Author name cluster

Qiuzhen Lin

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

21 papers

2 author rows

JBHI Journal 2026 Journal Article

Genetic Perturbation Modeling for Human Cell Therapy With BRNET

Luyang Cai
Jixang Yu
Qiuzhen Lin
Lichen Liu
Xiangtao Li
Ka-Chun Wong

Cellular responses to genetic perturbations are prevalent in wide contexts from the fundamental understandings on pathology to the development of clinical therapies and the discovery of novel drug targets. Nonetheless, the substantial amount of possible perturbation combinations renders wet-lab experiments prohibitively expensive and time-consuming. To address it, the BRNET model is proposed for predicting non-linear transcriptional outcomes where multiple perturbations exist. BRNET integrates prior knowledge with advanced embeddings into a non-stacked neural structure to predict transcriptional responses to both individual and multiple genetic perturbations. For unseen scenarios, BRNET also generalizes well under the corresponding perturbations. Experimental results highlight the capabilities of BRNET, demonstrating promising performance as compared to established deep learning models.

Details DOI

JBHI Journal 2026 Journal Article

Gero-LLM: A Multimodal Large Language Model for Geroprotector Discovery via Cross-Modal Differentiated Mutual Learning

Zhongshen Li
Jixiang Yu
Shen You
Danei Gong
Jiayue Liu
Luyang Cai
Qiuzhen Lin
Xiangtao Li

Geroprotectors underpin therapeutic strategies to intervene in aging pathologies and extend lifespans. Unfortunately, geroprotector discovery remains a significant challenge due to data quality and pathway redundancy. Existing methods often rely on single data modalities, which fail in capturing the intricate structure-activity relationships in geroprotector molecules. Therefore, we present Gero-LLM, a multimodal framework that synergizes the reasoning capabilities of pre-trained large language models (LLMs) with the topological modeling of Graph Isomorphism Network with Edge features (GINE) for geroprotector discovery. By fusing textual representations with structural embeddings, Gero-LLM leverages multimodal chemical information to enhance predictive ability. To overcome the limitations of standard fine-tuning, we utilize a cross-modal differentiated deep mutual learning (CM-Diff-DML) strategy. This training paradigm enforces the diversity between modalities, preventing mode collapse and improving model prediction ability. Gero-LLM achieves state-of-the-art performance, demonstrating promising robustness on highly imbalanced external datasets, resembling the real-world geroprotector screening scenarios. Furthermore, in silico mutagenesis confirms that Gero-LLM captures fundamental chemical pharmacophores beyond summary statistics. This work attempts to bridge the gaps between LLMs and multimodal molecule information, providing a robust platform to accelerate the discovery of therapeutic interventions on aging.

Details DOI

AAAI Conference 2026 Conference Paper

M3SR: Multi-Scale Multi-Perceptual Mamba for Efficient Spectral Reconstruction

Yuze Zhang
Lingjie Li
Qiuzhen Lin
Zhong Ming
Fei Yu
Victor C. M. Leung

The Mamba architecture has been widely applied to various low-level vision tasks due to its exceptional adaptability and strong performance. Although the Mamba architecture has been adopted for spectral reconstruction, it still faces the following two challenges: (1) Single spatial perception limits the ability to fully understand and analyze hyperspectral images; (2) Single-scale feature extraction struggles to capture the complex structures and fine details present in hyperspectral images. To address these issues, we propose a multi-scale, multi-perceptual Mamba architecture for the spectral reconstruction task, called M3SR. Specifically, we design a multi-perceptual fusion block to enhance the ability of the model to comprehensively understand and analyze the input features. By integrating the multi-perceptual fusion block into a U-Net structure, M3SR can effectively extract and fuse global, intermediate, and local features, thereby enabling accurate reconstruction of hyperspectral images at multiple scales. Extensive quantitative and qualitative experiments demonstrate that the proposed M3SR outperforms existing state-of-the-art methods while incurring a lower computational cost.

