In light of increased co-prescription of multiple drugs, the ability to discern and predict drug-drug interactions (DDI) has become crucial to guarantee the safety of patients undergoing treatment with multiple drugs. However, information on DDI profiles is incomplete and the experimental determination of DDIs is labor-intensive and time-consuming. Although previous studies have explored various feature spaces for in silico screening of interacting drug pairs, their use of conventional cross-validation prevents them from achieving generalizable performance on drug pairs where neither drug is seen during training. Here we demonstrate for the first time targets of adversely interacting drug pairs are significantly more likely to have synergistic genetic interactions than non-interacting drug pairs. Leveraging genetic interaction features and a novel training scheme, we construct a gradient boosting-based classifier that achieves robust DDI prediction even for drugs whose interaction profiles are completely unseen during training. We demonstrate that in addition to classification power-including the prediction of 432 novel DDIs-our genetic interaction approach offers interpretability by providing plausible mechanistic insights into the mode of action of DDIs.

Adverse drug effects (ADEs) are one of the leading causes of death in developed countries and are the main reason for drug recalls from the market, whereas the ADEs that are associated with action on the cardiovascular system are the most dangerous and widespread. The treatment of human diseases often requires the intake of several drugs, which can lead to undesirable drug-drug interactions (DDIs), thus causing an increase in the frequency and severity of ADEs. An evaluation of DDI-induced ADEs is a nontrivial task and requires numerous experimental and clinical studies. Therefore, we developed a computational approach to assess the cardiovascular ADEs of DDIs. This approach is based on the combined analysis of spontaneous reports (SRs) and predicted drug-target interactions to estimate the five cardiovascular ADEs that are induced by DDIs, namely, myocardial infarction, ischemic stroke, ventricular tachycardia, cardiac failure, and arterial hypertension. We applied a method based on least absolute shrinkage and selection operator (LASSO) logistic regression to SRs for the identification of interacting pairs of drugs causing corresponding ADEs, as well as noninteracting pairs of drugs. As a result, five datasets containing, on average, 3100 potentially ADE-causing and non-ADE-causing drug pairs were created. The obtained data, along with information on the interaction of drugs with 1553 human targets predicted by PASS Targets software, were used to create five classification models using the Random Forest method. The average area under the ROC curve of the obtained models, sensitivity, specificity and balanced accuracy were 0.837, 0.764, 0.754 and 0.759, respectively. The predicted drug targets were also used to hypothesize the potential mechanisms of DDI-induced ventricular tachycardia for the top-scoring drug pairs. The created five classification models can be used for the identification of drug combinations that are potentially the most or least dangerous for the cardiovascular system.

Identifying drug-drug interactions (DDIs) is a major challenge in drug development. Previous attempts have established formal approaches for pharmacokinetic (PK) DDIs, but there is not a feasible solution for pharmacodynamic (PD) DDIs because the endpoint is often a serious adverse event rather than a measurable change in drug concentration. Here, we developed a metric "S-score" that measures the strength of network connection between drug targets to predict PD DDIs. Utilizing known PD DDIs as golden standard positives (GSPs), we observed a significant correlation between S-score and the likelihood a PD DDI occurs. Our prediction was robust and surpassed existing methods as validated by two independent GSPs. Analysis of clinical side effect data suggested that the drugs having predicted DDIs have similar side effects. We further incorporated this clinical side effects evidence with S-score to increase the prediction specificity and sensitivity through a Bayesian probabilistic model. We have predicted 9,626 potential PD DDIs at the accuracy of 82% and the recall of 62%. Importantly, our algorithm provided opportunities for better understanding the potential molecular mechanisms or physiological effects underlying DDIs, as illustrated by the case studies.

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.

Recent research has demonstrated that consumption of food -especially fruits and vegetables- can alter the effects of drugs by interfering either with their pharmacokinetic or pharmacodynamic processes. Despite the recognition of such drug-food associations as an important element for successful therapeutic interventions, a systematic approach for identifying, predicting and preventing potential interactions between food and marketed or novel drugs is not yet available. The overall objective of this work was to sketch a comprehensive picture of the interference of ∼ 4,000 dietary components present in ∼1800 plant-based foods with the pharmacokinetics and pharmacodynamics processes of medicine, with the purpose of elucidating the molecular mechanisms involved. By employing a systems chemical biology approach that integrates data from the scientific literature and online databases, we gained a global view of the associations between diet and dietary molecules with drug targets, metabolic enzymes, drug transporters and carriers currently deposited in DrugBank. Moreover, we identified disease areas and drug targets that are most prone to the negative effects of drug-food interactions, showcasing a platform for making recommendations in relation to foods that should be avoided under certain medications. Lastly, by investigating the correlation of gene expression signatures of foods and drugs we were able to generate a completely novel drug-diet interactome map.

