Drug-target interaction prediction using semi-bipartite graph model and deep learning

BackgroundIn silico drug-target interaction (DTI) prediction plays an integral role in drug repositioning: the discovery of new uses for existing drugs. One popular method of drug repositioning is network-based DTI prediction, which uses complex network theory to predict DTIs from a drug-target network. Currently, most network-based DTI prediction is based on machine learning – methods such as Restricted Boltzmann Machines (RBM) or Support Vector Machines (SVM). These methods require additional information about the characteristics of drugs, targets and DTIs, such as chemical structure, genome sequence, binding types, causes of interactions, etc., and do not perform satisfactorily when such information is unavailable. We propose a new, alternative method for DTI prediction that makes use of only network topology information attempting to solve this problem.ResultsWe compare our method for DTI prediction against the well-known RBM approach. We show that when applied to the MATADOR database, our approach based on node neighborhoods yield higher precision for high-ranking predictions than RBM when no information regarding DTI types is available.ConclusionThis demonstrates that approaches purely based on network topology provide a more suitable approach to DTI prediction in the many real-life situations where little or no prior knowledge is available about the characteristics of drugs, targets, or their interactions.

Drug-target Interactions (DTIs) prediction plays a central role in drug discovery. Computational methods in DTIs prediction have gained more attention because carrying out in vitro and in vivo experiments on a large scale is costly and time-consuming. Machine learning methods, especially deep learning, are widely applied to DTIs prediction. In this study, the main goal is to provide a comprehensive overview of deep learning-based DTIs prediction approaches. Here, we investigate the existing approaches from multiple perspectives. We explore these approaches to find out which deep network architectures are utilized to extract features from drug compound and protein sequences. Also, the advantages and limitations of each architecture are analyzed and compared. Moreover, we explore the process of how to combine descriptors for drug and protein features. Likewise, a list of datasets that are commonly used in DTIs prediction is investigated. Finally, current challenges are discussed and a short future outlook of deep learning in DTI prediction is given.

Prediction of drug-target interactions is an essential step in drug discovery. Given drug-target interactions network, the objective of this task is to predict probable missing edges from known interactions. Computationally predicting drug-target interactions is an appropriate alternative for the time-consuming and costly experimental process of drug-target interaction prediction. A large number of computational methods for solving this problem have been proposed in recent years. In recent years, several review articles have been published in the field of drug-target interactions prediction. Compared to other review articles, this paper includes a qualitative analysis in the form of a framework, a drug-target interactions prediction (DTIP) framework. The framework consists of three sections. Initially, a classification has been presented for drug-target interactions prediction methods based on the link prediction approaches used in these methods. Secondly, general evaluation criteria have been introduced for analyzing approaches. Finally, a qualitative comparison is made between each approach in terms of their advantages and disadvantages. By providing a new classification of the drug-target interactions prediction approaches and comparing them with the proposed evaluation criteria, this framework provides a convenient and efficient way to select and compare the methods. Moreover, using the framework, we can improve these techniques further. This paper provides a study to select, compare, and improve chemogenomic drugtarget interactions prediction methods. To this aim, an analytical framework is presented.

Predicting possible drug-target interactions (DTIs) involves estimating the likelihood that drug molecules would bind to biological targets. By looking into the high cost and risk of in vivo and in vitro experiments, computational methods offer a cost- and time-efficient alternative for predicting DTIs in drug discovery. Many network-based methods have made significant progress in DTI prediction, but they often lack the ability to capture the topological and biological closeness between nodes, which is a crucial paradigm to identify hidden patterns in the DTI network. In this paper, we propose a novel computational-based framework─CAHNetF-DTP (Community Aware Heterogeneous Network-based Framework for Drug-Target interaction Prediction) that leverages a heterogeneous biomedical network comprising 15 distinct types of similarity-based subnetworks derived from drugs, targets, diseases, and side effects. To effectively capture the complex topological and semantic relationships among entities, we employ a community-aware framework that helps to capture local interaction patterns first before moving to another community. The resulting sequences are treated like sentences, enabling Word2Vec to generate embeddings that capture the contextual information on biomedical entities across multiple biological dimensions. To address the class imbalance issue, we incorporate a controlled negative sampling strategy and evaluate the proposed model under five experimental settings. The proposed method is further validated on benchmark data sets (KIBA and DAVIS), in real-world scenarios, and against SAR-based target prediction tools, where CAHNetF-DTP demonstrates robust and competitive performance, outperforming most of the methods. We carried out various case studies to check the model's capability to identify novel drug-target pairs. This work highlights the value of integrating heterogeneous biological data for improved DTI prediction.

