The Comparative Toxicogenomics Database: update 2013

Drug repositioning based on residual attention network and free multiscale adversarial training

BACKGROUND

Conducting traditional wet experiments to guide drug development is an expensive, time-consuming and risky process. Analyzing drug function and repositioning plays a key role in identifying new therapeutic potential of approved drugs and discovering therapeutic approaches for untreated diseases. Exploring drug-disease associations has far-reaching implications for identifying disease pathogenesis and treatment. However, reliable detection of drug-disease relationships via traditional methods is costly and slow. Therefore, investigations into computational methods for predicting drug-disease associations are currently needed.

RESULTS

This paper presents a novel drug-disease association prediction method, RAFGAE. First, RAFGAE integrates known associations between diseases and drugs into a bipartite network. Second, RAFGAE designs the Re_GAT framework, which includes multilayer graph attention networks (GATs) and two residual networks. The multilayer GATs are utilized for learning the node embeddings, which is achieved by aggregating information from multihop neighbors. The two residual networks are used to alleviate the deep network oversmoothing problem, and an attention mechanism is introduced to combine the node embeddings from different attention layers. Third, two graph autoencoders (GAEs) with collaborative training are constructed to simulate label propagation to predict potential associations. On this basis, free multiscale adversarial training (FMAT) is introduced. FMAT enhances node feature quality through small gradient adversarial perturbation iterations, improving the prediction performance. Finally, tenfold cross-validations on two benchmark datasets show that RAFGAE outperforms current methods. In addition, case studies have confirmed that RAFGAE can detect novel drug-disease associations.

CONCLUSIONS

The comprehensive experimental results validate the utility and accuracy of RAFGAE. We believe that this method may serve as an excellent predictor for identifying unobserved disease-drug associations.

GSRF-DTI: a framework for drug-target interaction prediction based on a drug-target pair network and representation learning on a large graph

BACKGROUND

Identification of potential drug-target interactions (DTIs) with high accuracy is a key step in drug discovery and repositioning, especially concerning specific drug targets. Traditional experimental methods for identifying the DTIs are arduous, time-intensive, and financially burdensome. In addition, robust computational methods have been developed for predicting the DTIs and are widely applied in drug discovery research. However, advancing more precise algorithms for predicting DTIs is essential to meet the stringent standards demanded by drug discovery.

RESULTS

We proposed a novel method called GSRF-DTI, which integrates networks with a deep learning algorithm to identify DTIs. Firstly, GSRF-DTI learned the embedding representation of drugs and targets by integrating multiple drug association information and target association information, respectively. Then, GSRF-DTI considered the influence of drug-target pair (DTP) association on DTI prediction to construct a drug-target pair network (DTP-NET). Next, we utilized GraphSAGE on DTP-NET to learn the potential features of the network and applied random forest (RF) to predict the DTIs. Furthermore, we conducted ablation experiments to validate the necessity of integrating different types of network features for identifying DTIs. It is worth noting that GSRF-DTI proposed three novel DTIs.

CONCLUSIONS

GSRF-DTI not only considered the influence of the interaction relationship between drug and target but also considered the impact of DTP association relationship on DTI prediction. We initially use GraphSAGE to aggregate the neighbor information of nodes for better identification. Experimental analysis on Luo's dataset and the newly constructed dataset revealed that the GSRF-DTI framework outperformed several state-of-the-art methods significantly.

CKG-IMC: An inductive matrix completion method enhanced by CKG and GNN for Alzheimer's disease compound-protein interactions prediction

Alzheimer's disease (AD) is one of the most prevalent chronic neurodegenerative disorders globally, with a rapidly growing population of AD patients and currently no effective therapeutic interventions available. Consequently, the development of therapeutic anti-AD drugs and the identification of AD targets represent one of the most urgent tasks. In this study, in addition to considering known drugs and targets, we explore compound-protein interactions (CPIs) between compounds and proteins relevant to AD. We propose a deep learning model called CKG-IMC to predict Alzheimer's disease compound-protein interaction relationships. CKG-IMC comprises three modules: a collaborative knowledge graph (CKG), a principal neighborhood aggregation graph neural network (PNA), and an inductive matrix completion (IMC). The collaborative knowledge graph is used to learn semantic associations between entities, PNA is employed to extract structural features of the relationship network, and IMC is utilized for CPIs prediction. Compared with a total of 16 baseline models based on similarities, knowledge graphs, and graph neural networks, our model achieves state-of-the-art performance in experiments of 10-fold cross-validation and independent test. Furthermore, we use CKG-IMC to predict compounds interacting with two confirmed AD targets, 42-amino-acid β-amyloid (Aβ42) protein and microtubule-associated protein tau (tau protein), as well as proteins interacting with five FDA-approved anti-AD drugs. The results indicate that the majority of predictions are supported by literature, and molecular docking experiments demonstrate a strong affinity between the predicted compounds and targets.

AI-based mining of biomedical literature: Applications for drug repurposing for the treatment of dementia

Neurodegenerative pathologies such as Alzheimer's disease, Parkinson's disease, Huntington's disease, Amyotrophic lateral sclerosis, Multiple sclerosis, HIV-associated neurocognitive disorder, and others significantly affect individuals, their families, caregivers, and healthcare systems. While there are no cures yet, researchers worldwide are actively working on the development of novel treatments that have the potential to slow disease progression, alleviate symptoms, and ultimately improve the overall health of patients. Huge volumes of new scientific information necessitate new analytical approaches for meaningful hypothesis generation. To enable the automatic analysis of biomedical data we introduced AGATHA, an effective AI-based literature mining tool that can navigate massive scientific literature databases, such as PubMed. The overarching goal of this effort is to adapt AGATHA for drug repurposing by revealing hidden connections between FDA-approved medications and a health condition of interest. Our tool converts the abstracts of peer-reviewed papers from PubMed into multidimensional space where each gene and health condition are represented by specific metrics. We implemented advanced statistical analysis to reveal distinct clusters of scientific terms within the virtual space created using AGATHA-calculated parameters for selected health conditions and genes. Partial Least Squares Discriminant Analysis was employed for categorizing and predicting samples (122 diseases and 20889 genes) fitted to specific classes. Advanced statistics were employed to build a discrimination model and extract lists of genes specific to each disease class. Here we focus on drugs that can be repurposed for dementia treatment as an outcome of neurodegenerative diseases. Therefore, we determined dementia-associated genes statistically highly ranked in other disease classes. Additionally, we report a mechanism for detecting genes common to multiple health conditions. These sets of genes were classified based on their presence in biological pathways, aiding in selecting candidates and biological processes that are exploitable with drug repurposing.

Author Summary

This manuscript outlines our project involving the application of AGATHA, an AI-based literature mining tool, to discover drugs with the potential for repurposing in the context of neurocognitive disorders. The primary objective is to identify connections between approved medications and specific health conditions through advanced statistical analysis, including techniques like Partial Least Squares Discriminant Analysis (PLSDA) and unsupervised clustering. The methodology involves grouping scientific terms related to different health conditions and genes, followed by building discrimination models to extract lists of disease-specific genes. These genes are then analyzed through pathway analysis to select candidates for drug repurposing.

NGCN: Drug-target interaction prediction by integrating information and feature learning from heterogeneous network

Drug-target interaction (DTI) prediction is essential for new drug design and development. Constructing heterogeneous network based on diverse information about drugs, proteins and diseases provides new opportunities for DTI prediction. However, the inherent complexity, high dimensionality and noise of such a network prevent us from taking full advantage of these network characteristics. This article proposes a novel method, NGCN, to predict drug-target interactions from an integrated heterogeneous network, from which to extract relevant biological properties and association information while maintaining the topology information. It focuses on learning the topology representation of drugs and targets to improve the performance of DTI prediction. Unlike traditional methods, it focuses on learning the low-dimensional topology representation of drugs and targets via graph-based convolutional neural network. NGCN achieves substantial performance improvements over other state-of-the-art methods, such as a nearly 1.0% increase in AUPR value. Moreover, we verify the robustness of NGCN through benchmark tests, and the experimental results demonstrate it is an extensible framework capable of combining heterogeneous information for DTI prediction.

