Efficient machine learning model for predicting drug-target interactions with case study for Covid-19

BackgroundDiscover possible Drug Target Interactions (DTIs) is a decisive step in the detection of the effects of drugs as well as drug repositioning. There is a strong incentive to develop effective computational methods that can effectively predict potential DTIs, as traditional DTI laboratory experiments are expensive, time-consuming, and labor-intensive. Some technologies have been developed for this purpose, however large numbers of interactions have not yet been detected, the accuracy of their prediction still low, and protein sequences and structured data are rarely used together in the prediction process.MethodsThis paper presents DTIs prediction model that takes advantage of the special capacity of the structured form of proteins and drugs. Our model obtains features from protein amino-acid sequences using physical and chemical properties, and from drugs smiles (Simplified Molecular Input Line Entry System) strings using encoding techniques. Comparing the proposed model with different existing methods under K-fold cross validation, empirical results show that our model based on ensemble learning algorithms for DTI prediction provide more accurate results from both structures and features data.ResultsThe proposed model is applied on two datasets:Benchmark (feature only) datasets and DrugBank (Structure data) datasets. Experimental results obtained by Light-Boost and ExtraTree using structures and feature data results in 98 % accuracy and 0.97 f-score comparing to 94 % and 0.92 achieved by the existing methods. Moreover, our model can successfully predict more yet undiscovered interactions, and hence can be used as a practical tool to drug repositioning.A case study of applying our prediction model on the proteins that are known to be affected by Corona viruses in order to predict the possible interactions among these proteins and existing drugs is performed. Also, our model is applied on Covid-19 related drugs announced on DrugBank. The results show that some drugs like DB00691 and DB05203 are predicted with 100 % accuracy to interact with ACE2 protein. This protein is a self-membrane protein that enables Covid-19 infection. Hence, our model can be used as an effective tool in drug reposition to predict possible drug treatments for Covid-19.     

Drug–target interaction prediction by integrating multiview network data

Drug–target interaction (DTI) prediction is a challenging step in further drug repositioning, drug discovery and drug design. The advent of high-throughput technologies brings convenience to the development of DTI prediction methods. With the generation of a high number of data sets, many mathematical models and computational algorithms have been developed to identify the potential drug–target pairs. However, most existing methods are proposed based on the single view data. By integrating the drug and target data from different views, we aim to get more stable and accurate prediction results.In this paper, a multiview DTI prediction method based on clustering is proposed. We first introduce a model for single view drug–target data. The model is formulated as an optimization problem, which aims to identify the clusters in both drug similarity network and target protein similarity network, and at the same time make the clusters with more known DTIs be connected together. Then the model is extended to multiview network data by maximizing the consistency of the clusters in each view. An approximation method is proposed to solve the optimization problem. We apply the proposed algorithms to two views of data. Comparisons with some existing algorithms show that the multiview DTI prediction algorithm can produce more accurate predictions. For the considered data set, we finally predict 54 possible DTIs. From the similarity analysis of the drugs/targets, enrichment analysis of DTIs and genes in each cluster, it is shown that the predicted DTIs have a high possibility to be true.     

Predictive Model for Drug-Induced Liver Injury Using Deep Neural Networks Based on Substructure Space

Drug-induced liver injury (DILI) is a major concern for drug developers, regulators, and clinicians. However, there is no adequate model system to assess drug-associated DILI risk in humans. In the big data era, computational models are expected to play a revolutionary role in this field. This study aimed to develop a deep neural network (DNN)-based model using extended connectivity fingerprints of diameter 4 (ECFP4) to predict DILI risk. Each data set for the predictive model was retrieved and curated from DILIrank, LiverTox, and other literature. The best model was constructed through ten iterations of stratified 10-fold cross-validation, and the applicability domain was defined based on integer ECFP4 bits of the training set which represented substructures. For the robustness test, we employed the concept of the endurance level. The best model showed an accuracy of 0.731, a sensitivity of 0.714, and a specificity of 0.750 on the validation data set in the complete applicability domain. The model was further evaluated with four external data sets and attained an accuracy of 0.867 on 15 drugs with DILI cases reported since 2019. Overall, the results suggested that the ECFP4-based DNN model represents a new tool to identify DILI risk for the evaluation of drug safety.     

Identification of SARS-CoV-2 Papain-like Protease (PLpro) Inhibitors Using Combined Computational Approach**

In the current pandemic, finding an effective drug to prevent or treat the infection is the highest priority. A rapid and safe approach to counteract COVID-19 is in silico drug repurposing. The SARS-CoV-2 PLpro promotes viral replication and modulates the host immune system, resulting in inhibition of the host antiviral innate immune response, and therefore is an attractive drug target. In this study, we used a combined in silico virtual screening for candidates for SARS-CoV-2 PLpro protease inhibitors. We used the Informational spectrum method applied for Small Molecules for searching the Drugbank database followed by molecular docking. After in silico screening of drug space, we identified 44 drugs as potential SARS-CoV-2 PLpro inhibitors that we propose for further experimental testing.     

