Graph Transformation Research Articles

Texture graph transformer for prostate cancer classification

Prostate cancer classification plays a pivotal role in the diagnosis and treatment of this disease. In this paper, we present a novel approach called the texture graph transformer, which combines texture analysis techniques, graph-based representations, and multi-head attention to enhance the accuracy of prostate cancer classification. Our texture graph transformer adeptly captures intricate texture details and patterns within prostate cancer lesion regions, efficiently improving the model’s ability to discern between different cancer types. By leveraging graph-based representations, our model constructs texture graphs that effectively capture the spatial and textural relationships among various regions in MRI images, enabling comprehensive feature extraction. The incorporation of a texture graph multi-head attention further enhances the model’s capacity to capture long-range dependencies and global context, with a specific focus on informative regions. Through extensive experiments conducted on a dataset comprising 226 MRI images, we demonstrate the efficacy of our proposed approach in significantly improving the performance of prostate cancer classification.

SGNN-T: Space graph neural network coupled transformer for molecular property prediction

Molecular properties play a crucial role in material discovery, protein interaction and drug development. The appearance of Graph Neural Network (GNN) significantly improved the performance of molecular property prediction. However, nodes in GNN only update the features of neighbor nodes, resulting in insufficient ability to encode global feature information. The self- attention mechanism in transformer can encode the global information except for local information of molecules, while its spatial information is insufficient. Since molecules are three-dimensional spatial structures, spatial geometry information is an important attribute for molecules properties. To consider these factors, a network model of Space Graph Neural Network coupled Transformer (SGNN-T) is proposed in this paper which can combine global and local molecule information with three-dimensional spatial structures for molecular properties prediction. In this model, Graph neural network Geometric Feature Fusion Module (GGFF) and Transformer Spatial Geometric Feature Enhancement Module (TSGFE) are included to enhance the spatial geometry learning ability of the network. The GGFF module constructs a parallel graph neural network by thinking over atoms, bonds and bond angles at the same time which effectively complements the spatial information of the network by leading into bond angles than normal GNN. The TSGFE module introduces the coordinates and centrality degree features coupled with the features by GGFF into transformer to further enhance the geometric expression ability of the module. Through these two parts, SGNN-T model can encode local and global information of molecules at the same time. Property prediction experiments are executed on the QM9, OMDB and MEGNet dataset. The results of MAE show the proposed model has the best performance than the popular models.

An Explainable Graph Neural Framework to Identify Cancer-Associated Intratumoral Microbial Communities.

Microbes are extensively present among various cancer tissues and play critical roles in carcinogenesis and treatment responses. However, the underlying relationships between intratumoral microbes and tumors remain poorly understood. Here, a MIcrobial Cancer-association Analysis using a Heterogeneous graph transformer (MICAH) to identify intratumoral cancer-associated microbial communities is presented. MICAH integrates metabolic and phylogenetic relationships among microbes into a heterogeneous graph representation. It uses a graph transformer to holistically capture relationships between intratumoral microbes and cancer tissues, which improves the explainability of the associations between identified microbial communities and cancers. MICAH is applied to intratumoral bacterial data across 5 cancer types and 5 fungi datasets, and its generalizability and reproducibility are demonstrated. After experimentally testing a representative observation using a mouse model of tumor-microbe-immune interactions, a result consistent with MICAH's identified relationship is observed. Source tracking analysis reveals that the primary known contributor to a cancer-associated microbial community is the organs affected by the type of cancer. Overall, this graph neural network framework refines the number of microbes that can be used for follow-up experimental validation from thousands to tens, thereby helping to accelerate the understanding of the relationship between tumors and intratumoral microbiomes.

A method for miRNA diffusion association prediction using machine learning decoding of multi-level heterogeneous graph Transformer encoded representations

MicroRNAs (miRNAs) are a key class of endogenous non-coding RNAs that play a pivotal role in regulating diseases. Accurately predicting the intricate relationships between miRNAs and diseases carries profound implications for disease diagnosis, treatment, and prevention. However, these prediction tasks are highly challenging due to the complexity of the underlying relationships. While numerous effective prediction models exist for validating these associations, they often encounter information distortion due to limitations in efficiently retaining information during the encoding-decoding process. Inspired by Multi-layer Heterogeneous Graph Transformer and Machine Learning XGboost classifier algorithm, this study introduces a novel computational approach based on multi-layer heterogeneous encoder—machine learning decoder structure for miRNA-disease association prediction (MHXGMDA). First, we employ the multi-view similarity matrices as the input coding for MHXGMDA. Subsequently, we utilize the multi-layer heterogeneous encoder to capture the embeddings of miRNAs and diseases, aiming to capture the maximum amount of relevant features. Finally, the information from all layers is concatenated to serve as input to the machine learning classifier, ensuring maximal preservation of encoding details. We conducted a comprehensive comparison of seven different classifier models and ultimately selected the XGBoost algorithm as the decoder. This algorithm leverages miRNA embedding features and disease embedding features to decode and predict the association scores between miRNAs and diseases. We applied MHXGMDA to predict human miRNA-disease associations on two benchmark datasets. Experimental findings demonstrate that our approach surpasses several leading methods in terms of both the area under the receiver operating characteristic curve and the area under the precision-recall curve.

