Jointly constrained group sparse connectivity representation improves early diagnosis of Alzheimer's disease on routinely acquired T1-weighted imaging-based brain network

Background

Radiomics-based morphological brain networks (radMBN) constructed from routinely acquired structural MRI (sMRI) data have gained attention in Alzheimer's disease (AD). However, the radMBN suffers from limited characterization of AD because sMRI only characterizes anatomical changes and is not a direct measure of neuronal pathology or brain activity.

Purpose

To establish a group sparse representation of the radMBN under a joint constraint of group-level white matter fiber connectivity and individual-level sMRI regional similarity (JCGS-radMBN).

Methods

Two publicly available datasets were adopted, including 120 subjects from ADNI with both T1-weighted image (T1WI) and diffusion MRI (dMRI) for JCGS-radMBN construction, 818 subjects from ADNI and 200 subjects solely with T1WI from AIBL for validation in early AD diagnosis. Specifically, the JCGS-radMBN was conducted by jointly estimating non-zero connections among subjects, with the regularization term constrained by group-level white matter fiber connectivity and individual-level sMRI regional similarity. Then, a triplet graph convolutional network was adopted for early AD diagnosis. The discriminative brain connections were identified using a two-sample t-test, and the neurobiological interpretation was validated by correlating the discriminative brain connections with cognitive scores.

Results

The JCGS-radMBN exhibited superior classification performance over five brain network construction methods. For the typical NC vs. AD classification, the JCGS-radMBN increased by 1-30% in accuracy over the alternatives on ADNI and AIBL. The discriminative brain connections exhibited a strong connectivity to hippocampus, parahippocampal gyrus, and basal ganglia, and had significant correlation with MMSE scores.

Conclusion

The proposed JCGS-radMBN facilitated the AD characterization of brain network established on routinely acquired imaging modality of sMRI.

Supplementary Information

The online version of this article (10.1007/s13755-023-00269-0) contains supplementary material, which is available to authorized users.

Optimal decision-making in relieving global high temperature-related disease burden by data-driven simulation

The rapid acceleration of global warming has led to an increased burden of high temperature-related diseases (HTDs), highlighting the need for advanced evidence-based management strategies. We have developed a conceptual framework aimed at alleviating the global burden of HTDs, grounded in the One Health concept. This framework refines the impact pathway and establishes systematic data-driven models to inform the adoption of evidence-based decision-making, tailored to distinct contexts. We collected extensive national-level data from authoritative public databases for the years 2010-2019. The burdens of five categories of disease causes - cardiovascular diseases, infectious respiratory diseases, injuries, metabolic diseases, and non-infectious respiratory diseases - were designated as intermediate outcome variables. The cumulative burden of these five categories, referred to as the total HTD burden, was the final outcome variable. We evaluated the predictive performance of eight models and subsequently introduced twelve intervention measures, allowing us to explore optimal decision-making strategies and assess their corresponding contributions. Our model selection results demonstrated the superior performance of the Graph Neural Network (GNN) model across various metrics. Utilizing simulations driven by the GNN model, we identified a set of optimal intervention strategies for reducing disease burden, specifically tailored to the seven major regions: East Asia and Pacific, Europe and Central Asia, Latin America and the Caribbean, Middle East and North Africa, North America, South Asia, and Sub-Saharan Africa. Sectoral mitigation and adaptation measures, acting upon our categories of Infrastructure & Community, Ecosystem Resilience, and Health System Capacity, exhibited particularly strong performance for various regions and diseases. Seven out of twelve interventions were included in the optimal intervention package for each region, including raising low-carbon energy use, increasing energy intensity, improving livestock feed, expanding basic health care delivery coverage, enhancing health financing, addressing air pollution, and improving road infrastructure. The outcome of this study is a global decision-making tool, offering a systematic methodology for policymakers to develop targeted intervention strategies to address the increasingly severe challenge of HTDs in the context of global warming.

Atom-ProteinQA: Atom-level protein model quality assessment through fine-grained joint learning

MOTIVATION

Protein model quality assessment (ProteinQA) is a fundamental task that is essential for biologically relevant applications, i.e., protein structure refinement, protein design, etc. Previous works aimed to conduct ProteinQA only on the global structure or per-residue level, ignoring potentially usable and precise cues from a fine-grained per-atom perspective. In this study, we propose an atom-level ProteinQA model, named Atom-ProteinQA, in which two innovative modules are designed to extract geometric and topological atom-level relationships respectively. Specifically, on the one hand, a geometric perception module exploits 3D sparse convolution to capture the geometric features of the input protein, generating fine-grained atom-level predictions. On the other hand, natural chemical bonds are utilized to construct an atom-level graph, then message passing from a topological perception module is applied to output residue-level predictions in parallel. Eventually, through a cross-model aggregation module, features from different modules mutually interact, enhancing performance on both the atom and residue levels.

RESULTS

Extensive experiments show that our proposed Atom-ProteinQA outperforms previous methods by a large margin, regardless of residue-level or atom-level assessment. Concretely, we achieved state-of-the-art performance on CATH-2084, Decoy-8000, public benchmarks CASP13 & CASP14, and the CAMEO.

AVAILABILITY

The repository of this project is released on: https://github.com/luyfcandy/Atom_ProteinQA.

Node-personalized multi-graph convolutional networks for recommendation

Graph neural networks have revealed powerful potential in ranking recommendation. Existing methods based on bipartite graphs for ranking recommendation mainly focus on homogeneous graphs and usually treat user and item nodes as the same kind of nodes, however, the user-item bipartite graph is always heterogeneous. Additionally, various types of nodes have varying effects on recommendations, and a good node representation can be learned by successfully differentiating the same type of nodes. In this paper, we develop a node-personalized multi-graph convolutional network (NP-MGCN) for ranking recommendation. It consists of a node importance awareness block, a graph construction module, and a node information propagation and aggregation framework. Specifically, a node importance awareness block is proposed to encode nodes using node degree information to highlight the differences between nodes. Subsequently, the Jaccard similarity and co-occurrence matrix fusion graph construction module is devised to acquire user-user and item-item graphs, enriching correlation information between users and between items. Finally, a composite hop node information propagation and aggregation framework, including single-hop and double-hop branches, is designed. The high-order connectivity is used to aggregate heterogeneous information for the single-hop branch, while the multi-hop dependency is utilized to aggregate homogeneous information for the double-hop branch. It makes user and item node embedding more discriminative and integrates the different nodes' heterogeneity into the model. Experiments on several datasets manifest that NP-MGCN achieves outstanding recommendation performance than existing methods.

A Comprehensive Survey on Deep Graph Representation Learning

Graph representation learning aims to effectively encode high-dimensional sparse graph-structured data into low-dimensional dense vectors, which is a fundamental task that has been widely studied in a range of fields, including machine learning and data mining. Classic graph embedding methods follow the basic idea that the embedding vectors of interconnected nodes in the graph can still maintain a relatively close distance, thereby preserving the structural information between the nodes in the graph. However, this is sub-optimal due to: (i) traditional methods have limited model capacity which limits the learning performance; (ii) existing techniques typically rely on unsupervised learning strategies and fail to couple with the latest learning paradigms; (iii) representation learning and downstream tasks are dependent on each other which should be jointly enhanced. With the remarkable success of deep learning, deep graph representation learning has shown great potential and advantages over shallow (traditional) methods, there exist a large number of deep graph representation learning techniques have been proposed in the past decade, especially graph neural networks. In this survey, we conduct a comprehensive survey on current deep graph representation learning algorithms by proposing a new taxonomy of existing state-of-the-art literature. Specifically, we systematically summarize the essential components of graph representation learning and categorize existing approaches by the ways of graph neural network architectures and the most recent advanced learning paradigms. Moreover, this survey also provides the practical and promising applications of deep graph representation learning. Last but not least, we state new perspectives and suggest challenging directions which deserve further investigations in the future.