TargetNet: a web service for predicting potential drug–target interaction profiling via multi-target SAR models

Drug–target interactions (DTIs) are central to current drug discovery processes and public health fields. Analyzing the DTI profiling of the drugs helps to infer drug indications, adverse drug reactions, drug–drug interactions, and drug mode of actions. Therefore, it is of high importance to reliably and fast predict DTI profiling of the drugs on a genome-scale level. Here, we develop the TargetNet server, which can make real-time DTI predictions based only on molecular structures, following the spirit of multi-target SAR methodology. Naïve Bayes models together with various molecular fingerprints were employed to construct prediction models. Ensemble learning from these fingerprints was also provided to improve the prediction ability. When the user submits a molecule, the server will predict the activity of the user’s molecule across 623 human proteins by the established high quality SAR model, thus generating a DTI profiling that can be used as a feature vector of chemicals for wide applications. The 623 SAR models related to 623 human proteins were strictly evaluated and validated by several model validation strategies, resulting in the AUC scores of 75–100 %. We applied the generated DTI profiling to successfully predict potential targets, toxicity classification, drug–drug interactions, and drug mode of action, which sufficiently demonstrated the wide application value of the potential DTI profiling. The TargetNet webserver is designed based on the Django framework in Python, and is freely accessible at http://targetnet.scbdd.com.     

Exploring the relationship between hub proteins and drug targets based on GO and intrinsic disorder

Protein–protein interactions (PPIs) play essential roles in many biological processes. In protein–protein interaction networks, hubs involve in numbers of PPIs and may constitute an important source of drug targets. The intrinsic disorder proteins (IDPs) with unstable structures can promote the promiscuity of hubs and also involve in many disease pathways, so they also could serve as potential drug targets. Moreover, proteins with similar functions measured by semantic similarity of gene ontology (GO) terms tend to interact with each other. Here, the relationship between hub proteins and drug targets based on GO terms and intrinsic disorder was explored. The semantic similarities of GO terms and genes between two proteins, and the rate of intrinsic disorder residues of each protein were extracted as features to characterize the functional similarity between two interacting proteins. Only using 8 feature variables, prediction models by support vector machine (SVM) were constructed to predict PPIs. The accuracy of the model on the PPI data from human hub proteins is as high as 83.72%, which is very promising compared with other PPI prediction models with hundreds or even thousands of features. Then, 118 of 142 PPIs between hubs are correctly predicted that the two interacting proteins are targets of the same drugs. The results indicate that only 8 functional features are fully efficient for representing PPIs. In order to identify new targets from IDP dataset, the PPIs between hubs and IDPs are predicted by the SVM model and the model yields a prediction accuracy of 75.84%. Further research proves that 3 of 5 PPIs between hubs and IDPs are correctly predicted that the two interacting proteins are targets of the same drugs. All results demonstrate that the model with only 8-dimensional features from GO terms and intrinsic disorder still gives a good performance in predicting PPIs and further identifying drug targets.     

Atomistic De-novo Inhibitor Generation-Guided Drug Repurposing for SARS-CoV-2 Spike Protein with Free-Energy Validation by Well-Tempered Metadynamics

Computational drug design is increasingly becoming important with new and unforeseen diseases like COVID-19. In this study, we present a new computational de novo drug design and repurposing method and applied it to find plausible drug candidates for the receptor binding domain (RBD) of SARS-CoV-2 (COVID-19). Our study comprises three steps: atom-by-atom generation of new molecules around a receptor, structural similarity mapping to existing approved and investigational drugs, and validation of their binding strengths to the viral spike proteins based on rigorous all-atom, explicit-water well-tempered metadynamics free energy calculations. By choosing the receptor binding domain of the viral spike protein, we showed that some of our new molecules and some of the repurposable drugs have stronger binding to RBD than hACE2. To validate our approach, we also calculated the free energy of hACE2 and RBD, and found it to be in an excellent agreement with experiments. These pool of drugs will allow strategic repurposing against COVID-19 for a particular prevailing conditions.     

Computational Drug Repurposing Based on a Recommendation System and Drug–Drug Functional Pathway Similarity

Drug repurposing identifies new clinical indications for existing drugs. It can be used to overcome common problems associated with cancers, such as heterogeneity and resistance to established therapies, by rapidly adapting known drugs for new treatment. In this study, we utilized a recommendation system learning model to prioritize candidate cancer drugs. We designed a drug–drug pathway functional similarity by integrating multiple genetic and epigenetic alterations such as gene expression, copy number variation (CNV), and DNA methylation. When compared with other similarities, such as SMILES chemical structures and drug targets based on the protein–protein interaction network, our approach provided better interpretable models capturing drug response mechanisms. Furthermore, our approach can achieve comparable accuracy when evaluated with other learning models based on large public datasets (CCLE and GDSC). A case study about the Erlotinib and OSI-906 (Linsitinib) indicated that they have a synergistic effect to reduce the growth rate of tumors, which is an alternative targeted therapy option for patients. Taken together, our computational method characterized drug response from the viewpoint of a multi-omics pathway and systematically predicted candidate cancer drugs with similar therapeutic effects.     