PDF Details DOI

JBHI Journal 2026 Journal Article

Phage Host Prediction Using Deep Neural Network With Multi-Source Protein Language Models and Squeeze-and-Excitation Attention Mechanism

Peng Gao
Long Xu
Yuan Bai
Qiuzhen Lin
Junkai Ji
Lijia Ma

Phage therapy (PT) has become a promising alternative for treating infections with the increase of antimicrobial resistance. PT utilizes phages to bind to specific receptors on bacterial surfaces via receptor-binding proteins (RBPs), enabling precise destruction of targeted hosts. In PT, a key issue is the phage host prediction (PHP), which tries to match therapeutic phages to pathogenic hosts. However, traditional PHP methods are often hindered by the time-consuming and expensive wet-lab experiments, while recent computational methods neglect the evolutionary diversity and local feature patterns of RBPs. In this article, we propose a novel deep neural network (called PHPRBP) for PHP based on phage RBPs. In PHPRBP, we first utilize pre-trained protein language models (i. e. , ESM2 and ProtT5) to learn the multi-source embedding representations from these RBPs, revealing diverse and complementary features. Then, we employ an adaptive synthetic technique to augment minority class samples, addressing the data scarcity issue. Subsequently, we design a deep neural network architecture, which uses a convolutional neural network to capture local sequence features, and applies a squeeze-and-excitation attention mechanism to enhance the contribution of important features. Finally, a fully connected network is used for host prediction. Experimental results show that PHPRBP outperforms the state-of-the-arts in host prediction at both genus and species levels.

Details DOI

JBHI Journal 2026 Journal Article

Synergizing Anti-Cancer Drug Combinations With Dual-View Hypergraph Representation Fusion

Jixiang Yu
Nanjun Chen
Linlin Cao
Ming Gao
Daizong Liu
Fuzhou Wang
Qiuzhen Lin
Xiangtao Li

Drug combination therapy plays a vital role in disease treatment, including cancer, as it contributes to treatment efficacy and can alleviate the effect of drug resistance. Although clinical trials and screening may provide valuable information about synergistic drug combinations, they suffer from challenging combinatorial space. Multiple methods are proposed to address those issues. However, they still fail in making full use of global and local triplet context relationships of known synergistic combinations. To this end, a deep learning model which leverages dual view hypergraph representation fusion for synergistic drug combinations identification is proposed, namely DVHSyn. It first extracts the transcriptome features of cancer cell lines and molecular structures of drugs. Subsequently, by modeling the synergistic effect on a hypergraph, DVHSyn simultaneously learns the local and global context of the sample triplets via a hypergraph view and its expanded heterogeneous graph view. Finally, the learned representations of the above two branches are fused selectively to predict synergistic drug combinations. Experiment results demonstrate that DVHSyn surpasses six other competing methods. One case study also reflects that DVHSyn has the potential to predict novel synergistic drug combinations. Overall, our method is effective in identifying synergistic drug combinations and provides new insights for novel drug development.

Details DOI

AAAI Conference 2026 Conference Paper

Zero-shot Recommendation: Towards Class Semantic Relation Learning for Inferring Labels of Unseen Micro-videos

Junyang Chen
Huan Wang
Yirui Wu
Qiuzhen Lin
Yunfeng Diao
Junkai Ji

Micro-video label prediction plays a pivotal role on contemporary video-sharing platforms, such as Kwai and Tiktok. The emergence of video content lacking labels presents a formidable challenge for conventional user interest prediction methods. This paper addresses the challenge of micro-video label prediction, particularly for unseen videos, by proposing a zero-shot method called Class Semantic Relation Learning (CSRL). Unlike traditional user interest prediction models, CSRL leverages the pre-trained Large Language Model (LLM) to enhance prediction accuracy for unlabeled videos. The novelty of CSRL lies in its integration of three key components: a raw feature autoencoder, LLM-enhanced features, and a decomposed graph network. The decomposed graph network is specifically designed to disentangle the relationships between labeled and unlabeled videos, offering a significant improvement over previous methods. By fusing hidden topics with LLM-enhanced text, CSRL effectively handles sparse video features. Experiments on large-scale datasets from the Kwai platform show that CSRL achieves state-of-the-art results, with up to 44.64% improvement in Hit Ratio (HR), highlighting its superiority over existing zero-shot recommendation models in predicting user interests within the user-video network.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Evolutionary Reinforcement Learning with Parameterized Action Primitives for Diverse Manipulation Tasks