Endocrine disruptors in e-waste dismantling dust: In silico prediction of mixture-induced reproductive toxicity mechanisms

The constant exposure of humans to a mixture of low doses of toxic substances, emerging from the daily emission of toxic dust containing various metals and organic compounds in electrical and electronic waste (e-waste) recycling areas, poses potential harmful effects on health and the environment. While individually recognized as endocrine disruptors affecting hormonal balance, the combined impact of these toxic substances in a mixture remains insufficiently explored, particularly in relation to reproductive health. Thus, the aim of this in silico analysis was to: (i) assess the relationship between the exposure to a mixture of DBDE, DBDPE, TBBPA, Pb, Cd and Ni and development of male and female reproductive system disorders; and (ii) demonstrate the ability of in silico toxicogenomic tools in revealing the potential molecular mechanisms involved in the mixture toxicity. As the main data-mining tool, Comparative Toxicogenomics Database (CTD) was used, along with the ToppGene Suite portal and GeneMANIA online server. Our analysis identified 5 genes common to all the investigated substances and linked to reproductive system disorders. Notably, the most prominent interactions among these genes were physical interactions (77.64 %). Pathway enrichment analysis identified oxidative stress response as the central disrupted molecular pathway linked to reproductive pathology in the investigated mixture, while our chemical-phenotype CTD analysis uncovered additional affected pathways - apoptosis, hormonal regulation, and developmental functions. These findings highlight an increased risk of reproductive system disorders associated with the exposure to the investigated mixture of toxic substances in electronic waste recycling areas, emphasizing the urgent need for attention to address this environmental health concern. Hence, future laboratory studies should prioritize investigating the specific genes and common mechanisms identified in this study.

GSL-DTI: Graph structure learning network for Drug-Target interaction prediction

MOTIVATION

Drug-target interaction prediction is an important area of research to predict whether there is an interaction between a drug molecule and its target protein. It plays a critical role in drug discovery and development by facilitating the identification of potential drug candidates and expediting the overall process. Given the time-consuming, expensive, and high-risk nature of traditional drug discovery methods, the prediction of drug-target interactions has become an indispensable tool. Using machine learning and deep learning to tackle this class of problems has become a mainstream approach, and graph-based models have recently received much attention in this field. However, many current graph-based Drug-Target Interaction (DTI) prediction methods rely on manually defined rules to construct the Drug-Protein Pair (DPP) network during the DPP representation learning process. However, these methods fail to capture the true underlying relationships between drug molecules and target proteins.

RESULTS

We propose GSL-DTI, an automatic graph structure learning model used for predicting drug-target interactions (DTIs). Initially, we integrate large-scale heterogeneous networks using a graph convolution network based on meta-paths, effectively learning the representations of drugs and target proteins. Subsequently, we construct drug-protein pairs based on these representations. In contrast to previous studies that construct DPP networks based on manual rules, our method introduces an automatic graph structure learning approach. This approach utilizes a filter gate on the affinity scores of DPPs and relies on the classification loss of downstream tasks to guide the learning of the underlying DPP network structure. Based on the learned DPP network, we transform the prediction of drug-target interactions into a node classification problem. The comprehensive experiments conducted on three public datasets have shown the superiority of GSL-DTI in the tasks of DTI prediction. Additionally, GSL-DTI provides a fresh perspective for advancing research in graph structure learning for DTI prediction.

Proteome changes in larval zebrafish (Danio rerio) and fathead minnow (Pimephales promelas) exposed to (±) anatoxin-a

Anatoxin-a and its analogues are potent neurotoxins produced by several genera of cyanobacteria. Due in part to its high toxicity and potential presence in drinking water, these toxins pose threats to public health, companion animals and the environment. It primarily exerts toxicity as a cholinergic agonist, with high affinity at neuromuscular junctions, but molecular mechanisms by which it elicits toxicological responses are not fully understood. To advance understanding of this cyanobacteria, proteomic characterization (DIA shotgun proteomics) of two common fish models (zebrafish and fathead minnow) was performed following  (±) anatoxin-a exposure. Specifically, proteome changes were identified and quantified in larval fish exposed for 96 h (0.01-3 mg/L (±) anatoxin-a and caffeine (a methodological positive control) with environmentally relevant treatment levels examined based on environmental exposure distributions of surface water data. Proteomic concentration - response relationships revealed 48 and 29 proteins with concentration - response relationships curves for zebrafish and fathead minnow, respectively. In contrast, the highest number of differentially expressed proteins (DEPs) varied between zebrafish (n = 145) and fathead minnow (n = 300), with only fatheads displaying DEPs at all treatment levels. For both species, genes associated with reproduction were significantly downregulated, with pathways analysis that broadly clustered genes into groups associated with DNA repair mechanisms. Importantly, significant differences in proteome response between the species was also observed, consistent with prior observations of differences in response using both behavioral assays and gene expression, adding further support to model specific differences in organismal sensitivity and/or response. When DEPs were read across from humans to zebrafish, disease ontology enrichment identified diseases associated with cognition and muscle weakness consistent with the prior literature. Our observations highlight limited knowledge of how (±) anatoxin-a, a commonly used synthetic racemate surrogate, elicits responses at a molecular level and advances its toxicological understanding.

CCL-DTI: contributing the contrastive loss in drug-target interaction prediction

BACKGROUND

The Drug-Target Interaction (DTI) prediction uses a drug molecule and a protein sequence as inputs to predict the binding affinity value. In recent years, deep learning-based models have gotten more attention. These methods have two modules: the feature extraction module and the task prediction module. In most deep learning-based approaches, a simple task prediction loss (i.e., categorical cross entropy for the classification task and mean squared error for the regression task) is used to learn the model. In machine learning, contrastive-based loss functions are developed to learn more discriminative feature space. In a deep learning-based model, extracting more discriminative feature space leads to performance improvement for the task prediction module.

RESULTS

In this paper, we have used multimodal knowledge as input and proposed an attention-based fusion technique to combine this knowledge. Also, we investigate how utilizing contrastive loss function along the task prediction loss could help the approach to learn a more powerful model. Four contrastive loss functions are considered: (1) max-margin contrastive loss function, (2) triplet loss function, (3) Multi-class N-pair Loss Objective, and (4) NT-Xent loss function. The proposed model is evaluated using four well-known datasets: Wang et al. dataset, Luo's dataset, Davis, and KIBA datasets.

CONCLUSIONS

Accordingly, after reviewing the state-of-the-art methods, we developed a multimodal feature extraction network by combining protein sequences and drug molecules, along with protein-protein interaction networks and drug-drug interaction networks. The results show it performs significantly better than the comparable state-of-the-art approaches.

Exploring the Role of Chemoinformatics in Accelerating Drug Discovery: A Computational Approach

Cheminformatics and its role in drug discovery is expected to be the privileged approach in handling large number of chemical datasets. This approach contributes toward the pharmaceutical development and assessment of chemical compounds at a faster rate efficiently. Additionally, as technological advancement impacts research, cheminformatics is being used more and more in the field of health science. This chapter describes the concepts of cheminformatics along with its involvement in drug discovery with a case study.

Involvement of toxic metals and PCBs mixture in the thyroid and male reproductive toxicity: In silico toxicogenomic data mining

Toxicological research is mostly limited to considering the effects of a single substance, even though the real exposure of people is reflected in their daily exposure to many different chemical substances in low-doses. This in silico toxicogenomic study aims to provide evidence for the selected environmental (organo)metals (lead, cadmium, methyl mercury) + polychlorinated biphenyls mixture involvement in the possible alteration of thyroid, and male reproductive system function, and furthermore to predict the possible toxic mechanisms of the environmental cocktail. The Comparative Toxicogenomic Database, GeneMANIA online software, and ToppGene Suite portal were used as the main tools for toxicogenomic data mining and gene ontology analysis. The results show that 35 annotated common genes between selected chemicals and endocrine system diseases can interact on the co-expression level. Our study highlighted the disruption of the cytokines, the cell's response to oxidative stress, and the influence of the transcription factors as the potential core of toxicological mechanisms of the discussed mixture's effects. The connected toxicological effects of the tested mixture were abnormal sperm cells, a disrupted level of testosterone, and thyroid hormones. The core mechanisms of these effects were inflammation, oxidative stress, disruption of androgen receptor signaling, and the alteration of the FOXO3-Keap-1/NRF2-HMOX1-NQO1 pathway signaling most likely controlled by the co-expression of overlapped genes among used chemicals. This in silico research can be used as a potential core for the determination of biomarkers that can be monitored in future further in vitro and in vivo experiments.

CrossFuse-XGBoost: accurate prediction of the maximum recommended daily dose through multi-feature fusion, cross-validation screening and extreme gradient boosting

In the drug development process, approximately 30% of failures are attributed to drug safety issues. In particular, the first-in-human (FIH) trial of a new drug represents one of the highest safety risks, and initial dose selection is crucial for ensuring safety in clinical trials. With traditional dose estimation methods, which extrapolate data from animals to humans, catastrophic events have occurred during Phase I clinical trials due to interspecies differences in compound sensitivity and unknown molecular mechanisms. To address this issue, this study proposes a CrossFuse-extreme gradient boosting (XGBoost) method that can directly predict the maximum recommended daily dose of a compound based on existing human research data, providing a reference for FIH dose selection. This method not only integrates multiple features, including molecular representations, physicochemical properties and compound-protein interactions, but also improves feature selection based on cross-validation. The results demonstrate that the CrossFuse-XGBoost method not only improves prediction accuracy compared to that of existing local weighted methods [k-nearest neighbor (k-NN) and variable k-NN (v-NN)] but also solves the low prediction coverage issue of v-NN, achieving full coverage of the external validation set and enabling more reliable predictions. Furthermore, this study offers a high level of interpretability by identifying the importance of different features in model construction. The 241 features with the most significant impact on the maximum recommended daily dose were selected, providing references for optimizing the structure of new compounds and guiding experimental research. The datasets and source code are freely available at https://github.com/cqmu-lq/CrossFuse-XGBoost.