Characterizing interactions between drugs is important to avoid potentially harmful combinations, to reduce off-target effects of treatments and to fight antibiotic resistant pathogens, among others. Here we present a network inference algorithm to predict uncharacterized drug-drug interactions. Our algorithm takes, as its only input, sets of previously reported interactions, and does not require any pharmacological or biochemical information about the drugs, their targets or their mechanisms of action. Because the models we use are abstract, our approach can deal with adverse interactions, synergistic/antagonistic/suppressing interactions, or any other type of drug interaction. We show that our method is able to accurately predict interactions, both in exhaustive pairwise interaction data between small sets of drugs, and in large-scale databases. We also demonstrate that our algorithm can be used efficiently to discover interactions of new drugs as part of the drug discovery process.

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.

The physiochemical determinants of drug-target interactions in the microenvironment of the cell are complex and generally not defined by simple diffusion and intrinsic chemical reactivity. Non-specific interactions of drugs and macromolecules in cells are rarely considered formally in assessing pharmacodynamics. Here, we demonstrate that non-specific interactions lead to very slow incorporation kinetics of DNA binding drugs. We observe a rate of drug incorporation in cell nuclei three orders of magnitude slower than in vitro due to anomalous drug diffusion within cells. This slow diffusion, however, has an advantageous consequence: it leads to virtually irreversible binding of the drug to specific DNA targets in cells. We show that non-specific interactions drive slow drug diffusion manifesting as slow reaction front propagation. We study the effect of non-specific interactions in different cellular compartments by permeabilization of plasma and nuclear membranes in order to pinpoint differential compartment effects on variability in intracellular drug kinetics. These results provide the basis for a comprehensive model of the determinants of intracellular diffusion of small-molecule drugs, their target-seeking trajectories, and the consequences of these processes on the apparent kinetics of drug-target interactions.

The adaptive landscape analogy has found practical use in recent years, as many have explored how their understanding can inform therapeutic strategies that subvert the evolution of drug resistance. A major barrier to applications of these concepts is a lack of detail concerning how the environment affects adaptive landscape topography, and consequently, the outcome of drug treatment. Here we combine empirical data, evolutionary theory, and computer simulations towards dissecting adaptive landscape by environment interactions for the evolution of drug resistance in two dimensions-drug concentration and drug type. We do so by studying the resistance mediated by Plasmodium falciparum dihydrofolate reductase (DHFR) to two related inhibitors-pyrimethamine and cycloguanil-across a breadth of drug concentrations. We first examine whether the adaptive landscapes for the two drugs are consistent with common definitions of cross-resistance. We then reconstruct all accessible pathways across the landscape, observing how their structure changes with drug environment. We offer a mechanism for non-linearity in the topography of accessible pathways by calculating of the interaction between mutation effects and drug environment, which reveals rampant patterns of epistasis. We then simulate evolution in several different drug environments to observe how these individual mutation effects (and patterns of epistasis) influence paths taken at evolutionary "forks in the road" that dictate adaptive dynamics in silico. In doing so, we reveal how classic metrics like the IC50 and minimal inhibitory concentration (MIC) are dubious proxies for understanding how evolution will occur across drug environments. We also consider how the findings reveal ambiguities in the cross-resistance concept, as subtle differences in adaptive landscape topography between otherwise equivalent drugs can drive drastically different evolutionary outcomes. Summarizing, we discuss the results with regards to their basic contribution to the study of empirical adaptive landscapes, and in terms of how they inform new models for the evolution of drug resistance.