Xianxu Qiu
Haiming Huang
Weiwei Chen
Qiuzhen Lin
Wei-Neng Chen
Fuchun Sun

Reinforcement learning (RL) has shown promising performance in tackling robotic manipulation tasks (RMTs), which require learning a prolonged sequence of manipulation actions to control robots efficiently. However, most RL algorithms often suffer from two problems when solving RMTs: inefficient exploration due to the extremely large action space and catastrophic forgetting due to the poor sampling efficiency. To alleviate these problems, this paper introduces an Evolutionary Reinforcement Learning algorithm with parameterized Action Primitives, called ERLAP, which combines the advantages of an evolutionary algorithm (EA) and hierarchical RL (HRL) to solve diverse RMTs. A library of heterogeneous action primitives is constructed in HRL to enhance the exploration efficiency of robots and dual populations with new evolutionary operators are run in EA to optimize these primitive sequences, which can diversify the distribution of replay buffer and avoid catastrophic forgetting. The experiments show that ERLAP outperforms four state-of-the-art RL algorithms in simulated RMTs with dense rewards and can effectively avoid catastrophic forgetting in a set of more challenging simulated RMTs with sparse rewards.

PDF Details DOI

ECAI Conference 2025 Conference Paper

Population-Based Multi-Objective Reinforcement Learning with Information Sharing and Differentiation

Xiaoqiang Wu
Qingling Zhu
Junkai Ji
Qiuzhen Lin
Wei-Neng Chen
Jianqiang Li 0001

To efficiently tackle problems with multiple conflicting objectives, several Multi-Objective Reinforcement Learning (MORL) algorithms utilize a universal policy network that takes preference weights as input to represent optimal policies for all different preferences. However, it is quite challenging to train such a universal policy as it is easy to forget or fail to learn skills for some preferences. To alleviate this issue, we propose an efficient Population-Based MORL (PB-MORL) method that trains multiple agents with universal policy networks using a shared replay buffer. Each agent is biased towards optimizing specific objectives by applying differentiated weights to the rewards sampled from the buffer. Therefore, the policy of each agent only needs to handle the specific part of the preference space rather than the entire space, simplifying the training task. Meanwhile, the experiences in the common buffer facilitate the information sharing among individuals, which can significantly reduce the number of interaction steps for training multiple agents. Experiments on both continuous and discrete tasks demonstrate the superiority of PB-MORL over several state-of-the-art MORL methods.

Details

IJCAI Conference 2025 Conference Paper

STLSP: Integrating Structure and Text with Large Language Models for Link Sign Prediction of Networks

Lijia Ma
Haoyang Fu
Zhijie Cao
Xiongnan Jin
Qiuzhen Lin
Jianqiang Li

Link Sign Prediction (LSP) in signed networks is a critical task with applications in recommendation systems, community detection, and social network analysis. Existing methods primarily rely on graph neural networks to exploit structural information, often neglecting the valuable insights from edge-level textual data. Furthermore, utilizing large language models (LLMs) for LSP faces challenges in reliability and interpreting graph structures. To address these issues, we propose a novel STLSP framework that integrates signed networks' \underline{S}tructural and \underline{T}extual information with LLMs for the \underline{LSP} task. STLSP leverages structural balance theory to generate node embeddings that capture positive and negative relationships. These embeddings are transformed into natural language representations through clustering techniques, allowing LLMs to utilize the structural context fully. By integrating these representations with edge text, STLSP improves the accuracy and reliability of the LSP task. Extensive experiments conducted on five real-world datasets demonstrate that STLSP outperformed state-of-the-art baselines, achieving an 8. 7% improvement in terms of accuracy. Moreover, STLSP shows robust performance across various LLMs, making it adaptable to different computational environments. The code and data are publically available at https: //github. com/sss483/STLSP.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Structure Balance and Gradient Matching-Based Signed Graph Condensation