MolMVC: Enhancing molecular representations for drug-related tasks through multi-view contrastive learning.

Effective molecular representation is critical in drug development. The complex nature of molecules demands comprehensive multi-view representations, considering 1D, 2D, and 3D aspects, to capture diverse perspectives. Obtaining representations that encompass these varied structures is crucial for a holistic understanding of molecules in drug-related contexts. In this study, we introduce an innovative multi-view contrastive learning framework for molecular representation, denoted as MolMVC. Initially, we use a Transformer encoder to capture 1D sequence information and a Graph Transformer to encode the intricate 2D and 3D structural details of molecules. Our approach incorporates a novel attention-guided augmentation scheme, leveraging prior knowledge to create positive samples tailored to different molecular data views. To align multi-view molecular positive samples effectively in latent space, we introduce an adaptive multi-view contrastive loss (AMCLoss). In particular, we calculate AMCLoss at various levels within the model to effectively capture the hierarchical nature of the molecular information. Eventually, we pre-train the encoders via minimizing AMCLoss to obtain the molecular representation, which can be used for various down-stream tasks. In our experiments, we evaluate the performance of our MolMVC on multiple tasks, including molecular property prediction (MPP), drug-target binding affinity (DTA) prediction and cancer drug response (CDR) prediction. The results demonstrate that the molecular representation learned by our MolMVC can enhance the predictive accuracy on these tasks and also reduce the computational costs. Furthermore, we showcase MolMVC's efficacy in drug repositioning across a spectrum of drug-related applications. The code and pre-trained model are publicly available at https://github.com/Hhhzj-7/MolMVC.

Learning Joint 2-D and 3-D Graph Diffusion Models for Complete Molecule Generation.

Designing new molecules is essential for drug discovery and material science. Recently, deep generative models that aim to model molecule distribution have made promising progress in narrowing down the chemical research space and generating high-fidelity molecules. However, current generative models only focus on modeling 2-D bonding graphs or 3-D geometries, which are two complementary descriptors for molecules. The lack of ability to jointly model them limits the improvement of generation quality and further downstream applications. In this article, we propose a joint 2-D and 3-D graph diffusion model (JODO) that generates geometric graphs representing complete molecules with atom types, formal charges, bond information, and 3-D coordinates. To capture the correlation between 2-D molecular graphs and 3-D geometries in the diffusion process, we develop a diffusion graph transformer (DGT) to parameterize the data prediction model that recovers the original data from noisy data. The DGT uses a relational attention mechanism that enhances the interaction between node and edge representations. This mechanism operates concurrently with the propagation and update of scalar attributes and geometric vectors. Our model can also be extended for inverse molecular design targeting single or multiple quantum properties. In our comprehensive evaluation pipeline for unconditional joint generation, the experimental results show that JODO remarkably outperforms the baselines on the QM9 and GEOM-Drugs datasets. Furthermore, our model excels in few-step fast sampling, as well as in inverse molecule design and molecular graph generation. Our code is provided in https://github.com/GRAPH-0/JODO.

Accelerating histopathology workflows with generative AI-based virtually multiplexed tumour profiling

Understanding the spatial heterogeneity of tumours and its links to disease initiation and progression is a cornerstone of cancer biology. Presently, histopathology workflows heavily rely on hematoxylin and eosin and serial immunohistochemistry staining, a cumbersome, tissue-exhaustive process that results in non-aligned tissue images. We propose the VirtualMultiplexer, a generative artificial intelligence toolkit that effectively synthesizes multiplexed immunohistochemistry images for several antibody markers (namely AR, NKX3.1, CD44, CD146, p53 and ERG) from only an input hematoxylin and eosin image. The VirtualMultiplexer captures biologically relevant staining patterns across tissue scales without requiring consecutive tissue sections, image registration or extensive expert annotations. Thorough qualitative and quantitative assessment indicates that the VirtualMultiplexer achieves rapid, robust and precise generation of virtually multiplexed imaging datasets of high staining quality that are indistinguishable from the real ones. The VirtualMultiplexer is successfully transferred across tissue scales and patient cohorts with no need for model fine-tuning. Crucially, the virtually multiplexed images enabled training a graph transformer that simultaneously learns from the joint spatial distribution of several proteins to predict clinically relevant endpoints. We observe that this multiplexed learning scheme was able to greatly improve clinical prediction, as corroborated across several downstream tasks, independent patient cohorts and cancer types. Our results showcase the clinical relevance of artificial intelligence-assisted multiplexed tumour imaging, accelerating histopathology workflows and cancer biology.

