MicroRNA-small molecule association identification: from experimental results to computational models

IRPCA: An Interpretable Robust Principal Component Analysis Framework for Inferring miRNA-Drug Associations

Recent evidence indicates that microribonucleic acids (miRNAs) are crucial in modulating drug sensitivity by orchestrating the expression of genes involved in drug metabolism and its pharmacological effects. Existing predictive methods struggle to extract features related to miRNAs and drugs, often overlooking the significance of data noise and the limitations of using a single similarity measure. To address these limitations, we propose an interpretable robust principal component analysis framework (IRPCA). IRPCA enhances the robustness of the model by employing a nonconvex low-rank approximation, thereby offering greater flexibility. Interpretability is ensured by analyzing low-rank matrix decomposition, which clarifies how miRNAs interact with drugs. Gaussian interaction profile kernel (GIPK) similarities are introduced to compute integrated similarities between miRNAs and drugs, addressing the issue of the single similarity feature. IRPCA is subsequently utilized to extract pertinent features, and a fully connected neural network is employed to generate the ultimate prediction scores. To assess the efficacy of IRPCA, we implemented 5-fold cross-validation (CV), which outperformed other leading methods, achieving the highest area under the curve (AUC) value of 0.9653. Additionally, case studies provide additional evidence supporting the efficacy of IRPCA.

PathSynergy: a deep learning model for predicting drug synergy in liver cancer

Cancer is a major public health problem while liver cancer is the main cause of global cancer-related deaths. The previous study demonstrates that the 5-year survival rate for advanced liver cancer is only 30%. Few of the first-line targeted drugs including sorafenib and lenvatinib are available, which often develop resistance. Drug combination therapy is crucial for improving the efficacy of cancer therapy and overcoming resistance. However, traditional methods for discovering drug synergy are costly and time consuming. In this study, we developed a novel predicting model PathSynergy by integrating drug feature data, cell line data, drug-target interactions, and signaling pathways. PathSynergy combined the advantages of graph neural networks and pathway map mapping. Comparing with other baseline models, PathSynergy showed better performance in model classification, accuracy, and precision. Excitingly, six Food and Drug Administration (FDA)-approved drugs including pimecrolimus, topiramate, nandrolone_decanoate, fluticasone propionate, zanubrutinib, and levonorgestrel were predicted and validated to show synergistic effects with sorafenib or lenvatinib against liver cancer for the first time. In general, the PathSynergy model provides a new perspective to discover synergistic combinations of drugs and has broad application potential in the fields of drug discovery and personalized medicine.

BINDTI: A Bi-Directional Intention Network for Drug-Target Interaction Identification Based on Attention Mechanisms

The identification of drug-target interactions (DTIs) is an essential step in drug discovery. In vitro experimental methods are expensive, laborious, and time-consuming. Deep learning has witnessed promising progress in DTI prediction. However, how to precisely represent drug and protein features is a major challenge for DTI prediction. Here, we developed an end-to-end DTI identification framework called BINDTI based on bi-directional Intention network. First, drug features are encoded with graph convolutional networks based on its 2D molecular graph obtained by its SMILES string. Next, protein features are encoded based on its amino acid sequence through a mixed model called ACmix, which integrates self-attention mechanism and convolution. Third, drug and target features are fused through bi-directional Intention network, which combines Intention and multi-head attention. Finally, unknown drug-target (DT) pairs are classified through multilayer perceptron based on the fused DT features. The results demonstrate that BINDTI greatly outperformed four baseline methods (i.e., CPI-GNN, TransfomerCPI, MolTrans, and IIFDTI) on the BindingDB, BioSNAP, DrugBank, and Human datasets. More importantly, it was more appropriate to predict new DTIs than the four baseline methods on imbalanced datasets. Ablation experimental results elucidated that both bi-directional Intention and ACmix could greatly advance DTI prediction. The fused feature visualization and case studies manifested that the predicted results by BINDTI were basically consistent with the true ones. We anticipate that the proposed BINDTI framework can find new low-cost drug candidates, improve drugs' virtual screening, and further facilitate drug repositioning as well as drug discovery.

Truncated Arctangent Rank Minimization and Double-Strategy Neighborhood Constraint Graph Inference for Drug-Disease Association Prediction

Accurately identifying new therapeutic uses for drugs is essential to advancing pharmaceutical research and development. Graph inference techniques have shown great promise in predicting drug-disease associations, offering both high convergence accuracy and efficiency. However, most existing methods fail to sufficiently address the issue of numerous missing information in drug-disease association networks. Moreover, existing methods are often constrained by local or single-directional reasoning. To overcome these limitations, we propose a novel approach, truncated arctangent rank minimization and double-strategy neighborhood constraint graph inference (TARMDNGI), for drug-disease association prediction. First, we calculate Gaussian kernel and Laplace kernel similarities for both drugs and diseases, which are then integrated using nonlinear fusion techniques. We introduce a new matrix completion technique, referred to as TARM. TARM takes the adjacency matrix of drug-disease heterogeneous networks as the target matrix and enhances the robustness and formability of the edges of DDA networks by truncated arctangent rank minimization. Additionally, we propose a double-strategy neighborhood constrained graph inference method to predict drug-disease associations. This technique focuses on the neighboring nodes of drugs and diseases, filtering out potential noise from more distant nodes. Furthermore, the DNGI method employs both top-down and bottom-up strategies to infer associations using the entire drug-disease heterogeneous network. The synergy of the dual strategies can enhance the comprehensive processing of complex structures and cross-domain associations in heterogeneous graphs, ensuring that the rich information in the network is fully utilized. Experimental results consistently demonstrate that TARMDNGI outperforms state-of-the-art models across two drug-disease datasets, one lncRNA-disease dataset, and one microbe-disease dataset.

MVCL-DTI: Predicting Drug-Target Interactions Using a Multiview Contrastive Learning Model on a Heterogeneous Graph

Accurate prediction of drug-target interactions (DTIs) is pivotal for accelerating the processes of drug discovery and drug repurposing. MVCL-DTI, a novel model leveraging heterogeneous graphs for predicting DTIs, tackles the challenge of synthesizing information from varied biological subnetworks. It integrates neighbor view, meta-path view, and diffusion view to capture semantic features and employs an attention-based contrastive learning approach, along with a multiview attention-weighted fusion module, to effectively integrate and adaptively weight the information from the different views. Tested under various conditions on benchmark data sets, including varying positive-to-negative sample ratios, conducting hard negative sampling experiments, and masking known DTIs with different ratios, as well as redundant DTIs with various similarity metrics, MVCL-DTI exhibits strong robust generalization. The model is then employed to predict novel DTIs, with a particular focus on COVID-19-related drugs, highlighting its practical applicability. Ultimately, through features visualization and computational properties analysis, we've pinpointed critical elements, including Gene Ontology and substituent nodes, along with a proper initialization strategy, underscoring their vital role in DTI prediction tasks.

Deep Drug-Target Binding Affinity Prediction Base on Multiple Feature Extraction and Fusion

Accurate drug-target binding affinity (DTA) prediction is crucial in drug discovery. Recently, deep learning methods for DTA prediction have made significant progress. However, there are still two challenges: (1) recent models always ignore the correlations in drug and target data in the drug/target representation process and (2) the interaction learning of drug-target pairs always is by simple concatenation, which is insufficient to explore their fusion. To overcome these challenges, we propose an end-to-end sequence-based model called BTDHDTA. In the feature extraction process, the bidirectional gated recurrent unit (GRU), transformer encoder, and dilated convolution are employed to extract global, local, and their correlation patterns of drug and target input. Additionally, a module combining convolutional neural networks with a Highway connection is introduced to fuse drug and protein deep features. We evaluate the performance of BTDHDTA on three benchmark data sets (Davis, KIBA, and Metz), demonstrating its superiority over several current state-of-the-art methods in key metrics such as Mean Squared Error (MSE), Concordance Index (CI), and Regression toward the mean (R m 2). The results indicate that our method achieves a better performance in DTA prediction. In the case study, we use the BTDHDTA model to predict the binding affinities between 3137 FDA-approved drugs and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) replication-related proteins, validating the model's effectiveness in practical scenarios.

