Joint deep autoencoder and subgraph augmentation for inferring microbial responses to drugs

Predicting potential microbe-disease associations based on dual branch graph convolutional network

Studying the association between microbes and diseases not only aids in the prevention and diagnosis of diseases, but also provides crucial theoretical support for new drug development and personalized treatment. Due to the time-consuming and costly nature of laboratory-based biological tests to confirm the relationship between microbes and diseases, there is an urgent need for innovative computational frameworks to anticipate new associations between microbes and diseases. Here, we propose a novel computational approach based on a dual branch graph convolutional network (GCN) module, abbreviated as DBGCNMDA, for identifying microbe-disease associations. First, DBGCNMDA calculates the similarity matrix of diseases and microbes by integrating functional similarity and Gaussian association spectrum kernel (GAPK) similarity. Then, semantic information from different biological networks is extracted by two GCN modules from different perspectives. Finally, the scores of microbe-disease associations are predicted based on the extracted features. The main innovation of this method lies in the use of two types of information for microbe/disease similarity assessment. Additionally, we extend the disease nodes to address the issue of insufficient features due to low data dimensionality. We optimize the connectivity between the homogeneous entities using random walk with restart (RWR), and then use the optimized similarity matrix as the initial feature matrix. In terms of network understanding, we design a dual branch GCN module, namely GlobalGCN and LocalGCN, to fine-tune node representations by introducing side information, including homologous neighbour nodes. We evaluate the accuracy of the DBGCNMDA model using five-fold cross-validation (5-fold-CV) technique. The results show that the area under the receiver operating characteristic curve (AUC) and area under the precision versus recall curve (AUPR) of the DBGCNMDA model in the 5-fold-CV are 0.9559 and 0.9630, respectively. The results from the case studies using published experimental data confirm a significant number of predicted associations, indicating that DBGCNMDA is an effective tool for predicting potential microbe-disease associations.

Knowledge enhanced attention aggregation network for medicine recommendation

The combination of deep learning and the medical field has recently achieved great success, particularly in recommending medicine for patients. However, patients' clinical records often contain repeated medical information that can significantly impact their health condition. Most existing methods for modeling longitudinal patient information overlook the impact of individual diagnoses and procedures on the patient's health, resulting in insufficient patient representation and limited accuracy of medicine recommendations. Therefore, we propose a medicine recommendation model called KEAN, which is based on an attention aggregation network and enhanced graph convolution. Specifically, KEAN can aggregate individual diagnoses and procedures in patient visits to capture significant features that affect patients' diseases. We further incorporate medicine knowledge from complex medicine combinations, reduce drug-drug interactions (DDIs), and recommend medicines that are beneficial to patients' health. The experimental results on the MIMIC-III dataset demonstrate that our model outperforms existing advanced methods, which highlights the effectiveness of the proposed method.

HPTRMF: Collaborative Matrix Factorization-Based Prediction Method for LncRNA-Disease Associations Using High-Order Perturbation and Flexible Trifactor Regularization

Existing matrix factorization methods face challenges, including the cold start problem and global nonlinear data loss during similarity learning, particularly in predicting associations between long noncoding RNAs (LncRNAs) and diseases. To overcome these issues, we introduce HPTRMF, a matrix factorization approach incorporating high-order perturbation and flexible trifactor regularization. HPTRMF constructs a high-order correlation matrix utilizing the known association matrix, leveraging high-order perturbation to effectively address the cold start problem caused by data sparsity. Additionally, HPTRMF incorporates a flexible trifactor regularization term to capture similarity information on LncRNAs and diseases, enabling the effective handling of global nonlinear data loss by capturing such data in the similarity matrix. Experimental results demonstrate the superiority of HPTRMF over nine state-of-the-art algorithms in Leave-One-Out Cross-Validation (LOOCV) and Five-Fold Cross-Validation (5-Fold CV) on three data sets.HPTRMF and data sets are available in https://github.com/Llvvvv/HPTRMF.

GraphADT: empowering interpretable predictions of acute dermal toxicity with multi-view graph pooling and structure remapping

MOTIVATION

Accurate prediction of acute dermal toxicity (ADT) is essential for the safe and effective development of contact drugs. Currently, graph neural networks, a form of deep learning technology, accurately model the structure of compound molecules, enhancing predictions of their ADT. However, many existing methods emphasize atom-level information transfer and overlook crucial data conveyed by molecular bonds and their interrelationships. Additionally, these methods often generate "equal" node representations across the entire graph, failing to accentuate "important" substructures like functional groups, pharmacophores, and toxicophores, thereby reducing interpretability.

