NRLMFβ: Beta-distribution-rescored neighborhood regularized logistic matrix factorization for improving the performance of drug–target interaction prediction

Techniques for predicting interactions between a drug and a target (protein) are useful for strategic drug repositioning. Neighborhood regularized logistic matrix factorization (NRLMF) is one of the state-of-the-art drug–target interaction prediction methods; it is based on a statistical model using the Bernoulli distribution. However, the prediction is not accurate when drug–target interaction pairs have less interaction information (e.g., the sum of the number of ligands for a target and the number of target proteins for a drug). This study aimed to address this issue by proposing NRLMF with beta distribution rescoring (NRLMFβ), which is an algorithm to improve the score of NRLMF. The score of NRLMFβ is equivalent to the value of the original NRLMF score when the concentration of the beta distribution becomes infinity. The beta distribution is known as a conjugative prior distribution of the Bernoulli distribution and can reflect the amount of interaction information to its shape based on Bayesian inference. Therefore, in NRLMFβ, the beta distribution was used for rescoring the NRLMF score. In the evaluation experiment, we measured the average values of area under the receiver operating characteristics and area under precision versus recall and the 95% confidence intervals. The performance of NRLMFβ was found to be better than that of NRLMF in the four types of benchmark datasets. Thus, we concluded that NRLMFβ improved the prediction accuracy of NRLMF. The source code is available at https://github.com/akiyamalab/NRLMFb.     

Drug-target interaction prediction via class imbalance-aware ensemble learning

Background

Multiple computational methods for predicting drug-target interactions have been developed to facilitate the drug discovery process. These methods use available data on known drug-target interactions to train classifiers with the purpose of predicting new undiscovered interactions. However, a key challenge regarding this data that has not yet been addressed by these methods, namely class imbalance, is potentially degrading the prediction performance. Class imbalance can be divided into two sub-problems. Firstly, the number of known interacting drug-target pairs is much smaller than that of non-interacting drug-target pairs. This imbalance ratio between interacting and non-interacting drug-target pairs is referred to as the between-class imbalance. Between-class imbalance degrades prediction performance due to the bias in prediction results towards the majority class (i.e. the non-interacting pairs), leading to more prediction errors in the minority class (i.e. the interacting pairs). Secondly, there are multiple types of drug-target interactions in the data with some types having relatively fewer members (or are less represented) than others. This variation in representation of the different interaction types leads to another kind of imbalance referred to as the within-class imbalance. In within-class imbalance, prediction results are biased towards the better represented interaction types, leading to more prediction errors in the less represented interaction types.

Results

We propose an ensemble learning method that incorporates techniques to address the issues of between-class imbalance and within-class imbalance. Experiments show that the proposed method improves results over 4 state-of-the-art methods. In addition, we simulated cases for new drugs and targets to see how our method would perform in predicting their interactions. New drugs and targets are those for which no prior interactions are known. Our method displayed satisfactory prediction performance and was able to predict many of the interactions successfully.

Conclusions

Our proposed method has improved the prediction performance over the existing work, thus proving the importance of addressing problems pertaining to class imbalance in the data.

     

Predicting Drug-Target Interactions Using Drug-Drug Interactions

Computational methods for predicting drug-target interactions have become important in drug research because they can help to reduce the time, cost, and failure rates for developing new drugs. Recently, with the accumulation of drug-related data sets related to drug side effects and pharmacological data, it has became possible to predict potential drug-target interactions. In this study, we focus on drug-drug interactions (DDI), their adverse effects () and pharmacological information (), and investigate the relationship among chemical structures, side effects, and DDIs from several data sources. In this study, data from the STITCH database, from drugs.com, and drug-target pairs from ChEMBL and SIDER were first collected. Then, by applying two machine learning approaches, a support vector machine (SVM) and a kernel-based L1-norm regularized logistic regression (KL1LR), we showed that DDI is a promising feature in predicting drug-target interactions. Next, the accuracies of predicting drug-target interactions using DDI were compared to those obtained using the chemical structure and side effects based on the SVM and KL1LR approaches, showing that DDI was the data source contributing the most for predicting drug-target interactions.     