ReduMixDTI: Prediction of Drug-Target Interaction with Feature Redundancy Reduction and Interpretable Attention Mechanism

Identifying drug-target interactions (DTIs) is essential for drug discovery and development. Existing deep learning approaches to DTI prediction often employ powerful feature encoders to represent drugs and targets holistically, which usually cause significant redundancy and noise by neglecting the restricted binding regions. Furthermore, many previous DTI networks ignore or simplify the complex intermolecular interaction process involving diverse binding types, which significantly limits both predictive ability and interpretability. We propose ReduMixDTI, an end-to-end model that addresses feature redundancy and explicitly captures complex local interactions for DTI prediction. In this study, drug and target features are encoded by using graph neural networks and convolutional neural networks, respectively. These features are refined from channel and spatial perspectives to enhance the representations. The proposed attention mechanism explicitly models pairwise interactions between drug and target substructures, improving the model's understanding of binding processes. In extensive comparisons with seven state-of-the-art methods, ReduMixDTI demonstrates superior performance across three benchmark data sets and external test sets reflecting real-world scenarios. Additionally, we perform comprehensive ablation studies and visualize protein attention weights to enhance the interpretability. The results confirm that ReduMixDTI serves as a robust and interpretable model for reducing feature redundancy, contributing to advances in DTI prediction.

sChemNET: a deep learning framework for predicting small molecules targeting microRNA function

MicroRNAs (miRNAs) have been implicated in human disorders, from cancers to infectious diseases. Targeting miRNAs or their target genes with small molecules offers opportunities to modulate dysregulated cellular processes linked to diseases. Yet, predicting small molecules associated with miRNAs remains challenging due to the small size of small molecule-miRNA datasets. Herein, we develop a generalized deep learning framework, sChemNET, for predicting small molecules affecting miRNA bioactivity based on chemical structure and sequence information. sChemNET overcomes the limitation of sparse chemical information by an objective function that allows the neural network to learn chemical space from a large body of chemical structures yet unknown to affect miRNAs. We experimentally validated small molecules predicted to act on miR-451 or its targets and tested their role in erythrocyte maturation during zebrafish embryogenesis. We also tested small molecules targeting the miR-181 network and other miRNAs using in-vitro and in-vivo experiments. We demonstrate that our machine-learning framework can predict bioactive small molecules targeting miRNAs or their targets in humans and other mammalian organisms.

DDI Prediction With Heterogeneous Information Network - Meta-Path Based Approach

Drug-drug interaction (DDI) indicates where a particular drug's desired course of action is modified when taken with other drug (s). DDIs may hamper, enhance, or reduce the expected effect of either drug or, in the worst possible scenario, cause an adverse side effect. While it is crucial to identify drug-drug interactions, it is quite impossible to detect all possible DDIs for a new drug during the clinical trial. Therefore, many computational methods are proposed for this task. This paper presents a novel method based on a heterogeneous information network (HIN), which consists of drugs and other biomedical entities like proteins, pathways, and side effects. Afterward, we extract the rich semantic relationships among these entities using different meta-path-based topological features and facilitate DDI prediction. In addition, we present a heterogeneous graph attention network-based end-to-end model for DDI prediction in the heterogeneous graph. Experimental results show that our proposed method accurately predicts DDIs and outperforms the baselines significantly.

Drug-Target Binding Affinity Prediction in a Continuous Latent Space Using Variational Autoencoders

Accurate prediction of Drug-Target binding Affinity (DTA) is a daunting yet pivotal task in the sphere of drug discovery. Over the years, a plethora of deep learning-based DTA models have emerged, rendering promising results in predicting the binding affinities between drugs and their target proteins. However, in contrast to the conventional approach of modeling binding affinity in vector spaces, we propose a more nuanced modeling process in a continuous space to account for the diversity of input samples. Initially, the drug is encoded using the Simplified Molecular Input Line Entry System (SMILES), while the target sequences are characterized via a pretrained language model. Subsequently, highly correlative information is extracted utilizing residual gated convolutional neural networks. In a departure from existing deep learning-based models, our model learns the hidden representations of the drugs and targets jointly. Instead of employing two vectors, our hidden representations consist of two Gaussian distributions. To validate the effectiveness of our proposal, we conducted evaluations on commonly utilized benchmark datasets. The experimental outcomes corroborated that our method surpasses the state-of-the-art vectorial representation methods in terms of performance. This approach, therefore, offers potential enhancements in the precision of DTA predictions, potentially contributing to more efficient drug discovery processes.

HTFSMMA: Higher-Order Topological Guided Small Molecule-MicroRNA Associations Prediction

Small molecules (SMs) play a pivotal role in regulating microRNAs (miRNAs). Existing prediction methods for associations between SM-miRNA have overlooked crucial aspects: the incorporation of local topological features between nodes, which represent either SMs or miRNAs, and the effective fusion of node features with topological features. This study introduces a novel approach, termed high-order topological features for SM-miRNA association prediction (HTFSMMA), which specifically addresses these limitations. Initially, an association graph is formed by integrating SM-miRNA association data, SM similarity, and miRNA similarity. Subsequently, we focus on the local information of links and propose target neighborhood graph convolutional network for extracting local topological features. Then, HTFSMMA employs graph attention networks to amalgamate these local features, thereby establishing a platform for the acquisition of high-order features through random walks. Finally, the extracted features are integrated into the multilayer perceptron to derive the association prediction scores. To demonstrate the performance of HTFSMMA, we conducted comprehensive evaluations including five-fold cross-validation, leave-one-out cross-validation (LOOCV), SM-fixed local LOOCV, and miRNA-fixed local LOOCV. The area under receiver operating characteristic curve values were 0.9958 ± 0.0024 (0.8722 ± 0.0021), 0.9986 (0.9504), 0.9974 (0.9111), and 0.9977 (0.9074), respectively. Our findings demonstrate the superior performance of HTFSMMA over existing approaches. In addition, three case studies and the DeLong test have confirmed the effectiveness of the proposed method. These results collectively underscore the significance of HTFSMMA in facilitating the inference of associations between SMs and miRNAs.

Versatile Framework for Drug-Target Interaction Prediction by Considering Domain-Specific Features

Predicting drug-target interactions (DTIs) is one of the crucial tasks in drug discovery, but traditional wet-lab experiments are costly and time-consuming. Recently, deep learning has emerged as a promising tool for accelerating DTI prediction due to its powerful performance. However, the models trained on limited known DTI data struggle to generalize effectively to novel drug-target pairs. In this work, we propose a strategy to train an ensemble of models by capturing both domain-generic and domain-specific features (E-DIS) to learn diverse domain features and adapt them to out-of-distribution data. Multiple experts were trained on different domains to capture and align domain-specific information from various distributions without accessing any data from unseen domains. E-DIS provides a comprehensive representation of proteins and ligands by capturing diverse features. Experimental results on four benchmark data sets in both in-domain and cross-domain settings demonstrated that E-DIS significantly improved model performance and domain generalization compared to existing methods. Our approach presents a significant advancement in DTI prediction by combining domain-generic and domain-specific features, enhancing the generalization ability of the DTI prediction model.

AIGO-DTI: Predicting Drug-Target Interactions Based on Improved Drug Properties Combined with Adaptive Iterative Algorithms

Artificial intelligence-based methods for predicting drug-target interactions (DTIs) aim to explore reliable drug candidate targets rapidly and cost-effectively to accelerate the drug development process. However, current methods are often limited by the topological regularities of drug molecules, making them difficult to generalize to a broader chemical space. Additionally, the use of similarity to measure DTI network links often introduces noise, leading to false DTI relationships and affecting the prediction accuracy. To address these issues, this study proposes an Adaptive Iterative Graph Optimization (AIGO)-DTI prediction framework. This framework integrates atomic cluster information and enhances molecular features through the design of functional group prompts and graph encoders, optimizing the construction of DTI association networks. Furthermore, the optimization of graph structure is transformed into a node similarity learning problem, utilizing multihead similarity metric functions to iteratively update the network structure to improve the quality of DTI information. Experimental results demonstrate the outstanding performance of AIGO-DTI on multiple public data sets and label reversal data sets. Case studies, molecular docking, and existing research validate its effectiveness and reliability. Overall, the method proposed in this study can construct comprehensive and reliable DTI association network information, providing new graphing and optimization strategies for DTI prediction, which contribute to efficient drug development and reduce target discovery costs.