Cross-view contrastive representation learning approach to predicting DTIs via integrating multi-source information

Drug-target interaction (DTI) prediction serves as the foundation of new drug findings and drug repositioning. For drugs/targets, the sequence data contains the biological structural information, while the heterogeneous network contains the biochemical functional information. These two types of information describe different aspects of drugs and targets. Due to the complexity of DTI machinery, it is necessary to learn the representation from multiple perspectives. We hereby try to design a way to leverage information from multi-source data to the maximum extent and find a strategy to fuse them. To address the above challenges, we propose a model, named MOVE (short for integrating multi-source information for predicting DTI via cross-view contrastive learning), for learning comprehensive representations of each drug and target from multi-source data. MOVE extracts information from the sequence view and the network view, then utilizes a fusion module with auxiliary contrastive learning to facilitate the fusion of representations. Experimental results on the benchmark dataset demonstrate that MOVE is effective in DTI prediction.

CTD tetramers: a new online tool that computationally links curated chemicals, genes, phenotypes, and diseases to inform molecular mechanisms for environmental health

The molecular mechanisms connecting environmental exposures to adverse endpoints are often unknown, reflecting knowledge gaps. At the Comparative Toxicogenomics Database (CTD), we developed a bioinformatics approach that integrates manually curated, literature-based interactions from CTD to generate a "CGPD-tetramer": a 4-unit block of information organized as a step-wise molecular mechanism linking an initiating Chemical, an interacting Gene, a Phenotype, and a Disease outcome. Here, we describe a novel, user-friendly tool called CTD Tetramers that generates these evidence-based CGPD-tetramers for any curated chemical, gene, phenotype, or disease of interest. Tetramers offer potential solutions for the unknown underlying mechanisms and intermediary phenotypes connecting a chemical exposure to a disease. Additionally, multiple tetramers can be assembled to construct detailed modes-of-action for chemical-induced disease pathways. As well, tetramers can help inform environmental influences on adverse outcome pathways (AOPs). We demonstrate the tool's utility with relevant use cases for a variety of environmental chemicals (eg, perfluoroalkyl substances, bisphenol A), phenotypes (eg, apoptosis, spermatogenesis, inflammatory response), and diseases (eg, asthma, obesity, male infertility). Finally, we map AOP adverse outcome terms to corresponding CTD terms, allowing users to query for tetramers that can help augment AOP pathways with additional stressors, genes, and phenotypes, as well as formulate potential AOP disease networks (eg, liver cirrhosis and prostate cancer). This novel tool, as part of the complete suite of tools offered at CTD, provides users with computational datasets and their supporting evidence to potentially fill exposure knowledge gaps and develop testable hypotheses about environmental health.

A Biological Feature and Heterogeneous Network Representation Learning-Based Framework for Drug-Target Interaction Prediction

The prediction of drug-target interaction (DTI) is crucial to drug discovery. Although the interactions between the drug and target can be accurately verified by traditional biochemical experiments, the determination of DTI through biochemical experiments is a time-consuming, laborious, and expensive process. Therefore, we propose a learning-based framework named BG-DTI for drug-target interaction prediction. Our model combines two main approaches based on biological features and heterogeneous networks to identify interactions between drugs and targets. First, we extract original features from the sequence to encode each drug and target. Later, we further consider the relationships among various biological entities by constructing drug-drug similarity networks and target-target similarity networks. Furthermore, a graph convolutional network and a graph attention network in the graph representation learning module help us learn the features representation of drugs and targets. After obtaining the features from graph representation learning modules, these features are combined into fusion descriptors for drug-target pairs. Finally, we send the fusion descriptors and labels to a random forest classifier for predicting DTI. The evaluation results show that BG-DTI achieves an average AUC of 0.938 and an average AUPR of 0.930, which is better than those of five existing state-of-the-art methods. We believe that BG-DTI can facilitate the development of drug discovery or drug repurposing.

Semi-supervised heterogeneous graph contrastive learning for drug-target interaction prediction

Identification of drug-target interactions (DTIs) is an important step in drug discovery and drug repositioning. In recent years, graph-based methods have attracted great attention and show advantages on predicting potential DTIs. However, these methods face the problem that the known DTIs are very limited and expensive to obtain, which decreases the generalization ability of the methods. Self-supervised contrastive learning is independent of labeled DTIs, which can mitigate the impact of the problem. Therefore, we propose a framework SHGCL-DTI for predicting DTIs, which supplements the classical semi-supervised DTI prediction task with an auxiliary graph contrastive learning module. Specifically, we generate representations for the nodes through the neighbor view and meta-path view, and define positive and negative pairs to maximize the similarity between positive pairs from different views. Subsequently, SHGCL-DTI reconstructs the original heterogeneous network to predict the potential DTIs. The experiments on the public dataset show that SHGCL-DTI has significant improvement in different scenarios, compared with existing state-of-the-art methods. We also demonstrate that the contrastive learning module improves the prediction performance and generalization ability of SHGCL-DTI through ablation study. In addition, we have found several novel predicted DTIs supported by the biological literature. The data and source code are available at: https://github.com/TOJSSE-iData/SHGCL-DTI.

Predicting Drug-Target Interaction Via Self-Supervised Learning

Recent advances in graph representation learning provide new opportunities for computational drug-target interaction (DTI) prediction. However, it still suffers from deficiencies of dependence on manual labels and vulnerability to attacks. Inspired by the success of self-supervised learning (SSL) algorithms, which can leverage input data itself as supervision,we propose SupDTI, a SSL-enhanced drug-target interaction prediction framework based on a heterogeneous network (i.e., drug-protein, drug-drug, and protein-protein interaction network; drug-disease, drug-side-effect, and protein-disease association network; drug-structure and protein-sequence similarity network). Specifically, SupDTI is an end-to-end learning framework consisting of five components. First, localized and globalized graph convolutions are designed to capture the nodes' information from both local and global perspectives, respectively. Then, we develop a variational autoencoder to constrain the nodes' representation to have desired statistical characteristics. Finally, a unified self-supervised learning strategy is leveraged to enhance the nodes' representation, namely, a contrastive learning module is employed to enable the nodes' representation to fit the graph-level representation, followed by a generative learning module which further maximizes the node-level agreement across the global and local views by learning the probabilistic connectivity distribution of the original heterogeneous network. Experimental results show that our model can achieve better prediction performance than state-of-the-art methods.

An Integration Framework of Secure Multiparty Computation and Deep Neural Network for Improving Drug-Drug Interaction Predictions

Drug-drug interaction (DDI) is a key concern in drug development and pharmacovigilance. It is important to improve DDI predictions by integrating multisource data from various pharmaceutical companies. Unfortunately, the data privacy and financial interest issues seriously influence the interinstitutional collaborations for DDI predictions. We propose multiparty computation DDI (MPCDDI), a secure MPC-based deep learning framework for DDI predictions. MPCDDI leverages the secret sharing technologies to incorporate the drug-related feature data from multiple institutions and develops a deep learning model for DDI predictions. In MPCDDI, all data transmission and deep learning operations are integrated into secure MPC frameworks to enable high-quality collaboration among pharmaceutical institutions without divulging private drug-related information. The results suggest that MPCDDI is superior to other eight baselines and achieves the similar performance to that of the corresponding plaintext collaborations. More interestingly, MPCDDI significantly outperforms methods that use private data from the single institution. In summary, MPCDDI is an effective framework for promoting collaborative and privacy-preserving drug discovery.

SAGDTI: self-attention and graph neural network with multiple information representations for the prediction of drug-target interactions

Motivation

Accurate identification of target proteins that interact with drugs is a vital step in silico, which can significantly foster the development of drug repurposing and drug discovery. In recent years, numerous deep learning-based methods have been introduced to treat drug-target interaction (DTI) prediction as a classification task. The output of this task is binary identification suggesting the absence or presence of interactions. However, existing studies often (i) neglect the unique molecular attributes when embedding drugs and proteins, and (ii) determine the interaction of drug-target pairs without considering biological interaction information.