Predictive approaches such as virtual screening have been used in drug discovery with the objective of reducing developmental time and costs. Current machine learning and network-based approaches have issues related to generalization, usability, or model interpretability, especially due to the complexity of target proteins' structure/function, and bias in system training datasets. Here, we propose a new method "DRUIDom" (DRUg Interacting Domain prediction) to identify bio-interactions between drug candidate compounds and targets by utilizing the domain modularity of proteins, to overcome problems associated with current approaches. DRUIDom is composed of two methodological steps. First, ligands/compounds are statistically mapped to structural domains of their target proteins, with the aim of identifying their interactions. As such, other proteins containing the same mapped domain or domain pair become new candidate targets for the corresponding compounds. Next, a million-scale dataset of small molecule compounds, including those mapped to domains in the previous step, are clustered based on their molecular similarities, and their domain associations are propagated to other compounds within the same clusters. Experimentally verified bioactivity data points, obtained from public databases, are meticulously filtered to construct datasets of active/interacting and inactive/non-interacting drug/compound-target pairs (~2.9M data points), and used as training data for calculating parameters of compound-domain mappings, which led to 27,032 high-confidence associations between 250 domains and 8,165 compounds, and a finalized output of ~5 million new compound-protein interactions. DRUIDom is experimentally validated by syntheses and bioactivity analyses of compounds predicted to target LIM-kinase proteins, which play critical roles in the regulation of cell motility, cell cycle progression, and differentiation through actin filament dynamics. We showed that LIMK-inhibitor-2 and its derivatives significantly block the cancer cell migration through inhibition of LIMK phosphorylation and the downstream protein cofilin. One of the derivative compounds (LIMKi-2d) was identified as a promising candidate due to its action on resistant Mahlavu liver cancer cells. The results demonstrated that DRUIDom can be exploited to identify drug candidate compounds for intended targets and to predict new target proteins based on the defined compound-domain relationships. Datasets, results, and the source code of DRUIDom are fully-available at: https://github.com/cansyl/DRUIDom.

Identification of drug-target interactions (DTIs) plays a key role in drug discovery. The high cost and labor-intensive nature of in vitro and in vivo experiments have highlighted the importance of in silico-based DTI prediction approaches. In several computational models, conventional protein descriptors have been shown to not be sufficiently informative to predict accurate DTIs. Thus, in this study, we propose a deep learning based DTI prediction model capturing local residue patterns of proteins participating in DTIs. When we employ a convolutional neural network (CNN) on raw protein sequences, we perform convolution on various lengths of amino acids subsequences to capture local residue patterns of generalized protein classes. We train our model with large-scale DTI information and demonstrate the performance of the proposed model using an independent dataset that is not seen during the training phase. As a result, our model performs better than previous protein descriptor-based models. Also, our model performs better than the recently developed deep learning models for massive prediction of DTIs. By examining pooled convolution results, we confirmed that our model can detect binding sites of proteins for DTIs. In conclusion, our prediction model for detecting local residue patterns of target proteins successfully enriches the protein features of a raw protein sequence, yielding better prediction results than previous approaches. Our code is available at https://github.com/GIST-CSBL/DeepConv-DTI.

A key question in mapping dynamics of protein-ligand interactions is to distinguish changes at binding sites from those associated with long range conformational changes upon binding at distal sites. This assumes a greater challenge when considering the interactions of low affinity ligands (dissociation constants, KD, in the μM range or lower). Amide hydrogen deuterium Exchange mass spectrometry (HDXMS) is a robust method that can provide both structural insights and dynamics information on both high affinity and transient protein-ligand interactions. In this study, an application of HDXMS for probing the dynamics of low affinity ligands to proteins is described using the N-terminal ATPase domain of Hsp90. Comparison of Hsp90 dynamics between high affinity natural inhibitors (KD ~ nM) and fragment compounds reveal that HDXMS is highly sensitive in mapping the interactions of both high and low affinity ligands. HDXMS reports on changes that reflect both orthosteric effects and allosteric changes accompanying binding. Orthosteric sites can be identified by overlaying HDXMS onto structural information of protein-ligand complexes. Regions distal to orthosteric sites indicate long range conformational changes with implications for allostery. HDXMS, thus finds powerful utility as a high throughput method for compound library screening to identify binding sites and describe allostery with important implications for fragment-based ligand discovery (FBLD).