PSA-GNN: An augmented GNN framework with priori subgraph knowledge

Graph neural networks have become the primary graph representation learning paradigm, in which nodes update their embeddings by aggregating messages from their neighbors iteratively. However, current message passing based GNNs exploit the higher-order subgraph information other than 1st-order neighbors insufficiently. In contrast, the long-standing graph research has investigated various subgraphs such as motif, clique, core, and truss that contain important structural information to downstream tasks like node classification, which deserve to be preserved by GNNs. In this work, we propose to use the pre-mined subgraphs as priori knowledge to extend the receptive field of GNNs and enhance their expressive power to go beyond the 1st-order Weisfeiler-Lehman isomorphism test. For that, we introduce a general framework called PSA-GNN (Priori Subgraph Augmented Graph Neural Network), which augments each GNN layer by a pair of parallel convolution layers based on a bipartite graph between nodes and priori subgraphs. PSA-GNN intrinsically builds a hybrid receptive field by incorporating priori subgraphs as neighbors, while the embeddings and weights of subgraphs are trainable. Moreover, PSA-GNN can purify the noisy subgraphs both heuristically before training and deterministically during training based on a novel metric called homogeneity. Experimental results show that PSA-GNN achieves an improved performance compared with state-of-the-art message passing based GNN models.

Global attention based GNN with Bayesian collaborative learning for glomerular lesion recognition

BACKGROUND

Glomerular lesions reflect the onset and progression of renal disease. Pathological diagnoses are widely regarded as the definitive method for recognizing these lesions, as the deviations in histopathological structures closely correlate with impairments in renal function.

METHODS

Deep learning plays a crucial role in streamlining the laborious, challenging, and subjective task of recognizing glomerular lesions by pathologists. However, the current methods treat pathology images as data in regular Euclidean space, limiting their ability to efficiently represent the complex local features and global connections. In response to this challenge, this paper proposes a graph neural network (GNN) that utilizes global attention pooling (GAP) to more effectively extract high-level semantic features from glomerular images. The model incorporates Bayesian collaborative learning (BCL), enhancing node feature fine-tuning and fusion during training. In addition, this paper adds a soft classification head to mitigate the semantic ambiguity associated with a purely hard classification.

RESULTS

This paper conducted extensive experiments on four glomerular datasets, comprising a total of 491 whole slide images (WSIs) and 9030 images. The results demonstrate that the proposed model achieves impressive F1 scores of 81.37%, 90.12%, 87.72%, and 98.68% on four private datasets for glomerular lesion recognition. These scores surpass the performance of the other models used for comparison. Furthermore, this paper employed a publicly available BReAst Carcinoma Subtyping (BRACS) dataset with an 85.61% F1 score to further prove the superiority of the proposed model.

CONCLUSION

The proposed model not only facilitates precise recognition of glomerular lesions but also serves as a potent tool for diagnosing kidney diseases effectively. Furthermore, the framework and training methodology of the GNN can be adeptly applied to address various pathology image classification challenges.

SUGAR: Spherical ultrafast graph attention framework for cortical surface registration

Cortical surface registration plays a crucial role in aligning cortical functional and anatomical features across individuals. However, conventional registration algorithms are computationally inefficient. Recently, learning-based registration algorithms have emerged as a promising solution, significantly improving processing efficiency. Nonetheless, there remains a gap in the development of a learning-based method that exceeds the state-of-the-art conventional methods simultaneously in computational efficiency, registration accuracy, and distortion control, despite the theoretically greater representational capabilities of deep learning approaches. To address the challenge, we present SUGAR, a unified unsupervised deep-learning framework for both rigid and non-rigid registration. SUGAR incorporates a U-Net-based spherical graph attention network and leverages the Euler angle representation for deformation. In addition to the similarity loss, we introduce fold and multiple distortion losses to preserve topology and minimize various types of distortions. Furthermore, we propose a data augmentation strategy specifically tailored for spherical surface registration to enhance the registration performance. Through extensive evaluation involving over 10,000 scans from 7 diverse datasets, we showed that our framework exhibits comparable or superior registration performance in accuracy, distortion, and test-retest reliability compared to conventional and learning-based methods. Additionally, SUGAR achieves remarkable sub-second processing times, offering a notable speed-up of approximately 12,000 times in registering 9,000 subjects from the UK Biobank dataset in just 32 min. This combination of high registration performance and accelerated processing time may greatly benefit large-scale neuroimaging studies.

MFA-DTI: Drug-target interaction prediction based on multi-feature fusion adopted framework

The identification of drug-target interactions (DTI) is a valuable step in the drug discovery and repositioning process. However, traditional laboratory experiments are time-consuming and expensive. Computational methods have streamlined research to determine DTIs. The application of deep learning methods has significantly improved the prediction performance for DTIs. Modern deep learning methods can leverage multiple sources of information, including sequence data that contains biological structural information, and interaction data. While useful, these methods cannot be effectively applied to each type of information individually (e.g., chemical structure and interaction network) and do not take into account the specificity of DTI data such as low- or zero-interaction biological entities. To overcome these limitations, we propose a method called MFA-DTI (Multi-feature Fusion Adopted framework for DTI). MFA-DTI consists of three modules: an interaction graph learning module that processes the interaction network to generate interaction vectors, a chemical structure learning module that extracts features from the chemical structure, and a fusion module that combines these features for the final prediction. To validate the performance of MFA-DTI, we conducted experiments on six public datasets under different settings. The results indicate that the proposed method is highly effective in various settings and outperforms state-of-the-art methods.

A Laplacian regularized graph neural network for predictive modeling of multiple chronic conditions

BACKGROUND AND GOALS

One of the biggest difficulties facing healthcare systems today is the prevalence of multiple chronic diseases (MCC). Mortality and the development of new chronic illnesses are more likely in those with MCC. Pre-existing diseases and risk factors specific to the patient have an impact on the complex stochastic process that guides the evolution of MCC. This study's goal is to use a brand-new Graph Neural Network (GNN) model to examine the connections between specific chronic illnesses, patient-level risk factors, and pre-existing conditions.

METHODS

We propose a graph neural network model to analyze the relationship between five chronic conditions (diabetes, obesity, cognitive impairment, hyperlipidemia, and hypertension). The proposed model adds a graph Laplacian regularization term to the loss function, which aims to improve the parameter learning process and accuracy of the GNN based on the graph structure. For validation, we used historical data from the Cameron County Hispanic Cohort (CCHC).

RESULTS

Evaluating the Laplacian regularized GNN on data from 600 patients, we expanded our analysis from two chronic conditions to five chronic conditions. The proposed model consistently surpassed a baseline GNN model, achieving an average accuracy of ≥89% across all combinations. In contrast, the performance of the standard model declined more markedly with the addition of more chronic conditions. The Laplacian regularization provided consistent predictions for adjacent nodes, beneficial in cases with shared attributes among nodes.

CONCLUSIONS

The incorporation of Laplacian regularization in our GNN model is essential, resulting in enhanced node categorization and better predictive performance by harnessing the graph structure. This study underscores the significance of considering graph structure when designing neural networks for graph data. Future research might further explore and refine this regularization method for various tasks using graph-structured data.

Mining channel-regulated peptides from animal venom by integrating sequence semantics and structural information

Channel-regulated peptides (CRPs) derived from animal venom hold great promise as potential drug candidates for numerous diseases associated with channel proteins. However, discovering and identifying CRPs using traditional bio-experimental methods is a time-consuming and laborious process. While there were a few computational studies on CRPs, they were limited to specific channel proteins, relied heavily on complex feature engineering, and lacked the incorporation of multi-source information. To address these problems, we proposed a novel deep learning model, called DeepCRPs, based on graph neural networks for systematically mining CRPs from animal venom. By combining the sequence semantic and structural information, the classification performance of four CRPs was significantly enhanced, reaching an accuracy of 0.92. This performance surpassed baseline models with accuracies ranging from 0.77 to 0.89. Furthermore, we employed advanced interpretable techniques to explore sequence and structural determinants relevant to the classification of CRPs, yielding potentially valuable bio-function interpretations. Comprehensive experimental results demonstrated the precision and interpretive capability of DeepCRPs, making it an accurate and bio-explainable suit for the identification and categorization of CRPs. Our research will contribute to the discovery and development of toxin peptides targeting channel proteins. The source data and code are freely available at https://github.com/liyigerry/DeepCRPs.