Predict lncRNA-drug associations based on graph neural network

LncRNAs are an essential type of non-coding RNAs, which have been reported to be involved in various human pathological conditions. Increasing evidence suggests that drugs can regulate lncRNAs expression, which makes it possible to develop lncRNAs as therapeutic targets. Thus, developing in-silico methods to predict lncRNA-drug associations (LDAs) is a critical step for developing lncRNA-based therapies. In this study, we predict LDAs by using graph convolutional networks (GCN) and graph attention networks (GAT) based on lncRNA and drug similarity networks. Results show that our proposed method achieves good performance (average AUCs > 0.92) on five datasets. In addition, case studies and KEGG functional enrichment analysis further prove that the model can effectively identify novel LDAs. On the whole, this study provides a deep learning-based framework for predicting novel LDAs, which will accelerate the lncRNA-targeted drug development process.

AttenSyn: An Attention-Based Deep Graph Neural Network for Anticancer Synergistic Drug Combination Prediction

Identifying synergistic drug combinations is fundamentally important to treat a variety of complex diseases while avoiding severe adverse drug-drug interactions. Although several computational methods have been proposed, they highly rely on handcrafted feature engineering and cannot learn better interactive information between drug pairs, easily resulting in relatively low performance. Recently, deep-learning methods, especially graph neural networks, have been widely developed in this area and demonstrated their ability to address complex biological problems. In this study, we proposed AttenSyn, an attention-based deep graph neural network for accurately predicting synergistic drug combinations. In particular, we adopted a graph neural network module to extract high-latent features based on the molecular graphs only and exploited the attention-based pooling module to learn interactive information between drug pairs to strengthen the representations of drug pairs. Comparative results on the benchmark datasets demonstrated that our AttenSyn performs better than the state-of-the-art methods in the prediction of anticancer synergistic drug combinations. Additionally, to provide good interpretability of our model, we explored and visualized some crucial substructures in drugs through attention mechanisms. Furthermore, we also verified the effectiveness of our proposed AttenSyn on two cell lines by visualizing the features of drug combinations learnt from our model, exhibiting satisfactory generalization ability.

HyperPCM: Robust Task-Conditioned Modeling of Drug-Target Interactions

A central problem in drug discovery is to identify the interactions between drug-like compounds and protein targets. Over the past few decades, various quantitative structure-activity relationship (QSAR) and proteo-chemometric (PCM) approaches have been developed to model and predict these interactions. While QSAR approaches solely utilize representations of the drug compound, PCM methods incorporate both representations of the protein target and the drug compound, enabling them to achieve above-chance predictive accuracy on previously unseen protein targets. Both QSAR and PCM approaches have recently been improved by machine learning and deep neural networks, that allow the development of drug-target interaction prediction models from measurement data. However, deep neural networks typically require large amounts of training data and cannot robustly adapt to new tasks, such as predicting interaction for unseen protein targets at inference time. In this work, we propose to use HyperNetworks to efficiently transfer information between tasks during inference and thus to accurately predict drug-target interactions on unseen protein targets. Our HyperPCM method reaches state-of-the-art performance compared to previous methods on multiple well-known benchmarks, including Davis, DUD-E, and a ChEMBL derived data set, and particularly excels at zero-shot inference involving unseen protein targets. Our method, as well as reproducible data preparation, is available at https://github.com/ml-jku/hyper-dti.

Harnessing machine learning to find synergistic combinations for FDA-approved cancer drugs

Combination therapy is a fundamental strategy in cancer chemotherapy. It involves administering two or more anti-cancer agents to increase efficacy and overcome multidrug resistance compared to monotherapy. However, drug combinations can exhibit synergy, additivity, or antagonism. This study presents a machine learning framework to classify and predict cancer drug combinations. The framework utilizes several key steps including data collection and annotation from the O'Neil drug interaction dataset, data preprocessing, stratified splitting into training and test sets, construction and evaluation of classification models to categorize combinations as synergistic, additive, or antagonistic, application of regression models to predict combination sensitivity scores for enhanced predictions compared to prior work, and the last step is examination of drug features and mechanisms of action to understand synergy behaviors for optimal combinations. The models identified combination pairs most likely to synergize against different cancers. Kinase inhibitors combined with mTOR inhibitors, DNA damage-inducing drugs or HDAC inhibitors showed benefit, particularly for ovarian, melanoma, prostate, lung and colorectal carcinomas. Analysis highlighted Gemcitabine, MK-8776 and AZD1775 as frequently synergizing across cancer types. This machine learning framework provides a valuable approach to uncover more effective multi-drug regimens.

Design of Tracers in Fluorescence Polarization Assay for Extensive Application in Small Molecule Drug Discovery

Development of fluorescence polarization (FP) assays, especially in a competitive manner, is a potent and mature tool for measuring the binding affinities of small molecules. This approach is suitable for high-throughput screening (HTS) for initial ligands and is also applicable for further study of the structure-activity relationships (SARs) of candidate compounds for drug discovery. Buffer and tracer, especially rational design of the tracer, play a vital role in an FP assay system. In this perspective, we provided different kinds of approaches for tracer design based on successful cases in recent years. We classified these tracers by different types of ligands in tracers, including peptide, nucleic acid, natural product, and small molecule. To make this technology accessible for more targets, we briefly described the basic theory and workflow, followed by highlighting the design and application of typical FP tracers from a perspective of medicinal chemistry.

RDRGSE: A Framework for Noncoding RNA-Drug Resistance Discovery by Incorporating Graph Skeleton Extraction and Attentional Feature Fusion

Identifying noncoding RNAs (ncRNAs)-drug resistance association computationally would have a marked effect on understanding ncRNA molecular function and drug target mechanisms and alleviating the screening cost of corresponding biological wet experiments. Although graph neural network-based methods have been developed and facilitated the detection of ncRNAs related to drug resistance, it remains a challenge to explore a highly trusty ncRNA-drug resistance association prediction framework, due to inevitable noise edges originating from the batch effect and experimental errors. Herein, we proposed a framework, referred to as RDRGSE (RDR association prediction by using graph skeleton extraction and attentional feature fusion), for detecting ncRNA-drug resistance association. Specifically, starting with the construction of the original ncRNA-drug resistance association as a bipartite graph, RDRGSE took advantage of a bi-view skeleton extraction strategy to obtain two types of skeleton views, followed by a graph neural network-based estimator for iteratively optimizing skeleton views aimed at learning high-quality ncRNA-drug resistance edge embedding and optimal graph skeleton structure, jointly. Then, RDRGSE adopted adaptive attentional feature fusion to obtain final edge embedding and identified potential RDRAs under an end-to-end pattern. Comprehensive experiments were conducted, and experimental results indicated the significant advantage of a skeleton structure for ncRNA-drug resistance association discovery. Compared with state-of-the-art approaches, RDRGSE improved the prediction performance by 6.7% in terms of AUC and 6.1% in terms of AUPR. Also, ablation-like analysis and independent case studies corroborated RDRGSE generalization ability and robustness. Overall, RDRGSE provides a powerful computational method for ncRNA-drug resistance association prediction, which can also serve as a screening tool for drug resistance biomarkers.

MSIF-LNP: microbial and human health association prediction based on matrix factorization noise reduction for similarity fusion and bidirectional linear neighborhood label propagation

Studies have shown that microbes are closely related to human health. Clarifying the relationship between microbes and diseases that cause health problems can provide new solutions for the treatment, diagnosis, and prevention of diseases, and provide strong protection for human health. Currently, more and more similarity fusion methods are available to predict potential microbe-disease associations. However, existing methods have noise problems in the process of similarity fusion. To address this issue, we propose a method called MSIF-LNP that can efficiently and accurately identify potential connections between microbes and diseases, and thus clarify the relationship between microbes and human health. This method is based on matrix factorization denoising similarity fusion (MSIF) and bidirectional linear neighborhood propagation (LNP) techniques. First, we use non-linear iterative fusion to obtain a similarity network for microbes and diseases by fusing the initial microbe and disease similarities, and then reduce noise by using matrix factorization. Next, we use the initial microbe-disease association pairs as label information to perform linear neighborhood label propagation on the denoised similarity network of microbes and diseases. This enables us to obtain a score matrix for predicting microbe-disease relationships. We evaluate the predictive performance of MSIF-LNP and seven other advanced methods through 10-fold cross-validation, and the experimental results show that MSIF-LNP outperformed the other seven methods in terms of AUC. In addition, the analysis of Cystic fibrosis and Obesity cases further demonstrate the predictive ability of this method in practical applications.