Rong Li
Long Xu
Songbai Liu
Junkai Ji
Lingjie Li
Qiuzhen Lin
Lijia Ma

Training graph neural networks (GNNs) for graph representation has received increasing concerns due to its outstanding performance in the link prediction and node classification tasks, but it incurs much time and storage for tackling large-scale graphs. To alleviate this issue, graph condensation has been emerged to condense the large graph into a small but highly-informative graph, while achieving comparable performance of GNNs trained on the small graph and large graph. However, existing works mainly focus on the gradient or distribution matching under GNN training trajectories to condense simple link structures, while overlooking the structure matching for condensing signed graph that exists conflict links and structural balance among nodes. To bridge this gap, we propose a novel Structure Balance and Gradient Matching-Based Signed Graph Condensation (SGSGC) method for condensing signed graph with node attributes, conflict links and structural balance into informative smaller ones. Specifically, we first propose a structure-balanced matching to match the structural balance between the original and condensed signed graph, and then combine it with the gradient matching to condense signed graph for the link sign prediction task, while preserving both conflicting link structures and node attributes. Moreover, we use the feature smoothing and the graph sparsification technique to improve the robustness for the GNN training, respectively. Finally, a bi-level optimization technique is proposed to simultaneously find the optimal node attributes and conflict structure of the condensed graph. Experiments on six datasets demonstrate that SGSGC achieves excellent performance. On Epinions, 94% test accuracy of training on the original signed graph, while reducing their graph size by 99.95% - 99.99%, and there exist 2.24% – 6.26% accuracy improvements for link sign prediction compared to the state-of-the-arts.

PDF Details DOI

JBHI Journal 2025 Journal Article

When East Meets West: Cross-Domain Drug Interaction Annotations With Large Language Models and Bidirectional Neural Networks

Ruoxuan Zhang
Weidun Xie
Qiuzhen Lin
Xiangtao Li
Ka-Chun Wong

Drug combination therapy is a promising strategy for managing complex and co-existing diseases. However, drug-drug interactions (DDIs) can result in unexpected adverse effects, making it crucial to understand such interactions to prevent adverse drug reactions and develop new therapeutic strategies. Current DDI annotation methods heavily rely on atom-level graph structural features, overlooking valuable drug contextual representations within medical literature. Additionally, these methods are typically designed for a specific task, limiting their scalability to diverse medical scenarios. To address these limitations, we propose TEmbed-DDI, a novel framework that leverages contextual representations and pre-trained large language model embeddings to enhance feature extraction for DDI annotations. Specifically, we retrieve meaningful contextual texts for each drug to enrich semantic features and adopt pre-trained large language model embeddings to capture rich features from these long-range contextual representations. TEmbed-DDI is the first framework to incorporate LLM-powered embeddings for medical interaction annotations. Furthermore, a bidirectional neural network is integrated into TEmbed-DDI for the integrative Western and traditional Chinese medicine DDI annotation tasks. Comparative results demonstrate that TEmbed-DDI achieves state-of-the-art performance, with the highest AUC scores of 0. 992 and 0. 95 on the Western CHCH and DEEP interaction annotation benchmarks. Even for the newly constructed Traditional Chinese Medicine (TCM) DDI annotation benchmark, TEmbed-DDI consistently exhibits outstanding generalization capability, achieving an AUC of 0. 956. Moreover, case studies further validate TEmbed-DDI's capability to annotate previously unknown interactions. These findings suggest that TEmbed-DDI can serve as a valuable tool in annotating previously unknown drug combinations for real-world applications, facilitating the development of efficacious therapies. Furthermore, as the first framework combining traditional Chinese medicine into DDI annotation tasks, its adaptability highlights the potential in supporting cross-domain medical research. TEmbed-DDI's design principles can inspire the development of flexible LLM-powered frameworks for drug combination discovery in the future.

Details DOI

EAAI Journal 2024 Journal Article

A Kriging-assisted evolutionary algorithm with multiple infill sampling for expensive many-objective optimization

Qingling Zhu
Gaoli Kang
Xunfeng Wu
Qiuzhen Lin
Huimei Tang
Jianyong Chen

Surrogate-assisted evolutionary algorithms (SAEAs) have been extensively used to solve computationally expensive multi-objective optimization problems (MOPs) as they can obtain a set of satisfyingly optimal solutions while remaining within a limited computational budget. Nevertheless, the expensive MOPs with more than three objectives have received little attention, and most existing SAEAs fail to achieve satisfactory results when solving them. Therefore, to fill this research gap, a Kriging-assisted evolutionary algorithm with multiple infill sampling for solving expensive many-objective optimization problems is proposed. In this paper, to balance exploration and exploitation, a new environmental selection operator is proposed, which is composed of three procedures conducted consecutively. In addition, a new multiple infill sampling strategy is proposed to select the most representative solutions for real function evaluations and model updates. Furthermore, to limit the computational costs of constructing/updating the surrogate model, a new archive update strategy is proposed to maneuver the training data set. In experiments, our method is verified on some benchmark problems. The experimental results demonstrate that the proposed algorithm shows promising performance when compared with four state-of-the-art SAEAs for solving expensive many-objective optimization problems.

