Siwei Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Siwei Liu has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Shangsong Liang
Sun Yat-Sen University, Guangzhou, China
4 shared publications - Zaiqiao Meng
University of Glasgow, Glasgow, United Kingdom
4 shared publications - Eran Segal
Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel
3 shared publications - Craig Macdonald
University of Glasgow, Glasgow, United Kingdom
2 shared publications - Iadh Ounis
University of Glasgow, Glasgow, United Kingdom
2 shared publications Nan Yin
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology , Clear Water Bay, Sai Kung District, Hong Kong SAR 999077
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 7 January 2026
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 27 (1)
SGAC: a graph neural network framework for imbalanced and structure-aware AMP classification
Classifying antimicrobial peptides (AMPs) from the vast collection of peptides derived from metagenomic sequencing offers a promising avenue for combating antibiotic resistance. However, most existing AMP classification methods rely primarily on sequence-based representations and fail to capture the spatial structural information critical for accurate identification. Although recent graph-based approaches attempt to incorporate structural information, they typically construct residue- or atom-level graphs that introduce redundant atomic details and increase structural complexity. Furthermore, the class imbalance between the small number of known AMPs and the abundant non-AMPs significantly hinders predictive performance. To address these challenges, we employ lightweight OmegaFold to predict the 3D structures of peptides and construct peptide graphs using C$_\alpha $ atoms to capture their backbone geometry and spatial topology. Building on this representation, we propose the spatial graph neural network (GNN)-based AMP classifier (SGAC), a novel framework that leverages GNNs to extract structural features and generate discriminative graph representations. To handle class imbalance, SGAC incorporates weight-enhanced contrastive learning to cluster structurally similar peptides and separate dissimilar ones through adaptive weighting, and applies weight-enhanced pseudo-label distillation to generate high-confidence pseudo labels for unlabeled samples, achieving balanced and consistent representation learning. Experiments on publicly available AMP and non-AMP datasets demonstrate that SGAC significantly achieves state-of-the-art performance compared to baselines. The complete code and dataset are available at: https://github.com/wyxwyx46941930/SGAC.
- 7 January 2026
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 27 (1)
Top Cited PapersOpen AccessSGAC: a graph neural network framework for imbalanced and structure-aware AMP classification
Classifying antimicrobial peptides (AMPs) from the vast collection of peptides derived from metagenomic sequencing offers a promising avenue for combating antibiotic resistance. However, most existing AMP classification methods rely primarily on sequence-based representations and fail to capture the spatial structural information critical for accurate identification. Although recent graph-based approaches attempt to incorporate structural information, they typically construct residue- or atom-level graphs that introduce redundant atomic details and increase structural complexity. Furthermore, the class imbalance between the small number of known AMPs and the abundant non-AMPs significantly hinders predictive performance. To address these challenges, we employ lightweight OmegaFold to predict the 3D structures of peptides and construct peptide graphs using C$_\alpha $ atoms to capture their backbone geometry and spatial topology. Building on this representation, we propose the spatial graph neural network (GNN)-based AMP classifier (SGAC), a novel framework that leverages GNNs to extract structural features and generate discriminative graph representations. To handle class imbalance, SGAC incorporates weight-enhanced contrastive learning to cluster structurally similar peptides and separate dissimilar ones through adaptive weighting, and applies weight-enhanced pseudo-label distillation to generate high-confidence pseudo labels for unlabeled samples, achieving balanced and consistent representation learning. Experiments on publicly available AMP and non-AMP datasets demonstrate that SGAC significantly achieves state-of-the-art performance compared to baselines. The complete code and dataset are available at: https://github.com/wyxwyx46941930/SGAC.