Prediction of small molecule drug-miRNA associations based on GNNs and CNNs

MicroRNAs (miRNAs) play a crucial role in various biological processes and human diseases, and are considered as therapeutic targets for small molecules (SMs). Due to the time-consuming and expensive biological experiments required to validate SM-miRNA associations, there is an urgent need to develop new computational models to predict novel SM-miRNA associations. The rapid development of end-to-end deep learning models and the introduction of ensemble learning ideas provide us with new solutions. Based on the idea of ensemble learning, we integrate graph neural networks (GNNs) and convolutional neural networks (CNNs) to propose a miRNA and small molecule association prediction model (GCNNMMA). Firstly, we use GNNs to effectively learn the molecular structure graph data of small molecule drugs, while using CNNs to learn the sequence data of miRNAs. Secondly, since the black-box effect of deep learning models makes them difficult to analyze and interpret, we introduce attention mechanisms to address this issue. Finally, the neural attention mechanism allows the CNNs model to learn the sequence data of miRNAs to determine the weight of sub-sequences in miRNAs, and then predict the association between miRNAs and small molecule drugs. To evaluate the effectiveness of GCNNMMA, we implement two different cross-validation (CV) methods based on two different datasets. Experimental results show that the cross-validation results of GCNNMMA on both datasets are better than those of other comparison models. In a case study, Fluorouracil was found to be associated with five different miRNAs in the top 10 predicted associations, and published experimental literature confirmed that Fluorouracil is a metabolic inhibitor used to treat liver cancer, breast cancer, and other tumors. Therefore, GCNNMMA is an effective tool for mining the relationship between small molecule drugs and miRNAs relevant to diseases.

MSF-LRR: Multi-Similarity Information Fusion Through Low-Rank Representation to Predict Disease-Associated Microbes

An Increase in microbial activity is shown to be intimately connected with the pathogenesis of diseases. Considering the expense of traditional verification methods, researchers are working to develop high-efficiency methods for detecting potential disease-related microbes. In this article, a new prediction method, MSF-LRR, is established, which uses Low-Rank Representation (LRR) to perform multi-similarity information fusion to predict disease-related microbes. Considering that most existing methods only use one class of similarity, three classes of microbe and disease similarity are added. Then, LRR is used to obtain low-rank structural similarity information. Additionally, the method adaptively extracts the local low-rank structure of the data from a global perspective, to make the information used for the prediction more effective. Finally, a neighbor-based prediction method that utilizes the concept of collaborative filtering is applied to predict unknown microbe-disease pairs. As a result, the AUC value of MSF-LRR is superior to other existing algorithms under 5-fold cross-validation. Furthermore, in case studies, excluding originally known associations, 16 and 19 of the top 20 microbes associated with Bacterial Vaginosis and Irritable Bowel Syndrome, respectively, have been confirmed by the recent literature. In summary, MSF-LRR is a good predictor of potential microbe-disease associations and can contribute to drug discovery and biological research.

Regulation of LncRNAs and microRNAs in neuronal development and disease

Non-coding RNAs (ncRNAs) are RNAs that do not encode proteins but play important roles in regulating cellular processes. Multiple studies over the past decade have demonstrated the role of microRNAs (miRNAs) in cancer, in which some miRNAs can act as biomarkers or provide therapy target. Accumulating evidence also points to the importance of long non-coding RNAs (lncRNAs) in regulating miRNA-mRNA networks. An increasing number of ncRNAs have been shown to be involved in the regulation of cellular processes, and dysregulation of ncRNAs often heralds disease. As the population ages, the incidence of neurodegenerative diseases is increasing, placing enormous pressure on global health systems. Given the excellent performance of ncRNAs in early cancer screening and treatment, here we attempted to aggregate and analyze the regulatory functions of ncRNAs in neuronal development and disease. In this review, we summarize current knowledge on ncRNA taxonomy, biogenesis, and function, and discuss current research progress on ncRNAs in relation to neuronal development, differentiation, and neurodegenerative diseases.

Prediction of potential small molecule-miRNA associations based on heterogeneous network representation learning

MicroRNAs (miRNAs) are closely associated with the occurrences and developments of many complex human diseases. Increasing studies have shown that miRNAs emerge as new therapeutic targets of small molecule (SM) drugs. Since traditional experiment methods are expensive and time consuming, it is particularly crucial to find efficient computational approaches to predict potential small molecule-miRNA (SM-miRNA) associations. Considering that integrating multi-source heterogeneous information related with SM-miRNA association prediction would provide a comprehensive insight into the features of both SMs and miRNAs, we proposed a novel model of Small Molecule-MiRNA Association prediction based on Heterogeneous Network Representation Learning (SMMA-HNRL) for more precisely predicting the potential SM-miRNA associations. In SMMA-HNRL, a novel heterogeneous information network was constructed with SM nodes, miRNA nodes and disease nodes. To access and utilize of the topological information of the heterogeneous information network, feature vectors of SM and miRNA nodes were obtained by two different heterogeneous network representation learning algorithms (HeGAN and HIN2Vec) respectively and merged with connect operation. Finally, LightGBM was chosen as the classifier of SMMA-HNRL for predicting potential SM-miRNA associations. The 10-fold cross validations were conducted to evaluate the prediction performance of SMMA-HNRL, it achieved an area under of ROC curve of 0.9875, which was superior to other three state-of-the-art models. With two independent validation datasets, the test experiment results revealed the robustness of our model. Moreover, three case studies were performed. As a result, 35, 37, and 22 miRNAs among the top 50 predicting miRNAs associated with 5-FU, cisplatin, and imatinib were validated by experimental literature works respectively, which confirmed the effectiveness of SMMA-HNRL. The source code and experimental data of SMMA-HNRL are available at https://github.com/SMMA-HNRL/SMMA-HNRL.

A message passing framework with multiple data integration for miRNA-disease association prediction

Micro RNA or miRNA is a highly conserved class of non-coding RNA that plays an important role in many diseases. Identifying miRNA-disease associations can pave the way for better clinical diagnosis and finding potential drug targets. We propose a biologically-motivated data-driven approach for the miRNA-disease association prediction, which overcomes the data scarcity problem by exploiting information from multiple data sources. The key idea is to enrich the existing miRNA/disease-protein-coding gene (PCG) associations via a message passing framework, followed by the use of disease ontology information for further feature filtering. The enriched and filtered PCG associations are then used to construct the inter-connected miRNA-PCG-disease network to train a structural deep network embedding (SDNE) model. Finally, the pre-trained embeddings and the biologically relevant features from the miRNA family and disease semantic similarity are concatenated to form the pair input representations to a Random Forest classifier whose task is to predict the miRNA-disease association probabilities. We present large-scale comparative experiments, ablation, and case studies to showcase our approach's superiority. Besides, we make the model prediction results for 1618 miRNAs and 3679 diseases, along with all related information, publicly available at  http://software.mpm.leibniz-ai-lab.de/ to foster assessments and future adoption.