Details DOI

EAAI Journal 2024 Journal Article

A localized decomposition evolutionary algorithm for imbalanced multi-objective optimization

Yulong Ye
Qiuzhen Lin
Ka-Chun Wong
Jianqiang Li
Zhong Ming
Carlos A. Coello Coello

Multi-objective evolutionary algorithms based on decomposition (MOEA/Ds) convert a multi-objective optimization problem (MOP) into a set of scalar subproblems, which are then optimized in a collaborative manner. However, when tackling imbalanced MOPs, the performance of most MOEA/Ds will evidently deteriorate, as a few solutions will replace most of the others in the evolutionary process, resulting in a significant loss of diversity. To address this issue, this paper suggests a localized decomposition evolutionary algorithm (LDEA) for imbalanced MOPs. A localized decomposition method is proposed to assign a local region for each subproblem, where the inside solutions are associated and the solution update is restricted inside (i. e. , solutions are only replaced by offspring within the same local region). Once off-spring are generated within an originally empty region, the best one is reserved for this subproblem to extend diversity. Meanwhile, the subproblem with the largest number of associated solutions will be found and one of its associated solutions with the worst aggregated value will be removed. Moreover, to speed up convergence for each subproblem while balancing the population's diversity, LDEA only evolves the best-associated solution in each subproblem and correspondingly tailors two decomposition methods in the environmental selection. When compared to nine competitive MOEAs, LDEA has shown the advantages in tackling two benchmark sets of imbalanced MOPs, one benchmark set of balanced yet complicated MOPs, and one real-world MOP.

Details DOI

AAMAS Conference 2024 Conference Paper

Adaptive Evolutionary Reinforcement Learning Algorithm with Early Termination Strategy

Xiaoqiang Wu
Qingling Zhu
Qiuzhen Lin
Weineng Chen
Jianqiang Li

Evolutionary reinforcement learning algorithms (ERLs), which combine evolutionary algorithms (EAs) with reinforcement learning (RL), have demonstrated significant success in enhancing RL performance. However, most ERLs rely heavily on Gaussian mutation operators to generate new individuals. When the standard deviation is too large or small, this approach will result in the production of poor or highly similar offspring. Such outcomes can be detrimental to the learning process of the RL agent, as too many poor or similar experiences are generated by these individuals. In order to alleviate these issues, this paper proposes an Adaptive Evolutionary Reinforcement Learning (AERL) method that adaptively adjusts both the standard deviation and the evaluation process. By tracking the performance of new individuals, AERL maintains the mutation strength within a suitable range without the need for additional gradient computations. Moreover, the proposed AERL approach early terminates unnecessary evaluations and discards experiences arising from poor individuals, thereby resulting in enhanced learning efficiency. Empirical assessments conducted on a variety of continuous control problems demonstrate the effectiveness of the AERL method.

PDF

AAAI Conference 2024 Conference Paper

ERL-TD: Evolutionary Reinforcement Learning Enhanced with Truncated Variance and Distillation Mutation

Qiuzhen Lin
Yangfan Chen
Lijia Ma
Wei-Neng Chen
Jianqiang Li

Recently, an emerging research direction called Evolutionary Reinforcement Learning (ERL) has been proposed, which combines evolutionary algorithm with reinforcement learning (RL) for tackling the tasks of sequential decision making. However, the recently proposed ERL algorithms often suffer from two challenges: the inaccuracy of policy estimation caused by the overestimation bias in RL and the insufficiency of exploration caused by inefficient mutations. To alleviate these problems, we propose an Evolutionary Reinforcement Learning algorithm enhanced with Truncated variance and Distillation mutation, called ERL-TD. We utilize multiple Q-networks to evaluate state-action pairs, so that multiple networks can provide more accurate evaluations for state-action pairs, in which the variance of evaluations can be adopted to control the overestimation bias in RL. Moreover, we propose a new distillation mutation to provide a promising mutation direction, which is different from traditional mutation generating a large number of random solutions. We evaluate ERL-TD on the continuous control benchmarks from the OpenAI Gym and DeepMind Control Suite. The experiments show that ERL-TD shows excellent performance and outperforms all baseline RL algorithms on the test suites.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Two-Stage Evolutionary Reinforcement Learning for Enhancing Exploration and Exploitation