- Open Access
- 8 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (1) , 1-18
DuSEGO: Dual Second-Order Equivariant Graph Ordinary Differential Equation
Graph Neural Networks (GNNs) with equivariant properties have achieved significant success in modeling complex dynamic systems and molecular properties. However, their expressiveness ability is limited by: (1) Existing methods often overlook the over-smoothing issue caused by traditional GNN models, as well as the gradient explosion or vanishing problems in deep GNNs. (2) Most models operate on first-order information, neglecting that the real world often consists of second-order systems, which further limits the model’s representation capabilities. To address these issues, we propose the Dual Second-order Equivariant Graph Ordinary (DuSEGO) Differential Equation for equivariant representation. Specifically, DuSEGO applies the dual second-order equivariant graph ordinary differential equations (Graph ODEs) to both graph embeddings and node coordinates simultaneously. Theoretically, we first prove that DuSEGO maintains the equivariant property. Furthermore, we provide theoretical insights showing that DuSEGO effectively alleviates the over-smoothing problem in both feature representation and coordinate update. Additionally, we demonstrate that the proposed DuSEGO mitigates the exploding and vanishing gradients problem, facilitating the training of deep multi-layer GNNs. Extensive experiments on benchmark datasets validate the superiority of the proposed DuSEGO compared to baselines.
- 8 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (1) , 1-18
Open AccessDuSEGO: Dual Second-Order Equivariant Graph Ordinary Differential Equation
Graph Neural Networks (GNNs) with equivariant properties have achieved significant success in modeling complex dynamic systems and molecular properties. However, their expressiveness ability is limited by: (1) Existing methods often overlook the over-smoothing issue caused by traditional GNN models, as well as the gradient explosion or vanishing problems in deep GNNs. (2) Most models operate on first-order information, neglecting that the real world often consists of second-order systems, which further limits the model’s representation capabilities. To address these issues, we propose the Dual Second-order Equivariant Graph Ordinary (DuSEGO) Differential Equation for equivariant representation. Specifically, DuSEGO applies the dual second-order equivariant graph ordinary differential equations (Graph ODEs) to both graph embeddings and node coordinates simultaneously. Theoretically, we first prove that DuSEGO maintains the equivariant property. Furthermore, we provide theoretical insights showing that DuSEGO effectively alleviates the over-smoothing problem in both feature representation and coordinate update. Additionally, we demonstrate that the proposed DuSEGO mitigates the exploding and vanishing gradients problem, facilitating the training of deep multi-layer GNNs. Extensive experiments on benchmark datasets validate the superiority of the proposed DuSEGO compared to baselines.
- Open Access
- 1 November 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (6)
ProtoMol: enhancing molecular property prediction via prototype-guided multimodal learning
Multimodal molecular representation learning, which jointly models molecular graphs and their textual descriptions, enhances predictive accuracy and interpretability by enabling more robust and reliable predictions of drug toxicity, bioactivity, and physicochemical properties through the integration of structural and semantic information. However, existing multimodal methods suffer from two key limitations: (i) they typically perform cross-modal interaction only at the final encoder layer, thus overlooking hierarchical semantic dependencies; (ii) they lack a unified prototype space for robust alignment between modalities. To address these limitations, we propose ProtoMol, a prototype-guided multimodal framework that enables fine-grained integration and consistent semantic alignment between molecular graphs and textual descriptions. ProtoMol incorporates dual-branch hierarchical encoders, utilizing Graph Neural Networks to process structured molecular graphs and Transformers to encode unstructured texts, resulting in comprehensive layer-wise representations. Then, ProtoMol introduces a layer-wise bidirectional cross-modal attention mechanism that progressively aligns semantic features across layers. Furthermore, a shared prototype space with learnable, class-specific anchors is constructed to guide both modalities toward coherent and discriminative representations. Extensive experiments on multiple benchmark datasets demonstrate that ProtoMol consistently outperforms state-of-the-art baselines across a variety of molecular property prediction tasks. Our source code is available at: https://github.com/zky04/Protomol.
- 1 November 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (6)
Open AccessProtoMol: enhancing molecular property prediction via prototype-guided multimodal learning
Multimodal molecular representation learning, which jointly models molecular graphs and their textual descriptions, enhances predictive accuracy and interpretability by enabling more robust and reliable predictions of drug toxicity, bioactivity, and physicochemical properties through the integration of structural and semantic information. However, existing multimodal methods suffer from two key limitations: (i) they typically perform cross-modal interaction only at the final encoder layer, thus overlooking hierarchical semantic dependencies; (ii) they lack a unified prototype space for robust alignment between modalities. To address these limitations, we propose ProtoMol, a prototype-guided multimodal framework that enables fine-grained integration and consistent semantic alignment between molecular graphs and textual descriptions. ProtoMol incorporates dual-branch hierarchical encoders, utilizing Graph Neural Networks to process structured molecular graphs and Transformers to encode unstructured texts, resulting in comprehensive layer-wise representations. Then, ProtoMol introduces a layer-wise bidirectional cross-modal attention mechanism that progressively aligns semantic features across layers. Furthermore, a shared prototype space with learnable, class-specific anchors is constructed to guide both modalities toward coherent and discriminative representations. Extensive experiments on multiple benchmark datasets demonstrate that ProtoMol consistently outperforms state-of-the-art baselines across a variety of molecular property prediction tasks. Our source code is available at: https://github.com/zky04/Protomol.