Local structure-aware graph contrastive representation learning

Traditional Graph Neural Network (GNN), as a graph representation learning method, is constrained by label information. However, Graph Contrastive Learning (GCL) methods, which tackles the label problem effectively, mainly focus on the feature information of the global graph or small subgraph structure (e.g., the first-order neighborhood). In this paper, we propose a Local Structure-aware Graph Contrastive representation Learning method (LS-GCL) to model the structural information of nodes from multiple views. Specifically, we construct the semantic subgraphs that are not limited to the first-order neighbors. For the local view, the semantic subgraph of each target node is input into a shared GNN encoder to obtain the target node embeddings at the subgraph-level. Then, we use a pooling function to generate the subgraph-level graph embeddings. For the global view, considering the original graph preserves indispensable semantic information of nodes, we leverage the shared GNN encoder to learn the target node embeddings at the global graph-level. The proposed LS-GCL model is optimized to maximize the common information among similar instances at three various perspectives through a multi-level contrastive loss function. Experimental results on six datasets illustrate that our method outperforms state-of-the-art graph representation learning approaches for both node classification and link prediction tasks.

GraphKM: machine and deep learning for KM prediction of wildtype and mutant enzymes

Michaelis constant (KM) is one of essential parameters for enzymes kinetics in the fields of protein engineering, enzyme engineering, and synthetic biology. As overwhelming experimental measurements of KM are difficult and time-consuming, prediction of the KM values from machine and deep learning models would increase the pace of the enzymes kinetics studies. Existing machine and deep learning models are limited to the specific enzymes, i.e., a minority of enzymes or wildtype enzymes. Here, we used a deep learning framework PaddlePaddle to implement a machine and deep learning approach (GraphKM) for KM prediction of wildtype and mutant enzymes. GraphKM is composed by graph neural networks (GNN), fully connected layers and gradient boosting framework. We represented the substrates through molecular graph and the enzymes through a pretrained transformer-based language model to construct the model inputs. We compared the difference of the model results made by the different GNN (GIN, GAT, GCN, and GAT-GCN). The GAT-GCN-based model generally outperformed. To evaluate the prediction performance of the GraphKM and other reported KM prediction models, we collected an independent KM dataset (HXKm) from literatures.

A Dual Robust Graph Neural Network Against Graph Adversarial Attacks

Graph Neural Networks (GNNs) have gained widespread usage and achieved remarkable success in various real-world applications. Nevertheless, recent studies reveal the vulnerability of GNNs to graph adversarial attacks that fool them by modifying graph structure. This vulnerability undermines the robustness of GNNs and poses significant security and privacy risks across various applications. Hence, it is crucial to develop robust GNN models that can effectively defend against such attacks. One simple approach is to remodel the graph. However, most existing methods cannot fully preserve the similarity relationship among the original nodes while learning the node representation required for reweighting the edges. Furthermore, they lack supervision information regarding adversarial perturbations, hampering their ability to recognize adversarial edges. To address these limitations, we propose a novel Dual Robust Graph Neural Network (DualRGNN) against graph adversarial attacks. DualRGNN first incorporates a node-similarity-preserving graph refining (SPGR) module to prune and refine the graph based on the learned node representations, which contain the original nodes' similarity relationships, weakening the poisoning of graph adversarial attacks on graph data. DualRGNN then employs an adversarial-supervised graph attention (ASGAT) network to enhance the model's capability in identifying adversarial edges by treating these edges as supervised signals. Through extensive experiments conducted on four benchmark datasets, DualRGNN has demonstrated remarkable robustness against various graph adversarial attacks.

GNNMF: a multi-view graph neural network for ATAC-seq motif finding

BACKGROUND

The Assay for Transposase-Accessible Chromatin using sequencing (ATAC-seq) utilizes the Transposase Tn5 to probe open chromatic, which simultaneously reveals multiple transcription factor binding sites (TFBSs) compared to traditional technologies. Deep learning (DL) technology, including convolutional neural networks (CNNs), has successfully found motifs from ATAC-seq data. Due to the limitation of the width of convolutional kernels, the existing models only find motifs with fixed lengths. A Graph neural network (GNN) can work on non-Euclidean data, which has the potential to find ATAC-seq motifs with different lengths. However, the existing GNN models ignored the relationships among ATAC-seq sequences, and their parameter settings should be improved.

RESULTS

In this study, we proposed a novel GNN model named GNNMF to find ATAC-seq motifs via GNN and background coexisting probability. Our experiment has been conducted on 200 human datasets and 80 mouse datasets, demonstrated that GNNMF has improved the area of eight metrics radar scores of 4.92% and 6.81% respectively, and found more motifs than did the existing models.

CONCLUSIONS

In this study, we developed a novel model named GNNMF for finding multiple ATAC-seq motifs. GNNMF built a multi-view heterogeneous graph by using ATAC-seq sequences, and utilized background coexisting probability and the iterloss to find different lengths of ATAC-seq motifs and optimize the parameter sets. Compared to existing models, GNNMF achieved the best performance on TFBS prediction and ATAC-seq motif finding, which demonstrates that our improvement is available for ATAC-seq motif finding.

A novel spatiotemporal graph convolutional network framework for functional connectivity biomarkers identification of Alzheimer's disease

BACKGROUND

Functional connectivity (FC) biomarkers play a crucial role in the early diagnosis and mechanistic study of Alzheimer's disease (AD). However, the identification of effective FC biomarkers remains challenging. In this study, we introduce a novel approach, the spatiotemporal graph convolutional network (ST-GCN) combined with the gradient-based class activation mapping (Grad-CAM) model (STGC-GCAM), to effectively identify FC biomarkers for AD.

METHODS

This multi-center cross-racial retrospective study involved 2,272 participants, including 1,105 cognitively normal (CN) subjects, 790 mild cognitive impairment (MCI) individuals, and 377 AD patients. All participants underwent functional magnetic resonance imaging (fMRI) and T1-weighted MRI scans. In this study, firstly, we optimized the STGC-GCAM model to enhance classification accuracy. Secondly, we identified novel AD-associated biomarkers using the optimized model. Thirdly, we validated the imaging biomarkers using Kaplan-Meier analysis. Lastly, we performed correlation analysis and causal mediation analysis to confirm the physiological significance of the identified biomarkers.

RESULTS

The STGC-GCAM model demonstrated great classification performance (The average area under the curve (AUC) values for different categories were: CN vs MCI = 0.98, CN vs AD = 0.95, MCI vs AD = 0.96, stable MCI vs progressive MCI = 0.79). Notably, the model identified specific brain regions, including the sensorimotor network (SMN), visual network (VN), and default mode network (DMN), as key differentiators between patients and CN individuals. These brain regions exhibited significant associations with the severity of cognitive impairment (p < 0.05). Moreover, the topological features of important brain regions demonstrated excellent predictive capability for the conversion from MCI to AD (Hazard ratio = 3.885, p < 0.001). Additionally, our findings revealed that the topological features of these brain regions mediated the impact of amyloid beta (Aβ) deposition (bootstrapped average causal mediation effect: β = -0.01 [-0.025, 0.00], p < 0.001) and brain glucose metabolism (bootstrapped average causal mediation effect: β = -0.02 [-0.04, -0.001], p < 0.001) on cognitive status.

CONCLUSIONS

This study presents the STGC-GCAM framework, which identifies FC biomarkers using a large multi-site fMRI dataset.

AI-enhanced chemical paradigm: From molecular graphs to accurate prediction and mechanism

The development of accurate and interpretable models for predicting reaction constants of organic compounds with hydroxyl radicals is vital for advancing quantitative structure-activity relationships (QSAR) in pollutant degradation. Methods like molecular descriptors, molecular fingerprinting, and group contribution methods have limitations, as traditional machine learning struggles to capture all intramolecular information simultaneously. To address this, we established an integrated graph neural network (GNN) with approximately 12 million learnable parameters. GNN represents atoms as nodes and chemical bonds as edges, thus transforming molecules into a graph structures, effectively capturing microscopic properties while depicting atom connectivity in non-Euclidean space. Our datasets comprise 1401 pollutants to develop an integrated GNN model with Bayesian optimization, the model achieves root mean square errors of 0.165, 0.172, and 0.189 on the training, validation, and test datasets, respectively. Furthermore, we assess molecular structure similarity using molecular fingerprint to enhance the model's applicability. Afterwards, we propose a gradient weight mapping method for model explainability, uncovering the key functional groups in chemical reactions in artificial intelligence perspective, which would boost chemistry through artificial intelligence extreme arithmetic power.

