Prediction of Drug-Target Affinity Using Attention Neural Network.

Studying drug-target interactions (DTIs) is the foundational and crucial phase in drug discovery. Biochemical experiments, while being the most reliable method for determining drug-target affinity (DTA), are time-consuming and costly, making it challenging to meet the current demands for swift and efficient drug development. Consequently, computational DTA prediction methods have emerged as indispensable tools for this research. In this article, we propose a novel deep learning algorithm named GRA-DTA, for DTA prediction. Specifically, we introduce Bidirectional Gated Recurrent Unit (BiGRU) combined with a soft attention mechanism to learn target representations. We employ Graph Sample and Aggregate (GraphSAGE) to learn drug representation, especially to distinguish the different features of drug and target representations and their dimensional contributions. We merge drug and target representations by an attention neural network (ANN) to learn drug-target pair representations, which are fed into fully connected layers to yield predictive DTA. The experimental results showed that GRA-DTA achieved mean squared error of 0.142 and 0.225 and concordance index reached 0.897 and 0.890 on the benchmark datasets KIBA and Davis, respectively, surpassing the most state-of-the-art DTA prediction algorithms.

Automatic disease prediction from human gut metagenomic data using boosting GraphSAGE.

BACKGROUND: The human microbiome plays a critical role in maintaining human health. Due to the recent advances in high-throughput sequencing technologies, the microbiome profiles present in the human body have become publicly available. Hence, many works have been done to analyze human microbiome profiles. These works have identified that different microbiome profiles are present in healthy and sick individuals for different diseases. Recently, several computational methods have utilized the microbiome profiles to automatically diagnose and classify the host phenotype. RESULTS: In this work, a novel deep learning framework based on boosting GraphSAGE is proposed for automatic prediction of diseases from metagenomic data. The proposed framework has two main components, (a). Metagenomic Disease graph (MD-graph) construction module, (b). Disease prediction Network (DP-Net) module. The graph construction module constructs a graph by considering each metagenomic sample as a node in the graph. The graph captures the relationship between the samples using a proximity measure. The DP-Net consists of a boosting GraphSAGE model which predicts the status of a sample as sick or healthy. The effectiveness of the proposed method is verified using real and synthetic datasets corresponding to diseases like inflammatory bowel disease and colorectal cancer. The proposed model achieved a highest AUC of 93%, Accuracy of 95%, F1-score of 95%, AUPRC of 95% for the real inflammatory bowel disease dataset and a best AUC of 90%, Accuracy of 91%, F1-score of 87% and AUPRC of 93% for the real colorectal cancer dataset. CONCLUSION: The proposed framework outperforms other machine learning and deep learning models in terms of classification accuracy, AUC, F1-score and AUPRC for both synthetic and real metagenomic data.

Graph Neural Network-Based Method of Spatiotemporal Land Cover Mapping Using Satellite Imagery.

Multispectral satellite imagery offers a new perspective for spatial modelling, change detection and land cover classification. The increased demand for accurate classification of geographically diverse regions led to advances in object-based methods. A novel spatiotemporal method is presented for object-based land cover classification of satellite imagery using a Graph Neural Network. This paper introduces innovative representation of sequential satellite images as a directed graph by connecting segmented land region through time. The method's novel modular node classification pipeline utilises the Convolutional Neural Network as a multispectral image feature extraction network, and the Graph Neural Network as a node classification model. To evaluate the performance of the proposed method, we utilised EfficientNetV2-S for feature extraction and the GraphSAGE algorithm with Long Short-Term Memory aggregation for node classification. This innovative application on Sentinel-2 L2A imagery produced complete 4-year intermonthly land cover classification maps for two regions: Graz in Austria, and the region of Portoroz, Izola and Koper in Slovenia. The regions were classified with Corine Land Cover classes. In the level 2 classification of the Graz region, the method outperformed the state-of-the-art UNet model, achieving an average F1-score of 0.841 and an accuracy of 0.831, as opposed to UNet's 0.824 and 0.818, respectively. Similarly, the method demonstrated superior performance over UNet in both regions under the level 1 classification, which contains fewer classes. Individual classes have been classified with accuracies up to 99.17%.

MGDHGS: Gene-bridged metabolite-disease relationships prediction via GraphSAGE and self-attention mechanism.