Predicting Drug-Target Interactions for New Drug Compounds Using a Weighted Nearest Neighbor Profile

In silico discovery of interactions between drug compounds and target proteins is of core importance for improving the efficiency of the laborious and costly experimental determination of drug-target interaction. Drug-target interaction data are available for many classes of pharmaceutically useful target proteins including enzymes, ion channels, GPCRs and nuclear receptors. However, current drug-target interaction databases contain a small number of drug-target pairs which are experimentally validated interactions. In particular, for some drug compounds (or targets) there is no available interaction. This motivates the need for developing methods that predict interacting pairs with high accuracy also for these ''new'' drug compounds (or targets). We show that a simple weighted nearest neighbor procedure is highly effective for this task. We integrate this procedure into a recent machine learning method for drug-target interaction we developed in previous work. Results of experiments indicate that the resulting method predicts true interactions with high accuracy also for new drug compounds and achieves results comparable or better than those of recent state-of-the-art algorithms. Software is publicly available at http://cs.ru.nl/~tvanlaarhoven/drugtarget2013/.     

Genome-Scale Screening of Drug-Target Associations Relevant to Ki Using a Chemogenomics Approach

The identification of interactions between drugs and target proteins plays a key role in genomic drug discovery. In the present study, the quantitative binding affinities of drug-target pairs are differentiated as a measurement to define whether a drug interacts with a protein or not, and then a chemogenomics framework using an unbiased set of general integrated features and random forest (RF) is employed to construct a predictive model which can accurately classify drug-target pairs. The predictability of the model is further investigated and validated by several independent validation sets. The built model is used to predict drug-target associations, some of which were confirmed by comparing experimental data from public biological resources. A drug-target interaction network with high confidence drug-target pairs was also reconstructed. This network provides further insight for the action of drugs and targets. Finally, a web-based server called PreDPI-K_i was developed to predict drug-target interactions for drug discovery. In addition to providing a high-confidence list of drug-target associations for subsequent experimental investigation guidance, these results also contribute to the understanding of drug-target interactions. We can also see that quantitative information of drug-target associations could greatly promote the development of more accurate models. The PreDPI-K_i server is freely available via: http://sdd.whu.edu.cn/dpiki.     

A computational approach to finding novel targets for existing drugs

Repositioning existing drugs for new therapeutic uses is an efficient approach to drug discovery. We have developed a computational drug repositioning pipeline to perform large-scale molecular docking of small molecule drugs against protein drug targets, in order to map the drug-target interaction space and find novel interactions. Our method emphasizes removing false positive interaction predictions using criteria from known interaction docking, consensus scoring, and specificity. In all, our database contains 252 human protein drug targets that we classify as reliable-for-docking as well as 4621 approved and experimental small molecule drugs from DrugBank. These were cross-docked, then filtered through stringent scoring criteria to select top drug-target interactions. In particular, we used MAPK14 and the kinase inhibitor BIM-8 as examples where our stringent thresholds enriched the predicted drug-target interactions with known interactions up to 20 times compared to standard score thresholds. We validated nilotinib as a potent MAPK14 inhibitor in vitro (IC50 40 nM), suggesting a potential use for this drug in treating inflammatory diseases. The published literature indicated experimental evidence for 31 of the top predicted interactions, highlighting the promising nature of our approach. Novel interactions discovered may lead to the drug being repositioned as a therapeutic treatment for its off-target's associated disease, added insight into the drug's mechanism of action, and added insight into the drug's side effects.     

基于机器学习的药物-靶标相互作用预测*

近年来,随着计算机硬件、软件工具和数据丰度的不断突破,以机器学习为代表的人工智能技术在生物、基础医学和药学等领域的应用不断拓展和融合,极大地推动了这些领域的发展,尤其是药物研发领域的变革。其中,药物-靶标相互作用(drug-target interactions, DTI)的识别是药物研发领域中的重要难题和人工智能技术交叉融合的热门方向,研究人员在DTI预测方面做了大量的工作,构建了许多重要的数据库,开发或拓展了各类机器学习算法和工具软件。对基于机器学习的DTI预测的基本流程进行了介绍,并对利用机器学习预测DTI的研究进行了回顾,同时对不同的机器学习方法运用于DTI预测的优缺点进行了简单总结,以期对开发更加有效的预测算法和DTI预测的发展提供帮助。     

Chemogenomic Approaches for Revealing Drug Target Interactions in Drug Discovery

The drug discovery process has been a crucial and cost-intensive process. This cost is not only monetary but also involves risks, time, and labour that are incurred while introducing a drug in the market. In order to reduce this cost and the risks associated with the drugs that may result in severe side effects, the in silico methods have gained popularity in recent years. These methods have had a significant impact on not only drug discovery but also the related areas such as drug repositioning, drug-target interaction prediction, drug side effect prediction, personalised medicine, etc. Amongst these research areas predicting interactions between drugs and targets forms the basis for drug discovery. The availability of big data in the form of bioinformatics, genetic databases, along with computational methods, have further supported data-driven decision-making. The results obtained through these methods may be further validated using in vitro or in vivo experiments. This validation step can further justify the predictions resulting from in silico approaches, further increasing the accuracy of the overall result in subsequent stages. A variety of approaches are used in predicting drug-target interactions, including ligand-based, molecular docking based and chemogenomic-based approaches. This paper discusses the chemogenomic methods, considering drug target interaction as a classification problem on whether or not an interaction between a particular drug and target would serve as a basis for understanding drug discovery/drug repositioning. We present the advantages and disadvantages associated with their application.     