Geometry-Augmented Molecular Representation Learning for Property Prediction.

Accurate molecular representation plays a crucial role in expediting the process of drug discovery. Graph neural networks (GNNs) have demonstrated robust capabilities in molecular representation learning, adept at capturing structural and spatial information in molecular graphs. For molecular representation learning, most previous GNN methods are specialized in dealing with 2D or 3D molecular data formats. By further fusing the geometric attributes and structural features of molecules, we can elevate the performance of molecular representation. To realize this, we present a novel geometry-augmented molecular representation learning model, designed to effectively encode both the 2D structural and 3D spatial information inherent in molecular graphs. By incorporating structural and spatial information as attention biases in the graph Transformer framework, our model offers a comprehensive architecture that introduces molecular structural details at both atom and bond levels. We further propose a geometry information fusion module to encode the geometry information within 3D molecular graphs. The experimental results show the efficacy of our model, demonstrating its ability to achieve competitive performance when compared to state-of-the-art (SOTA) models in various property prediction tasks.

Integration of Diffusion Transformer and Knowledge Graph for Efficient Cucumber Disease Detection in Agriculture.

In this study, a deep learning method combining knowledge graph and diffusion Transformer has been proposed for cucumber disease detection. By incorporating the diffusion attention mechanism and diffusion loss function, the research aims to enhance the model's ability to recognize complex agricultural disease features and to address the issue of sample imbalance efficiently. Experimental results demonstrate that the proposed method outperforms existing deep learning models in cucumber disease detection tasks. Specifically, the method achieved a precision of 93%, a recall of 89%, an accuracy of 92%, and a mean average precision (mAP) of 91%, with a frame rate of 57 frames per second (FPS). Additionally, the study successfully implemented model lightweighting, enabling effective operation on mobile devices, which supports rapid on-site diagnosis of cucumber diseases. The research not only optimizes the performance of cucumber disease detection, but also opens new possibilities for the application of deep learning in the field of agricultural disease detection.

Structural damage detection and localization via an unsupervised anomaly detection method

This study introduces an unsupervised machine learning framework for damage detection and localization in Structural Health Monitoring (SHM), leveraging dynamic graph convolutional neural networks and Transformer networks. This approach is specifically tailored to overcome the challenge of limited labeled data in SHM, enabling precise analysis and feature synthesis from sensor-derived time series data for accurate damage identification. Incorporating a novel ‘localization score’ enhances the framework’s precision in pinpointing structural damages by integrating data-driven insights with a physics-informed understanding of structural dynamics. Extensive validations on diverse structures, including a benchmark steel structure and a real-world cable-stayed bridge, underscore the framework’s effectiveness in anomaly detection and damage localization, showcasing its potential to safeguard critical infrastructure through advanced data-effective machine learning techniques.

An advanced hybrid deep learning model for accurate energy load prediction in smart building

In smart cities, sustainable development depends on energy load prediction since it directs utilities in effectively planning, distributing and generating energy. This work presents a novel hybrid deep learning model including components of the Improved-convolutional neural network (CNN), bidirectional long short-term memory (Bi-LSTM), Graph neural network (GNN), Transformer and Fusion Layer architectures for precise energy load forecasting. Better feature extraction results from the Improved-CNN's dilated convolution and residual block accommodation of wide receptive fields reduced the vanishing gradient problem. By capturing temporal links in both directions, Bi-LSTM networks help to better grasp complicated energy use patterns. Graph neural networks improve predictive capacities across linked systems by characterizing the spatial relationships between energy-consuming units in smart cities. Emphasizing critical trends to guarantee reliable forecasts, transformer models use attention methods to manage long-term dependencies in energy consumption data. Combining CNN, Bi-LSTM, Transformer and GNN component predictions in a Fusion Layer synthesizes numerous data representations to increase accuracy. With Root Mean Square Error of 5.7532 Wh, Mean Absolute Percentage Error of 3.5001%, Mean Absolute Error of 6.7532 Wh and R2 of 0.9701, the hybrid model fared better than other models on the ‘Electric Power Consumption’ Kaggle dataset. This work develops a realistic model that helps informed decision-making and enhances energy efficiency techniques, promoting energy load forecasting in smart cities.