Results

In this study, we propose an end-to-end attention-derived method based on the self-attention mechanism and graph neural network, termed SAGDTI. The aim of this method is to overcome the aforementioned drawbacks in the identification of DTI. SAGDTI is the first method to sufficiently consider the unique molecular attribute representations for both drugs and targets in the input form of the SMILES sequences and three-dimensional structure graphs. In addition, our method aggregates the feature attributes of biological information between drugs and targets through multi-scale topologies and diverse connections. Experimental results illustrate that SAGDTI outperforms existing prediction models, which benefit from the unique molecular attributes embedded by atom-level attention and biological interaction information representation aggregated by node-level attention. Moreover, a case study on severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) shows that our model is a powerful tool for identifying DTIs in real life.

Availability and implementation

The data and codes underlying this article are available in Github at https://github.com/lixiaokun2020/SAGDTI.

Inferring drug-disease associations by a deep analysis on drug and disease networks

Drugs, which treat various diseases, are essential for human health. However, developing new drugs is quite laborious, time-consuming, and expensive. Although investments into drug development have greatly increased over the years, the number of drug approvals each year remain quite low. Drug repositioning is deemed an effective means to accelerate the procedures of drug development because it can discover novel effects of existing drugs. Numerous computational methods have been proposed in drug repositioning, some of which were designed as binary classifiers that can predict drug-disease associations (DDAs). The negative sample selection was a common defect of this method. In this study, a novel reliable negative sample selection scheme, named RNSS, is presented, which can screen out reliable pairs of drugs and diseases with low probabilities of being actual DDAs. This scheme considered information from k-neighbors of one drug in a drug network, including their associations to diseases and the drug. Then, a scoring system was set up to evaluate pairs of drugs and diseases. To test the utility of the RNSS, three classic classification algorithms (random forest, bayes network and nearest neighbor algorithm) were employed to build classifiers using negative samples selected by the RNSS. The cross-validation results suggested that such classifiers provided a nearly perfect performance and were significantly superior to those using some traditional and previous negative sample selection schemes.

DEDTI versus IEDTI: efficient and predictive models of drug-target interactions

Drug repurposing is an active area of research that aims to decrease the cost and time of drug development. Most of those efforts are primarily concerned with the prediction of drug-target interactions. Many evaluation models, from matrix factorization to more cutting-edge deep neural networks, have come to the scene to identify such relations. Some predictive models are devoted to the prediction's quality, and others are devoted to the efficiency of the predictive models, e.g., embedding generation. In this work, we propose new representations of drugs and targets useful for more prediction and analysis. Using these representations, we propose two inductive, deep network models of IEDTI and DEDTI for drug-target interaction prediction. Both of them use the accumulation of new representations. The IEDTI takes advantage of triplet and maps the input accumulated similarity features into meaningful embedding corresponding vectors. Then, it applies a deep predictive model to each drug-target pair to evaluate their interaction. The DEDTI directly uses the accumulated similarity feature vectors of drugs and targets and applies a predictive model on each pair to identify their interactions. We have done a comprehensive simulation on the DTINet dataset as well as gold standard datasets, and the results show that DEDTI outperforms IEDTI and the state-of-the-art models. In addition, we conduct a docking study on new predicted interactions between two drug-target pairs, and the results confirm acceptable drug-target binding affinity between both predicted pairs.

Multi-modality attribute learning-based method for drug-protein interaction prediction based on deep neural network

Identification of active candidate compounds for target proteins, also called drug-protein interaction (DPI) prediction, is an essential but time-consuming and expensive step, which leads to fostering the development of drug discovery. In recent years, deep network-based learning methods were frequently proposed in DPIs due to their powerful capability of feature representation. However, the performance of existing DPI methods is still limited by insufficiently labeled pharmacological data and neglected intermolecular information. Therefore, overcoming these difficulties to perfect the performance of DPIs is an urgent challenge for researchers. In this article, we designed an innovative 'multi-modality attributes' learning-based framework for DPIs with molecular transformer and graph convolutional networks, termed, multi-modality attributes (MMA)-DPI. Specifically, intermolecular sub-structural information and chemical semantic representations were extracted through an augmented transformer module from biomedical data. A tri-layer graph convolutional neural network module was applied to associate the neighbor topology information and learn the condensed dimensional features by aggregating a heterogeneous network that contains multiple biological representations of drugs, proteins, diseases and side effects. Then, the learned representations were taken as the input of a fully connected neural network module to further integrate them in molecular and topological space. Finally, the attribute representations were fused with adaptive learning weights to calculate the interaction score for the DPIs tasks. MMA-DPI was evaluated in different experimental conditions and the results demonstrate that the proposed method achieved higher performance than existing state-of-the-art frameworks.

Drug-target interaction prediction based on spatial consistency constraint and graph convolutional autoencoder

BACKGROUND

Drug-target interaction (DTI) prediction plays an important role in drug discovery and repositioning. However, most of the computational methods used for identifying relevant DTIs do not consider the invariance of the nearest neighbour relationships between drugs or targets. In other words, they do not take into account the invariance of the topological relationships between nodes during representation learning. It may limit the performance of the DTI prediction methods.

RESULTS

Here, we propose a novel graph convolutional autoencoder-based model, named SDGAE, to predict DTIs. As the graph convolutional network cannot handle isolated nodes in a network, a pre-processing step was applied to reduce the number of isolated nodes in the heterogeneous network and facilitate effective exploitation of the graph convolutional network. By maintaining the graph structure during representation learning, the nearest neighbour relationships between nodes in the embedding space remained as close as possible to the original space.

CONCLUSIONS

Overall, we demonstrated that SDGAE can automatically learn more informative and robust feature vectors of drugs and targets, thus exhibiting significantly improved predictive accuracy for DTIs.

Integrated Multi-Omics Techniques and Network Pharmacology Analysis to Explore the Material Basis and Mechanism of Simiao Pill in the Treatment of Rheumatoid Arthritis

The Simiao pill (SMP) is a classic prescription that has shown anti-inflammatory, analgesic, and immunomodulatory effects and is clinically used to treat inflammatory diseases, such as rheumatoid arthritis (RA) and gouty arthritis, for which the effects and mechanism of action remain largely unknown. In this study, serum samples from RA rats were analyzed using ultra-high performance liquid chromatography-quadrupole time-of-flight mass spectrometry based metabolomics technology and liquid chromatography with tandem mass spectrometry proteomics technology together with network pharmacology to explore the pharmacodynamic substances of SMP. To further verify the above results, we constructed a fibroblast-like synoviocyte (FLS) cell model and administered phellodendrine for the test. All these clues suggested that SMP can significantly reduce the level of interleukin-1β (IL-1β), interleukin-6 (IL-6), and tumor necrosis factor-α (TNF-α) in complete Freund's adjuvant rat serum and improve the degree of foot swelling; combined with metabolomics, proteomics, and network pharmacological technology, it is determined that SMP plays a therapeutic role through the inflammatory pathway, and phellodendrine is found to be one of the pharmacodynamic substances. By constructing an FLS model, it is further determined that phellodendrine could effectively inhibit the activity of synovial cells and reduce the expression level of inflammatory factors by downregulating the expression level of related proteins in the TLR4-MyD88-IRAK4-MAPK signal pathway to alleviate joint inflammation and cartilage injury. Overall, these findings suggested that phellodendrine is an effective component of SMP in the treatment of RA.

Deciphering crucial genes in multiple sclerosis pathogenesis and drug repurposing: A systems biology approach

This study employed systems biology and high-throughput technologies to analyze complex molecular components of MS pathophysiology, combining data from multiple omics sources to identify potential biomarkers and propose therapeutic targets and repurposed drugs for MS treatment. This study analyzed GEO microarray datasets and MS proteomics data using geWorkbench, CTD, and COREMINE to identify differentially expressed genes associated with MS disease. Protein-protein interaction networks were constructed using Cytoscape and its plugins, and functional enrichment analysis was performed to identify crucial molecules. A drug-gene interaction network was also created using DGIdb to propose medications. This study identified 592 differentially expressed genes (DEGs) associated with MS disease using GEO, proteomics, and text-mining datasets. 37 DEGs were found to be important by topographical network studies, and 6 were identified as the most significant for MS pathophysiology. Additionally, we proposed six drugs that target these key genes. Crucial molecules identified in this study were dysregulated in MS and likely play a key role in the disease mechanism, warranting further research. Additionally, we proposed repurposing certain FDA-approved drugs for MS treatment. Our in silico results were supported by previous experimental research on some of the target genes and drugs. SIGNIFICANCE: As the long-lasting investigations continue to discover new pathological territories in neurodegeneration, here we apply a systems biology approach to determine multiple sclerosis's molecular and pathophysiological origin and identify multiple sclerosis crucial genes that contribute to candidating new biomarkers and proposing new medications.