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.     

Exploring polypharmacology using a ROCS-based target fishing approach

Polypharmacology has emerged as a new theme in drug discovery. In this paper, we studied polypharmacology using a ligand-based target fishing (LBTF) protocol. To implement the protocol, we first generated a chemogenomic database that links individual protein targets with a specified set of drugs or target representatives. Target profiles were then generated for a given query molecule by computing maximal shape/chemistry overlap between the query molecule and the drug sets assigned to each protein target. The overlap was computed using the program ROCS (Rapid Overlay of Chemical Structures). We validated this approach using the Directory of Useful Decoys (DUD). DUD contains 2950 active compounds, each with 36 property-matched decoys, against 40 protein targets. We chose a set of known drugs to represent each DUD target, and we carried out ligand-based virtual screens using data sets of DUD actives seeded into DUD decoys for each target. We computed Receiver Operator Characteristic (ROC) curves and associated area under the curve (AUC) values. For the majority of targets studied, the AUC values were significantly better than for the case of a random selection of compounds. In a second test, the method successfully identified off-targets for drugs such as rimantadine, propranolol, and domperidone that were consistent with those identified by recent experiments. The results from our ROCS-based target fishing approach are promising and have potential application in drug repurposing for single and multiple targets, identifying targets for orphan compounds, and adverse effect prediction.     

In Vitro Confirmation of Siramesine as a Novel Antifungal Agent with In Silico Lead Proposals of Structurally Related Antifungals

The limited number of medicinal products available to treat of fungal infections makes control of fungal pathogens problematic, especially since the number of fungal resistance incidents increases. Given the high costs and slow development of new antifungal treatment options, repurposing of already known compounds is one of the proposed strategies. The objective of this study was to perform in vitro experimental tests of already identified lead compounds in our previous in silico drug repurposing study, which had been conducted on the known Drugbank database using a seven-step procedure which includes machine learning and molecular docking. This study identifies siramesine as a novel antifungal agent. This novel indication was confirmed through in vitro testing using several yeast species and one mold. The results showed susceptibility of Candida species to siramesine with MIC at concentration 12.5 µg/mL, whereas other candidates had no antifungal activity. Siramesine was also effective against in vitro biofilm formation and already formed biofilm was reduced following 24 h treatment with a MBEC range of 50–62.5 µg/mL. Siramesine is involved in modulation of ergosterol biosynthesis in vitro, which indicates it is a potential target for its antifungal activity. This implicates the possibility of siramesine repurposing, especially since there are already published data about nontoxicity. Following our in vitro results, we provide additional in depth in silico analysis of siramesine and compounds structurally similar to siramesine, providing an extended lead set for further preclinical and clinical investigation, which is needed to clearly define molecular targets and to elucidate its in vivo effectiveness as well.     

Identification of Potential Parkinson’s Disease Drugs Based on Multi-Source Data Fusion and Convolutional Neural Network

Parkinson’s disease (PD) is a serious neurodegenerative disease. Most of the current treatment can only alleviate symptoms, but not stop the progress of the disease. Therefore, it is crucial to find medicines to completely cure PD. Finding new indications of existing drugs through drug repositioning can not only reduce risk and cost, but also improve research and development efficiently. A drug repurposing method was proposed to identify potential Parkinson’s disease-related drugs based on multi-source data integration and convolutional neural network. Multi-source data were used to construct similarity networks, and topology information were utilized to characterize drugs and PD-associated proteins. Then, diffusion component analysis method was employed to reduce the feature dimension. Finally, a convolutional neural network model was constructed to identify potential associations between existing drugs and LProts (PD-associated proteins). Based on 10-fold cross-validation, the developed method achieved an accuracy of 91.57%, specificity of 87.24%, sensitivity of 95.27%, Matthews correlation coefficient of 0.8304, area under the receiver operating characteristic curve of 0.9731 and area under the precision–recall curve of 0.9727, respectively. Compared with the state-of-the-art approaches, the current method demonstrates superiority in some aspects, such as sensitivity, accuracy, robustness, etc. In addition, some of the predicted potential PD therapeutics through molecular docking further proved that they can exert their efficacy by acting on the known targets of PD, and may be potential PD therapeutic drugs for further experimental research. It is anticipated that the current method may be considered as a powerful tool for drug repurposing and pathological mechanism studies.