Drug-drug interactions (DDIs) arise when multiple drugs are administered concurrently. Accurately predicting the specific mechanisms underlying DDIs (named DDI events or DDIEs) is critical for the safe clinical use of drugs. DDIEs are typically represented as textual descriptions. However, most computational methods focus more on predicting the DDIE class label over generating human-readable natural language increasing clinicians’ interpretation costs. Furthermore, current methods overlook the fact that each drug assumes distinct biological functions in a DDI, which, when used as input context, can enhance the understanding of the DDIE process and benefit DDIE generation by the language model (LM). In this work, we propose a novel pairwise knowledge-augmented generative method (termed PKAG-DDI) for DDIE text generation. It consists of a pairwise knowledge selector efficiently injecting structural information between drugs bidirectionally and simultaneously to select pairwise biological functions from the knowledge set, and a pairwise knowledge integration strategy that matches and integrates the selected biological functions into the LM. Experiments on two professional datasets show that PKAG-DDI outperforms existing methods in DDIE text generation, especially in challenging inductive scenarios, indicating its practicality and generalization.

Accurately predicting protein-ligand binding affinity (PLA) remains a critical challenge in structure-based drug discovery. Recent advances have focused on using geometry-aware graph neural networks to model the three-dimensional (3D) structure of protein-ligand complexes for PLA prediction. However, they still achieve suboptimal performance due to two potential issues. 1) Representing the protein-ligand complex as a homogeneous graph ignores the inherent difference between intra- and intermolecular interactions, limiting the expressive ability of the models. 2) Given that the geometric complementarity between the ligand and protein binding pocket serves as a fundamental determinant of binding strength, the incomplete exploitation of geometric information constrains the predictive performance. In this study, we propose a novel Geometric Heterogeneous Graph Neural Network (GeoHGN) for PLA prediction. Specifically, we consider complete geometries to characterize the directions of edges in coordinate space through quantum inspired basis functions. To sufficiently incorporate the 3D information and heterogeneous topology of the complexes, we elaborately design a novel heterogeneous directional message passing mechanism (HDMP), which enables the propagation and aggregation of messages from intra- and intermolecular neighbors along with the directional information of linked edges. Extensive benchmarking experiments demonstrate the superiority of GeoHGN in predicting PLA.

Therapeutic peptides represent a unique class of pharmaceutical agents crucial for the treatment of human diseases. Recently, deep generative models have exhibited remarkable potential for generating therapeutic peptides, but they only utilize sequence or structure information alone, which hinders the performance in generation. In this study, we propose a Multi-Modal Contrastive Diffusion model (MMCD), fusing both sequence and structure modalities in a diffusion framework to co-generate novel peptide sequences and structures. Specifically, MMCD constructs the sequence-modal and structure-modal diffusion models, respectively, and devises a multi-modal contrastive learning strategy with inter-contrastive and intra-contrastive in each diffusion timestep, aiming to capture the consistency between two modalities and boost model performance. The inter-contrastive aligns sequences and structures of peptides by maximizing the agreement of their embeddings, while the intra-contrastive differentiates therapeutic and non-therapeutic peptides by maximizing the disagreement of their sequence/structure embeddings simultaneously. The extensive experiments demonstrate that MMCD performs better than other state-of-the-art deep generative methods in generating therapeutic peptides across various metrics, including antimicrobial/anticancer score, diversity, and peptide-docking.