BackgroundMost phenotypic effects of drugs are involved in the interactions between drugs and their target proteins, however, our knowledge about the molecular mechanism of the drug-target interactions is very limited. One of challenging issues in recent pharmaceutical science is to identify the underlying molecular features which govern drug-target interactions.ResultsIn this paper, we make a systematic analysis of the correlation between drug side effects and protein domains, which we call "pharmacogenomic features," based on the drug-target interaction network. We detect drug side effects and protein domains that appear jointly in known drug-target interactions, which is made possible by using classifiers with sparse models. It is shown that the inferred pharmacogenomic features can be used for predicting potential drug-target interactions. We also discuss advantages and limitations of the pharmacogenomic features, compared with the chemogenomic features that are the associations between drug chemical substructures and protein domains.ConclusionThe inferred side effect-domain association network is expected to be useful for estimating common drug side effects for different protein families and characteristic drug side effects for specific protein domains.

Computational prediction of drug-target interactions (DTIs) and drug repositioning provides a low-cost and high-efficiency approach for drug discovery and development. The traditional social network-derived methods based on the naïve DTI topology information cannot predict potential targets for new chemical entities or failed drugs in clinical trials. There are currently millions of commercially available molecules with biologically relevant representations in chemical databases. It is urgent to develop novel computational approaches to predict targets for new chemical entities and failed drugs on a large scale. In this study, we developed a useful tool, namely substructure-drug-target network-based inference (SDTNBI), to prioritize potential targets for old drugs, failed drugs and new chemical entities. SDTNBI incorporates network and chemoinformatics to bridge the gap between new chemical entities and known DTI network. High performance was yielded in 10-fold and leave-one-out cross validations using four benchmark data sets, covering G protein-coupled receptors, kinases, ion channels and nuclear receptors. Furthermore, the highest areas under the receiver operating characteristic curve were 0.797 and 0.863 for two external validation sets, respectively. Finally, we identified thousands of new potential DTIs via implementing SDTNBI on a global network. As a proof-of-principle, we showcased the use of SDTNBI to identify novel anticancer indications for nonsteroidal anti-inflammatory drugs by inhibiting AKR1C3, CA9 or CA12. In summary, SDTNBI is a powerful network-based approach that predicts potential targets for new chemical entities on a large scale and will provide a new tool for DTI prediction and drug repositioning. The program and predicted DTIs are available on request.

BackgroundIdentification of drug target interactions (DTI) is an important part of the drug discovery process. Since prediction of DTI using laboratory tests is time consuming and laborious, automated tools using computational intelligence (CI) techniques become essential. The prediction of DTI is a challenging process due to the absence of known drug-target relationship and no experimentally verified negative samples. The datasets with limited or unbalanced data, do not perform well. The models that use heterogeneous networks, non-linear fusion techniques, and heuristic similarity selection may need a lot of computational power and experience to implement and fine-tune. The latest developments in machine learning (ML) and deep learning (DL) models can be employed for effective DTI prediction process.ResultsTo that end, this study develops a novel DTI Prediction model, namely, DTIP-WINDGRU Drug-Target Interaction Prediction with Wind-Enhanced GRU. The major aim is to determine the DTIs in both labelled and unlabelled samples accurately compared to traditional wet lab experiments. To accomplish this, the proposed DTIP-WINDGRU model primarily performs pre-processing and class labelling. In addition, drug-to-drug (D-D) and target-to-target (T-T) interactions are employed to initialize the weights of the GRU model and are employed for the, DTI prediction process. Finally, the Wind Driven Optimization (WDO) algorithm is utilized to optimally choose the hyperparameters involved in the GRU model.ConclusionsFor ensuring the effectual prediction results of the DTIP-WINDGRU model, a widespread experimentation process was carried out using four datasets. This comprehensive comparative study highlighted the better performance of the DTIP-WINDGRU model over existing techniques.