Relationship between drug targets and drug-signature networks: a network-based genome-wide landscape

Drugs produce pharmaceutical and adverse effects that arise from the complex relationship between drug targets and signatures; by considering such relationships, we can begin to understand the cellular mechanisms of drugs. In this study, we selected 463 genes from the DSigDB database corresponding to targets and signatures for 382 FDA-approved drugs with both protein binding information for a drug-target score (KDTN, i.e., the degree to which the protein encoded by the gene binds to a number of drugs) and microarray signature information for a drug-sensitive score (KDSN, i.e., the degree to which gene expression is stimulated by the drug). Accordingly, we constructed two drug-gene bipartite network models, a drug-target network and drug-signature network, which were merged into a multidimensional model. Analysis revealed that the KDTN and KDSN were in mutually exclusive and reciprocal relationships in terms of their biological network structure and gene function. A symmetric balance between the KDTN and KDSN of genes facilitates the possibility of therapeutic drug effects in whole genome. These results provide new insights into the relationship between drugs and genes, specifically drug targets and drug signatures.

Metapath-aggregated heterogeneous graph neural network for drug-target interaction prediction

Drug-target interaction (DTI) prediction is an essential step in drug repositioning. A few graph neural network (GNN)-based methods have been proposed for DTI prediction using heterogeneous biological data. However, existing GNN-based methods only aggregate information from directly connected nodes restricted in a drug-related or a target-related network and are incapable of capturing high-order dependencies in the biological heterogeneous graph. In this paper, we propose a metapath-aggregated heterogeneous graph neural network (MHGNN) to capture complex structures and rich semantics in the biological heterogeneous graph for DTI prediction. Specifically, MHGNN enhances heterogeneous graph structure learning and high-order semantics learning by modeling high-order relations via metapaths. Additionally, MHGNN enriches high-order correlations between drug-target pairs (DTPs) by constructing a DTP correlation graph with DTPs as nodes. We conduct extensive experiments on three biological heterogeneous datasets. MHGNN favorably surpasses 17 state-of-the-art methods over 6 evaluation metrics, which verifies its efficacy for DTI prediction. The code is available at https://github.com/Zora-LM/MHGNN-DTI.

In Vitro Transcriptome Analysis of Cobalt Boride Nanoparticles on Human Pulmonary Alveolar Cells

Nanobiotechnology influences many different areas, including the medical, food, energy, clothing, and cosmetics industries. Considering the wide usage of nanomaterials, it is necessary to investigate the toxicity potentials of specific nanosized molecules. Boron-containing nanoparticles (NPs) are attracting much interest from scientists due to their unique physicochemical properties. However, there is limited information concerning the toxicity of boron-containing NPs, including cobalt boride (Co₂B) NPs. Therefore, in this study, Co₂B NPs were characterized using X-ray crystallography (XRD), transmission electron microscope (TEM), scanning electron microscope (SEM), and energy-dispersive X-ray spectroscopy (EDX) techniques. Then, we performed 3-(4,5-dimethyl-thiazol-2-yl) 2,5-diphenyltetrazolium bromide (MTT), lactate dehydrogenase (LDH) release, and neutral red (NR) assays for assessing cell viability against Co₂B NP exposure on cultured human pulmonary alveolar epithelial cells (HPAEpiC). In addition, whole-genome microarray analysis was carried out to reveal the global gene expression differentiation of HPAEpiC cells after Co₂B NP application. The cell viability tests unveiled an IC50 value for Co₂B NPs of 310.353 mg/L. The results of our microarray analysis displayed 719 gene expression differentiations (FC ≥ 2) among the analyzed 40,000 genes. The performed visualization and integrated discovery (DAVID) analysis revealed that there were interactions between various gene pathways and administration of the NPs. Based on gene ontology biological processes analysis, we found that the P53 signaling pathway, cell cycle, and cancer-affecting genes were mostly affected by the Co₂B NPs. In conclusion, we suggested that Co₂B NPs would be a safe and effective nanomolecule for industrial applications, particularly for medical purposes.

Multi-Attribute Discriminative Representation Learning for Prediction of Adverse Drug-Drug Interaction

Adverse drug-drug interaction (ADDI) is a significant life-threatening issue, posing a leading cause of hospitalizations and deaths in healthcare systems. This paper proposes a unified Multi-Attribute Discriminative Representation Learning (MADRL) model for ADDI prediction. Unlike the existing works that equally treat features of each attribute without discrimination and do not consider the underlying relationship among drugs, we first develop a regularized optimization problem based on CUR matrix decomposition for joint representative drug and discriminative feature selection such that the selected drugs and features can well approximate the original feature spaces and the critical factors discriminative to ADDIs can be properly explored. Different from the existing models that ignore the consistent and unique properties among attributes, a Generative Adversarial Network (GAN) framework is then designed to capture the inter-attribute shared and intra-attribute specific representations of adverse drug pairs for exploiting their consensus and complementary information in ADDI prediction. Meanwhile, MADRL is compatible with any kind of attributes and capable of exploring their respective effects on ADDI prediction. An iterative algorithm based on the alternating direction method of multipliers is developed for optimization. Experiments on publicly available dataset demonstrate the effectiveness of MADRL when compared with eleven baselines and its six variants.

Computational Prediction of Drug-Disease Association Based on Graph-Regularized One Bit Matrix Completion

Investigation of existing drugs is an effective alternative to the discovery of new drugs for treating diseases. This task of drug re-positioning can be assisted by various kinds of computational methods to predict the best indication for a drug given the open-source biological datasets. Owing to the fact that similar drugs tend to have common pathways and disease indications, the association matrix is assumed to be of low-rank structure. Hence, the problem of drug-disease association prediction can be modeled as a low-rank matrix completion problem. In this work, we propose a novel matrix completion framework that makes use of the side-information associated with drugs/diseases for the prediction of drug-disease indications modeled as neighborhood graph: Graph regularized 1-bit matrix completion (GR1BMC). The algorithm is specially designed for binary data and uses parallel proximal algorithm to solve the aforesaid minimization problem taking into account all the constraints including the neighborhood graph incorporation and restricting predicted scores within the specified range. The results have been validated on two standard databases by evaluating the AUC across the 10-fold cross-validation splits. The usage of the method is also evaluated through a case study where top 5 indications are predicted for novel drugs, which then are verified with the CTD database.

Mechanism of Salvia miltiorrhiza Bge. for the Treatment of Ischemic Stroke Based on Bioinformatics and Network Pharmacology

Background and Purpose. A large number of pharmacological experiments have proved that many components of Salvia miltiorrhiza Bge. have neuroprotective, anti-inflammatory, and antioxidant effects. Middle cerebral artery occlusion (MCAO) models treated with Salvia miltiorrhiza Bge. can significantly reduce the infarct size and change the pathological morphology of brain tissue. However, not only the internal mechanism but also the material basis is unclear to researchers. Our research aims to elucidate the potential effective material basis and molecular internal mechanism between Salvia miltiorrhiza Bge. and stroke. Methods. In this study, SymMap was used to screen the 50 bioactive scored components and 65 putative targets of Salvia miltiorrhiza Bge., and their targets were standardized using the UniProt platform. The disease targets related to stroke were collected by comparative toxicogenomics database (CTD), GeneCards, and quantitative structure-activity relationships-TargetNet (QSAR-TargetNet). Thereafter, the protein-protein interaction (PPI) network was constructed using the STRING platform and visualized by Cytoscape (3.8.2) software. Then, the Metascape platform was used to analyze the Gene Ontology (GO) enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway. Cytoscape (3.7.2) software was also used to construct the network of the “herb-component-target-pathway.” We found that Tanshinol B, Tanshinol A, Przewaquinone C, Tanshinone II, and other main components of Salvia miltiorrhiza Bge. may regulate neurotransmitters and neurological function. Therefore, we speculate Salvia miltiorrhiza Bge. has a neuroprotective effect. For further verification, potential core targets (STAT3, MMP2, ESR1, TERT, and MMP9 proteins) for ischemic stroke and core active ingredients (Tanshinol A, Tanshinol B, Tanshinone II A, and Przewaquinone C) for Salvia miltiorrhiza Bge. were further verified by molecular docking. Results. Our findings revealed that Tanshinol A, Tanshinol B, Tanshinone II A, and Przewaquinone C as the main component of Salvia miltiorrhiza Bge. may have a neuroprotective effect against ischemic stroke, which provides a new understanding for the development of therapies for the prevention and treatment of ischemic stroke.