Bearing fault detection by using graph autoencoder and ensemble learning

The research and application of bearing fault diagnosis techniques are crucial for enhancing equipment reliability, extending bearing lifespan, and reducing maintenance expenses. Nevertheless, most existing methods encounter challenges in discriminating between signals from machines operating under normal and faulty conditions, leading to unstable detection results. To tackle this issue, the present study proposes a novel approach for bearing fault detection based on graph neural networks and ensemble learning. Our key contribution is a novel stochasticity-based compositional method that transforms Euclidean-structured data into a graph format for processing by graph neural networks, with feature fusion and a newly proposed ensemble learning strategy for outlier detection specifically designed for bearing fault diagnosis. This approach marks a significant advancement in accurately identifying bearing faults, highlighting our study's pivotal role in enhancing diagnostic methodologies.

SSLDTI: A novel method for drug-target interaction prediction based on self-supervised learning

Many computational methods have been proposed to identify potential drug-target interactions (DTIs) to expedite drug development. Graph neural network (GNN) methods are considered to be one of the most effective approaches. However, shallow GNN methods can only aggregate local information from nodes. Also, deep GNN methods may result in over-smoothing while obtaining long-distance neighbourhood information. As a result, existing GNN methods struggle to extract the complete features of the graph. Additionally, the number of known DTIs is insufficient, and there are far more unknown drug-target pairs than known DTIs, leading to class imbalance. This article proposes a model that combines graph autoencoder and self-supervised learning to accurately encode multilevel features of graphs using only a small number of labelled samples. We introduce a positive sample compensation coefficient to the objective function to mitigate the impact of class imbalance. Experiments on two datasets demonstrated that our model outperforms the four baseline methods, and the new DTIs predicted by the SSLDTI model were verified by the DrugBank database.

Improving chemical reaction yield prediction using pre-trained graph neural networks

Graph neural networks (GNNs) have proven to be effective in the prediction of chemical reaction yields. However, their performance tends to deteriorate when they are trained using an insufficient training dataset in terms of quantity or diversity. A promising solution to alleviate this issue is to pre-train a GNN on a large-scale molecular database. In this study, we investigate the effectiveness of GNN pre-training in chemical reaction yield prediction. We present a novel GNN pre-training method for performance improvement.Given a molecular database consisting of a large number of molecules, we calculate molecular descriptors for each molecule and reduce the dimensionality of these descriptors by applying principal component analysis. We define a pre-text task by assigning a vector of principal component scores as the pseudo-label to each molecule in the database. A GNN is then pre-trained to perform the pre-text task of predicting the pseudo-label for the input molecule. For chemical reaction yield prediction, a prediction model is initialized using the pre-trained GNN and then fine-tuned with the training dataset containing chemical reactions and their yields. We demonstrate the effectiveness of the proposed method through experimental evaluation on benchmark datasets.

Dynamic multiple-graph spatial-temporal synchronous aggregation framework for traffic prediction in intelligent transportation systems

Accurate traffic prediction contributes significantly to the success of intelligent transportation systems (ITS), which enables ITS to rationally deploy road resources and enhance the utilization efficiency of road networks. Improvements in prediction performance are evident by utilizing synchronized rather than stepwise components to model spatial-temporal correlations. Some existing studies have designed graph structures containing spatial and temporal attributes to achieve spatial-temporal synchronous learning. However, two challenges remain due to the intricate dynamics: (a) Accounting for the impact of external factors in spatial-temporal synchronous modeling. (b) Multiple perspectives in constructing spatial-temporal synchronous graphs. To address the mentioned limitations, a novel model named dynamic multiple-graph spatial-temporal synchronous aggregation framework (DMSTSAF) for traffic prediction is proposed. Specifically, DMSTSAF utilizes a feature augmentation module (FAM) to adaptively incorporate traffic data with external factors and generate fused features as inputs to subsequent modules. Moreover, DMSTSAF introduces diverse spatial and temporal graphs according to different spatial-temporal relationships. Based on this, two types of spatial-temporal synchronous graphs and the corresponding synchronous aggregation modules are designed to simultaneously extract hidden features from various aspects. Extensive experiments constructed on four real-world datasets indicate that our model improves by 3.68-8.54% compared to the state-of-the-art baseline.

Predicting abiotic stress-responsive miRNA in plants based on multi-source features fusion and graph neural network

BACKGROUND

More and more studies show that miRNA plays a crucial role in plants' response to different abiotic stresses. However, traditional experimental methods are often expensive and inefficient, so it is important to develop efficient and economical computational methods. Although researchers have developed machine learning-based method, the information of miRNAs and abiotic stresses has not been fully exploited. Therefore, we propose a novel approach based on graph neural networks for predicting potential miRNA-abiotic stress associations.

RESULTS

In this study, we fully considered the multi-source feature information from miRNAs and abiotic stresses, and calculated and integrated the similarity network of miRNA and abiotic stress from different feature perspectives using multiple similarity measures. Then, the above multi-source similarity network and association information between miRNAs and abiotic stresses are effectively fused through heterogeneous networks. Subsequently, the Restart Random Walk (RWR) algorithm is employed to extract global structural information from heterogeneous networks, providing feature vectors for miRNA and abiotic stress. After that, we utilized the graph autoencoder based on GIN (Graph Isomorphism Networks) to learn and reconstruct a miRNA-abiotic stress association matrix to obtain potential miRNA-abiotic stress associations. The experimental results show that our model is superior to all known methods in predicting potential miRNA-abiotic stress associations, and the AUPR and AUC metrics of our model achieve 98.24% and 97.43%, respectively, under five-fold cross-validation.

CONCLUSIONS

The robustness and effectiveness of our proposed model position it as a valuable approach for advancing the field of miRNA-abiotic stress association prediction.

Real-time water quality prediction in water distribution networks using graph neural networks with sparse monitoring data

Ensuring the safety and reliability of drinking water supply requires accurate prediction of water quality in water distribution networks (WDNs). However, existing hydraulic model-based approaches for system state prediction face challenges in model calibration with limited sensor data and intensive computing requirements, while current machine learning models are lack of capacity to predict the system states at sites that are not monitored or included in model training. To address these gaps, this study proposes a novel gated graph neural network (GGNN) model for real-time water quality prediction in WDNs. The GGNN model integrates hydraulic flow directions and water quality data to represent the topology and system dynamics, and employs a masking operation for training to enhance prediction accuracy. Evaluation results from a real-world WDN demonstrate that the GGNN model is capable to achieve accurate water quality prediction across the entire WDN. Despite being trained with water quality data from a limited number of sensor sites, the model can achieve high predictive accuracies (Mean Absolute Error = 0.07 mg L-1 and Mean Absolute Percentage Error = 10.0 %) across the entire network including those unmonitored sites. Furthermore, water quality-based sensor placement significantly improves predictive accuracy, emphasizing the importance of careful sensor location selection. This research advances water quality prediction in WDNs by offering a practical and effective machine learning solution to address challenges related to limited sensor data and network complexity. This study provides a first step towards developing machine learning models to replace hydraulic models in WDN modelling.

Graph neural network recommendation algorithm based on improved dual tower model

In this era of information explosion, recommendation systems play a key role in helping users to uncover content of interest among massive amounts of information. Pursuing a breadth of recall while maintaining accuracy is a core challenge for current recommendation systems. In this paper, we propose a new recommendation algorithm model, the interactive higher-order dual tower (IHDT), which improves current models by adding interactivity and higher-order feature learning between the dual tower neural networks. A heterogeneous graph is constructed containing different types of nodes, such as users, items, and attributes, extracting richer feature representations through meta-paths. To achieve feature interaction, an interactive learning mechanism is introduced to inject relevant features between the user and project towers. Additionally, this method utilizes graph convolutional networks for higher-order feature learning, pooling the node embeddings of the twin towers to obtain enhanced end-user and item representations. IHDT was evaluated on the MovieLens dataset and outperformed multiple baseline methods. Ablation experiments verified the contribution of interactive learning and high-order GCN components.