- Open Access
ProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning
Multimodal molecular representation learning, which jointly models molecular graphs and their textual descriptions, enhances predictive accuracy and interpretability by enabling more robust and reliable predictions of drug toxicity, bioactivity, and physicochemical properties through the integration of structural and semantic information. However, existing multimodal methods suffer from two key limitations: (1) they typically perform cross-modal interaction only at the final encoder layer, thus overlooking hierarchical semantic dependencies; (2) they lack a unified prototype space for robust alignment between modalities. To address these limitations, we propose ProtoMol, a prototype-guided multimodal framework that enables fine-grained integration and consistent semantic alignment between molecular graphs and textual descriptions. ProtoMol incorporates dual-branch hierarchical encoders, utilizing Graph Neural Networks to process structured molecular graphs and Transformers to encode unstructured texts, resulting in comprehensive layer-wise representations. Then, ProtoMol introduces a layer-wise bidirectional cross-modal attention mechanism that progressively aligns semantic features across layers. Furthermore, a shared prototype space with learnable, class-specific anchors is constructed to guide both modalities toward coherent and discriminative representations. Extensive experiments on multiple benchmark datasets demonstrate that ProtoMol consistently outperforms state-of-the-art baselines across a variety of molecular property prediction tasks.
Open AccessProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning
Multimodal molecular representation learning, which jointly models molecular graphs and their textual descriptions, enhances predictive accuracy and interpretability by enabling more robust and reliable predictions of drug toxicity, bioactivity, and physicochemical properties through the integration of structural and semantic information. However, existing multimodal methods suffer from two key limitations: (1) they typically perform cross-modal interaction only at the final encoder layer, thus overlooking hierarchical semantic dependencies; (2) they lack a unified prototype space for robust alignment between modalities. To address these limitations, we propose ProtoMol, a prototype-guided multimodal framework that enables fine-grained integration and consistent semantic alignment between molecular graphs and textual descriptions. ProtoMol incorporates dual-branch hierarchical encoders, utilizing Graph Neural Networks to process structured molecular graphs and Transformers to encode unstructured texts, resulting in comprehensive layer-wise representations. Then, ProtoMol introduces a layer-wise bidirectional cross-modal attention mechanism that progressively aligns semantic features across layers. Furthermore, a shared prototype space with learnable, class-specific anchors is constructed to guide both modalities toward coherent and discriminative representations. Extensive experiments on multiple benchmark datasets demonstrate that ProtoMol consistently outperforms state-of-the-art baselines across a variety of molecular property prediction tasks.
- 3 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 279
RRGMambaFormer: A hybrid Transformer-Mamba architecture for radiology report generation
- 3 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 279
RRGMambaFormer: A hybrid Transformer-Mamba architecture for radiology report generation
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 643-655
EvoAgentX: An Automated Framework for Evolving Agentic Workflows
Yingxu Wang, Siwei Liu, Jinyuan Fang, Zaiqiao Meng. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 643-655
Open AccessEvoAgentX: An Automated Framework for Evolving Agentic Workflows
Yingxu Wang, Siwei Liu, Jinyuan Fang, Zaiqiao Meng. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2025.
- Open Access
- 28 October 2024
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 5 (4) , 045028
PASCL: supervised contrastive learning with perturbative augmentation for particle decay reconstruction
In high-energy physics, particles produced in collision events decay in a format of a hierarchical tree structure, where only the final decay products can be observed using detectors. However, the large combinatorial space of possible tree structures makes it challenging to recover the actual decay process given a set of final particles. To better analyse the hierarchical tree structure, we propose a graph-based deep learning model to infer the tree structure to reconstruct collision events. In particular, we use a compact matrix representation termed as lowest common ancestor generations matrix, to encode the particle decay tree structure. Then, we introduce a perturbative augmentation technique applied to node features, aiming to mimic experimental uncertainties and increase data diversity. We further propose a supervised graph contrastive learning algorithm to utilize the information of inter-particle relations from multiple decay processes. Extensive experiments show that our proposed supervised graph contrastive learning with perturbative augmentation method outperforms state-of-the-art baseline models on an existing physics-based dataset, significantly improving the reconstruction accuracy. This method provides a more effective training strategy for models with the same parameters and makes way for more accurate and efficient high-energy particle physics data analysis.