Multiple similarity drug-target interaction prediction with random walks and matrix factorization

The discovery of drug-target interactions (DTIs) is a very promising area of research with great potential. The accurate identification of reliable interactions among drugs and proteins via computational methods, which typically leverage heterogeneous information retrieved from diverse data sources, can boost the development of effective pharmaceuticals. Although random walk and matrix factorization techniques are widely used in DTI prediction, they have several limitations. Random walk-based embedding generation is usually conducted in an unsupervised manner, while the linear similarity combination in matrix factorization distorts individual insights offered by different views. To tackle these issues, we take a multi-layered network approach to handle diverse drug and target similarities, and propose a novel optimization framework, called Multiple similarity DeepWalk-based Matrix Factorization (MDMF), for DTI prediction. The framework unifies embedding generation and interaction prediction, learning vector representations of drugs and targets that not only retain higher order proximity across all hyper-layers and layer-specific local invariance, but also approximate the interactions with their inner product. Furthermore, we develop an ensemble method (MDMF2A) that integrates two instantiations of the MDMF model, optimizing the area under the precision-recall curve (AUPR) and the area under the receiver operating characteristic curve (AUC), respectively. The empirical study on real-world DTI datasets shows that our method achieves statistically significant improvement over current state-of-the-art approaches in four different settings. Moreover, the validation of highly ranked non-interacting pairs also demonstrates the potential of MDMF2A to discover novel DTIs.

Integrative analysis prioritised oxytocin-related biomarkers associated with the aetiology of autism spectrum disorder

Background

Autism spectrum disorder (ASD) is a neurodevelopmental disorder with high phenotypic and genetic heterogeneity. The common variants of specific oxytocin-related genes (OTRGs), particularly OXTR, are associated with the aetiology of ASD. The contribution of rare genetic variations in OTRGs to ASD aetiology remains unclear.

Methods

We catalogued publicly available de novo mutations (DNMs) [from 6,511 patients with ASD and 3,391 controls], rare inherited variants (RIVs) [from 1,786 patients with ASD and 1,786 controls], and both de novo copy number variations (dnCNVs) and inherited CNVs (ihCNVs) [from 15,581 patients with ASD and 6,017 controls] in 963 curated OTRGs to explore their contribution to ASD pathology, respectively. Finally, a combined model was designed to prioritise the contribution of each gene to ASD aetiology by integrating DNMs and CNVs.

Findings

The rare genetic variations of OTRGs were significantly associated with ASD aetiology, in the order of dnCNVs > ihCNVs > DNMs. Furthermore, 172 OTRGs and their connected 286 ASD core genes were prioritised to positively contribute to ASD aetiology, including top-ranked MAPK3. Probands carrying rare disruptive variations in these genes were estimated to account for 10∼11% of all ASD probands.

Interpretation

Our findings suggest that rare disruptive variations in 172 OTRGs and their connected 286 ASD core genes are associated with ASD aetiology and may be potential biomarkers predicting the effects of oxytocin treatment.

Funding

Guangdong Key Project, National Natural Science Foundation of China, Key Laboratory of Clinical Laboratory Diagnosis and Translational Research of Zhejiang Province.

Metapath Aggregated Graph Neural Network and Tripartite Heterogeneous Networks for Microbe-Disease Prediction

More and more studies have shown that understanding microbe-disease associations cannot only reveal the pathogenesis of diseases, but also promote the diagnosis and prognosis of diseases. Because traditional medical experiments are time-consuming and expensive, many computational methods have been proposed in recent years to identify potential microbe-disease associations. In this study, we propose a method based on heterogeneous network and metapath aggregated graph neural network (MAGNN) to predict microbe-disease associations, called MATHNMDA. First, we introduce microbe-drug interactions, drug-disease associations, and microbe-disease associations to construct a microbe-drug-disease heterogeneous network. Then we take the heterogeneous network as input to MAGNN. Second, for each layer of MAGNN, we carry out intra-metapath aggregation with a multi-head attention mechanism to learn the structural and semantic information embedded in the target node context, the metapath-based neighbor nodes, and the context between them, by encoding the metapath instances under the metapath definition mode. We then use inter-metapath aggregation with an attention mechanism to combine the semantic information of all different metapaths. Third, we can get the final embedding of microbe nodes and disease nodes based on the output of the last layer in the MAGNN. Finally, we predict potential microbe-disease associations by reconstructing the microbe-disease association matrix. In addition, we evaluated the performance of MATHNMDA by comparing it with that of its variants, some state-of-the-art methods, and different datasets. The results suggest that MATHNMDA is an effective prediction method. The case studies on asthma, inflammatory bowel disease (IBD), and coronavirus disease 2019 (COVID-19) further validate the effectiveness of MATHNMDA.

HGDTI: predicting drug-target interaction by using information aggregation based on heterogeneous graph neural network

BACKGROUND

In research on new drug discovery, the traditional wet experiment has a long period. Predicting drug-target interaction (DTI) in silico can greatly narrow the scope of search of candidate medications. Excellent algorithm model may be more effective in revealing the potential connection between drug and target in the bioinformatics network composed of drugs, proteins and other related data.

RESULTS

In this work, we have developed a heterogeneous graph neural network model, named as HGDTI, which includes a learning phase of network node embedding and a training phase of DTI classification. This method first obtains the molecular fingerprint information of drugs and the pseudo amino acid composition information of proteins, then extracts the initial features of nodes through Bi-LSTM, and uses the attention mechanism to aggregate heterogeneous neighbors. In several comparative experiments, the overall performance of HGDTI significantly outperforms other state-of-the-art DTI prediction models, and the negative sampling technology is employed to further optimize the prediction power of model. In addition, we have proved the robustness of HGDTI through heterogeneous network content reduction tests, and proved the rationality of HGDTI through other comparative experiments. These results indicate that HGDTI can utilize heterogeneous information to capture the embedding of drugs and targets, and provide assistance for drug development.

CONCLUSIONS

The HGDTI based on heterogeneous graph neural network model, can utilize heterogeneous information to capture the embedding of drugs and targets, and provide assistance for drug development. For the convenience of related researchers, a user-friendly web-server has been established at http://bioinfo.jcu.edu.cn/hgdti .

Review on predicting pairwise relationships between human microbes, drugs and diseases: from biological data to computational models

In recent years, with the rapid development of techniques in bioinformatics and life science, a considerable quantity of biomedical data has been accumulated, based on which researchers have developed various computational approaches to discover potential associations between human microbes, drugs and diseases. This paper provides a comprehensive overview of recent advances in prediction of potential correlations between microbes, drugs and diseases from biological data to computational models. Firstly, we introduced the widely used datasets relevant to the identification of potential relationships between microbes, drugs and diseases in detail. And then, we divided a series of a lot of representative computing models into five major categories including network, matrix factorization, matrix completion, regularization and artificial neural network for in-depth discussion and comparison. Finally, we analysed possible challenges and opportunities in this research area, and at the same time we outlined some suggestions for further improvement of predictive performances as well.

A novel chemo-phenotypic method identifies mixtures of salpn, vitamin D3, and pesticides involved in the development of colorectal and pancreatic cancer

Environmental chemical (EC) exposures and our interactions with them has significantly increased in the recent decades. Toxicity associated biological characterization of these chemicals is challenging and inefficient, even with available high-throughput technologies. In this report, we describe a novel computational method for characterizing toxicity, associated biological perturbations and disease outcome, called the Chemo-Phenotypic Based Toxicity Measurement (CPTM). CPTM is used to quantify the EC "toxicity score" (Z_ts), which serves as a holistic metric of potential toxicity and disease outcome. CPTM quantitative toxicity is the measure of chemical features, biological phenotypic effects, and toxicokinetic properties of the ECs. For proof-of-concept, we subject ECs obtained from the Environmental Protection Agency's (EPA) database to the CPTM. We validated the CPTM toxicity predictions by correlating 'Z_ts' scores with known toxicity effects. We also confirmed the CPTM predictions with in-vitro, and in-vivo experiments. In in-vitro and zebrafish models, we showed that, mixtures of the motor oil and food additive 'Salpn' with endogenous nuclear receptor ligands such as Vitamin D3, dysregulated the nuclear receptors and key transcription pathways involved in Colorectal Cancer. Further, in a human patient derived cell organoid model, we found that a mixture of the widely used pesticides 'Tetramethrin' and 'Fenpropathrin' significantly impacts the population of patient derived pancreatic cancer cells and 3D organoid models to support rapid PDAC disease progression. The CPTM method is, to our knowledge, the first comprehensive toxico-physicochemical, and phenotypic bionetwork-based platform for efficient high-throughput screening of environmental chemical toxicity, mechanisms of action, and connection to disease outcomes.