A Systematic Review of Clinical Validated and Potential miRNA Markers Related to the Efficacy of Fluoropyrimidine Drugs

Colorectal cancer (CRC) is becoming increasingly prevalent worldwide. Fluoropyrimidine drugs are the primary chemotherapy regimens in routine clinical practice of CRC. However, the survival rate of patients on fluoropyrimidine-based chemotherapy varies significantly among individuals. Biomarkers of fluoropyrimidine drugs'' efficacy are needed to implement personalized medicine. This review summarized fluoropyrimidine drug-related microRNA (miRNA) by affecting metabolic enzymes or showing the relevance of drug efficacy. We first outlined 42 miRNAs that may affect the metabolism of fluoropyrimidine drugs. Subsequently, we filtered another 41 miRNAs related to the efficacy of fluoropyrimidine drugs based on clinical trials. Bioinformatics analysis showed that most well-established miRNA biomarkers were significantly enriched in the cancer pathways instead of the fluoropyrimidine drug metabolism pathways. The result also suggests that the miRNAs screened from metastasis patients have a more critical role in cancer development than those from non-metastasis patients. There are five miRNAs shared between these two lists. The miR-21, miR-215, and miR-218 can suppress fluoropyrimidine drugs'' catabolism. The miR-326 and miR-328 can reduce the efflux of fluoropyrimidine drugs. These five miRNAs could jointly act by increasing intracellular levels of fluoropyrimidine drugs'' cytotoxic metabolites, leading to better chemotherapy responses. In conclusion, we demonstrated that the dynamic changes in the transcriptional regulation via miRNAs might play significant roles in the efficacy and toxicity of the fluoropyrimidine drug. The reported miRNA biomarkers would help evaluate the efficacy of fluoropyrimidine drug-based chemotherapy and improve the prognosis of colorectal cancer patients.

DRDB: A Machine Learning Platform to Predict Chemical-Protein Interactions towards Diabetic Retinopathy

Diabetic retinopathy (DR), a diabetic microangiopathy caused by diabetes, affects approximately 93 million people, worldwide. However, the drugs used to treat DR have limited efficacy and the variety of side effects. This is possibly because the complicated pathogenesis of DR is associated with multiple proteins. In this work, we attempted to identify potential drugs against DR-associated proteins and predict potential targets for drugs using in silico prediction of chemical-protein interactions (CPI) based on multitarget quantitative structure-activity relationship (mt-QSAR) method. Therefore, we developed 128 binary classifiers to predict the CPI for 15 DR targets using random forest (RF), k-nearest neighbours (KNN), support vector machine (SVM), and neural network (NN) algorithms with MACCS, extended connectivity fingerprints (ECFP6) fingerprints, and protein descriptors. In order to facilitate discovery of the novel drugs and target identification using the 128 binary classifiers, a free web server (DRDB) was developed. Compound Danshen Dripping Pills (CDDP), composed of Salvia miltiorrhiza, Panax notoginseng, and borneol, is commonly used in the treatment of cardiovascular diseases. To explore the applicability of DRDB, the potential CPIs of CDDP in treatment of DR were investigated based on DRDB. In vitro experimental validation demonstrated that cryptotanshinone and protocatechuic acid, two key components of CDDP, are capable of targeting ICAM-1 which is one of the key target of DR. We hope that this work can facilitate development of more effective clinical strategies for the treatment of DR.

Impact of smoking-induced dysregulated human miRNAs in chronic disease development and their potential use in prognostic and therapeutic purposes

MicroRNAs (miRNAs) are evolutionary conserved small noncoding RNA molecules with a significant ability to regulate gene expression at the posttranscriptional level either through translation repression or messenger RNA degradation. miRNAs are differentially expressed in various pathophysiological conditions, affecting the course of the disease by modulating several critical target genes. As the persistence of irreversible molecular changes caused by cigarette smoking is central to the pathogenesis of various chronic diseases, several studies have shown its direct correlation with the dysregulation of different miRNAs, affecting numerous essential biological processes. This review provides an insight into the current status of smoking-induced miRNAs dysregulation in chronic diseases such as COPD, atherosclerosis, pulmonary hypertension, and different cancers and explores the diagnostic/prognostic potential of miRNA-based biomarkers and their efficacy as therapeutic targets.

Predicting circRNA-drug sensitivity associations via graph attention auto-encoder

Background

Circular RNAs (circRNAs) play essential roles in cancer development and therapy resistance. Many studies have shown that circRNA is closely related to human health. The expression of circRNAs also affects the sensitivity of cells to drugs, thereby significantly affecting the efficacy of drugs. However, traditional biological experiments are time-consuming and expensive to validate drug-related circRNAs. Therefore, it is an important and urgent task to develop an effective computational method for predicting unknown circRNA-drug associations.

Results

In this work, we propose a computational framework (GATECDA) based on graph attention auto-encoder to predict circRNA-drug sensitivity associations. In GATECDA, we leverage multiple databases, containing the sequences of host genes of circRNAs, the structure of drugs, and circRNA-drug sensitivity associations. Based on the data, GATECDA employs Graph attention auto-encoder (GATE) to extract the low-dimensional representation of circRNA/drug, effectively retaining critical information in sparse high-dimensional features and realizing the effective fusion of nodes’ neighborhood information. Experimental results indicate that GATECDA achieves an average AUC of 89.18% under 10-fold cross-validation. Case studies further show the excellent performance of GATECDA.

Conclusions

Many experimental results and case studies show that our proposed GATECDA method can effectively predict the circRNA-drug sensitivity associations.

Graph Convolutional Autoencoder and Generative Adversarial Network-Based Method for Predicting Drug-Target Interactions

The computational prediction of novel drug-target interactions (DTIs) may effectively speed up the process of drug repositioning and reduce its costs. Most previous methods integrated multiple kinds of connections about drugs and targets by constructing shallow prediction models. These methods failed to deeply learn the low-dimension feature vectors for drugs and targets and ignored the distribution of these feature vectors. We proposed a graph convolutional autoencoder and generative adversarial network (GAN)-based method, GANDTI, to predict DTIs. We constructed a drug-target heterogeneous network to integrate various connections related to drugs and targets, i.e., the similarities and interactions between drugs or between targets and the interactions between drugs and targets. A graph convolutional autoencoder was established to learn the network embeddings of the drug and target nodes in a low-dimensional feature space, and the autoencoder deeply integrated different kinds of connections within the network. A GAN was introduced to regularize the feature vectors of nodes into a Gaussian distribution. Severe class imbalance exists between known and unknown DTIs. Thus, we constructed a classifier based on an ensemble learning model, LightGBM, to estimate the interaction propensities of drugs and targets. This classifier completely exploited all unknown DTIs and counteracted the negative effect of class imbalance. The experimental results indicated that GANDTI outperforms several state-of-the-art methods for DTI prediction. Additionally, case studies of five drugs demonstrated the ability of GANDTI to discover the potential targets for drugs.

Identification of miRNA-Small Molecule Associations by Continuous Feature Representation Using Auto-Encoders

MicroRNAs (miRNAs) are short non-coding RNAs that play important roles in the body and affect various diseases, including cancers. Controlling miRNAs with small molecules is studied herein to provide new drug repurposing perspectives for miRNA-related diseases. Experimental methods are time- and effort-consuming, so computational techniques have been applied, relying mostly on biological feature similarities and a network-based scheme to infer new miRNA–small molecule associations. Collecting such features is time-consuming and may be impractical. Here we suggest an alternative method of similarity calculation, representing miRNAs and small molecules through continuous feature representation. This representation is learned by the proposed deep learning auto-encoder architecture. Our suggested representation was compared to previous works and achieved comparable results using 5-fold cross validation (92% identified within top 25% predictions), and better predictions for most of the case studies (avg. of 31% vs. 25% identified within the top 25% of predictions). The results proved the effectiveness of our proposed method to replace previous time- and effort-consuming methods.

Biological features between miRNAs and their targets are unveiled from deep learning models

MicroRNAs (miRNAs) are ~ 22 nucleotide ubiquitous gene regulators. They modulate a broad range of essential cellular processes linked to human health and diseases. Consequently, identifying miRNA targets and understanding how they function are critical for treating miRNA associated diseases. In our earlier work, a hybrid deep learning-based approach (miTAR) was developed for predicting miRNA targets. It performs substantially better than the existing methods. The approach integrates two major types of deep learning algorithms: convolutional neural networks (CNNs) and recurrent neural networks (RNNs). However, the features in miRNA:target interactions learned by miTAR have not been investigated. In the current study, we demonstrated that miTAR captures known features, including the involvement of seed region and the free energy, as well as multiple novel features, in the miRNA:target interactions. Interestingly, the CNN and RNN layers of the model perform differently at capturing the free energy feature: the units in RNN layer is more unique at capturing the feature but collectively the CNN layer is more efficient at capturing the feature. Although deep learning models are commonly thought “black-boxes”, our discoveries support that the biological features in miRNA:target can be unveiled from deep learning models, which will be beneficial to the understanding of the mechanisms in miRNA:target interactions.