Qingling Zhu
Xiaoqiang Wu
Qiuzhen Lin
Wei-Neng Chen

The integration of Evolutionary Algorithm (EA) and Reinforcement Learning (RL) has emerged as a promising approach for tackling some challenges in RL, such as sparse rewards, lack of exploration, and brittle convergence properties. However, existing methods often employ actor networks as individuals of EA, which may constrain their exploratory capabilities, as the entire actor population will stop evolution when the critic network in RL falls into local optimal. To alleviate this issue, this paper introduces a Two-stage Evolutionary Reinforcement Learning (TERL) framework that maintains a population containing both actor and critic networks. TERL divides the learning process into two stages. In the initial stage, individuals independently learn actor-critic networks, which are optimized alternatively by RL and Particle Swarm Optimization (PSO). This dual optimization fosters greater exploration, curbing susceptibility to local optima. Shared information from a common replay buffer and PSO algorithm substantially mitigates the computational load of training multiple agents. In the subsequent stage, TERL shifts to a refined exploitation phase. Here, only the best individual undergoes further refinement, while the rest individuals continue PSO-based optimization. This allocates more computational resources to the best individual for yielding superior performance. Empirical assessments, conducted across a range of continuous control problems, validate the efficacy of the proposed TERL paradigm.

PDF Details DOI

EAAI Journal 2023 Journal Article

A Kriging model-based evolutionary algorithm with support vector machine for dynamic multimodal optimization

Xunfeng Wu
Qiuzhen Lin
Wu Lin
Yulong Ye
Qingling Zhu
Victor C.M. Leung

Dynamic multimodal optimization problems (DMMOPs) have to search multiple global optimal solutions with the objectives and constraints dynamically changing over time. In recent years, dynamic optimization problems and multimodal optimization problems have been extensively studied in the field of evolutionary computation. However, DMMOPs have not yet been paid significant attention and only a few studies have been designed for dynamic multimodal optimization. The key issue in optimizing DMMOPs is to address the challenges induced by both the multimodal nature and the dynamic nature. Existing works perform poorly in locating all global optima in static environments and tracking global optima with various change modes. Therefore, in this paper, a Kriging Model-based Evolutionary Algorithm with Support Vector Machine called KMEA-SVM is proposed for tackling DMMOPs. Two important operators are designed in this algorithm, including a Kriging-based preselection and a support vector machine (SVM)-based prediction. The aim of Kriging-based preselection is to search all global optimal solutions more efficiently by preselecting promising solutions with a trained Kriging model, while the purpose of SVM-based prediction is to predict more outstanding solutions as the initial population for new environment when the environment changes. The proposed KMEA-SVM is compared with several state-of-the-art evolutionary algorithms on twenty-four test DMMOPs and the experimental results validate the advantages of KMEA-SVM on seeking more multiple optima in dynamic environments.

Details DOI

EAAI Journal 2022 Journal Article

A convergence and diversity guided leader selection strategy for many-objective particle swarm optimization

Lingjie Li
Yongfeng Li
Qiuzhen Lin
Zhong Ming
Carlos A. Coello Coello

Recently, particle swarm optimizer (PSO) is extended to solve many-objective optimization problems (MaOPs) and becomes a hot research topic in the field of evolutionary computation. Particularly, the leader particle selection (LPS) and the search direction used in a velocity update strategy are two crucial factors in PSOs. However, the LPS strategies for most existing PSOs are not so efficient in high-dimensional objective space, mainly due to the lack of convergence pressure or loss of diversity. In order to address these two issues and improve the performance of PSO in high-dimensional objective space, this paper proposes a convergence and diversity guided leader selection strategy for PSO, denoted as CDLS, in which different leader particles are adaptively selected for each particle based on its corresponding situation of convergence and diversity. In this way, a good tradeoff between the convergence and diversity can be achieved by CDLS. To verify the effectiveness of CDLS, it is embedded into the PSO search process of three well-known PSOs. Furthermore, a new variant of PSO combining with the CDLS strategy, namely PSO/CDLS, is also presented. The experimental results validate the superiority of our proposed CDLS strategy and the effectiveness of PSO/CDLS, when solving numerous MaOPs with regular and irregular Pareto fronts ( PF s).