- 28 October 2024
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 5 (4) , 045028
Open AccessPASCL: supervised contrastive learning with perturbative augmentation for particle decay reconstruction
In high-energy physics, particles produced in collision events decay in a format of a hierarchical tree structure, where only the final decay products can be observed using detectors. However, the large combinatorial space of possible tree structures makes it challenging to recover the actual decay process given a set of final particles. To better analyse the hierarchical tree structure, we propose a graph-based deep learning model to infer the tree structure to reconstruct collision events. In particular, we use a compact matrix representation termed as lowest common ancestor generations matrix, to encode the particle decay tree structure. Then, we introduce a perturbative augmentation technique applied to node features, aiming to mimic experimental uncertainties and increase data diversity. We further propose a supervised graph contrastive learning algorithm to utilize the information of inter-particle relations from multiple decay processes. Extensive experiments show that our proposed supervised graph contrastive learning with perturbative augmentation method outperforms state-of-the-art baseline models on an existing physics-based dataset, significantly improving the reconstruction accuracy. This method provides a more effective training strategy for models with the same parameters and makes way for more accurate and efficient high-energy particle physics data analysis.
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on the Web
- Vol. 18 (4) , 1-34
Enhancing Graph Neural Networks via Memorized Global Information
Graph neural networks (GNNs) have gained significant attention for their impressive results on different graph-based tasks. The essential mechanism of GNNs is the message-passing framework, whereby node representations are aggregated from local neighborhoods. Recently, Transformer-based GNNs have been introduced to learn the long-range dependencies, enhancing performance. However, their quadratic computational complexity, due to the attention computation, has constrained their applicability on large-scale graphs. To address this issue, we propose MGIGNN ( M emorized G lobal I nformation G raph N eural N etwork), an innovative approach that leverages memorized global information to enhance existing GNNs in both transductive and inductive scenarios. Specifically, MGIGNN captures long-range dependencies by identifying and incorporating global similar nodes, which are defined as nodes exhibiting similar features, structural patterns and label information within a graph. To alleviate the computational overhead associated with computing embeddings for all nodes, we introduce an external memory module to facilitate the retrieval of embeddings and optimize performance on large graphs. To enhance the memory-efficiency, MGIGNN selectively retrieves global similar nodes from a small set of candidate nodes. These candidate nodes are selected from the training nodes based on a sparse node selection distribution with a Dirichlet prior. This selecting approach not only reduces the memory size required but also ensures efficient utilization of computational resources. Through comprehensive experiments conducted on ten widely-used and real-world datasets, including seven homogeneous datasets and three heterogeneous datasets, we demonstrate that our MGIGNN can generally improve the performance of existing GNNs on node classification tasks under both inductive and transductive settings.
- 8 October 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on the Web
- Vol. 18 (4) , 1-34
Open AccessEnhancing Graph Neural Networks via Memorized Global Information
Graph neural networks (GNNs) have gained significant attention for their impressive results on different graph-based tasks. The essential mechanism of GNNs is the message-passing framework, whereby node representations are aggregated from local neighborhoods. Recently, Transformer-based GNNs have been introduced to learn the long-range dependencies, enhancing performance. However, their quadratic computational complexity, due to the attention computation, has constrained their applicability on large-scale graphs. To address this issue, we propose MGIGNN ( M emorized G lobal I nformation G raph N eural N etwork), an innovative approach that leverages memorized global information to enhance existing GNNs in both transductive and inductive scenarios. Specifically, MGIGNN captures long-range dependencies by identifying and incorporating global similar nodes, which are defined as nodes exhibiting similar features, structural patterns and label information within a graph. To alleviate the computational overhead associated with computing embeddings for all nodes, we introduce an external memory module to facilitate the retrieval of embeddings and optimize performance on large graphs. To enhance the memory-efficiency, MGIGNN selectively retrieves global similar nodes from a small set of candidate nodes. These candidate nodes are selected from the training nodes based on a sparse node selection distribution with a Dirichlet prior. This selecting approach not only reduces the memory size required but also ensures efficient utilization of computational resources. Through comprehensive experiments conducted on ten widely-used and real-world datasets, including seven homogeneous datasets and three heterogeneous datasets, we demonstrate that our MGIGNN can generally improve the performance of existing GNNs on node classification tasks under both inductive and transductive settings.