Type-adaptive graph Transformer for heterogeneous information networks

Type-adaptive graph Transformer for heterogeneous information networks

Graph Artificial Intelligence in Medicine.

In clinical artificial intelligence (AI), graph representation learning, mainly through graph neural networks and graph transformer architectures, stands out for its capability to capture intricate relationships and structures within clinical datasets. With diverse data-from patient records to imaging-graph AI models process data holistically by viewing modalities and entities within them as nodes interconnected by their relationships. Graph AI facilitates model transfer across clinical tasks, enabling models to generalize across patient populations without additional parameters and with minimal to no retraining. However, the importance of human-centered design and model interpretability in clinical decision-making cannot be overstated. Since graph AI models capture information through localized neural transformations defined on relational datasets, they offer both an opportunity and a challenge in elucidating model rationale. Knowledge graphs can enhance interpretability by aligning model-driven insights with medical knowledge. Emerging graph AI models integrate diverse data modalities through pretraining, facilitate interactive feedback loops, and foster human-AI collaboration, paving the way toward clinically meaningful predictions.

Enhancing fraud detection efficiency in mobile transactions through the integration of bidirectional 3d Quasi-Recurrent Neural network and blockchain technologies

Cases of financial fraud are increasing despite recent technical breakthroughs. It is tough to find authentic financial transaction data due to privacy issues and a lack of inter-organization synergy. However, for technologies based on data, such as machine learning to function accurately inside practical systems, they require actual data. This manuscript proposes a Fraud Detection (FD) Efficiency in Mobile Transactions through the Integration of Bidirectional 3D Quasi-Recurrent Neural Networks and Proof of Voting consensus Blockchain Technologies (Bi-3DQRNN-PoV-FD-MT). A dataset of Bitcoin transactions is employed in the suggested model. The banking sector’s Bitcoin transactions serve as the foundation for this dataset. Then the data balancing is performed using a Self-Adaptive Synthetic Over-Sampling Technique (SASOS). Then, the proposed framework utilizes the Bi-3DQRNN to determine if the information is fraudulent or not. Moreover, an intelligent Enhanced Artificial Gorilla Troops (EAGTO) Optimization algorithm is introduced to tune the weights of the model parameters. A blockchain-based proof of Voting (PoV) consensus algorithm is integrated with the proposed model for forecasting upcoming transactions. The developed scheme is instigated in Python and the performance provides 12.09%, 8.91%, and 6.92% higher accuracy compared with existing techniques like K-nearest neighbor- Distributed Blockchain Consortium (KNN-DBC), Decision tree-Ethereum blockchain-enabled smart contract (DT-EBSC) and Heterogeneous Graph Transformer Networks-Ethereum smart contract (HGTN-ESC).

Graph Transformer for 3D point clouds classification and semantic segmentation

Recently, graph-based and Transformer-based deep learning have demonstrated excellent performances on various point cloud tasks. Most of the existing graph-based methods rely on static graph, which take a fixed input to establish graph relations. Moreover, many graph-based methods apply maximizing and averaging to aggregate neighboring features, so that only a single neighboring point affects the feature of centroid or different neighboring points own the same influence on the centroid’s feature, which ignoring the correlation and difference between points. Most Transformer-based approaches extract point cloud features based on global attention and lack the feature learning on local neighbors. To solve the above issues of graph-based and Transformer-based models, we propose a new feature extraction block named Graph Transformer and construct a 3D point cloud learning network called GTNet to learn features of point clouds on local and global patterns. Graph Transformer integrates the advantages of graph-based and Transformer-based methods, and consists of Local Transformer that use intra-domain cross-attention and Global Transformer that use global self-attention. Finally, we use GTNet for shape classification, part segmentation and semantic segmentation tasks in this paper. The experimental results show that our model achieves good learning and prediction ability on most tasks. The source code and pre-trained model of GTNet will be released on https://github.com/NWUzhouwei/GTNet.

Phishing Webpage Detection via Multi-Modal Integration of HTML DOM Graphs and URL Features Based on Graph Convolutional and Transformer Networks

Phishing Webpage Detection via Multi-Modal Integration of HTML DOM Graphs and URL Features Based on Graph Convolutional and Transformer Networks

Multi-Scale Spatial-Temporal Attention Networks for Functional Connectome Classification.