Details DOI

JBHI Journal 2022 Journal Article

SRG-Vote: Predicting Mirna-Gene Relationships via Embedding and LSTM Ensemble

Weidun Xie
Zetian Zheng
Weitong Zhang
Lei Huang
Qiuzhen Lin
Ka-Chun Wong

Targeted therapy for one for a set of genes has made it possible to apply precision medicine for different patients due to the existence of tumor heterogeneity. However, how to regulate those genes are still problematic. One of the natural regulators of genes is microRNAs. Thus, a better understanding of the miRNA-gene interaction mechanism might contribute to future diagnosis, prevention, and cancer therapy. The interactions between microRNA and genes play an essential role in molecular genetics. The in-vivo experiments validating the relationships between them are time-consuming, money-costly, and labor-intensive. With the development of high-throughput technology, we dealt with tons of biological data. However, extracting features from tremendous raw data and making a mathematical model is still a challenging topic. Machine learning and deep learning algorithms have become powerful tools in dealing with biological data. Inspired by this, in this paper, we propose a model that combines features/embedding extraction methods, deep learning algorithms, and a voting system. We leverage doc2vec to generate sequential embedding from molecular sequences. The role2vec, GCN, and GMM for geometrical embedding were generated from the complex network from similarity and pair-wise datasets. For the deep learning algorithms, we leveraged LSTM and Bi-LSTM according to different embedding and features. Finally, we adopted a voting system to balance results from different data sources. The results have shown that our voting system could achieve a higher AUC than the existing benchmark. The case studies demonstrate that our model could reveal potential relationships between miRNAs and genes. The source code, features, and predictive results can be downloaded at https://github.com/Xshelton/SRG-vote.

Details DOI

JBHI Journal 2022 Journal Article

Subclass-Specific Prognosis and Treatment Efficacy Inference in Head and Neck Squamous Carcinoma

Zetian Zheng
Weidun Xie
Xingjian Chen
Fuzhou Wang
Lei Huang
Xiangtao Li
Qiuzhen Lin
Ka-Chun Wong

Exploring the prognostic classification and biomarkers in Head and Neck Squamous Carcinoma (HNSC) is of great clinical significance. We hybridized three prominent strategies to comprehensively characterize the molecular features of HNSC. We constructed a 15-gene signature to predict patients’ death risk with an average AUC of 0. 744 for 1-, 3-, and 5-year on TCGA-HNSC training set, and average AUCs of 0. 636, 0. 584, 0. 755 in GSE65858, GSE-112026, CPTAC-HNSCC datasets, respectively. By combined with NMF clustering and consensus clustering of fraction of tumor immune cell infiltration (ICI) in the tumor microenvironment (TME), we captured a more refined biological characteristics of HNSC, and observed a prognosis heterogeneity in high tumor immunity patients. By matching tumor subset-specific expression signatures to drug-induced cell line expression profiles from large-scale pharmacogenomic databases in the OCTAD workspace, we identified a group of HNSC patients featured with poor prognosis and demonstrated that the individuals in this group are likely to receive increased drug sensitivity to reverse differentially expressed disease signature genes. This trend is especially highlighted among those with higher death risk and tumour immunity.

Details DOI

JBHI Journal 2019 Journal Article

PathEmb: Random Walk Based Document Embedding for Global Pathway Similarity Search

Jiao Zhang
Sam Kwong
Guangming Liu
Qiuzhen Lin
Ka-Chun Wong

Pathway analysis is a cornerstone of system biology. In particular, pathway similarity search plays a key role in establishing structural, functional, and evolutionary relationships between different biological entities. Given a query pathway as well as a database, a pathway similarity search aims to identify novel pathways that are homologous to the query pathway. Unfortunately, the pathway similarity search is computationally inefficient due to the NP-complete graph isomorphism problem. In this study, we introduce a novel algorithmic framework for pathway similarity search, named PathEmb (Pathway Embedding), which is analogous to the Skip-gram model where each pathway is represented as a “document. ” PathEmb exploits a second order random walk strategy to explore diverse pathway patterns. All signaling paths traversed from random walks are regarded as “sentences, ” which are constituted as a “document” afterwards. Then, the “document” pattern for the individual pathway is mapped into a low-dimensional feature space for downstream tasks. Furthermore, PathEmb is a topology-free pathway similarity search algorithm, which is feasible to handle any pathway with arbitrary structure. We have extensively evaluated PathEmb and other cuttingedge methods on three pathway datasets. The experimental results demonstrate that PathEmb outperforms the existing methods in terms of computational efficiency and search accuracy. The source code of PathEmb are freely available online https://github.com/zhangjiaobxy/PathEmb.

Details DOI