Predicting drug-target interactions using Lasso with random forest based on evolutionary information and chemical structure

The identification of drug-target interactions has great significance for pharmaceutical scientific research. Since traditional experimental methods identifying drug-target interactions is costly and time-consuming, the use of machine learning methods to predict potential drug-target interactions has attracted widespread attention. This paper presents a novel drug-target interactions prediction method called LRF-DTIs. Firstly, the pseudo-position specific scoring matrix (PsePSSM) and FP2 molecular fingerprinting were used to extract the features of drug-target. Secondly, using Lasso to reduce the dimension of the extracted feature information and then the Synthetic Minority Oversampling Technique (SMOTE) method was used to deal with unbalanced data. Finally, the processed feature vectors were input into a random forest (RF) classifier to predict drug-target interactions. Through 10 trials of 5-fold cross-validation, the overall prediction accuracies on the enzyme, ion channel (IC), G-protein-coupled receptor (GPCR) and nuclear receptor (NR) datasets reached 98.09%, 97.32%, 95.69%, and 94.88%, respectively, and compared with other prediction methods. In addition, we have tested and verified that our method not only could be applied to predict the new interactions but also could obtain a satisfactory result on the new dataset. All the experimental results indicate that our method can significantly improve the prediction accuracy of drug-target interactions and play a vital role in the new drug research and target protein development. The source code and all datasets are available at https://github.com/QUST-AIBBDRC/LRF-DTIs/ for academic use.     

A unified solution for different scenarios of predicting drug-target interactions via triple matrix factorization

Background

During the identification of potential candidates, computational prediction of drug-target interactions (DTIs) is important to subsequent expensive validation in wet-lab. DTI screening considers four scenarios, depending on whether the drug is an existing or a new drug and whether the target is an existing or a new target. However, existing approaches have the following limitations. First, only a few of them can address the most difficult scenario (i.e., predicting interactions between new drugs and new targets). More importantly, none of the existing approaches could provide the explicit information for understanding the mechanism of forming interactions, such as the drug-target feature pairs contributing to the interactions.

Results

In this paper, we propose a Triple Matrix Factorization-based model (TMF) to tackle these problems. Compared with former state-of-the-art predictive methods, TMF demonstrates its significant superiority by assessing the predictions on four benchmark datasets over four kinds of screening scenarios. Also, it exhibits its outperformance by validating predicted novel interactions. More importantly, by using PubChem fingerprints of chemical structures as drug features and occurring frequencies of amino acid trimer as protein features, TMF shows its ability to find out the features determining interactions, including dominant feature pairs, frequently occurring substructures, and conserved triplet of amino acids.

Conclusions

Our TMF provides a unified framework of DTI prediction for all the screening scenarios. It also presents a new insight for the underlying mechanism of DTIs by indicating dominant features, which play important roles in the forming of DTI.

     

Prediction of drug-target interactions and drug repositioning via network-based inference

Drug-target interaction (DTI) is the basis of drug discovery and design. It is time consuming and costly to determine DTI experimentally. Hence, it is necessary to develop computational methods for the prediction of potential DTI. Based on complex network theory, three supervised inference methods were developed here to predict DTI and used for drug repositioning, namely drug-based similarity inference (DBSI), target-based similarity inference (TBSI) and network-based inference (NBI). Among them, NBI performed best on four benchmark data sets. Then a drug-target network was created with NBI based on 12,483 FDA-approved and experimental drug-target binary links, and some new DTIs were further predicted. In vitro assays confirmed that five old drugs, namely montelukast, diclofenac, simvastatin, ketoconazole, and itraconazole, showed polypharmacological features on estrogen receptors or dipeptidyl peptidase-IV with half maximal inhibitory or effective concentration ranged from 0.2 to 10 μM. Moreover, simvastatin and ketoconazole showed potent antiproliferative activities on human MDA-MB-231 breast cancer cell line in MTT assays. The results indicated that these methods could be powerful tools in prediction of DTIs and drug repositioning.     