Multicellular tumour spheroids capture many characteristics of human tumour microenvironments, including hypoxia, and represent an experimentally tractable in vitro model for studying interactions between radiotherapy and anticancer drugs. However, interpreting spheroid data is challenging because of limited ability to observe cell fate within spheroids dynamically. To overcome this limitation, we have developed a hybrid continuum/agent-based model (ABM) for HCT116 tumour spheroids, parameterised using experimental models (monolayers and multilayers) in which reaction and diffusion can be measured directly. In the ABM, cell fate is simulated as a function of local oxygen, glucose and drug concentrations, determined by solving diffusion equations and intracellular reactions. The model is lattice-based, with cells occupying discrete locations on a 3D grid embedded within a coarser grid that encompasses the culture medium; separate solvers are employed for each grid. The generated concentration fields account for depletion in the medium and specify concentration-time profiles within the spheroid. Cell growth and survival are determined by intracellular oxygen and glucose concentrations, the latter based on direct measurement of glucose diffusion/reaction (in multilayers) for the first time. The ABM reproduces known features of spheroids including overall growth rate, its oxygen and glucose dependence, peripheral cell proliferation, central hypoxia and necrosis. We extended the ABM to describe in detail the hypoxia-dependent interaction between ionising radiation and a hypoxia-activated prodrug (SN30000), again using experimentally determined parameters; the model accurately simulated clonogenic cell killing in spheroids, while inclusion of reversible cell cycle delay was required to account for the marked spheroid growth delay after combined radiation and SN30000. This ABM of spheroid growth and response exemplifies the utility of integrating computational and experimental tools for investigating radiation/drug interactions, and highlights the critical importance of understanding oxygen, glucose and drug concentration gradients in interpreting activity of therapeutic agents in spheroid models.

Proteins do not function in isolation; it is their interactions with one another and also with other molecules (e.g. DNA, RNA) that mediate metabolic and signaling pathways, cellular processes, and organismal systems. Due to their central role in biological function, protein interactions also control the mechanisms leading to healthy and diseased states in organisms. Diseases are often caused by mutations affecting the binding interface or leading to biochemically dysfunctional allosteric changes in proteins. Therefore, protein interaction networks can elucidate the molecular basis of disease, which in turn can inform methods for prevention, diagnosis, and treatment. In this chapter, we will describe the computational approaches to predict and map networks of protein interactions and briefly review the experimental methods to detect protein interactions. We will describe the application of protein interaction networks as a translational approach to the study of human disease and evaluate the challenges faced by these approaches.

De novo experimental drug discovery is an expensive and time-consuming task. It requires the identification of drug-target interactions (DTIs) towards targets of biological interest, either to inhibit or enhance a specific molecular function. Dedicated computational models for protein simulation and DTI prediction are crucial for speed and to reduce the costs associated with DTI identification. In this paper we present a computational pipeline that enables the discovery of putative leads for drug repositioning that can be applied to any microbial proteome, as long as the interactome of interest is at least partially known. Network metrics calculated for the interactome of the bacterial organism of interest were used to identify putative drug-targets. Then, a random forest classification model for DTI prediction was constructed using known DTI data from publicly available databases, resulting in an area under the ROC curve of 0.91 for classification of out-of-sampling data. A drug-target network was created by combining 3,081 unique ligands and the expected ten best drug targets. This network was used to predict new DTIs and to calculate the probability of the positive class, allowing the scoring of the predicted instances. Molecular docking experiments were performed on the best scoring DTI pairs and the results were compared with those of the same ligands with their original targets. The results obtained suggest that the proposed pipeline can be used in the identification of new leads for drug repositioning. The proposed classification model is available at http://bioinformatics.ua.pt/software/dtipred/.

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

High-throughput drug screening has facilitated the discovery of drug combinations in cancer. Many existing studies adopted a full matrix design, aiming for the characterization of drug pair effects for cancer cells. However, the full matrix design may be suboptimal as it requires a drug pair to be combined at multiple concentrations in a full factorial manner. Furthermore, many of the computational tools assess only the synergy but not the sensitivity of drug combinations, which might lead to false positive discoveries. We proposed a novel cross design to enable a more cost-effective and simultaneous testing of drug combination sensitivity and synergy. We developed a drug combination sensitivity score (CSS) to determine the sensitivity of a drug pair, and showed that the CSS is highly reproducible between the replicates and thus supported its usage as a robust metric. We further showed that CSS can be predicted using machine learning approaches which determined the top pharmaco-features to cluster cancer cell lines based on their drug combination sensitivity profiles. To assess the degree of drug interactions using the cross design, we developed an S synergy score based on the difference between the drug combination and the single drug dose-response curves. We showed that the S score is able to detect true synergistic and antagonistic drug combinations at an accuracy level comparable to that using the full matrix design. Taken together, we showed that the cross design coupled with the CSS sensitivity and S synergy scoring methods may provide a robust and accurate characterization of both drug combination sensitivity and synergy levels, with minimal experimental materials required. Our experimental-computational approach could be utilized as an efficient pipeline for improving the discovery rate in high-throughput drug combination screening, particularly for primary patient samples which are difficult to obtain.