Metabolites represent the underlying information of biological systems. Revealing the links between metabolites and diseases can facilitate the development of targeted drugs. Traditional biological experiments can be used to validate the relationships of metabolite-disease, but these methods are time-consuming and labor-intensive. In contrast, the prevailing computational methods have improved efficiency but primarily rely on the metabolite-disease interactions, overlooking the impact of other biological components. To remedy the problem, we present a novel computational framework (MGDHGS) based on metabolite-gene-disease heterogeneous network to forecast potential associations. Specifically, we initially integrate data from multiple sources to construct metabolite-gene-disease heterogeneous network that includes known associations and computationally-derived similarities. Then, the GraphSAGE is harnessed to learn the low dimensional neighborhood representation in the heterogeneous network and self-attention mechanism is applied to effectively capture the connectivity patterns, which contributions to combine with nodes intrinsic and extrinsic features. Finally, the ultimate relationships probability scores are predicted by linear regression based on the these characteristics. The five-fold cross-validation showcases impressive AUC (0.9734) and PR (0.9718) for MGDHGS compared with five state-of-the-art methods, and the case studies validate that the metabolite-disease associations predicted by MGDHGS can be substantiated through pertinent biological experiments. The findings of this study show great potential contribution in the development of targeted drugs as well as offering solid support for our understanding of the complex interactions between metabolites, genes and diseases.

Implementing link prediction in protein networks via feature fusion models based on graph neural networks.

MOTIVATION: Protein-protein interactions serve as the cornerstone for various biochemical processes within biological organisms. Existing research methodologies predominantly employ link prediction techniques to analyze these interaction networks. However, traditional approaches often fall short in delivering satisfactory predictive performance when applied to multi-species datasets. Current computational methods largely focus on analyzing the network topology, resulting in a somewhat monolithic feature set. The integration of diverse features in the model could potentially yield superior performance and broader applicability. To this end, we propose an autoencoder model built on graph neural networks, designed to enhance both predictive performance and generalizability by leveraging the integration of gene ontology. RESULTS: In this research, we developed AGraphSAGE, a model specifically designed for analyzing protein-protein interaction network data. By seamlessly integrating gene ontology into the graph structure, we employed a dual-channel graph sampling and aggregation network that capitalizes on topological information to process high-dimensional features. Feature fusion is achieved through the implementation of graph attention mechanisms, and we adopted a link prediction framework as the experimental training model. Performance was evaluated on real-world datasets using key metrics, such as Area Under the Curve (AUC). A hyperparameter search space was established, and a Bayesian optimization strategy was applied to iteratively fine-tune the model, assessing the impact of various parameters on predictive efficacy. The experimental results validate that our proposed model is capable of effectively predicting protein-protein interactions across diverse biological species.

SAGESDA: Multi-GraphSAGE networks for predicting SnoRNA-disease associations.

Over the years, extensive research has highlighted the functional roles of small nucleolar RNAs in various biological processes associated with the development of complex human diseases. Therefore, understanding the existing relationships between different snoRNAs and diseases is crucial for advancing disease diagnosis and treatment. However, classical biological experiments for identifying snoRNA-disease associations are expensive and time-consuming. Therefore, there is an urgent need for cost-effective computational techniques that can enhance the efficiency and accuracy of prediction. While several computational models have already been proposed, many suffer from limitations and suboptimal performance. In this study, we introduced a novel Graph Neural Network-based (GNN) classification model, called SAGESDA, which is implemented through the GraphSAGE architecture with attention for the prediction of snoRNA-disease associations. The classifier leverages local neighbouring nodes in a heterogeneous network to generate new node embeddings through message passing. The mini-batch gradient descent technique was applied to divide the graph into smaller sub-graphs, which enhances the model's accuracy, speed and scalability. With these advancements, SAGESDA attained an area under the receiver operating characteristic (ROC) curve (AUC) of 0.92 using the standard dot product classifier, surpassing previous related studies. This notable performance demonstrates that SAGESDA is a promising model for predicting unknown snoRNA-disease associations with high accuracy. The SAGESDA implementation details can be obtained from https://github.com/momanyibiffon/SAGESDA.git.

A GraphSAGE-based model with fingerprints only to predict drug-drug interactions.

Drugs are an effective way to treat various diseases. Some diseases are so complicated that the effect of a single drug for such diseases is limited, which has led to the emergence of combination drug therapy. The use multiple drugs to treat these diseases can improve the drug efficacy, but it can also bring adverse effects. Thus, it is essential to determine drug-drug interactions (DDIs). Recently, deep learning algorithms have become popular to design DDI prediction models. However, most deep learning-based models need several types of drug properties, inducing the application problems for drugs without these properties. In this study, a new deep learning-based model was designed to predict DDIs. For wide applications, drugs were first represented by commonly used properties, referred to as fingerprint features. Then, these features were perfectly fused with the drug interaction network by a type of graph convolutional network method, GraphSAGE, yielding high-level drug features. The inner product was adopted to score the strength of drug pairs. The model was evaluated by 10-fold cross-validation, resulting in an AUROC of 0.9704 and AUPR of 0.9727. Such performance was better than the previous model which directly used drug fingerprint features and was competitive compared with some other previous models that used more drug properties. Furthermore, the ablation tests indicated the importance of the main parts of the model, and we analyzed the strengths and limitations of a model for drugs with different degrees in the network. This model identified some novel DDIs that may bring expected benefits, such as the combination of PEA and cannabinol that may produce better effects. DDIs that may cause unexpected side effects have also been discovered, such as the combined use of WIN 55,212-2 and cannabinol. These DDIs can provide novel insights for treating complex diseases or avoiding adverse drug events.