HIDTI: integration of heterogeneous information to predict drug-target interactions

Identification of drug-target interactions (DTIs) plays a crucial role in drug development. Traditional laboratory-based DTI discovery is generally costly and time-consuming. Therefore, computational approaches have been developed to predict interactions between drug candidates and disease-causing proteins. We designed a novel method, termed heterogeneous information integration for DTI prediction (HIDTI), based on the concept of predicting vectors for all of unknown/unavailable heterogeneous drug- and protein-related information. We applied a residual network in HIDTI to extract features of such heterogeneous information for predicting DTIs, and tested the model using drug-based ten-fold cross-validation to examine the prediction performance for unseen drugs. As a result, HIDTI outperformed existing models using heterogeneous information, and was demonstrating that our method predicted heterogeneous information on unseen data better than other models. In conclusion, our study suggests that HIDTI has the potential to advance the field of drug development by accurately predicting the targets of new drugs.

IMCHGAN: Inductive Matrix Completion With Heterogeneous Graph Attention Networks for Drug-Target Interactions Prediction

Identification of targets among known drugs plays an important role in drug repurposing and discovery. Computational approaches for prediction of drug-target interactions (DTIs)are highly desired in comparison to traditional biological experiments as its fast and low price. Moreover, recent advances of systems biology approaches have generated large-scale heterogeneous, biological information networks data, which offer opportunities for machine learning-based identification of DTIs. We present a novel Inductive Matrix Completion with Heterogeneous Graph Attention Network approach (IMCHGAN)for predicting DTIs. IMCHGAN first adopts a two-level neural attention mechanism approach to learn drug and target latent feature representations from the DTI heterogeneous network respectively. Then, the learned latent features are fed into the Inductive Matrix Completion (IMC)prediction score model which computes the best projection from drug space onto target space and output DTI score via the inner product of projected drug and target feature representations. IMCHGAN is an end-to-end neural network learning framework where the parameters of both the prediction score model and the feature representation learning model are simultaneously optimized via backpropagation under supervising of the observed known drug-target interactions data. We compare IMCHGAN with other state-of-the-art baselines on two real DTI experimental datasets. The results show that our method is superior to existing methods in term of AUC and AUPR. Moreover, IMCHGAN also shows it has strong predictive power for novel (unknown)DTIs. All datasets and code can be obtained from https://github.com/ljatynu/IMCHGAN/.

Drug–target interactions prediction via deep collaborative filtering with multiembeddings

Drug–target interactions (DTIs) prediction research presents important significance for promoting the development of modern medicine and pharmacology. Traditional biochemical experiments for DTIs prediction confront the challenges including long time period, high cost and high failure rate, and finally leading to a low-drug productivity. Chemogenomic-based computational methods can realize high-throughput prediction. In this study, we develop a deep collaborative filtering prediction model with multiembeddings, named DCFME (deep collaborative filtering prediction model with multiembeddings), which can jointly utilize multiple feature information from multiembeddings. Two different representation learning algorithms are first employed to extract heterogeneous network features. DCFME uses the generated low-dimensional dense vectors as input, and then simulates the drug–target relationship from the perspective of both couplings and heterogeneity. In addition, the model employs focal loss that concentrates the loss on sparse and hard samples in the training process. Comparative experiments with five baseline methods show that DCFME achieves more significant performance improvement on sparse datasets. Moreover, the model has better robustness and generalization capacity under several harder prediction scenarios.

Integrated molecular response of exposure to traffic-related pollutants in the US trucking industry

Exposure to traffic-related pollutants, including diesel exhaust, is associated with increased risk of cardiopulmonary disease and mortality; however, the precise biochemical pathways underlying these effects are not known. To investigate biological response mechanisms underlying exposure to traffic related pollutants, we used an integrated molecular response approach that included high-resolution metabolomic profiling and peripheral blood gene expression to identify biological responses to diesel exhaust exposure. Plasma samples were collected from 73 non-smoking males employed in the US trucking industry between February 2009 and October 2010, and analyzed using untargeted high-resolution metabolomics to characterize metabolite associations with shift- and week-averaged levels of elemental carbon (EC), organic carbon (OC) and particulate matter with diameter ≤ 2.5 μm (PM2.5). Metabolic associations with EC, OC and PM2.5 were evaluated for biochemical processes known to be associated with disease risk. Annotated metabolites associated with exposure were then tested for relationships with the peripheral blood transcriptome using multivariate selection and network correlation. Week-averaged EC and OC levels, which were averaged across multiple shifts during the workweek, resulted in the greatest exposure-associated metabolic alterations compared to shift-averaged exposure levels. Metabolic changes associated with EC exposure suggest increased lipid peroxidation products, biomarkers of oxidative stress, thrombotic signaling lipids, and metabolites associated with endothelial dysfunction from altered nitric oxide metabolism, while OC exposures were associated with antioxidants, oxidative stress biomarkers and critical intermediates in nitric oxide production. Correlation with whole blood RNA gene expression provided additional evidence of changes in processes related to endothelial function, immune response, inflammation, and oxidative stress. We did not detect metabolic associations with PM2.5. This study provides an integrated molecular assessment of human exposure to traffic-related air pollutants that includes diesel exhaust. Metabolite and transcriptomic changes associated with exposure to EC and OC are consistent with increased risk of cardiovascular diseases and the adverse health effects of traffic-related air pollution.

BGMSDDA: a bipartite graph diffusion algorithm with multiple similarity integration for drug-disease association prediction

Drug repositioning, a method that relies on the information from the original drug-disease association matrix, aims to identify new indications for existing drugs and is expected to greatly reduce the cost and time of drug development. However, most current drug repositioning methods make use of the original drug-disease association matrix directly without preconditioning. As relatively only a few associations between drugs and diseases have been determined from actual observations, the original drug-disease association matrix used in the prediction is sparse, which affects the performance of the prediction method. A method for mining similar features of drugs and diseases is still lacking. To solve these problems, we developed a bipartite graph diffusion algorithm with multiple similarity integration for drug-disease association prediction (BGMSDDA). First, the weight K nearest known neighbors (WKNKN) algorithm was used to reconstruct the drug-disease association matrix. Secondly, an effective method was designed to extract similar characteristics of drugs and diseases based on integrating linear neighborhood similarity and Gaussian kernel similarity. Finally, bipartite graph diffusion was used to infer undiscovered drug-disease associations. After carrying out 10-fold cross-validation experiments, BGMSDDA showed excellent performance on two datasets, specifically with AUC values of 0.939 (Fdataset) and 0.954 (Cdataset), and AUPR values of 0.466 (Fdataset) and 0.565 (Cdataset). Furthermore, to evaluate the accuracy of the results of BGMSDDA, we conducted case studies on three medically used drugs selected from Fdataset and Cdataset and validated the predictive associated diseases of each drug with some databases. Based on the results obtained, BGMSDDA was demonstrated to be useful for predicting drug-disease associations.

Using High-Throughput Screening to Evaluate Perturbations Potentially Linked to Neurobehavioral Outcomes: A Case Study Using Publicly Available Tools on FDA Batch-Certified Synthetic Food Dyes

There is growing evidence from human and animal studies indicating an association between exposure to synthetic food dyes and adverse neurobehavioral outcomes in children. However, data gaps persist for potential mechanisms by which the synthetic food dyes could elicit neurobehavioral impacts. We developed an approach to evaluate seven US FDA-batch-certified food dyes using publicly available high-throughput screening (HTS) data from the US EPA's Toxicity Forecaster to assess potential underlying molecular mechanisms that may be linked to neurological pathway perturbations. The dyes were screened through 270 assays identified based on whether they had a neurological-related gene target and/or were mapped to neurodevelopmental processes or neurobehavioral outcomes, and were conducted in brain tissue, targeted specific hormone receptors, or targeted oxidative stress and inflammation. Some results provided support for neurological impacts found in human and animal studies, while other results showed a lack of correlation with in vivo findings. The azo dyes had a range of activity in assays mapped to G-protein-coupled receptors and were active in assays targeting dopaminergic, serotonergic, and opioid receptors. Assays mapped to nuclear receptors (androgen, estrogen, and thyroid hormone) also exhibited activity with the food dyes. Other molecular targets included the aryl hydrocarbon receptor, acetylcholinesterase, and monoamine oxidase. The Toxicological Prioritization Index tool was used to visualize the results of the Novascreen assays. Our results highlight certain limitations of HTS assays but provide insight into potential underlying mechanisms of neurobehavioral effects observed in in vivo animal toxicology studies and human clinical studies.

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.

Trends in the Application of "Omics" to Ecotoxicology and Stress Ecology

Our ability to predict and assess how environmental changes such as pollution and climate change affect components of the Earth's biome is of paramount importance. This need positioned the fields of ecotoxicology and stress ecology at the center of environmental monitoring efforts. Advances in these interdisciplinary fields depend not only on conceptual leaps but also on technological advances and data integration. High-throughput "omics" technologies enabled the measurement of molecular changes at virtually all levels of an organism's biological organization and thus continue to influence how the impacts of stressors are understood. This bibliometric review describes literature trends (2000-2020) that indicate that more different stressors than species are studied each year but that only a few stressors have been studied in more than two phyla. At the same time, the molecular responses of a diverse set of non-model species have been investigated, but cross-species comparisons are still rare. While transcriptomics studies dominated until 2016, a shift towards proteomics and multiomics studies is apparent. There is now a wealth of data at functional omics levels from many phylogenetically diverse species. This review, therefore, addresses the question of how to integrate omics information across species.