Incorporating Clinical, Chemical and Biological Information for Predicting Small Molecule-microRNA Associations Based on Non-Negative Matrix Factorization

Small molecule(SM) drugs can affect the expression of miRNAs, which plays crucial roles in many important biological processes. The chemical structure and clinical information of small molecule can simultaneously incorporate information such as anatomical distribution, therapeutic effects and structural characteristics. It is necessary to develop a novel model that incorporates small molecule chemical structure and clinical information to reveal the unknown small molecule-miRNA associations. In this study, we developed a new framework based on non-negative matrix factorization, called SMANMF, to discover the potential small molecules-miRNAs associations. First, the functional similarity of two miRNAs can be obtained by computing the overlap of the target gene sets in which the miRNAs interact together, and we integrated two types of small molecule similarities, including chemical similarity and clinical similarity. Then, we utilized a non-negative matrix factorization model to discover the unknown relationship between small molecules and miRNAs. The evaluation results indicate that our model can achieve superior prediction performance compared with previous approaches in 5-fold cross-validation. At the same time, the results of case studies also reveal that the SMANMF model has good predictive performance for predicting the potential association between small molecules and miRNAs.

Prediction of Drug-Target Interactions Based on Network Representation Learning and Ensemble Learning

Identifying interactions between drugs and target proteins is a critical step in the drug development process, as it helps identify new targets for drugs and accelerate drug development. The number of known drug-protein interactions (positive samples) is much lower than that of the unknown ones (negative samples), which forms a class imbalance. Most previous methods only utilised part of the negative samples to train the prediction model, so most of the information on negative samples was neglected. Therefore, a new method must be developed to predict candidate drug-related proteins and fully utilise negative samples to improve prediction performance. We present a method based on non-negative matrix factorisation and gradient boosting decision tree (GBDT), named NGDTP, to identify the candidate drug-protein interactions. NGDTP integrates multiple kinds of protein similarities, drugs-proteins interactions, and multiple kinds of drugs similarities at different levels, including target proteins of drugs, drug-related diseases, and side effects of drugs. We propose a network representation learning method based on matrix factorisation to learn low-dimensional vector representations of drug and protein nodes. On the basis of these low-dimensional node representations, a GBDT-based prediction model was constructed and it obtains the association scores through establishing multiple decision trees for a drug-protein pairs. NGDTP is an ensemble learning model that fully utilises all the negative samples to effectively alleviate the problem of class imbalance. NGDTP achieves superior prediction performance when it is compared with several state-of-the-art methods. The experimental results indicate that NGDTP also retrieves more actual drug-protein interactions in the top part of prediction result, which drew significant attention from the biologists. In addition, case studies on 10 drugs further confirmed the ability of the NGDTP to identify potential candidate proteins for drugs.

DTI-HeNE: a novel method for drug-target interaction prediction based on heterogeneous network embedding

BACKGROUND

Prediction of the drug-target interaction (DTI) is a critical step in the drug repurposing process, which can effectively reduce the following workload for experimental verification of potential drugs' properties. In recent studies, many machine-learning-based methods have been proposed to discover unknown interactions between drugs and protein targets. A recent trend is to use graph-based machine learning, e.g., graph embedding to extract features from drug-target networks and then predict new drug-target interactions. However, most of the graph embedding methods are not specifically designed for DTI predictions; thus, it is difficult for these methods to fully utilize the heterogeneous information of drugs and targets (e.g., the respective vertex features of drugs and targets and path-based interactive features between drugs and targets).

RESULTS

We propose a DTI prediction method DTI-HeNE (DTI based on Heterogeneous Network Embedding), which is specifically designed to cope with the bipartite DTI relations for generating high-quality embeddings of drug-target pairs. This method splits a heterogeneous DTI network into a bipartite DTI network, multiple drug homogeneous networks and target homogeneous networks, and extracts features from these sub-networks separately to better utilize the characteristics of bipartite DTI relations as well as the auxiliary similarity information related to drugs and targets. The features extracted from each sub-network are integrated using pathway information between these sub-networks to acquire new features, i.e., embedding vectors of drug-target pairs. Finally, these features are fed into a random forest (RF) model to predict novel DTIs.

CONCLUSIONS

Our experimental results show that, the proposed DTI network embedding method can learn higher-quality features of heterogeneous drug-target interaction networks for novel DTIs discovery.

An Ensemble Matrix Completion Model for Predicting Potential Drugs Against SARS-CoV-2

Because of the catastrophic outbreak of global coronavirus disease 2019 (COVID-19) and its strong infectivity and possible persistence, computational repurposing of existing approved drugs will be a promising strategy that facilitates rapid clinical treatment decisions and provides reasonable justification for subsequent clinical trials and regulatory reviews. Since the effects of a small number of conditionally marketed vaccines need further clinical observation, there is still an urgent need to quickly and effectively repurpose potentially available drugs before the next disease peak. In this work, we have manually collected a set of experimentally confirmed virus-drug associations through the publicly published database and literature, consisting of 175 drugs and 95 viruses, as well as 933 virus-drug associations. Then, because the samples are extremely sparse and unbalanced, negative samples cannot be easily obtained. We have developed an ensemble model, EMC-Voting, based on matrix completion and weighted soft voting, a semi-supervised machine learning model for computational drug repurposing. Finally, we have evaluated the prediction performance of EMC-Voting by fivefold crossing-validation and compared it with other baseline classifiers and prediction models. The case study for the virus SARS-COV-2 included in the dataset demonstrates that our model achieves the outperforming AUPR value of 0.934 in virus-drug association's prediction.

Inferring Synergistic Drug Combinations Based on Symmetric Meta-Path in a Novel Heterogeneous Network

Combinatorial drug therapy is a promising way for treating cancers, which can reduce drug side effects and improve drug efficacy. However, due to the large-scale combinatorial space, it is difficult to quickly and effectively identify novel synergistic drug combinations for further implementing combinatorial drug therapy. The computational method of fusing multi-source knowledge is a time- and cost-efficient strategy to infer synergistic drug combinations for testing. However, for the existing computational methods of inferring synergistic drug combinations, it still remains a challenging to effectively combine multi-source information to achieve the desired results. Hence, in this study, we developed a novel Inference method of Synergistic Drug Combinations based on Symmetric Meta-Path (ISDCSMP), which can systematically and accurately prioritize synergistic drug combinations in a novel drug-target heterogeneous network integrating multi-source information. In the experiment, ISDCSMP outperformed the state-of-the-art methods in terms of AUC and precision on the benchmark dataset in five-fold cross validation. Moreover, we further illustrated performances of different ways for obtaining the combination coefficients, and analyzed the influences of the maximum meta-path length. The performances of various single meta-paths were described in five-fold cross validation. Finally, we confirmed the practical usefulness of ISDCSMP with the predicted novel synergistic drug combinations. The source code of ISDCSMP is available at https://github.com/KDDing/ISDCSMP.

Predicting Drug-Target Interactions With Multi-Label Classification and Label Partitioning

Identifying drug-target interactions is crucial for drug discovery. Despite modern technologies used in drug screening, experimental identification of drug-target interactions is an extremely demanding task. Predicting drug-target interactions in silico can thereby facilitate drug discovery as well as drug repositioning. Various machine learning models have been developed over the years to predict such interactions. Multi-output learning models in particular have drawn the attention of the scientific community due to their high predictive performance and computational efficiency. These models are based on the assumption that all the labels are correlated with each other. However, this assumption is too optimistic. Here, we address drug-target interaction prediction as a multi-label classification task that is combined with label partitioning. We show that building multi-output learning models over groups (clusters) of labels often leads to superior results. The performed experiments confirm the efficiency of the proposed framework.