- Open Access
- 25 July 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 25 (5)
Heterogeneous biomedical entity representation learning for gene–disease association prediction
Understanding the genetic basis of disease is a fundamental aspect of medical research, as genes are the classic units of heredity and play a crucial role in biological function. Identifying associations between genes and diseases is critical for diagnosis, prevention, prognosis, and drug development. Genes that encode proteins with similar sequences are often implicated in related diseases, as proteins causing identical or similar diseases tend to show limited variation in their sequences. Predicting gene–disease association (GDA) requires time-consuming and expensive experiments on a large number of potential candidate genes. Although methods have been proposed to predict associations between genes and diseases using traditional machine learning algorithms and graph neural networks, these approaches struggle to capture the deep semantic information within the genes and diseases and are dependent on training data. To alleviate this issue, we propose a novel GDA prediction model named FusionGDA, which utilizes a pre-training phase with a fusion module to enrich the gene and disease semantic representations encoded by pre-trained language models. Multi-modal representations are generated by the fusion module, which includes rich semantic information about two heterogeneous biomedical entities: protein sequences and disease descriptions. Subsequently, the pooling aggregation strategy is adopted to compress the dimensions of the multi-modal representation. In addition, FusionGDA employs a pre-training phase leveraging a contrastive learning loss to extract potential gene and disease features by training on a large public GDA dataset. To rigorously evaluate the effectiveness of the FusionGDA model, we conduct comprehensive experiments on five datasets and compare our proposed model with five competitive baseline models on the DisGeNet-Eval dataset. Notably, our case study further demonstrates the ability of FusionGDA to discover hidden associations effectively. The complete code and datasets of our experiments are available at https://github.com/ZhaohanM/FusionGDA.
- 25 July 2024
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 25 (5)
Open AccessHeterogeneous biomedical entity representation learning for gene–disease association prediction
Understanding the genetic basis of disease is a fundamental aspect of medical research, as genes are the classic units of heredity and play a crucial role in biological function. Identifying associations between genes and diseases is critical for diagnosis, prevention, prognosis, and drug development. Genes that encode proteins with similar sequences are often implicated in related diseases, as proteins causing identical or similar diseases tend to show limited variation in their sequences. Predicting gene–disease association (GDA) requires time-consuming and expensive experiments on a large number of potential candidate genes. Although methods have been proposed to predict associations between genes and diseases using traditional machine learning algorithms and graph neural networks, these approaches struggle to capture the deep semantic information within the genes and diseases and are dependent on training data. To alleviate this issue, we propose a novel GDA prediction model named FusionGDA, which utilizes a pre-training phase with a fusion module to enrich the gene and disease semantic representations encoded by pre-trained language models. Multi-modal representations are generated by the fusion module, which includes rich semantic information about two heterogeneous biomedical entities: protein sequences and disease descriptions. Subsequently, the pooling aggregation strategy is adopted to compress the dimensions of the multi-modal representation. In addition, FusionGDA employs a pre-training phase leveraging a contrastive learning loss to extract potential gene and disease features by training on a large public GDA dataset. To rigorously evaluate the effectiveness of the FusionGDA model, we conduct comprehensive experiments on five datasets and compare our proposed model with five competitive baseline models on the DisGeNet-Eval dataset. Notably, our case study further demonstrates the ability of FusionGDA to discover hidden associations effectively. The complete code and datasets of our experiments are available at https://github.com/ZhaohanM/FusionGDA.
- 14 December 2023
- Published by Elsevier in Information Processing & Management
- Vol. 61 (2)
A Social-aware Gaussian Pre-trained model for effective cold-start recommendation
- 14 December 2023
- Published by Elsevier in Information Processing & Management
- Vol. 61 (2)
A Social-aware Gaussian Pre-trained model for effective cold-start recommendation