Drug-drug interactions (DDIs) could lead to various unexpected adverse consequences, so-called DDI events. Predicting DDI events can reduce the potential risk of combinatorial therapy and improve the safety of medication use, and has attracted much attention in the deep learning community. Recently, graph neural network (GNN)-based models have aroused broad interest and achieved satisfactory results in the DDI event prediction. Most existing GNN-based models ignore either drug structural information or drug interactive information, but both aspects of information are important for DDI event prediction. Furthermore, accurately predicting rare DDI events is hindered by their inadequate labeled instances. In this paper, we propose a new method, Multi-Relational Contrastive learning Graph Neural Network, MRCGNN for brevity, to predict DDI events. Specifically, MRCGNN integrates the two aspects of information by deploying a GNN on the multi-relational DDI event graph attributed with the drug features extracted from drug molecular graphs. Moreover, we implement a multi-relational graph contrastive learning with a designed dual-view negative counterpart augmentation strategy, to capture implicit information about rare DDI events. Extensive experiments on two datasets show that MRCGNN outperforms the state-of-the-art methods. Besides, we observe that MRCGNN achieves satisfactory performance when predicting rare DDI events.

Identifying the potential associations among drugs, microbes and diseases is of great significance in exploring the pathogenesis and improving precision medicine. There are plenty of computational methods for pair-wise association prediction, such as drug-microbe and microbe-disease associations, but few methods focus on the higher-order triple-wise drug-microbe-disease (DMD) associations. Driven by the advancement of hypergraph neural networks (HGNNs), we expect them to fully capture high-order interaction patterns behind the hypergraph formulated by DMD associations and realize sound prediction performance. However, the confirmed DMD associations are insufficient due to the high cost of in vitro screening, which forms a sparse DMD hypergraph and thus brings in suboptimal generalization ability. To mitigate the limitation, we propose a Multi-view Contrastive Learning Hypergraph Neural Network, named MCHNN, for DMD association prediction. We design a novel multi-view contrastive learning on the DMD hypergraph as an auxiliary task, which guides the HGNN to learn more discriminative representations and enhances the generalization ability. Extensive computational experiments show that MCHNN achieves satisfactory performance in DMD association prediction and, more importantly, demonstrate the effectiveness of our devised multi-view contrastive learning on the sparse DMD hypergraph.

Accurate prediction of molecular properties is an important topic in drug discovery. Recent works have developed various representation schemes for molecular structures to capture different chemical information in molecules. The atom and motif can be viewed as hierarchical molecular structures that are widely used for learning molecular representations to predict chemical properties. Previous works have attempted to exploit both atom and motif to address the problem of information loss in single representation learning for various tasks. To further fuse such hierarchical information, the correspondence between learned chemical features from different molecular structures should be considered. Herein, we propose a novel framework for molecular property prediction, called hierarchical molecular graph neural networks (HimGNN). HimGNN learns hierarchical topology representations by applying graph neural networks on atom- and motif-based graphs. In order to boost the representational power of the motif feature, we design a Transformer-based local augmentation module to enrich motif features by introducing heterogeneous atom information in motif representation learning. Besides, we focus on the molecular hierarchical relationship and propose a simple yet effective rescaling module, called contextual self-rescaling, that adaptively recalibrates molecular representations by explicitly modelling interdependencies between atom and motif features. Extensive computational experiments demonstrate that HimGNN can achieve promising performances over state-of-the-art baselines on both classification and regression tasks in molecular property prediction.

Predicting the response of a cancer cell line to a therapeutic drug is an important topic in modern oncology that can help personalized treatment for cancers. Although numerous machine learning methods have been developed for cancer drug response (CDR) prediction, integrating diverse information about cancer cell lines, drugs and their known responses still remains a great challenge. In this paper, we propose a graph neural network method with contrastive learning for CDR prediction. GraphCDR constructs a graph neural network based on multi-omics profiles of cancer cell lines, the chemical structure of drugs and known cancer cell line-drug responses for CDR prediction, while a contrastive learning task is presented as a regularizer within a multi-task learning paradigm to enhance the generalization ability. In the computational experiments, GraphCDR outperforms state-of-the-art methods under different experimental configurations, and the ablation study reveals the key components of GraphCDR: biological features, known cancer cell line-drug responses and contrastive learning are important for the high-accuracy CDR prediction. The experimental analyses imply the predictive power of GraphCDR and its potential value in guiding anti-cancer drug selection.