Novel Potential Small Molecule-MiRNA-Cancer Associations Prediction Model Based on Fingerprint, Sequence, and Clinical Symptoms

As an important biomarker in organisms, miRNA is closely related to various small molecules and diseases. Research on small molecule-miRNA-cancer associations is helpful for the development of cancer treatment drugs and the discovery of pathogenesis. It is very urgent to develop theoretical methods for identifying potential small molecular-miRNA-cancer associations, because experimental approaches are usually time-consuming, laborious, and expensive. To overcome this problem, we developed a new computational method, in which features derived from structure, sequence, and symptoms were utilized to characterize small molecule, miRNA, and cancer, respectively. A feature vector was construct to characterize small molecule-miRNA-cancer association by concatenating these features, and a random forest algorithm was utilized to construct a model for recognizing potential association. Based on the 5-fold cross-validation and benchmark data set, the model achieved an accuracy of 93.20 ± 0.52%, a precision of 93.22 ± 0.51%, a recall of 93.20 ± 0.53%, and an F1-measure of 93.20 ± 0.52%. The areas under the receiver operating characteristic curve and precision recall curve were 0.9873 and 0.9870. The real prediction ability and application performance of the developed method have also been further evaluated and verified through an independent data set test and case study. Some potential small molecules and miRNAs related to cancer have been identified and are worthy of further experimental research. It is anticipated that our model could be regarded as a useful high-throughput virtual screening tool for drug research and development. All source codes can be downloaded from https://github.com/LeeKamlong/Multi-class-SMMCA.

Construction of liver hepatocellular carcinoma-specific lncRNA-miRNA-mRNA network based on bioinformatics analysis

Liver hepatocellular carcinoma (LIHC) is one of the major causes of cancer-related death worldwide with increasing incidences, however there are very few studies about the underlying mechanisms and pathways in the development of LIHC. We obtained LIHC samples from The Cancer Genome Atlas (TCGA) to screen differentially expressed mRNAs, lncRNAs, miRNAs and driver mutations. The Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway, Gene ontology enrichment analyses and protein–protein interaction (PPI) network were performed. Moreover, we constructed a competing endogenous lncRNAs-miRNAs-mRNAs network. Finally, cox proportional hazards regression analysis was used to identify important prognostic differentially expressed genes. Total of 1284 mRNAs, 123 lncRNAs, 47 miRNAs were identified within different tissues of LIHC patients. GO analysis indicated that upregulated and downregulated differentially expressed mRNAs (DEmRNAs) were mainly associated with cell division, DNA replication, mitotic sister chromatid segregation and complement activation respectively. Meanwhile, KEGG terms revealed that upregulated and downregulated DEmRNAs were primarily involved in DNA replication, Metabolic pathways, cell cycle and Metabolic pathways, chemical carcinogenesis, retinol metabolism pathway respectively. Among the DERNAs, 542 lncRNAs-miRNAs-mRNAs pairs were predicted to construct a ceRNA regulatory network including 35 DElncRNAs, 26 DEmiRNAs and 112 DEmRNAs. In the Kaplan‐Meier analysis, total of 43 mRNAs, 14 lncRNAs and 3 miRNAs were screened out to be significantly correlated with overall survival of LIHC. The mutation signatures were analyzed and its correlation with immune infiltrates were evaluated using the TIMER in LIHC. Among the mutation genes, TTN mutation is often associated with poor immune infiltration and a worse prognosis in LIHC. This work conducted a novel lncRNAs-miRNAs-mRNAs network and mutation signatures for finding potential molecular mechanisms underlying the development of LIHC. The biomarkers also can be used for predicting prognosis of LIHC.

A landscape for drug-target interactions based on network analysis

In this work, we performed an analysis of the networks of interactions between drugs and their targets to assess how connected the compounds are. For our purpose, the interactions were downloaded from the DrugBank database, and we considered all drugs approved by the FDA. Based on topological analysis of this interaction network, we obtained information on degree, clustering coefficient, connected components, and centrality of these interactions. We identified that this drug-target interaction network cannot be divided into two disjoint and independent sets, i.e., it is not bipartite. In addition, the connectivity or associations between every pair of nodes identified that the drug-target network is constituted of 165 connected components, where one giant component contains 4376 interactions that represent 89.99% of all the elements. In this regard, the histamine H1 receptor, which belongs to the family of rhodopsin-like G-protein-coupled receptors and is activated by the biogenic amine histamine, was found to be the most important node in the centrality of input-degrees. In the case of centrality of output-degrees, fostamatinib was found to be the most important node, as this drug interacts with 300 different targets, including arachidonate 5-lipoxygenase or ALOX5, expressed on cells primarily involved in regulation of immune responses. The top 10 hubs interacted with 33% of the target genes. Fostamatinib stands out because it is used for the treatment of chronic immune thrombocytopenia in adults. Finally, 187 highly connected sets of nodes, structured in communities, were also identified. Indeed, the largest communities have more than 400 elements and are related to metabolic diseases, psychiatric disorders and cancer. Our results demonstrate the possibilities to explore these compounds and their targets to improve drug repositioning and contend against emergent diseases.

Machine and deep learning approaches for cancer drug repurposing

Knowledge of the underpinnings of cancer initiation, progression and metastasis has increased exponentially in recent years. Advanced "omics" coupled with machine learning and artificial intelligence (deep learning) methods have helped elucidate targets and pathways critical to those processes that may be amenable to pharmacologic modulation. However, the current anti-cancer therapeutic armamentarium continues to lag behind. As the cost of developing a new drug remains prohibitively expensive, repurposing of existing approved and investigational drugs is sought after given known safety profiles and reduction in the cost barrier. Notably, successes in oncologic drug repurposing have been infrequent. Computational in-silico strategies have been developed to aid in modeling biological processes to find new disease-relevant targets and discovering novel drug-target and drug-phenotype associations. Machine and deep learning methods have especially enabled leaps in those successes. This review will discuss these methods as they pertain to cancer biology as well as immunomodulation for drug repurposing opportunities in oncologic diseases.

A novel computational model for predicting potential LncRNA-disease associations based on both direct and indirect features of LncRNA-disease pairs

Background

Accumulating evidence has demonstrated that long non-coding RNAs (lncRNAs) are closely associated with human diseases, and it is useful for the diagnosis and treatment of diseases to get the relationships between lncRNAs and diseases. Due to the high costs and time complexity of traditional bio-experiments, in recent years, more and more computational methods have been proposed by researchers to infer potential lncRNA-disease associations. However, there exist all kinds of limitations in these state-of-the-art prediction methods as well.

Results

In this manuscript, a novel computational model named FVTLDA is proposed to infer potential lncRNA-disease associations. In FVTLDA, its major novelty lies in the integration of direct and indirect features related to lncRNA-disease associations such as the feature vectors of lncRNA-disease pairs and their corresponding association probability fractions, which guarantees that FVTLDA can be utilized to predict diseases without known related-lncRNAs and lncRNAs without known related-diseases. Moreover, FVTLDA neither relies solely on known lncRNA-disease nor requires any negative samples, which guarantee that it can infer potential lncRNA-disease associations more equitably and effectively than traditional state-of-the-art prediction methods. Additionally, to avoid the limitations of single model prediction techniques, we combine FVTLDA with the Multiple Linear Regression (MLR) and the Artificial Neural Network (ANN) for data analysis respectively. Simulation experiment results show that FVTLDA with MLR can achieve reliable AUCs of 0.8909, 0.8936 and 0.8970 in 5-Fold Cross Validation (fivefold CV), 10-Fold Cross Validation (tenfold CV) and Leave-One-Out Cross Validation (LOOCV), separately, while FVTLDA with ANN can achieve reliable AUCs of 0.8766, 0.8830 and 0.8807 in fivefold CV, tenfold CV, and LOOCV respectively. Furthermore, in case studies of gastric cancer, leukemia and lung cancer, experiment results show that there are 8, 8 and 8 out of top 10 candidate lncRNAs predicted by FVTLDA with MLR, and 8, 7 and 8 out of top 10 candidate lncRNAs predicted by FVTLDA with ANN, having been verified by recent literature. Comparing with the representative prediction model of KATZLDA, comparison results illustrate that FVTLDA with MLR and FVTLDA with ANN can achieve the average case study contrast scores of 0.8429 and 0.8515 respectively, which are both notably higher than the average case study contrast score of 0.6375 achieved by KATZLDA.

Conclusion

The simulation results show that FVTLDA has good prediction performance, which is a good supplement to future bioinformatics research.