Quantifying uncertainty: Air quality forecasting based on dynamic spatial-temporal denoising diffusion probabilistic model

Air pollution constitutes a substantial peril to human health, thereby catalyzing the evolution of an array of air quality prediction models. These models span from mechanistic and statistical strategies to machine learning methodologies. The burgeoning field of deep learning has given rise to a plethora of advanced models, which have demonstrated commendable performance. However, previous investigations have overlooked the salience of quantifying prediction uncertainties and potential future interconnections among air monitoring stations. Moreover, prior research typically utilized static predetermined spatial relationships, neglecting dynamic dependencies. To address these limitations, we propose a model named Dynamic Spatial-Temporal Denoising Diffusion Probabilistic Model (DST-DDPM) for air quality prediction. Our model is underpinned by the renowned denoising diffusion model, aiding us in discerning indeterminacy. In order to encapsulate dynamic patterns, we design a dynamic context encoder to generate dynamic adjacency matrices, whilst maintaining static spatial information. Furthermore, we incorporate a spatial-temporal denoising model to concurrently learn both spatial and temporal dependencies. Authenticating our model's performance using a real-world dataset collected in Beijing, the outcomes indicate that our model eclipses other baseline models in terms of both short-term and long-term predictions by 1.36% and 11.62% respectively. Finally, we conduct a case study to exhibit our model's capacity to quantify uncertainties.

Prediction of emergency department revisits among child and youth mental health outpatients using deep learning techniques

BACKGROUND

The proportion of Canadian youth seeking mental health support from an emergency department (ED) has risen in recent years. As EDs typically address urgent mental health crises, revisiting an ED may represent unmet mental health needs. Accurate ED revisit prediction could aid early intervention and ensure efficient healthcare resource allocation. We examine the potential increased accuracy and performance of graph neural network (GNN) machine learning models compared to recurrent neural network (RNN), and baseline conventional machine learning and regression models for predicting ED revisit in electronic health record (EHR) data.

METHODS

This study used EHR data for children and youth aged 4-17 seeking services at McMaster Children's Hospital's Child and Youth Mental Health Program outpatient service to develop and evaluate GNN and RNN models to predict whether a child/youth with an ED visit had an ED revisit within 30 days. GNN and RNN models were developed and compared against conventional baseline models. Model performance for GNN, RNN, XGBoost, decision tree and logistic regression models was evaluated using F1 scores.

RESULTS

The GNN model outperformed the RNN model by an F1-score increase of 0.0511 and the best performing conventional machine learning model by an F1-score increase of 0.0470. Precision, recall, receiver operating characteristic (ROC) curves, and positive and negative predictive values showed that the GNN model performed the best, and the RNN model performed similarly to the XGBoost model. Performance increases were most noticeable for recall and negative predictive value than for precision and positive predictive value.

CONCLUSIONS

This study demonstrates the improved accuracy and potential utility of GNN models in predicting ED revisits among children and youth, although model performance may not be sufficient for clinical implementation. Given the improvements in recall and negative predictive value, GNN models should be further explored to develop algorithms that can inform clinical decision-making in ways that facilitate targeted interventions, optimize resource allocation, and improve outcomes for children and youth.

LSTM-SAGDTA: Predicting Drug-Target Binding Affinity with an Attention Graph Neural Network and LSTM Approach

INTRODUCTION

Drug development is a challenging and costly process, yet it plays a crucial role in improving healthcare outcomes. Drug development requires extensive research and testing to meet the demands for economic efficiency, cures, and pain relief.

METHODS

Drug development is a vital research area that necessitates innovation and collaboration to achieve significant breakthroughs. Computer-aided drug design provides a promising avenue for drug discovery and development by reducing costs and improving the efficiency of drug design and testing.

RESULTS

In this study, a novel model, namely LSTM-SAGDTA, capable of accurately predicting drug-target binding affinity, was developed. We employed SeqVec for characterizing the protein and utilized the graph neural networks to capture information on drug molecules. By introducing self-attentive graph pooling, the model achieved greater accuracy and efficiency in predicting drug-target binding affinity.

CONCLUSION

Moreover, LSTM-SAGDTA obtained superior accuracy over current state-of-the-art methods only by using less training time. The results of experiments suggest that this method represents a highprecision solution for the DTA predictor.

Gated graph neural networks for identifying contamination sources in water distribution systems

Contamination events in water distribution networks (WDN) pose significant threats to water supply and public health. Rapid and accurate contamination source identification (CSI) can facilitate the development of remedial measures to reduce impacts. Though many machine learning (ML) methods have been proposed for fast detection, there is a critical need for approaches capturing complex spatial dynamics in WDNs to enhance prediction accuracy. This study proposes a gated graph neural network (GGNN) for CSI in the WDN, incorporating both spatiotemporal water quality data and flow directionality between network nodes. Evaluated across various contamination scenarios, the GGNN demonstrates high prediction accuracy even with limited sensor coverage. Notably, directional connections significantly enhance the GGNN CSI accuracy, underscoring the importance of network topology and flow dynamics in ML-based WDN CSI approaches. Specifically, the method achieves a 92.27% accuracy in narrowing the contamination source to 5 points using just 2 h of sensor data. The GGNN showcases resilience under model and measurement uncertainties, reaffirming its potential for real-time implementation in practice. Moreover, our findings highlight the impact of sensor sampling frequency and measurement accuracy on CSI accuracy, offering practical insights for ML methods in water network applications.

Prediction of miRNA-disease associations based on strengthened hypergraph convolutional autoencoder

Most existing graph neural network-based methods for predicting miRNA-disease associations rely on initial association matrices to pass messages, but the sparsity of these matrices greatly limits performance. To address this issue and predict potential associations between miRNAs and diseases, we propose a method called strengthened hypergraph convolutional autoencoder (SHGAE). SHGAE leverages multiple layers of strengthened hypergraph neural networks (SHGNN) to obtain robust node embeddings. Within SHGNN, we design a strengthened hypergraph convolutional network module (SHGCN) that enhances original graph associations and reduces matrix sparsity. Additionally, SHGCN expands node receptive fields by utilizing hyperedge features as intermediaries to obtain high-order neighbor embeddings. To improve performance, we also incorporate attention-based fusion of self-embeddings and SHGCN embeddings. SHGAE predicts potential miRNA-disease associations using a multilayer perceptron as the decoder. Across multiple metrics, SHGAE outperforms other state-of-the-art methods in five-fold cross-validation. Furthermore, we evaluate SHGAE on colon and lung neoplasms cases to demonstrate its ability to predict potential associations. Notably, SHGAE also performs well in the analysis of gastric neoplasms without miRNA associations.

Transfer learning enhanced graph neural network for aldehyde oxidase metabolism prediction and its experimental application

Aldehyde oxidase (AOX) is a molybdoenzyme that is primarily expressed in the liver and is involved in the metabolism of drugs and other xenobiotics. AOX-mediated metabolism can result in unexpected outcomes, such as the production of toxic metabolites and high metabolic clearance, which can lead to the clinical failure of novel therapeutic agents. Computational models can assist medicinal chemists in rapidly evaluating the AOX metabolic risk of compounds during the early phases of drug discovery and provide valuable clues for manipulating AOX-mediated metabolism liability. In this study, we developed a novel graph neural network called AOMP for predicting AOX-mediated metabolism. AOMP integrated the tasks of metabolic substrate/non-substrate classification and metabolic site prediction, while utilizing transfer learning from 13C nuclear magnetic resonance data to enhance its performance on both tasks. AOMP significantly outperformed the benchmark methods in both cross-validation and external testing. Using AOMP, we systematically assessed the AOX-mediated metabolism of common fragments in kinase inhibitors and successfully identified four new scaffolds with AOX metabolism liability, which were validated through in vitro experiments. Furthermore, for the convenience of the community, we established the first online service for AOX metabolism prediction based on AOMP, which is freely available at https://aomp.alphama.com.cn.

Hand function after neonatal stroke: A graph model based on basal ganglia and thalami structure

INTRODUCTION

Neonatal arterial ischemic stroke (NAIS) is a common model to study the impact of a unilateral early brain insult on developmental brain plasticity and the appearance of long-term outcomes. Motor difficulties that may arise are typically related to poor function of the affected (contra-lesioned) hand, but surprisingly also of the ipsilesional hand. Although many longitudinal studies after NAIS have shown that predicting the occurrence of gross motor difficulties is easier, accurately predicting hand motor function (for both hands) from morphometric MRI remains complicated. The hypothesis of an association between the structural organization of the basal ganglia (BG) and thalamus with hand motor function seems intuitive given their key role in sensorimotor function. Neuroimaging studies have frequently investigated these structures to evaluate the correlation between their volumes and motor function following early brain injury. However, the results have been controversial. We hypothesize the involvement of other structural parameters.