RESULTS

We introduce a novel model, GraphADT, utilizing structure remapping and multi-view graph pooling (MVPool) technologies to accurately predict compound ADT. Initially, our model applies structure remapping to better delineate bonds, transforming "bonds" into new nodes and "bond-atom-bond" interactions into new edges, thereby reconstructing the compound molecular graph. Subsequently, we use MVPool to amalgamate data from various perspectives, minimizing biases inherent to single-view analyses. Following this, the model generates a robust node ranking collaboratively, emphasizing critical nodes or substructures to enhance model interpretability. Lastly, we apply a graph comparison learning strategy to train both the original and structure remapped molecular graphs, deriving the final molecular representation. Experimental results on public datasets indicate that the GraphADT model outperforms existing state-of-the-art models. The GraphADT model has been demonstrated to effectively predict compound ADT, offering potential guidance for the development of contact drugs and related treatments.

AVAILABILITY AND IMPLEMENTATION

Our code and data are accessible at: https://github.com/mxqmxqmxq/GraphADT.git.

GEnDDn: An lncRNA-Disease Association Identification Framework Based on Dual-Net Neural Architecture and Deep Neural Network

Accumulating studies have demonstrated close relationships between long non-coding RNAs (lncRNAs) and diseases. Identification of new lncRNA-disease associations (LDAs) enables us to better understand disease mechanisms and further provides promising insights into cancer targeted therapy and anti-cancer drug design. Here, we present an LDA prediction framework called GEnDDn based on deep learning. GEnDDn mainly comprises two steps: First, features of both lncRNAs and diseases are extracted by combining similarity computation, non-negative matrix factorization, and graph attention auto-encoder, respectively. And each lncRNA-disease pair (LDP) is depicted as a vector based on concatenation operation on the extracted features. Subsequently, unknown LDPs are classified by aggregating dual-net neural architecture and deep neural network. Using six different evaluation metrics, we found that GEnDDn surpassed four competing LDA identification methods (SDLDA, LDNFSGB, IPCARF, LDASR) on the lncRNADisease and MNDR databases under fivefold cross-validation experiments on lncRNAs, diseases, LDPs, and independent lncRNAs and independent diseases, respectively. Ablation experiments further validated the powerful LDA prediction performance of GEnDDn. Furthermore, we utilized GEnDDn to find underlying lncRNAs for lung cancer and breast cancer. The results elucidated that there may be dense linkages between IFNG-AS1 and lung cancer as well as between HIF1A-AS1 and breast cancer. The results require further biomedical experimental verification. GEnDDn is publicly available at https://github.com/plhhnu/GEnDDn.

CVGAE: A Self-Supervised Generative Method for Gene Regulatory Network Inference Using Single-Cell RNA Sequencing Data

Gene regulatory network (GRN) inference based on single-cell RNA sequencing data (scRNAseq) plays a crucial role in understanding the regulatory mechanisms between genes. Various computational methods have been employed for GRN inference, but their performance in terms of network accuracy and model generalization is not satisfactory, and their poor performance is caused by high-dimensional data and network sparsity. In this paper, we propose a self-supervised method for gene regulatory network inference using single-cell RNA sequencing data (CVGAE). CVGAE uses graph neural network for inductive representation learning, which merges gene expression data and observed topology into a low-dimensional vector space. The well-trained vectors will be used to calculate mathematical distance of each gene, and further predict interactions between genes. In overall framework, FastICA is implemented to relief computational complexity caused by high dimensional data, and CVGAE adopts multi-stacked GraphSAGE layers as an encoder and an improved decoder to overcome network sparsity. CVGAE is evaluated on several single cell datasets containing four related ground-truth networks, and the result shows that CVGAE achieve better performance than comparative methods. To validate learning and generalization capabilities, CVGAE is applied in few-shot environment by change the ratio of train set and test set. In condition of few-shot, CVGAE obtains comparable or superior performance.