LMI-DForest: A deep forest model towards the prediction of lncRNA-miRNA interactions

The interactions between miRNAs and long non-coding RNAs (lncRNAs) are subject to intensive recent studies due to its critical role in gene regulations. Computational prediction of lncRNA-miRNA interactions has become a popular alternative strategy to the experimental methods for identification of underlying interactions. It is desirable to develop the machine learning-based models for prediction of lncRNA-miRNA based on the experimentally validated interactions between lncRNAs and miRNAs. The accuracy and robustness of existing models based on machine learning techniques are subject to further improvement. Considering that the attributes of lncRNA and miRNA contribute key importance in the interaction between these two RNAs, a deep learning model, named LMI-DForest, is proposed here by combining the deep forest and autoencoder strategies. Systematic comparison on the experiment validated datasets for lncRNA-miRNA interaction datasets demonstrates that the proposed method consistently shows superior performance over the other machine learning models in the lncRNA-miRNA interaction prediction.

Target RNA modification for epigenetic drug repositioning in neuroblastoma: computational omics proximity between repurposing drug and disease

RNA modifications modulate most steps of gene expression. However, little is known about its role in neuroblastoma (NBL) and the inhibitors targeting it. We analyzed the RNA-seq (n=122) and CNV data (n=78) from NBL patients in Therapeutically Applicable Research to Generate Effective Treatments (TARGET) database. The NBL sub-clusters (cluster1/2) were identified via consensus clustering for expression of RNA modification regulators (RNA-MRs). Cox regression, principle component analysis and chi-square analysis were used to compare differences of survival, transcriptome, and clinicopathology between clusters. Cluster1 showed significantly poor prognosis, of which RNA-MRs' expression and CNV alteration were closely related to pathologic stage. RNA-MRs and functional related prognostic genes were obtained using spearman correlation analysis, and queried in CMap and L1000 FWD database to obtain 88 inhibitors. The effects of 5 inhibitors on RNA-MRs were confirmed in SH-SY5Y cells. The RNA-MRs exhibited two complementary regulation functions: one conducted by TET2 and related to translation and glycolysis; another conducted by ALYREF, NSUN2 and ADARB1 and related to cell cycle and DNA repair. The perturbed proteomic profile of HDAC inhibitors was different from that of others, thus drug combination overcame drug resistance and was potential for NBL therapy with RNA-MRs as therapeutic targets.

iDrug: Integration of drug repositioning and drug-target prediction via cross-network embedding

Computational drug repositioning and drug-target prediction have become essential tasks in the early stage of drug discovery. In previous studies, these two tasks have often been considered separately. However, the entities studied in these two tasks (i.e., drugs, targets, and diseases) are inherently related. On one hand, drugs interact with targets in cells to modulate target activities, which in turn alter biological pathways to promote healthy functions and to treat diseases. On the other hand, both drug repositioning and drug-target prediction involve the same drug feature space, which naturally connects these two problems and the two domains (diseases and targets). By using the wisdom of the crowds, it is possible to transfer knowledge from one of the domains to the other. The existence of relationships among drug-target-disease motivates us to jointly consider drug repositioning and drug-target prediction in drug discovery. In this paper, we present a novel approach called iDrug, which seamlessly integrates drug repositioning and drug-target prediction into one coherent model via cross-network embedding. In particular, we provide a principled way to transfer knowledge from these two domains and to enhance prediction performance for both tasks. Using real-world datasets, we demonstrate that iDrug achieves superior performance on both learning tasks compared to several state-of-the-art approaches. Our code and datasets are available at: https://github.com/Case-esaC/iDrug.

ncRPheno: a comprehensive database platform for identification and validation of disease related noncoding RNAs

Noncoding RNAs (ncRNAs) play critical roles in many critical biological processes and have become a novel class of potential targets and bio-markers for disease diagnosis, therapy, and prognosis. Annotating and analysing ncRNA-disease association data are essential but challenging. Current computational resources lack comprehensive database platforms to consistently interpret and prioritize ncRNA-disease association data for biomedical investigation and application. Here, we present the ncRPheno database platform (http://lilab2.sysu.edu.cn/ncrpheno), which comprehensively integrates and annotates ncRNA-disease association data and provides novel searches, visualizations, and utilities for association identification and validation. ncRPheno contains 482,751 non-redundant associations between 14,494 ncRNAs and 3,210 disease phenotypes across 11 species with supporting evidence in the literature. A scoring model was refined to prioritize the associations based on evidential metrics. Moreover, ncRPheno provides user-friendly web interfaces, novel visualizations, and programmatic access to enable easy exploration, analysis, and utilization of the association data. A case study through ncRPheno demonstrated a comprehensive landscape of ncRNAs dysregulation associated with 22 cancers and uncovered 821 cancer-associated common ncRNAs. As a unique database platform, ncRPheno outperforms the existing similar databases in terms of data coverage and utilities, and it will assist studies in encoding ncRNAs associated with phenotypes ranging from genetic disorders to complex diseases.

ABBREVIATIONS

APIs: application programming interfaces; circRNA: circular RNA; ECO: Evidence & Conclusion Ontology; EFO: Experimental Factor Ontology; FDR: false discovery rate; GO: Gene Ontology; GWAS: genome wide association studies; HPO: Human Phenotype Ontology; ICGC: International Cancer Genome Consortium; lncRNA: long noncoding RNA; miRNA: micro RNA; ncRNA: noncoding RNA; NGS: next generation sequencing; OMIM: Online Mendelian Inheritance in Man; piRNA: piwi-interacting RNA; snoRNA: small nucleolar RNA; TCGA: The Cancer Genome Atlas.

MLCDForest: multi-label classification with deep forest in disease prediction for long non-coding RNAs

The long non-coding RNAs (lncRNAs) are subject of intensive recent studies due to its association with various human diseases. It is desirable to build the artificial intelligence-based models for prediction of diseases or tissues based on the lncRNAs data, which will be useful in disease diagnosis and therapy. The accuracy and robustness of existing models based on the machine learning techniques are subject to further improvement. In this study, we propose a deep learning model, called Multi-Label Classifications with Deep Forest, termed MLCDForest, to address multi-label classification on tissue prediction for a given lncRNA, which can be regarded as an implementation of the deep forest model in multi-label classification. The MLCDForest is a sequential multi-label-grained scanning method, which distinguishes from the standard deep forest model. It is proposed to train in sequential of multi-labels with label correlation considered. A systematic comparison using the lncRNA-disease association datasets demonstrates that our method consistently shows superior performance over the state-of-the-art methods in disease prediction. Considering label correlation in the sequential multi-label-grained scanning, our model provides a powerful tool to make multi-label classification and tissue prediction based on given lncRNAs.

Identifying Small Molecule-miRNA Associations Based on Credible Negative Sample Selection and Random Walk

Recently, many studies have demonstrated that microRNAs (miRNAs) are new small molecule drug targets. Identifying small molecule-miRNA associations (SMiRs) plays an important role in finding new clues for various human disease therapy. Wet experiments can discover credible SMiR associations; however, this is a costly and time-consuming process. Computational models have therefore been developed to uncover possible SMiR associations. In this study, we designed a new SMiR association prediction model, RWNS. RWNS integrates various biological information, credible negative sample selections, and random walk on a triple-layer heterogeneous network into a unified framework. It includes three procedures: similarity computation, negative sample selection, and SMiR association prediction based on random walk on the constructed small molecule-disease-miRNA association network. To evaluate the performance of RWNS, we used leave-one-out cross-validation (LOOCV) and 5-fold cross validation to compare RWNS with two state-of-the-art SMiR association methods, namely, TLHNSMMA and SMiR-NBI. Experimental results showed that RWNS obtained an AUC value of 0.9829 under LOOCV and 0.9916 under 5-fold cross validation on the SM2miR1 dataset, and it obtained an AUC value of 0.8938 under LOOCV and 0.9899 under 5-fold cross validation on the SM2miR2 dataset. More importantly, RWNS successfully captured 9, 17, and 37 SMiR associations validated by experiments among the predicted top 10, 20, and 50 SMiR candidates with the highest scores, respectively. We inferred that enoxacin and decitabine are associated with mir-21 and mir-155, respectively. Therefore, RWNS can be a powerful tool for SMiR association prediction.