METHOD

The study involves 35 children (mean age 7.3 years, SD 0.4) with middle cerebral artery NAIS who underwent a structural T1-weighted 3D MRI and clinical examination to assess manual dexterity using the Box and Blocks Test (BBT). Graphs are used to represent high-level structural information of the BG and thalami (volumes, elongations, distances) measured from the MRI. A graph neural network (GNN) is proposed to predict children's hand motor function through a graph regression. To reduce the impact of external factors on motor function (such as behavior and cognition), we calculate a BBT score ratio for each child and hand.

RESULTS

The results indicate a significant correlation between the score ratios predicted by our method and the actual score ratios of both hands (p < 0.05), together with a relatively high accuracy of prediction (mean L1 distance < 0.03). The structural information seems to have a different influence on each hand's motor function. The affected hand's motor function is more correlated with the volume, while the 'unaffected' hand function is more correlated with the elongation of the structures. Experiments emphasize the importance of considering the whole macrostructural organization of the basal ganglia and thalami networks, rather than the volume alone, to predict hand motor function.

CONCLUSION

There is a significant correlation between the structural characteristics of the basal ganglia/thalami and motor function in both hands. These results support the use of MRI macrostructural features of the basal ganglia and thalamus as an early biomarker for predicting motor function in both hands after early brain injury.

Dynamical graph neural network with attention mechanism for epilepsy detection using single channel EEG

Epilepsy is a chronic brain disease, and identifying seizures based on electroencephalogram (EEG) signals would be conducive to implement interventions to help patients reduce impairment and improve quality of life. In this paper, we propose a classification algorithm to apply dynamical graph neural network with attention mechanism to single channel EEG signals. Empirical mode decomposition (EMD) are adopted to construct graphs and the optimal adjacency matrix is obtained by model optimization. A multilayer dynamic graph neural network with attention mechanism is proposed to learn more discriminative graph features. The MLP-pooling structure is proposed to fuse graph features. We performed 12 classification tasks on the epileptic EEG database of the University of Bonn, and experimental results showed that using 25 runs of ten-fold cross-validation produced the best classification results with an average of 99.83[Formula: see text] accuracy, 99.91[Formula: see text] specificity, 99.78[Formula: see text] sensitivity, 99.87[Formula: see text] precision, and 99.47[Formula: see text] [Formula: see text] score for the 12 classification tasks.

AttentionMGT-DTA: A multi-modal drug-target affinity prediction using graph transformer and attention mechanism

The accurate prediction of drug-target affinity (DTA) is a crucial step in drug discovery and design. Traditional experiments are very expensive and time-consuming. Recently, deep learning methods have achieved notable performance improvements in DTA prediction. However, one challenge for deep learning-based models is appropriate and accurate representations of drugs and targets, especially the lack of effective exploration of target representations. Another challenge is how to comprehensively capture the interaction information between different instances, which is also important for predicting DTA. In this study, we propose AttentionMGT-DTA, a multi-modal attention-based model for DTA prediction. AttentionMGT-DTA represents drugs and targets by a molecular graph and binding pocket graph, respectively. Two attention mechanisms are adopted to integrate and interact information between different protein modalities and drug-target pairs. The experimental results showed that our proposed model outperformed state-of-the-art baselines on two benchmark datasets. In addition, AttentionMGT-DTA also had high interpretability by modeling the interaction strength between drug atoms and protein residues. Our code is available at https://github.com/JK-Liu7/AttentionMGT-DTA.

Preserving specificity in federated graph learning for fMRI-based neurological disorder identification

Resting-state functional magnetic resonance imaging (rs-fMRI) offers a non-invasive approach to examining abnormal brain connectivity associated with brain disorders. Graph neural network (GNN) gains popularity in fMRI representation learning and brain disorder analysis with powerful graph representation capabilities. Training a general GNN often necessitates a large-scale dataset from multiple imaging centers/sites, but centralizing multi-site data generally faces inherent challenges related to data privacy, security, and storage burden. Federated Learning (FL) enables collaborative model training without centralized multi-site fMRI data. Unfortunately, previous FL approaches for fMRI analysis often ignore site-specificity, including demographic factors such as age, gender, and education level. To this end, we propose a specificity-aware federated graph learning (SFGL) framework for rs-fMRI analysis and automated brain disorder identification, with a server and multiple clients/sites for federated model aggregation and prediction. At each client, our model consists of a shared and a personalized branch, where parameters of the shared branch are sent to the server while those of the personalized branch remain local. This can facilitate knowledge sharing among sites and also helps preserve site specificity. In the shared branch, we employ a spatio-temporal attention graph isomorphism network to learn dynamic fMRI representations. In the personalized branch, we integrate vectorized demographic information (i.e., age, gender, and education years) and functional connectivity networks to preserve site-specific characteristics. Representations generated by the two branches are then fused for classification. Experimental results on two fMRI datasets with a total of 1218 subjects suggest that SFGL outperforms several state-of-the-art approaches.

Transformer with convolution and graph-node co-embedding: An accurate and interpretable vision backbone for predicting gene expressions from local histopathological image

Inferring gene expressions from histopathological images has long been a fascinating yet challenging task, primarily due to the substantial disparities between the two modality. Existing strategies using local or global features of histological images are suffering model complexity, GPU consumption, low interpretability, insufficient encoding of local features, and over-smooth prediction of gene expressions among neighboring sites. In this paper, we develop TCGN (Transformer with Convolution and Graph-Node co-embedding method) for gene expression estimation from H&E-stained pathological slide images. TCGN comprises a combination of convolutional layers, transformer encoders, and graph neural networks, and is the first to integrate these blocks in a general and interpretable computer vision backbone. Notably, TCGN uniquely operates with just a single spot image as input for histopathological image analysis, simplifying the process while maintaining interpretability. We validate TCGN on three publicly available spatial transcriptomic datasets. TCGN consistently exhibited the best performance (with median PCC 0.232). TCGN offers superior accuracy while keeping parameters to a minimum (just 86.241 million), and it consumes minimal memory, allowing it to run smoothly even on personal computers. Moreover, TCGN can be extended to handle bulk RNA-seq data while providing the interpretability. Enhancing the accuracy of omics information prediction from pathological images not only establishes a connection between genotype and phenotype, enabling the prediction of costly-to-measure biomarkers from affordable histopathological images, but also lays the groundwork for future multi-modal data modeling. Our results confirm that TCGN is a powerful tool for inferring gene expressions from histopathological images in precision health applications.

Beyond the individual: An improved telecom fraud detection approach based on latent synergy graph learning

The development of telecom technology not only facilitates social interactions but also inevitably provides the breeding ground for telecom fraud crimes. However, telecom fraud detection is a challenging task as fraudsters tend to commit co-fraud and disguise themselves within the mass of benign ones. Previous approaches work by unearthing differences in calling sequential patterns between independent fraudsters, but they may ignore synergic fraud patterns and oversimplify fraudulent behaviors. Fortunately, graph-like data formed by traceable telecom interaction provides opportunities for graph neural network (GNN)-based telecom fraud detection methods. Therefore, we develop a latent synergy graph (LSG) learning-based telecom fraud detector, named LSG-FD, to model both sequential and interactive fraudulent behaviors. Specifically, LSG-FD introduces (1) a multi-view LSG extractor to reconstruct synergy relationship-oriented graphs from the meta-interaction graph based on second-order proximity assumption; (2) an LSTM-based calling behavior encoder to capture the sequential patterns from the perspective of local individuals; (3) a dual-channel based graph learning module to alleviate the disassortativity issue (caused by the camouflages of fraudsters) by incorporating the dual-channel frequency filters and the learnable controller to adaptively aggregate high- and low-frequency information from their neighbors; (4) an imbalance-resistant model trainer to remedy the graph imbalance issue by developing a label-aware sampler. Experiment results on the telecom fraud dataset and another two widely used fraud datasets have verified the effectiveness of our model.