Predicting drug-target interactions (DTIs) is crucial at many phases of drug discovery and repositioning. Many computational methods based on heterogeneous networks (HNs) have proved their potential to predict DTIs by capturing extensive biological knowledge and semantic information from meta-paths. However, existing methods manually customize meta-paths, which is overly dependent on some specific expertise. Such strategy heavily limits the scalability and flexibility of these models, and even affects their predictive performance. To alleviate this limitation, we propose a novel HN-based method with attentive meta-path extraction for DTI prediction, named HampDTI, which is capable of automatically extracting useful meta-paths through a learnable attention mechanism instead of pre-definition based on domain knowledge. Specifically, by scoring multi-hop connections across various relations in the HN with each relation assigned an attention weight, HampDTI constructs a new trainable graph structure, called meta-path graph. Such meta-path graph implicitly measures the importance of every possible meta-path between drugs and targets. To enable HampDTI to extract more diverse meta-paths, we adopt a multi-channel mechanism to generate multiple meta-path graphs. Then, a graph neural network is deployed on the generated meta-path graphs to yield the multi-channel embeddings of drugs and targets. Finally, HampDTI fuses all embeddings from different channels for predicting DTIs. The meta-path graphs are optimized along with the model training such that HampDTI can adaptively extract valuable meta-paths for DTI prediction. The experiments on benchmark datasets not only show the superiority of HampDTI in DTI prediction over several baseline methods, but also, more importantly, demonstrate the effectiveness of the model discovering important meta-paths.

MOTIVATION: There are various interaction/association bipartite networks in biomolecular systems. Identifying unobserved links in biomedical bipartite networks helps to understand the underlying molecular mechanisms of human complex diseases and thus benefits the diagnosis and treatment of diseases. Although a great number of computational methods have been proposed to predict links in biomedical bipartite networks, most of them heavily depend on features and structures involving the bioentities in one specific bipartite network, which limits the generalization capacity of applying the models to other bipartite networks. Meanwhile, bioentities usually have multiple features, and how to leverage them has also been challenging. RESULTS: In this study, we propose a novel multi-view graph convolution network (MVGCN) framework for link prediction in biomedical bipartite networks. We first construct a multi-view heterogeneous network (MVHN) by combining the similarity networks with the biomedical bipartite network, and then perform a self-supervised learning strategy on the bipartite network to obtain node attributes as initial embeddings. Further, a neighborhood information aggregation (NIA) layer is designed for iteratively updating the embeddings of nodes by aggregating information from inter- and intra-domain neighbors in every view of the MVHN. Next, we combine embeddings of multiple NIA layers in each view, and integrate multiple views to obtain the final node embeddings, which are then fed into a discriminator to predict the existence of links. Extensive experiments show MVGCN performs better than or on par with baseline methods and has the generalization capacity on six benchmark datasets involving three typical tasks. AVAILABILITY AND IMPLEMENTATION: Source code and data can be downloaded from https://github.com/fuhaitao95/MVGCN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Drug repositioning/repurposing is a very important approach towards identifying novel treatments for diseases in drug discovery. Recently, large-scale biological datasets are increasingly available for pharmaceutical research and promote the development of drug repositioning, but efficiently utilizing these datasets remains challenging. In this paper, we develop a novel multimodal framework, termed GraphPK (Graph-based Prior Knowledge) for improving in silico drug repositioning via using the prior knowledge from a drug knowledge graph. First, we construct a knowledge graph by integrating relevant bio-entities (drugs, diseases, etc.) and associations/interactions among them, and apply the knowledge graph embedding technique to extract prior knowledge of drugs and diseases. Moreover, we make use of the known drug-disease association, and obtain known association-based features from an association bipartite graph through graph embedding, and also take into account biological domain features, i.e., drug chemical structures and disease semantic similarity. Finally, we design a multimodal neural network to combine three types of features from the knowledge graph, the known associations and the biological domain, and build the prediction model for predicting drug-disease associations. Massive experiments show that our method outperforms other state-of-the-art methods in terms of most metrics, and the ablation analysis regarding the three types of features reveals that prior knowledge from knowledge graphs can not only lift the predictive power of in silico drug repositioning, but also enhance the model's robustness to different scenarios. The results of case studies offer support that GraphPK has the potential for actual use.