TripletMultiDTI: Multimodal representation learning in drug-target interaction prediction with triplet loss function

DeepACTION: A deep learning-based method for predicting novel drug-target interactions

<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Motivation:</i> The prediction of drug-target interaction (DTI) from heterogeneous biological data is critical to predict drugs and therapeutic targets for known diseases such as tumor and bowel disease. The study of DTI based on drug representation learning can strengthen or integrate our knowledge of pharmacological and chemical phenomena. Therefore, there is a strong motivation to develop effective methods that can detect these potential drug-target interactions. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Results:</i> We have developed a novel Knowledge-Enhanced Multi-View framework (KEMV) to predict unknown DTIs from pharmacological data and chemical data on a large scale. The proposed method consists of two steps: (i) learning more comprehensive drug representations via the proposed multi-view attention mechanism, which bridges pharmacological and chemical information, and interactively summarizes the attention values depending on varying interactions between different pairs of drug features. (ii) predicting unknown drug-target interactions based on the drug and target representations. The method is tested on real-world dataset KEGG with three classes of important drug–target interactions involving enzymes, ion channels, and G-protein-coupled receptors. Our framework is proven to uncover potential DTIs with scientific evidences explaining the mechanism of the interactions through the processing of high-dimensional, heterogeneous, and sparse drug data. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Availability:</i> The originality of the proposed method lies in the attentive integration of pharmacological and chemical information for representation of drug candidate compounds and the prediction of drug-target interaction toward drug discovery in a unified framework. Our results are reproducible and and code is available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/YuanKQ/DTI-Prediction</uri> .

Identification of interaction between drugs and target proteins plays an important role in discovering new drug candidates. However, through the experimental method to identify the drug-target interactions remain to be extremely time-consuming, expensive and challenging even nowadays. Therefore, it is urgent to develop new computational methods to predict potential drugtarget interactions (DTI). In this article, a novel computational model is developed for predicting potential drug-target interactions under the theory that each drug-target interaction pair can be represented by the structural properties from drugs and evolutionary information derived from proteins. Specifically, the protein sequences are encoded as Position-Specific Scoring Matrix (PSSM) descriptor which contains information of biological evolutionary and the drug molecules are encoded as fingerprint feature vector which represents the existence of certain functional groups or fragments. Four benchmark datasets involving enzymes, ion channels, GPCRs and nuclear receptors, are independently used for establishing predictive models with Rotation Forest (RF) model. The proposed method achieved the prediction accuracy of 91.3%, 89.1%, 84.1% and 71.1% for four datasets respectively. In order to make our method more persuasive, we compared our classifier with the state-of-theart Support Vector Machine (SVM) classifier. We also compared the proposed method with other excellent methods. Experimental results demonstrate that the proposed method is effective in the prediction of DTI, and can provide assistance for new drug research and development.