Prediction of chemical-protein interactions network with weighted network-based inference method

Chemical-protein interaction (CPI) is the central topic of target identification and drug discovery. However, large scale determination of CPI is a big challenge for in vitro or in vivo experiments, while in silico prediction shows great advantages due to low cost and high accuracy. On the basis of our previous drug-target interaction prediction via network-based inference (NBI) method, we further developed node- and edge-weighted NBI methods for CPI prediction here. Two comprehensive CPI bipartite networks extracted from ChEMBL database were used to evaluate the methods, one containing 17,111 CPI pairs between 4,741 compounds and 97 G protein-coupled receptors, the other including 13,648 CPI pairs between 2,827 compounds and 206 kinases. The range of the area under receiver operating characteristic curves was 0.73 to 0.83 for the external validation sets, which confirmed the reliability of the prediction. The weak-interaction hypothesis in CPI network was identified by the edge-weighted NBI method. Moreover, to validate the methods, several candidate targets were predicted for five approved drugs, namely imatinib, dasatinib, sertindole, olanzapine and ziprasidone. The molecular hypotheses and experimental evidence for these predictions were further provided. These results confirmed that our methods have potential values in understanding molecular basis of drug polypharmacology and would be helpful for drug repositioning.     

A systematic prediction of multiple drug-target interactions from chemical, genomic, and pharmacological data

In silico prediction of drug-target interactions from heterogeneous biological data can advance our system-level search for drug molecules and therapeutic targets, which efforts have not yet reached full fruition. In this work, we report a systematic approach that efficiently integrates the chemical, genomic, and pharmacological information for drug targeting and discovery on a large scale, based on two powerful methods of Random Forest (RF) and Support Vector Machine (SVM). The performance of the derived models was evaluated and verified with internally five-fold cross-validation and four external independent validations. The optimal models show impressive performance of prediction for drug-target interactions, with a concordance of 82.83%, a sensitivity of 81.33%, and a specificity of 93.62%, respectively. The consistence of the performances of the RF and SVM models demonstrates the reliability and robustness of the obtained models. In addition, the validated models were employed to systematically predict known/unknown drugs and targets involving the enzymes, ion channels, GPCRs, and nuclear receptors, which can be further mapped to functional ontologies such as target-disease associations and target-target interaction networks. This approach is expected to help fill the existing gap between chemical genomics and network pharmacology and thus accelerate the drug discovery processes.     

Graph neural network approaches for drug-target interactions

Developing new drugs remains prohibitively expensive, time-consuming, and often involves safety issues. Accurate prediction of drug-target interactions (DTIs) can guide the drug discovery process and thus facilitate drug development. Non-Euclidian data such as drug-like molecule structures, key pocket residue structures, and protein interaction networks can be represented effectively using graphs. Therefore, the emerging graph neural network has been rapidly applied to predict DTIs, and proved effective in finding repositioning drugs and accelerating drug discovery. In this review, we provide a brief overview of deep neural networks used in DTI models. Then, we summarize the database required for DTI prediction, followed by a comprehensive introduction of applications of graph neural networks for DTI prediction. We also highlight current challenges and future directions to guide the further development of this field.     

Mining significant substructure pairs for interpreting polypharmacology in drug-target network

A current key feature in drug-target network is that drugs often bind to multiple targets, known as polypharmacology or drug promiscuity. Recent literature has indicated that relatively small fragments in both drugs and targets are crucial in forming polypharmacology. We hypothesize that principles behind polypharmacology are embedded in paired fragments in molecular graphs and amino acid sequences of drug-target interactions. We developed a fast, scalable algorithm for mining significantly co-occurring subgraph-subsequence pairs from drug-target interactions. A noteworthy feature of our approach is to capture significant paired patterns of subgraph-subsequence, while patterns of either drugs or targets only have been considered in the literature so far. Significant substructure pairs allow the grouping of drug-target interactions into clusters, covering approximately 75% of interactions containing approved drugs. These clusters were highly exclusive to each other, being statistically significant and logically implying that each cluster corresponds to a distinguished type of polypharmacology. These exclusive clusters cannot be easily obtained by using either drug or target information only but are naturally found by highlighting significant substructure pairs in drug-target interactions. These results confirm the effectiveness of our method for interpreting polypharmacology in drug-target network.     