Molecular interactions are significant resources for analyzing sophisticated biological systems. Identification of multifarious molecular interactions attracts increasing attention in biomedicine, bioinformatics, and human healthcare communities. Recently, a plethora of methods have been proposed to reveal molecular interactions in one specific domain. However, existing methods heavily rely on features or structures involving molecules, which limits the capacity of transferring the models to other tasks. Therefore, generalized models for the multifarious molecular interaction prediction (MIP) are in demand. In this paper, we propose a contrastive self-supervised graph neural network (CSGNN) to predict molecular interactions. CSGNN injects a mix-hop neighborhood aggregator into a graph neural network (GNN) to capture high-order dependency in the molecular interaction networks and leverages a contrastive self-supervised learning task as a regularizer within a multi-task learning paradigm to enhance the generalization ability. Experiments on seven molecular interaction networks show that CSGNN outperforms classic and state-of-the-art models. Comprehensive experiments indicate that the mix-hop aggregator and the self-supervised regularizer can effectively facilitate the link inference in multifarious molecular networks.

MicroRNAs (miRNAs) play crucial roles in multifarious biological processes associated with human diseases. Identifying potential miRNA-disease associations contributes to understanding the molecular mechanisms of miRNA-related diseases. Most of the existing computational methods mainly focus on predicting whether a miRNA-disease association exists or not. However, the roles of miRNAs in diseases are prominently diverged, for instance, Genetic variants of miRNA (mir-15) may affect the expression level of miRNAs leading to B cell chronic lymphocytic leukemia, while circulating miRNAs (including mir-1246, mir-1307-3p, etc.) have potentials to detecting breast cancer in the early stage. In this paper, we aim to predict multi-type miRNA-disease associations instead of taking them as binary. To this end, we innovatively represent miRNA-disease-type triples as a tensor and introduce tensor decomposition methods to solve the prediction task. Experimental results on two widely-adopted miRNA-disease datasets: HMDD v2.0 and HMDD v3.2 show that tensor decomposition methods improve a recent baseline in a large scale (up to $38\%$ in Top-1F1). We then propose a novel method, Tensor Decomposition with Relational Constraints (TDRC), which incorporates biological features as relational constraints to further the existing tensor decomposition methods. Compared with two existing tensor decomposition methods, TDRC can produce better performance while being more efficient.

BACKGROUND: Determining drug-disease associations is an integral part in the process of drug development. However, the identification of drug-disease associations through wet experiments is costly and inefficient. Hence, the development of efficient and high-accuracy computational methods for predicting drug-disease associations is of great significance. RESULTS: In this paper, we propose a novel computational method named as layer attention graph convolutional network (LAGCN) for the drug-disease association prediction. Specifically, LAGCN first integrates the known drug-disease associations, drug-drug similarities and disease-disease similarities into a heterogeneous network, and applies the graph convolution operation to the network to learn the embeddings of drugs and diseases. Second, LAGCN combines the embeddings from multiple graph convolution layers using an attention mechanism. Third, the unobserved drug-disease associations are scored based on the integrated embeddings. Evaluated by 5-fold cross-validations, LAGCN achieves an area under the precision-recall curve of 0.3168 and an area under the receiver-operating characteristic curve of 0.8750, which are better than the results of existing state-of-the-art prediction methods and baseline methods. The case study shows that LAGCN can discover novel associations that are not curated in our dataset. CONCLUSION: LAGCN is a useful tool for predicting drug-disease associations. This study reveals that embeddings from different convolution layers can reflect the proximities of different orders, and combining the embeddings by the attention mechanism can improve the prediction performances.

