the subjective patterns about information leakage and privacy protection and further provide practical implications for interested party.Design/methodology/approach: Q method is a semi-qualitative methodology which is designed for identifying typologies of perspectives. In order to have a comprehensive understanding of users’ viewpoints, this study incorporates LDA & TextRank method and other information extraction technologies to capture the statements from large-scale literature, app reviews, typical cases and survey interviews, which could be regarded as the resource of the viewpoints.Findings: By adopting the Q method that aims for studying subjective thought patterns to identify users’ potential views, the authors have identified three categories of stakeholders’ subjectivities: macro-policy sensitive, trade-offs and personal information sensitive, each of which perceives different risk and affordance of information leakage and importance and urgency of privacy protection. All of the subjectivities of the respondents reflect the awareness of the issue of information leakage, that is, the interested parties like social network sites are unable to protect their full personal information, while reflecting varied resistance and susceptibility of disclosing personal information for big data technology applications.Originality/value: The findings of this study provide an overview of the subjective patterns on the information leakage issue. Being the first to incorporate the Q method to study the views of personal information leakage and privacy protection, the research not only broadens the application field of the Q method but also enriches the research methods for personal information protection. Besides, the proposed LDA & TextRank method in this paper alleviates the limitation of statements resource in the Q method.

17 April 2024 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
RLRui Liu
Rui Liu
HYHuang Yuan
Huang Yuan
YHYao Hu
Yao Hu
LHLei Huang
Lei Huang
Ka-Chun WongKa-Chun Wong
Ka-Chun Wong
KTKay Chen Tan
Kay Chen Tan
Facing the prevalence of mental disorders around the world, the burden of healthcare services becomes increasingly imminent. To lessen patients' suffering, the timely diagnosis and therapy of mental disorders are particularly essential. Functional magnetic resonance imaging (fMRI), as the de facto non-invasive neuroimaging technique, can effectively examine the spatial and temporal patterns of brain activity. Recently, computer-aided diagnosis (CAD) approaches have emerged to assist doctors in interpreting fMRI images. However, existing CAD methods cannot fully exploit the spatio-temporal dependence in fMRI signals, possibly leading to inaccurate diagnosis. In this study, we propose a spatio-temporal hybrid attentive graph network (ST-HAG) for diagnosing autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD) from fMRI data. Specifically, a hybrid graph convolution network is developed to effectively capture complex spatio-temporal dynamics. Meanwhile, a Transformer-based self-attention module helps ST-HAG to extract the full-scale temporal correlation. Finally, we use a gated fusion unit to learn discriminative spatio-temporal graph representations for classification. Cross-validation experiments demonstrate that the proposed ST-HAG achieves state-of-the-art performance with a mean accuracy of 71.9% and 74.8% for ASD and ADHD on ABIDE (1035 subjects) and ADHD-200 (939 subjects) datasets, respectively. Moreover, thanks to the adopted dynamic graph attentive representation, the potent interpretability enables ST-HAG to detect the remarkable temporal association patterns among different brain regions based on dynamic functional connectivity networks.

11 April 2024 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Closed access
LHLei Huang
Lei Huang
ZYZheng Yuan
Zheng Yuan
HYHuihui Yan
Huihui Yan
RSRong Sheng
Rong Sheng
LLLinjing Liu
Linjing Liu
YZYaoyun Zhang
Yaoyun Zhang
Advances in deep generative models shed light on de novo molecule generation with desired properties. However, molecule generation targeted for dual protein targets still faces formidable challenges including insufficient protein 3D structure data requisition for conditioned model training, inflexibility of auto-regressive sampling, and model generalization to unseen targets. Here, this study proposed DiffDTM, a novel unified structure-free deep generative framework based on a diffusion model for dual-target based molecule generation to address the above issues. Specifically, DiffDTM receives representations of protein sequences and molecular graphs pretrained on large-scale datasets as inputs instead of protein and molecular conformations and incorporates an information fusion module to achieve conditional generation in a one-shot manner. We perform comprehensive multi-view experiments to demonstrate that DiffDTM can generate drug-like, synthesis-accessible, novel, and high-binding affinity molecules targeting specific dual proteins, outperforming the state-of-the-art (SOTA) models in terms of multiple evaluation metrics. Furthermore, DiffDTM could directly generate molecules toward dopamine receptor D2 and 5- hydroxytryptamine receptor 1A as new antipsychotics. Experimental comparisons highlight the generalizability of DiffDTM to easily adapt to unseen dual targets and generate bioactive molecules, addressing the issues of insufficient active molecule data for model training when new targets are encountered.

6 August 2019 in Nature Communications
Verified
Journal Article
Open access
PDF file
MMMylène M. Maury
Mylène M. Maury
HBHélène Bracq-Dieye
Hélène Bracq-Dieye
LHLei Huang
Lei Huang
GVGuillaume Vales
Guillaume Vales
MLMorgane Lavina
Morgane Lavina
MLMarc Lecuit
Marc Lecuit
An amendment to this paper has been published and can be accessed via a link at the top of the paper.