Chemical-genomic and genetic interaction profiling approaches are widely used to study mechanisms of drug action and resistance. However, there exist a number of scoring algorithms customized to different experimental assays, the relative performance of which remains poorly understood, especially with respect to different types of chemogenetic assays. Using yeast Saccharomyces cerevisiae as a test bed, we carried out a systematic evaluation among the main drug target analysis approaches in terms of predicting global drug-target interaction networks. We found drastic differences in their performance across different chemical-genomic assay types, such as those based on heterozygous and homozygous diploid or haploid deletion mutant libraries. Moreover, a relatively small overlap in the predicted targets was observed between those approaches that use either chemical-genomic screening alone or combined with genetic interaction profiling. A rank-based integration of the complementary scoring approaches led to improved overall performance, demonstrating that genetic interaction profiling provides added information on drug target prediction. Optimal performance was achieved when focusing specifically on the negative tail of the genetic interactions, suggesting that combining synthetic lethal interactions with chemical-genetic interactions provides highest information on drug-target interactions. A network view of rapamycin-interacting genes, pathways and complexes was used as an example to demonstrate the benefits of such integrated and optimized analysis of chemogenetic assays in yeast.

Drug-target interactions (DTIs) prediction plays a vital role in drug discovery and design. Current studies typically use only standard drug similarity and target similarity, but the influence of known interactions has not been taken into account. In this paper, we propose an ensembled computational approach called multi-similarity fusion and sparse dual-graph regularized matrix factorization (MSDGRMF) for DTIs prediction. Specifically, different similarities are integrated to mine more useful information from the known interactions. The dual-graph regularized matrix factorization is used to predict the DTIs, in which the manifold learning is used for the low-dimensional representation of the drugs and targets data. In addition, not all the information of drug pairs and target pairs is useful. Thus, the useless information is discarded by sparse process. The proposed MSDGRMF is evaluated and compared on some benchmark datasets. Comparison results show that the MSDGRMF is better than some state-of-the-art approaches. More importantly, the proposed method can contribute to predicting potential DTIs.

Existing deep learning methods have shown outstanding performance in predicting drug-target interactions. However, they still have limitations: (1) the over-reliance on locally extracted features by some single encoders, with insufficient consideration of global features, and (2) the inadequate modeling and learning of local crucial interaction sites in drug-target interaction pairs. In this study, we propose a novel drug-target interaction prediction model called the Neural Fingerprint and Self-Attention Mechanism (NFSA-DTI), which effectively integrates the local information of drug molecules and target sequences with their respective global features. The neural fingerprint method is used in this model to extract global features of drug molecules, while the self-attention mechanism is utilized to enhance CNN's capability in capturing the long-distance dependencies between the subsequences in the target amino acid sequence. In the feature fusion module, we improve the bilinear attention network by incorporating attention pooling, which enhances the model's ability to learn local crucial interaction sites in the drug-target pair. The experimental results on three benchmark datasets demonstrated that NFSA-DTI outperformed all baseline models in predictive performance. Furthermore, case studies illustrated that our model could provide valuable insights for drug discovery. Moreover, our model offers molecular-level interpretations.

The prediction of Drug-Target Interaction (DTI) is an important research direction in bioinformatics as it greatly shortens the development cycle of new drugs. State-of-the-art computational methods for DTI prediction adopt a binary classification framework. The supervision is incomplete, i.e. only a small amount of DTIs are known and treated as positive instances, while the rest are unknown and treated as negative. Two severe problems occur in such a framework: (1) the number of negative samples is overwhelming and (2) a negative label cannot rule out the possibility of a positive drug-target interaction. In this paper, we address the problem of learning from incomplete labels in DTI prediction. The key assumption here is that labels are missing not at random. For example, negative DTI labels are more likely to be missing because biomedical researchers prioritize to study DTIs that are more likely to be positive. We introduce a novel probabilistic model, factorization with non-random missing labels (FNML). It models the generative process for the DTI labels (i.e. the labels are positive or negative) and responses (i.e. the labels are observed or missing). In particular, the probability of observing or missing a label is associated with the sign of the label. In order to further reduce prediction variance and improve prediction accuracy on highly imbalanced DTI datasets, we present FNML-EN, an ensemble scheme which is designed specifically for FNML model. We conduct comprehensive experiments on the latest DTI database, demonstrating the superior and robust performance of the proposed models.