Drug-target interaction prediction by random walk on the heterogeneous network

Predicting potential drug-target interactions from heterogeneous biological data is critical not only for better understanding of the various interactions and biological processes, but also for the development of novel drugs and the improvement of human medicines. In this paper, the method of Network-based Random Walk with Restart on the Heterogeneous network (NRWRH) is developed to predict potential drug-target interactions on a large scale under the hypothesis that similar drugs often target similar target proteins and the framework of Random Walk. Compared with traditional supervised or semi-supervised methods, NRWRH makes full use of the tool of the network for data integration to predict drug-target associations. It integrates three different networks (protein-protein similarity network, drug-drug similarity network, and known drug-target interaction networks) into a heterogeneous network by known drug-target interactions and implements the random walk on this heterogeneous network. When applied to four classes of important drug-target interactions including enzymes, ion channels, GPCRs and nuclear receptors, NRWRH significantly improves previous methods in terms of cross-validation and potential drug-target interaction prediction. Excellent performance enables us to suggest a number of new potential drug-target interactions for drug development.     

Predicting new molecular targets for rhein using network pharmacology

Background

Drugs can influence the whole biological system by targeting interaction reactions. The existence of interactions between drugs and network reactions suggests a potential way to discover targets. The in silico prediction of potential interactions between drugs and target proteins is of core importance for the identification of new drugs or novel targets for existing drugs. However, only a tiny portion of drug-targets in current datasets are validated interactions. This motivates the need for developing computational methods that predict true interaction pairs with high accuracy. Currently, network pharmacology has used in identifying potential drug targets to predicting the spread of drug activity and greatly contributed toward the analysis of biological systems on a much larger scale than ever before.

Methods

In this article, we present a computational method to predict targets for rhein by exploring drug-reaction interactions. We have implemented a computational platform that integrates pathway, protein-protein interaction, differentially expressed genome and literature mining data to result in comprehensive networks for drug-target interaction. We used Cytoscape software for prediction rhein-target interactions, to facilitate the drug discovery pipeline.

Results

Results showed that 3 differentially expressed genes confirmed by Cytoscape as the central nodes of the complicated interaction network (99 nodes, 153 edges). Of note, we further observed that the identified targets were found to encompass a variety of biological processes related to immunity, cellular apoptosis, transport, signal transduction, cell growth and proliferation and metabolism.

Conclusions

Our findings demonstrate that network pharmacology can not only speed the wide identification of drug targets but also find new applications for the existing drugs. It also implies the significant contribution of network pharmacology to predict drug targets.     

Determining the mode of action of bioactive compounds

Matching bioactive molecules with molecular targets is key to understanding their modes of action (MOA). Moving beyond the mere discovery of drugs, investigators are now just beginning to integrate both biochemical and chemical-genetic approaches for MOA studies. Beginning with simple screens for changes in cell phenotype upon drug treatment, drug bioactivity has been traditionally explored with affinity chromatography, radiolabeling, and cell-based affinity tagging procedures. However, such approaches can present an oversimplified view of MOA, especially in light of the recent realization of the extent of polypharmacology and the unexpected complexity of drug-target interactions. With the advent of more sophisticated tools for genetic manipulation, a flood of powerful techniques has been used to create characteristic drug MOA 'fingerprints'. In particular, whole genome expression profiling and deletion and overexpression libraries have greatly enhanced our understanding of bioactive compounds in vivo. Here we highlight challenges and advances in studying bioactive compound-target interactions.     

Prediction of Drug-Target Interactions for Drug Repositioning Only Based on Genomic Expression Similarity

Small drug molecules usually bind to multiple protein targets or even unintended off-targets. Such drug promiscuity has often led to unwanted or unexplained drug reactions, resulting in side effects or drug repositioning opportunities. So it is always an important issue in pharmacology to identify potential drug-target interactions (DTI). However, DTI discovery by experiment remains a challenging task, due to high expense of time and resources. Many computational methods are therefore developed to predict DTI with high throughput biological and clinical data. Here, we initiatively demonstrate that the on-target and off-target effects could be characterized by drug-induced in vitro genomic expression changes, e.g. the data in Connectivity Map (CMap). Thus, unknown ligands of a certain target can be found from the compounds showing high gene-expression similarity to the known ligands. Then to clarify the detailed practice of CMap based DTI prediction, we objectively evaluate how well each target is characterized by CMap. The results suggest that (1) some targets are better characterized than others, so the prediction models specific to these well characterized targets would be more accurate and reliable; (2) in some cases, a family of ligands for the same target tend to interact with common off-targets, which may help increase the efficiency of DTI discovery and explain the mechanisms of complicated drug actions. In the present study, CMap expression similarity is proposed as a novel indicator of drug-target interactions. The detailed strategies of improving data quality by decreasing the batch effect and building prediction models are also effectively established. We believe the success in CMap can be further translated into other public and commercial data of genomic expression, thus increasing research productivity towards valid drug repositioning and minimal side effects.