Increasing evidences revealed that microRNAs (miRNAs) play critical roles in important biological processes. The identification of disease-related miRNAs is critical to understand the molecular mechanisms of human diseases. Most existing computational methods require diverse features to predict miRNA-disease associations. However, diverse features are not available for all miRNAs or diseases. In addition, most methods can't predict links for miRNAs or diseases without association information. In this paper, we propose a fast linear neighborhood similarity-based network link inference method, named FLNSNLI, to predict miRNA-disease associations. First, known miRNA-disease associations are formulated as a bipartite network, and miRNAs (or diseases) are expressed as association profiles. Second, miRNA-miRNA similarity and disease-disease similarity are calculated by fast linear neighborhood similarity measure and association profiles. Third, the label propagation algorithm is respectively implemented on two sides to score candidate miRNA-disease associations. Finally, FLNSNLI adopts the weighted average strategy and makes predictions. Moreover, we develop a link complementing approach, and extend FLNSNLI to predict links for miRNAs (or diseases) without known associations. In computational experiments, FLNSNLI produces high-accuracy performances, and outperforms other state-of-the-art methods. More importantly, FLNSNLI requires less information but performs well. Case studies on three popular diseases show that FLNSNLI is useful for the microRNA-disease association prediction.

BACKGROUND: Drug-disease associations provide important information for the drug discovery. Wet experiments that identify drug-disease associations are time-consuming and expensive. However, many drug-disease associations are still unobserved or unknown. The development of computational methods for predicting unobserved drug-disease associations is an important and urgent task. RESULTS: In this paper, we proposed a similarity constrained matrix factorization method for the drug-disease association prediction (SCMFDD), which makes use of known drug-disease associations, drug features and disease semantic information. SCMFDD projects the drug-disease association relationship into two low-rank spaces, which uncover latent features for drugs and diseases, and then introduces drug feature-based similarities and disease semantic similarity as constraints for drugs and diseases in low-rank spaces. Different from the classic matrix factorization technique, SCMFDD takes the biological context of the problem into account. In computational experiments, the proposed method can produce high-accuracy performances on benchmark datasets, and outperform existing state-of-the-art prediction methods when evaluated by five-fold cross validation and independent testing. CONCLUSION: We developed a user-friendly web server by using known associations collected from the CTD database, available at http://www.bioinfotech.cn/SCMFDD/ . The case studies show that the server can find out novel associations, which are not included in the CTD database.

LncRNA-protein interactions play important roles in post-transcriptional gene regulation, poly-adenylation, splicing and translation. Identification of lncRNA-protein interactions helps to understand lncRNA-related activities. Existing computational methods utilize multiple lncRNA features or multiple protein features to predict lncRNA-protein interactions, but features are not available for all lncRNAs or proteins; most of existing methods are not capable of predicting interacting proteins (or lncRNAs) for new lncRNAs (or proteins), which don't have known interactions. In this paper, we propose the sequence-based feature projection ensemble learning method, "SFPEL-LPI", to predict lncRNA-protein interactions. First, SFPEL-LPI extracts lncRNA sequence-based features and protein sequence-based features. Second, SFPEL-LPI calculates multiple lncRNA-lncRNA similarities and protein-protein similarities by using lncRNA sequences, protein sequences and known lncRNA-protein interactions. Then, SFPEL-LPI combines multiple similarities and multiple features with a feature projection ensemble learning frame. In computational experiments, SFPEL-LPI accurately predicts lncRNA-protein associations and outperforms other state-of-the-art methods. More importantly, SFPEL-LPI can be applied to new lncRNAs (or proteins). The case studies demonstrate that our method can find out novel lncRNA-protein interactions, which are confirmed by literature. Finally, we construct a user-friendly web server, available at http://www.bioinfotech.cn/SFPEL-LPI/.