Drug-induced liver injury (DILI) is a significant concern in drug development due to the poor concordance between preclinical and clinical findings of liver toxicity. We hypothesized that the DILI types (hepatotoxic side effects) seen in the clinic can be translated into the development of predictive in silico models for use in the drug discovery phase. We identified 13 hepatotoxic side effects with high accuracy for classifying marketed drugs for their DILI potential. We then developed in silico predictive models for each of these 13 side effects, which were further combined to construct a DILI prediction system (DILIps). The DILIps yielded 60-70% prediction accuracy for three independent validation sets. To enhance the confidence for identification of drugs that cause severe DILI in humans, the "Rule of Three" was developed in DILIps by using a consensus strategy based on 13 models. This gave high positive predictive value (91%) when applied to an external dataset containing 206 drugs from three independent literature datasets. Using the DILIps, we screened all the drugs in DrugBank and investigated their DILI potential in terms of protein targets and therapeutic categories through network modeling. We demonstrated that two therapeutic categories, anti-infectives for systemic use and musculoskeletal system drugs, were enriched for DILI, which is consistent with current knowledge. We also identified protein targets and pathways that are related to drugs that cause DILI by using pathway analysis and co-occurrence text mining. While marketed drugs were the focus of this study, the DILIps has a potential as an evaluation tool to screen and prioritize new drug candidates or chemicals, such as environmental chemicals, to avoid those that might cause liver toxicity. We expect that the methodology can be also applied to other drug safety endpoints, such as renal or cardiovascular toxicity.

Tailored therapy aims to cure cancer patients effectively and safely, based on the complex interactions between patients' genomic features, disease pathology and drug metabolism. Thus, the continual increase in scientific literature drives the need for efficient methods of data mining to improve the extraction of useful information from texts based on patients' genomic features. An important application of text mining to tailored therapy in cancer encompasses the use of mutations and cancer fusion genes as moieties that change patients' cellular networks to develop cancer, and also affect drug metabolism. Fusion proteins, which are derived from the slippage of two parental genes, are produced in cancer by chromosomal aberrations and trans-splicing. Given that the two parental proteins for predicted fusion proteins are known, we used our previously developed method for identifying chimeric protein-protein interactions (ChiPPIs) associated with the fusion proteins. Here, we present a validation approach that receives fusion proteins of interest, predicts their cellular network alterations by ChiPPI and validates them by our new method, ProtFus, using an online literature search. This process resulted in a set of 358 fusion proteins and their corresponding protein interactions, as a training set for a Naïve Bayes classifier, to identify predicted fusion proteins that have reliable evidence in the literature and that were confirmed experimentally. Next, for a test group of 1817 fusion proteins, we were able to identify from the literature 2908 PPIs in total, across 18 cancer types. The described method, ProtFus, can be used for screening the literature to identify unique cases of fusion proteins and their PPIs, as means of studying alterations of protein networks in cancers. Availability: http://protfus.md.biu.ac.il/.

The rapidly increasing amount of public data in chemistry and biology provides new opportunities for large-scale data mining for drug discovery. Systematic integration of these heterogeneous sets and provision of algorithms to data mine the integrated sets would permit investigation of complex mechanisms of action of drugs. In this work we integrated and annotated data from public datasets relating to drugs, chemical compounds, protein targets, diseases, side effects and pathways, building a semantic linked network consisting of over 290,000 nodes and 720,000 edges. We developed a statistical model to assess the association of drug target pairs based on their relation with other linked objects. Validation experiments demonstrate the model can correctly identify known direct drug target pairs with high precision. Indirect drug target pairs (for example drugs which change gene expression level) are also identified but not as strongly as direct pairs. We further calculated the association scores for 157 drugs from 10 disease areas against 1683 human targets, and measured their similarity using a [Formula: see text] score matrix. The similarity network indicates that drugs from the same disease area tend to cluster together in ways that are not captured by structural similarity, with several potential new drug pairings being identified. This work thus provides a novel, validated alternative to existing drug target prediction algorithms. The web service is freely available at: http://chem2bio2rdf.org/slap.