Ilm-NMR-P31: an open-access 31P nuclear magnetic resonance database and data-driven prediction of 31P NMR shifts

This publication introduces a novel open-access 31P Nuclear Magnetic Resonance (NMR) shift database. With 14,250 entries encompassing 13,730 distinct molecules from 3,648 references, this database offers a comprehensive repository of organic and inorganic compounds. Emphasizing single-phosphorus atom compounds, the database facilitates data mining and machine learning endeavors, particularly in signal prediction and Computer-Assisted Structure Elucidation (CASE) systems. Additionally, the article compares different models for 31P NMR shift prediction, showcasing the database's potential utility. Hierarchically Ordered Spherical Environment (HOSE) code-based models and Graph Neural Networks (GNNs) perform exceptionally well with a mean squared error of 11.9 and 11.4 ppm respectively, achieving accuracy comparable to quantum chemical calculations.

DL-PPI: a method on prediction of sequenced protein-protein interaction based on deep learning

PURPOSE

Sequenced Protein-Protein Interaction (PPI) prediction represents a pivotal area of study in biology, playing a crucial role in elucidating the mechanistic underpinnings of diseases and facilitating the design of novel therapeutic interventions. Conventional methods for extracting features through experimental processes have proven to be both costly and exceedingly complex. In light of these challenges, the scientific community has turned to computational approaches, particularly those grounded in deep learning methodologies. Despite the progress achieved by current deep learning technologies, their effectiveness diminishes when applied to larger, unfamiliar datasets.

RESULTS

In this study, the paper introduces a novel deep learning framework, termed DL-PPI, for predicting PPIs based on sequence data. The proposed framework comprises two key components aimed at improving the accuracy of feature extraction from individual protein sequences and capturing relationships between proteins in unfamiliar datasets. 1. Protein Node Feature Extraction Module: To enhance the accuracy of feature extraction from individual protein sequences and facilitate the understanding of relationships between proteins in unknown datasets, the paper devised a novel protein node feature extraction module utilizing the Inception method. This module efficiently captures relevant patterns and representations within protein sequences, enabling more informative feature extraction. 2. Feature-Relational Reasoning Network (FRN): In the Global Feature Extraction module of our model, the paper developed a novel FRN that leveraged Graph Neural Networks to determine interactions between pairs of input proteins. The FRN effectively captures the underlying relational information between proteins, contributing to improved PPI predictions. DL-PPI framework demonstrates state-of-the-art performance in the realm of sequence-based PPI prediction.

A deep learning method for drug-target affinity prediction based on sequence interaction information mining

Background

A critical aspect of in silico drug discovery involves the prediction of drug-target affinity (DTA). Conducting wet lab experiments to determine affinity is both expensive and time-consuming, making it necessary to find alternative approaches. In recent years, deep learning has emerged as a promising technique for DTA prediction, leveraging the substantial computational power of modern computers.

Methods

We proposed a novel sequence-based approach, named KC-DTA, for predicting drug-target affinity (DTA). In this approach, we converted the target sequence into two distinct matrices, while representing the molecule compound as a graph. The proposed method utilized k-mers analysis and Cartesian product calculation to capture the interactions and evolutionary information among various residues, enabling the creation of the two matrices for target sequence. For molecule, it was represented by constructing a molecular graph where atoms serve as nodes and chemical bonds serve as edges. Subsequently, the obtained target matrices and molecule graph were utilized as inputs for convolutional neural networks (CNNs) and graph neural networks (GNNs) to extract hidden features, which were further used for the prediction of binding affinity.

Results

In order to evaluate the effectiveness of the proposed method, we conducted several experiments and made a comprehensive comparison with the state-of-the-art approaches using multiple evaluation metrics. The results of our experiments demonstrated that the KC-DTA method achieves high performance in predicting drug-target affinity (DTA). The findings of this research underscore the significance of the KC-DTA method as a valuable tool in the field of in silico drug discovery, offering promising opportunities for accelerating the drug development process. All the data and code are available for access on https://github.com/syc2017/KCDTA.

Prediction of cancer recurrence based on compact graphs of whole slide images

Cancer recurrence is one of the primary causes of patient mortality following treatment, indicating increased aggressiveness of cancer cells and difficulties in achieving a cure. A critical step to improve patients' survival is accurately predicting recurrence status and giving appropriate treatment. Whole Slide Images (WSIs) are a common type of image data in the field of digital pathology, containing high-resolution tissue information. Furthermore, WSIs of primary tumors contain microenvironmental information directly associated with the growth of tumor cells. To effectively utilize this microenvironmental information. Firstly, we represented microenvironmental features of histopathological images as compact graphs. Secondly, this work aims to develop an enhanced lightweight graph neural network called the Adaptive Graph Clustering Network (AGCNet) for predicting cancer recurrence. Experiments are conducted on three cancer datasets from The Cancer Genome Atlas (TCGA), and AGCNet achieved an accuracy of 81.81% in BLCA, 69.66% in PAAD, and 81.96% in STAD. These results indicated that AGCNet is an effective model for predicting cancer recurrence and is expected to be applied in clinical applications.

Graph neural networks for the identification of novel inhibitors of a small RNA

MicroRNAs (miRNAs) play a crucial role in post-transcriptional gene regulation and have been implicated in various diseases, including cancers and lung disease. In recent years, Graph Neural Networks (GNNs) have emerged as powerful tools for analyzing graph-structured data, making them well-suited for the analysis of molecular structures. In this work, we explore the application of GNNs in ligand-based drug screening for small molecules targeting miR-21. By representing a known dataset of small molecules targeting miR-21 as graphs, GNNs can learn complex relationships between their structures and activities, enabling the prediction of potential miRNA-targeting small molecules by capturing the structural features and similarity between known miRNA-targeting compounds. The use of GNNs in miRNA-targeting drug screening holds promise for the discovery of novel therapeutic agents and provides a computational framework for efficient screening of large chemical libraries.

Meta-path guided graph attention network for explainable herb recommendation

Traditional Chinese Medicine (TCM) has been widely adopted in clinical practice by Eastern Asia people for thousands of years. Nowadays, TCM still plays a critical role in Chinese society and receives increasing attention worldwide. The existing herb recommenders learn the complex relations between symptoms and herbs by mining the TCM prescriptions. Given a set of symptoms, they will provide a set of herbs and explanations from the TCM theory. However, the foundation of TCM is Yinyangism (i.e. the combination of Five Phases theory with Yin-yang theory), which is very different from modern medicine philosophy. Only recommending herbs from the TCM theory aspect largely prevents TCM from modern medical treatment. As TCM and modern medicine share a common view at the molecular level, it is necessary to integrate the ancient practice of TCM and standards of modern medicine. In this paper, we explore the underlying action mechanisms of herbs from both TCM and modern medicine, and propose a Meta-path guided Graph Attention Network (MGAT) to provide the explainable herb recommendations. Technically, to translate TCM from an experience-based medicine to an evidence-based medicine system, we incorporate the pharmacology knowledge of modern Chinese medicine with the TCM knowledge. We design a meta-path guided information propagation scheme based on the extended knowledge graph, which combines information propagation and decision process. This scheme adopts meta-paths (predefined relation sequences) to guide neighbor selection in the propagation process. Furthermore, the attention mechanism is utilized in aggregation to help distinguish the salience of different paths connecting a symptom with a herb. In this way, our model can distill the long-range semantics along meta-paths and generate fine-grained explanations. We conduct extensive experiments on a public TCM dataset, demonstrating comparable performance to the state-of-the-art herb recommendation models and the strong explainability.

Hexagonal image segmentation on spatially resolved transcriptomics

Spatial transcriptomics is a rapidly evolving field that enables researchers to capture comprehensive molecular profiles while preserving information about the physical locations. One major challenge in this research area involves the identification of spatial domains, which are distinct regions characterized by unique gene expression patterns. However, current unsupervised methods have struggled to perform well in this regard due to the presence of high levels of noise and dropout events in spatial transcriptomic profiles. In this paper, we propose a novel hexagonal Convolutional Neural Network (hexCNN) for hexagonal image segmentation on spatially resolved transcriptomics. To address the problem of noise and dropout occurrences within spatial transcriptomics data, we first extend an unsupervised algorithm to a supervised learning method that can identify useful features and reduce noise hindrance. Then, inspired by the classical convolution in convolutional neural networks (CNNs), we designed a regular hexagonal convolution to compensate for the missing gene expression patterns from adjacent spots. We evaluated the performance of hexCNN by applying it to the DLPFC dataset. The results show that hexCNN achieves a classification accuracy of 86.8% and an average Rand index (ARI) of 77.1% (1.4% and 2.5% higher than those of GNNs). The results also demonstrate that hexCNN is capable of removing the noise caused by batch effect while preserving the biological signal differences.