Finding potential lncRNA-disease associations using a boosting-based ensemble learning model

Introduction: Long non-coding RNAs (lncRNAs) have been in the clinical use as potential prognostic biomarkers of various types of cancer. Identifying associations between lncRNAs and diseases helps capture the potential biomarkers and design efficient therapeutic options for diseases. Wet experiments for identifying these associations are costly and laborious. Methods: We developed LDA-SABC, a novel boosting-based framework for lncRNA-disease association (LDA) prediction. LDA-SABC extracts LDA features based on singular value decomposition (SVD) and classifies lncRNA-disease pairs (LDPs) by incorporating LightGBM and AdaBoost into the convolutional neural network. Results: The LDA-SABC performance was evaluated under five-fold cross validations (CVs) on lncRNAs, diseases, and LDPs. It obviously outperformed four other classical LDA inference methods (SDLDA, LDNFSGB, LDASR, and IPCAF) through precision, recall, accuracy, F1 score, AUC, and AUPR. Based on the accurate LDA prediction performance of LDA-SABC, we used it to find potential lncRNA biomarkers for lung cancer. The results elucidated that 7SK and HULC could have a relationship with non-small-cell lung cancer (NSCLC) and lung adenocarcinoma (LUAD), respectively. Conclusion: We hope that our proposed LDA-SABC method can help improve the LDA identification.

Identifying potential ligand-receptor interactions based on gradient boosted neural network and interpretable boosting machine for intercellular communication analysis

Cell-cell communication is essential to many key biological processes. Intercellular communication is generally mediated by ligand-receptor interactions (LRIs). Thus, building a comprehensive and high-quality LRI resource can significantly improve intercellular communication analysis. Meantime, due to lack of a "gold standard" dataset, it remains a challenge to evaluate LRI-mediated intercellular communication results. Here, we introduce CellGiQ, a high-confident LRI prediction framework for intercellular communication analysis. Highly confident LRIs are first inferred by LRI feature extraction with BioTriangle, LRI selection using LightGBM, and LRI classification based on ensemble of gradient boosted neural network and interpretable boosting machine. Subsequently, known and identified high-confident LRIs are filtered by combining single-cell RNA sequencing (scRNA-seq) data and further applied to intercellular communication inference through a quartile scoring strategy. To validation the predictions, CellGiQ exploited several evaluation strategies: using AUC and AUPR, it surpassed six competing LRI prediction models on four LRI datasets; through Venn diagrams and molecular docking, its predicted LRIs were validated by five other popular intercellular communication inference methods; based on the overlapping LRIs, it computed high Jaccard index with six other state-of-the-art intercellular communication prediction tools within human HNSCC tissues; by comparing with classical models and literature retrieve, its inferred HNSCC-related intercellular communication results was further validated. The novelty of this study is to identify high-confident LRIs based on machine learning as well as design several LRI validation ways, providing reference for computational LRI prediction. CellGiQ provides an open-source and useful tool to decompose LRI-mediated intercellular communication at single cell resolution. CellGiQ is freely available at https://github.com/plhhnu/CellGiQ.

scGIR: deciphering cellular heterogeneity via gene ranking in single-cell weighted gene correlation networks

Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool for investigating cellular heterogeneity through high-throughput analysis of individual cells. Nevertheless, challenges arise from prevalent sequencing dropout events and noise effects, impacting subsequent analyses. Here, we introduce a novel algorithm, Single-cell Gene Importance Ranking (scGIR), which utilizes a single-cell gene correlation network to evaluate gene importance. The algorithm transforms single-cell sequencing data into a robust gene correlation network through statistical independence, with correlation edges weighted by gene expression levels. We then constructed a random walk model on the resulting weighted gene correlation network to rank the importance of genes. Our analysis of gene importance using PageRank algorithm across nine authentic scRNA-seq datasets indicates that scGIR can effectively surmount technical noise, enabling the identification of cell types and inference of developmental trajectories. We demonstrated that the edges of gene correlation, weighted by expression, play a critical role in enhancing the algorithm's performance. Our findings emphasize that scGIR outperforms in enhancing the clustering of cell subtypes, reverse identifying differentially expressed marker genes, and uncovering genes with potential differential importance. Overall, we proposed a promising method capable of extracting more information from single-cell RNA sequencing datasets, potentially shedding new lights on cellular processes and disease mechanisms.