Many neuropsychiatric disorders are considered to be associated with abnormalities in the functional connectivity networks of the brain. The research on the classification of functional connectivity can therefore provide new perspectives for understanding the pathology of disorders and contribute to early diagnosis and treatment. Functional connectivity exhibits a nature of dynamically changing over time, however, the majority of existing methods are unable to collectively reveal the spatial topology and time-varying characteristics. Furthermore, despite the efforts of limited spatial-temporal studies to capture rich information across different spatial scales, they have not delved into the temporal characteristics among different scales. To address above issues, we propose a novel Multi-Scale Spatial-Temporal Attention Networks (MSSTAN) to exploit the multi-scale spatial-temporal information provided by functional connectome for classification. To fully extract spatial features of brain regions, we propose a Topology Enhanced Graph Transformer module to guide the attention calculations in the learning of spatial features by incorporating topology priors. A Multi-Scale Pooling Strategy is introduced to obtain representations of brain connectome at various scales. Considering the temporal dynamic characteristics between dynamic functional connectome, we employ Locality Sensitive Hashing attention to further capture long-term dependencies in time dynamics across multiple scales and reduce the computational complexity of the original attention mechanism. Experiments on three brain fMRI datasets of MDD and ASD demonstrate the superiority of our proposed approach. In addition, benefiting from the attention mechanism in Transformer, our results are interpretable, which can contribute to the discovery of biomarkers. The code is available at https://github.com/LIST-KONG/MSSTAN.

Innovative Mamba and graph transformer framework for superior protein-ligand affinity prediction

Accurate measurement of the affinity between drug targets is of great importance in the field of drug discovery, as it provides significant information about drug action. However, the diverse representations of compounds and proteins increase the difficulty of this task. Recently, numerous studies have explored the application of various deep learning methods and architectures in Drug-Target Affinity (DTA) prediction tasks, continuously improving performance. In this work, we present a multimodal late-stage fusion prediction model called MGDTA that combines the pioneering Mamba architecture with a hybrid model architecture based on graph transformers and transformers (GTT). For molecular compounds, structural characterisation is extracted using GTT layers. Additionally, a feature integration module is utilized to obtain molecular features from derived molecular fingerprints, culminating in a unified representation of drug molecules through a feature integration module. For proteins, we adopt the state-space model (SSM) module Mamba to learn feature representations from target protein sequences. This represents a preliminary exploration of the Mamba module in protein sequence feature extraction in DTA tasks. Finally, we predict the results by integrating the feature representations of both molecules and proteins. Our results indicate that the proposed model achieves superior performance on benchmark datasets, validating the feasibility of using the Mamba architecture for DTA tasks. Furthermore, sequence feature visualization demonstrates the capability of the Mamba block to focus on binding site residues within drug targets.

Molecular subgraph representation learning based on spatial structure transformer

In the field of molecular biology, graph representation learning is crucial for molecular structure analysis. However, challenges arise in recognising functional groups and distinguishing isomers due to a lack of spatial structure information. To address these problems, we design a novel graph representation learning method based on a spatial structure information extraction Transformer (SSET). The SSET model comprises the Edge Feature Fusion Subgraph Spatial Structure Extractor (ETSE) module and the Positional Information Encoding Graph Transformer (PEGT) module. The ETSE module extracts spatial structural information by fusing edge features and generating the most-value subgraph (Mv-subgraph). The PEGT module encodes positional information based on the graph transformer, addressing the indistinguishability problem among nodes with identical features. In addition, the SSET model alleviates the burden of high computational complexity by using subgraph. Experiments on real datasets show that the SSET model, built on the graph transformer, considerably improves graph representation learning.

DDGformer: Direction- and distance-aware graph transformer for traffic flow prediction

Being an indispensable core technology of intelligent transportation systems, accurate traffic flow prediction contributes to improving people’s travel efficiency and safety. How to accurately model the dynamic spatio-temporal correlation in traffic data is a key challenge in traffic flow prediction. The models based on self-attention and Graph Neural Networks (GNN) have shown great potential in addressing this challenge. However, existing methods ignore the relative distance and direction of traffic flow series, and cannot accurately capture the real dynamic spatio-temporal correlations in traffic systems. To overcome this limitation, we propose a novel framework called Direction- and Distance-aware Graph Transformer (DDGformer). Specifically, it utilizes a self-attention module that simultaneously perceives direction and distance, enabling it to identify the relative position and direction of the original traffic flow series, and models long-term temporal correlations. Additionally, a dynamically enhanced adaptive graph convolution network is designed to capture dynamic traffic patterns in traffic systems. Extensive experimental results on four real-world traffic datasets show that our approach is overall more competitive and exhibits outstanding computational efficiency.