GSLAlign: community detection and local PPI network alignment.

High throughput protein-protein interaction (PPI) profiling and computational techniques have resulted in generating a large amount of PPI network data. The study of PPI networks helps in understanding the biological processes of the proteins. The comparative study of the PPI networks helps in identifying the conserved interactions across the species. This article presents a novel local PPI network aligner 'GSLAlign' that consists of two stages. It first detects the communities from the PPI networks by applying the GraphSAGE algorithm using gene expression data. In the second stage, the detected communities are aligned using a community aligner that is based on protein sequence similarity. The community detection algorithm produces more separable and biologically accurate communities as compared to previous community detection algorithms. Moreover, the proposed community alignment algorithm achieves 3-8% better results in terms of semantic similarity as compared to previous local aligners. The average connectivity and coverage of the proposed algorithm are also better than the existing aligners.Communicated by Ramaswamy H. Sarma.

Data-driven drug treatment: enhancing clinical decision-making with SalpPSO-optimized GraphSAGE.

Safe drug recommendation systems play a crucial role in minimizing adverse drug reactions and enhancing patient safety. In this research, we propose an innovative approach to develop a safety drug recommendation system by integrating the Salp Swarm Optimization-based Particle Swarm Optimization (SalpPSO) with the GraphSAGE algorithm. The goal is to optimize the hyper parameters of GraphSAGE, enabling more accurate drug-drug interaction prediction and personalized drug recommendations. The research begins with data collection from real-world datasets, including MIMIC-III, Drug Bank, and ICD-9 ontology. The databases provide comprehensive and diverse clinical data related to patients, diseases, and drugs, forming the foundation of a knowledge graph. It represents drug-related entities and their relationships, such as drugs, indications, adverse effects, and drug-drug interactions. The knowledge graph's integration of patient data, disease ontology, and drug information enhances the system's accuracy to predict drug-drug interactions as well as identifying potential detrimental drug reactions. The GraphSAGE algorithm is employed as the base model for learning node embeddings in the knowledge graph. To enhance its performance, we propose the SalpPSO algorithm for hyper parameter optimization. SalpPSO combines features from Salp Swarm Optimization and Particle Swarm Optimization, offering a robust and effective optimization process. The optimized hyper parameters lead to more reliable and accurate drug recommendation system. For evaluation, the dataset is split into training and validation sets and compared the performance of the modified GraphSAGE model with SalpPSO-optimized hyper parameters to the standard models. The experimental analysis conducted in terms of various measures proves the efficiency of the proposed safe recommendation system, offering valuable for healthcare experts in making more informed and personalized drug treatment decisions for patients.

Drug Repositioning with GraphSAGE and Clustering Constraints Based on Drug and Disease Networks.

The understanding of therapeutic properties is important in drug repositioning and drug discovery. However, chemical or clinical trials are expensive and inefficient to characterize the therapeutic properties of drugs. Recently, artificial intelligence (AI)-assisted algorithms have received extensive attention for discovering the potential therapeutic properties of drugs and speeding up drug development. In this study, we propose a new method based on GraphSAGE and clustering constraints (DRGCC) to investigate the potential therapeutic properties of drugs for drug repositioning. First, the drug structure features and disease symptom features are extracted. Second, the drug-drug interaction network and disease similarity network are constructed according to the drug-gene and disease-gene relationships. Matrix factorization is adopted to extract the clustering features of networks. Then, all the features are fed to the GraphSAGE to predict new associations between existing drugs and diseases. Benchmark comparisons on two different datasets show that our method has reliable predictive performance and outperforms other six competing. We have also conducted case studies on existing drugs and diseases and aimed to predict drugs that may be effective for the novel coronavirus disease 2019 (COVID-19). Among the predicted anti-COVID-19 drug candidates, some drugs are being clinically studied by pharmacologists, and their binding sites to COVID-19-related protein receptors have been found via the molecular docking technology.