A-GCL: Adversarial graph contrastive learning for fMRI analysis to diagnose neurodevelopmental disorders

Accurate diagnosis of neurodevelopmental disorders is a challenging task due to the time-consuming cognitive tests and potential human bias in clinics. To address this challenge, we propose a novel adversarial self-supervised graph neural network (GNN) based on graph contrastive learning, named A-GCL, for diagnosing neurodevelopmental disorders using functional magnetic resonance imaging (fMRI) data. Taking advantage of the success of GNNs in psychiatric disease diagnosis using fMRI, our proposed A-GCL model is expected to improve the performance of diagnosis and provide more robust results. A-GCL takes graphs constructed from the fMRI images as input and uses contrastive learning to extract features for classification. The graphs are constructed with 3 bands of the amplitude of low-frequency fluctuation (ALFF) as node features and Pearson's correlation coefficients (PCC) of the average fMRI time series in different brain regions as edge weights. The contrastive learning creates an edge-dropped graph from a trainable Bernoulli mask to extract features that are invariant to small variations of the graph. Experiment results on three datasets - Autism Brain Imaging Data Exchange (ABIDE) I, ABIDE II, and attention deficit hyperactivity disorder (ADHD) - with 3 atlases - AAL1, AAL3, Shen268 - demonstrate the superiority and generalizability of A-GCL compared to the other GNN-based models. Extensive ablation studies verify the robustness of the proposed approach to atlas selection and model variation. Explanatory results reveal key functional connections and brain regions associated with neurodevelopmental disorders.

Drug-target affinity prediction method based on multi-scale information interaction and graph optimization

Drug-target affinity (DTA) prediction as an emerging and effective method is widely applied to explore the strength of drug-target interactions in drug development research. By predicting these interactions, researchers can assess the potential efficacy and safety of candidate drugs at an early stage, narrowing down the search space for therapeutic targets and accelerating the discovery and development of new drugs. However, existing DTA prediction models mainly use graphical representations of drug molecules, which lack information on interactions between individual substructures, thus affecting prediction accuracy and model interpretability. Therefore, transformer and diffusion on drug graphs in DTA prediction (TDGraphDTA) are introduced to predict drug-target interactions using multi-scale information interaction and graph optimization. An interactive module is integrated into feature extraction of drug and target features at different granularity levels. A diffusion model-based graph optimization module is proposed to improve the representation of molecular graph structures and enhance the interpretability of graph representations while obtaining optimal feature representations. In addition, TDGraphDTA improves the accuracy and reliability of predictions by capturing relationships and contextual information between molecular substructures. The performance of the proposed TDGraphDTA in DTA prediction was verified on three publicly available benchmark datasets (Davis, Metz, and KIBA). Compared with state-of-the-art baseline models, it achieved better results in terms of consistency index, R-squared, etc. Furthermore, compared with some existing methods, the proposed TDGraphDTA is demonstrated to have better structure capturing capabilities by visualizing the feature capturing capabilities of the model using Grad-AAM toxicity labels in the ToxCast dataset. The corresponding source codes are available at https://github.com/Lamouryz/TDGraph.

ProS-GNN: Predicting effects of mutations on protein stability using graph neural networks

Predicting protein stability change upon variation through a computational approach is a valuable tool to unveil the mechanisms of mutation-induced drug failure and develop immunotherapy strategies. Some previous machine learning-based techniques exhibit anti-symmetric bias toward destabilizing situations, whereas others struggle with generalization to unseen examples. To address these issues, we propose a gated graph neural network-based approach to predict changes in protein stability upon mutation. The model uses message passing to encode the links between the molecular structure and property after eliminating the non-mutant structure and creating input feature vectors. While doing so, it also incorporates the coordinates of the raw atoms to provide spatial insights into the chemical systems. We test the model on the Ssym, Myoglobin, Broom, and p53 datasets to demonstrate the generalization performance. Compared to existing approaches, our proposed method achieves improved linearity with symmetry in less time. The code for this study is available at: https://github.com/HongzhouTang/Pros-GNN.

BBLN: A bilateral-branch learning network for unknown protein-protein interaction prediction

Unknown Protein-Protein Interactions (PPIs) prediction has a huge demand in the biological analysis field. Since the effect of the limited availability of protein data is severe, transferable representations are highly demanded to be learned from various data. The latest works enhance the model performance on unknown PPIs prediction and have achieved certain improvements by combining protein information and relation information on PPI graph. However, such methods inevitably suffer from a so-called information monotonicity problem that limits the improvements when encountering large amounts of unknown PPIs. The prediction performance cannot be actually increased without considering the complementary information and relationship information among various modalities of protein data. To this end, we propose a bilateral-branch learning network to deeply enhance the both complementary and relationship information based on the amino acid sequence and gene ontology from multi- and cross-modal views. Experimental results on massive real-world datasets show that our method significantly outperforms the previous state-of-the-art on both traditional and novel unknown PPIs prediction.

A Multi-perspective Model for Protein-Ligand-Binding Affinity Prediction

Gathering information from multi-perspective graphs is an essential issue for many applications especially for protein-ligand-binding affinity prediction. Most of traditional approaches obtained such information individually with low interpretability. In this paper, we harness the rich information from multi-perspective graphs with a general model, which abstractly represents protein-ligand complexes with better interpretability while achieving excellent predictive performance. In addition, we specially analyze the protein-ligand-binding affinity problem, taking into account the heterogeneity of proteins and ligands. Experimental evaluations demonstrate the effectiveness of our data representation strategy on public datasets by fusing information from different perspectives. All codes are available in the https://github.com/Jthy-af/HaPPy .

Multi-cell type and multi-level graph aggregation network for cancer grading in pathology images

In pathology, cancer grading is crucial for patient management and treatment. Recent deep learning methods, based upon convolutional neural networks (CNNs), have shown great potential for automated and accurate cancer diagnosis. However, these do not explicitly utilize tissue/cellular composition, and thus difficult to incorporate the existing knowledge of cancer pathology. In this study, we propose a multi-cell type and multi-level graph aggregation network (MMGA-Net) for cancer grading. Given a pathology image, MMGA-Net constructs multiple cell graphs at multiple levels to represent intra- and inter-cell type relationships and to incorporate global and local cell-to-cell interactions. In addition, it extracts tissue contextual information using a CNN. Then, the tissue and cellular information are fused to predict a cancer grade. The experimental results on two types of cancer datasets demonstrate the effectiveness of MMGA-Net, outperforming other competing models. The results also suggest that the information fusion of multiple cell types and multiple levels via graphs is critical for improved pathology image analysis.

Deep graph convolutional network for small-molecule retention time prediction

The retention time (RT) is a crucial source of data for liquid chromatography-mass spectrometry (LCMS). A model that can accurately predict the RT for each molecule would empower filtering candidates with similar spectra but differing RT in LCMS-based molecule identification. Recent research shows that graph neural networks (GNNs) outperform traditional machine learning algorithms in RT prediction. However, all of these models use relatively shallow GNNs. This study for the first time investigates how depth affects GNNs' performance on RT prediction. The results demonstrate that a notable improvement can be achieved by pushing the depth of GNNs to 16 layers by the adoption of residual connection. Additionally, we also find that graph convolutional network (GCN) model benefits from the edge information. The developed deep graph convolutional network, DeepGCN-RT, significantly outperforms the previous state-of-the-art method and achieves the lowest mean absolute percentage error (MAPE) of 3.3% and the lowest mean absolute error (MAE) of 26.55 s on the SMRT test set. We also finetune DeepGCN-RT on seven datasets with various chromatographic conditions. The mean MAE of the seven datasets largely decreases 30% compared to previous state-of-the-art method. On the RIKEN-PlaSMA dataset, we also test the effectiveness of DeepGCN-RT in assisting molecular structure identification. By 30% lessening the number of potential structures, DeepGCN-RT is able to improve top-1 accuracy by about 11%.