LUNAR :Drug Screening for Novel Coronavirus Based on Representation Learning Graph Convolutional Network

An outbreak of COVID-19 that began in late 2019 was caused by a novel coronavirus(SARS-CoV-2). It has become a global pandemic. As of June 9, 2020, it has infected nearly 7 million people and killed more than 400,000, but there is no specific drug. Therefore, there is an urgent need to find or develop more drugs to suppress the virus. Here, we propose a new nonlinear end-to-end model called LUNAR. It uses graph convolutional neural networks to automatically learn the neighborhood information of complex heterogeneous relational networks and combines the attention mechanism to reflect the importance of the sum of different types of neighborhood information to obtain the representation characteristics of each node. Finally, through the topology reconstruction process, the feature representations of drugs and targets are forcibly extracted to match the observed network as much as possible. Through this reconstruction process, we obtain the strength of the relationship between different nodes and predict drug candidates that may affect the treatment of COVID-19 based on the known targets of COVID-19. These selected candidate drugs can be used as a reference for experimental scientists and accelerate the speed of drug development. LUNAR can well integrate various topological structure information in heterogeneous networks, and skillfully combine attention mechanisms to reflect the importance of neighborhood information of different types of nodes, improving the interpretability of the model. The area under the curve(AUC) of the model is 0.949 and the accurate recall curve (AUPR) is 0.866 using 10-fold cross-validation. These two performance indexes show that the model has superior predictive performance. Besides, some of the drugs screened out by our model have appeared in some clinical studies to further illustrate the effectiveness of the model.

MultiDTI: Drug-target interaction prediction based on multi-modal representation learning to bridge the gap between new chemical entities and known heterogeneous network

MOTIVATION

Predicting new drug-target interactions is an important step in new drug development, understanding of its side effects, and drug repositioning. Heterogeneous data sources can provide comprehensive information and different perspectives for drug-target interaction prediction. Thus, there have been many calculation methods relying on heterogeneous networks. Most of them use graph-related algorithms to characterize nodes in heterogeneous networks for predicting new DTI. However, these methods can only make predictions in known heterogeneous network datasets, and cannot support the prediction of new chemical entities outside the heterogeneous network, which hinder further drug discovery and development.

RESULTS

To solve this problem, we proposed a multi-modal DTI prediction model named 'MultiDTI' which uses our proposed joint learning framework based on heterogeneous networks. It combines the interaction or association information of the heterogeneous network and the drug/target sequence information, and maps the drugs, targets, side effects and disease nodes in the heterogeneous network into a common space. In this way, 'MultiDTI' can map the new chemical entity to this learned common space based on the chemical structure of the new entity. That is, bridging the gap between new chemical entities and known heterogeneous network. Our model has strong predictive performance, and the area under the receiver operating characteristic curve(AUC) of the model is 0.961 and the area under the precision recall curve (AUPRC) is 0.947 with 10-fold cross validation. In addition, some predicted new DTIs have been confirmed by ChEMBL database. Our results indicate that 'MultiDTI' is a powerful and practical tool for predicting new DTI, which can promote the development of drug discovery or drug repositioning.

AVAILABILITY

Python codes and dataset are available at https://github.com/Deshan-Zhou/MultiDTI/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Drug-Drug Interaction Predictions via Knowledge Graph and Text Embedding: Instrument Validation Study

Background

Minimizing adverse reactions caused by drug-drug interactions (DDIs) has always been a prominent research topic in clinical pharmacology. Detecting all possible interactions through clinical studies before a drug is released to the market is a demanding task. The power of big data is opening up new approaches to discovering various DDIs. However, these data contain a huge amount of noise and provide knowledge bases that are far from being complete or used with reliability. Most existing studies focus on predicting binary DDIs between drug pairs and ignore other interactions.

Objective

Leveraging both drug knowledge graphs and biomedical text is a promising pathway for rich and comprehensive DDI prediction, but it is not without issues. Our proposed model seeks to address the following challenges: data noise and incompleteness, data sparsity, and computational complexity.

Methods

We propose a novel framework, Predicting Rich DDI, to predict DDIs. The framework uses graph embedding to overcome data incompleteness and sparsity issues to make multiple DDI label predictions. First, a large-scale drug knowledge graph is generated from different sources. The knowledge graph is then embedded with comprehensive biomedical text into a common low-dimensional space. Finally, the learned embeddings are used to efficiently compute rich DDI information through a link prediction process.

Results

To validate the effectiveness of the proposed framework, extensive experiments were conducted on real-world data sets. The results demonstrate that our model outperforms several state-of-the-art baseline methods in terms of capability and accuracy.

Conclusions

We propose a novel framework, Predicting Rich DDI, to predict DDIs. Using rich DDI information, it can competently predict multiple labels for a pair of drugs across numerous domains, ranging from pharmacological mechanisms to side effects. To the best of our knowledge, this framework is the first to provide a joint translation-based embedding model that learns DDIs by integrating drug knowledge graphs and biomedical text simultaneously in a common low-dimensional space. The model also predicts DDIs using multiple labels rather than single or binary labels. Extensive experiments were conducted on real-world data sets to demonstrate the effectiveness and efficiency of the model. The results show our proposed framework outperforms several state-of-the-art baselines.

Transcriptional drug repositioning and cheminformatics approach for differentiation therapy of leukaemia cells

Differentiation therapy is attracting increasing interest in cancer as it can be more specific than conventional chemotherapy approaches, and it has offered new treatment options for some cancer types, such as treating acute promyelocytic leukaemia (APL) by retinoic acid. However, there is a pressing need to identify additional molecules which act in this way, both in leukaemia and other cancer types. In this work, we hence developed a novel transcriptional drug repositioning approach, based on both bioinformatics and cheminformatics components, that enables selecting such compounds in a more informed manner. We have validated the approach for leukaemia cells, and retrospectively retinoic acid was successfully identified using our method. Prospectively, the anti-parasitic compound fenbendazole was tested in leukaemia cells, and we were able to show that it can induce the differentiation of leukaemia cells to granulocytes in low concentrations of 0.1 μM and within as short a time period as 3 days. This work hence provides a systematic and validated approach for identifying small molecules for differentiation therapy in cancer.

Multiscale Virtual Screening Optimization for Shotgun Drug Repurposing Using the CANDO Platform

Drug repurposing, the practice of utilizing existing drugs for novel clinical indications, has tremendous potential for improving human health outcomes and increasing therapeutic development efficiency. The goal of multi-disease multitarget drug repurposing, also known as shotgun drug repurposing, is to develop platforms that assess the therapeutic potential of each existing drug for every clinical indication. Our Computational Analysis of Novel Drug Opportunities (CANDO) platform for shotgun multitarget repurposing implements several pipelines for the large-scale modeling and simulation of interactions between comprehensive libraries of drugs/compounds and protein structures. In these pipelines, each drug is described by an interaction signature that is compared to all other signatures that are subsequently sorted and ranked based on similarity. Pipelines within the platform are benchmarked based on their ability to recover known drugs for all indications in our library, and predictions are generated based on the hypothesis that (novel) drugs with similar signatures may be repurposed for the same indication(s). The drug-protein interactions used to create the drug-proteome signatures may be determined by any screening or docking method, but the primary approach used thus far has been BANDOCK, our in-house bioanalytical or similarity docking protocol. In this study, we calculated drug-proteome interaction signatures using the publicly available molecular docking method Autodock Vina and created hybrid decision tree pipelines that combined our original bio- and chem-informatic approach with the goal of assessing and benchmarking their drug repurposing capabilities and performance. The hybrid decision tree pipeline outperformed the two docking-based pipelines from which it was synthesized, yielding an average indication accuracy of 13.3% at the top10 cutoff (the most stringent), relative to 10.9% and 7.1% for its constituent pipelines, and a random control accuracy of 2.2%. We demonstrate that docking-based virtual screening pipelines have unique performance characteristics and that the CANDO shotgun repurposing paradigm is not dependent on a specific docking method. Our results also provide further evidence that multiple CANDO pipelines can be synthesized to enhance drug repurposing predictive capability relative to their constituent pipelines. Overall, this study indicates that pipelines consisting of varied docking-based signature generation methods can capture unique and useful signals for accurate comparison of drug-proteome interaction signatures, leading to improvements in the benchmarking and predictive performance of the CANDO shotgun drug repurposing platform.