PDATC-NCPMKL: Predicting drug's Anatomical Therapeutic Chemical (ATC) codes based on network consistency projection and multiple kernel learning

The development and discovery of new drugs is time-consuming and needs lots of human and material resources. Therefore, discovery of novel effects of existing drugs is an important alternative way, which can accelerate the process of designing "new" drugs. The anatomical Therapeutic Chemical (ATC) classification system recommended by World Health Organization (WHO) is a basic research area in this regard. A novel ATC code of an existing drug suggests its novel effects. Some computational models have been proposed, which can predict the drug-ATC code associations. However, their performance is not very high. There still exist spaces for improvement. In this study, a new recommendation system (named PDATC-NCPMKL), which incorporated network consistency projection and multi-kernel learning, was designed to identify drug-ATC code associations. For drugs or ATC codes, several kernels were constructed, which were fused by a multiple kernel learning method and an additional kernel integration scheme. To enhance the performance, the drug-ATC code association adjacency matrix was reformulated by a variant of weighted K nearest known neighbors (WKNKN). The reformulated adjacency matrix, drug and ATC code kernels were fed into network consistency projection to generate the association score matrix. The proposed recommendation system was tested on the ATC codes at the second, third and fourth levels in drug ATC classification system using ten-fold cross-validation. The results indicated that all AUROC and AUPR values were close to or exceeded 0.96. Such performance was higher than some existing computational models. Some additional tests were conducted to prove the utility of adjacency matrix reformulation and to analyze the importance of drug and ATC code kernels.

RNPredATC: A Deep Residual Learning-Based Model With Applications to the Prediction of Drug-ATC Code Association

The Anatomical Therapeutic Chemical (ATC) classification system, designated by the World Health Organization Collaborating Center (WHOCC), has been widely used in drug screening, repositioning, and similarity research. The ATC classification system assigns different codes to drugs according to the organ or system on which they act and/or their therapeutic and chemical characteristics. Correctly identifying the potential ATC codes for drugs can accelerate drug development and reduce the cost of experiments. Several classifiers have been proposed in this regard. However, they lack of ability to learn basic features from sparsely known drug-ATC code associations. Therefore, there is an urgent need for novel computational methods to precisely predict potential drug-ATC code associations in multiple levels of the ATC classification system based on known associations between drugs and ATC codes. In this paper, we provide a novel end-to-end model, so-called RNPredATC, to predict potential drug-ATC code associations in five ATC classification levels. RNPredATC can extract dense feature vectors from sparsely known drug-ATC code associations and reduce the impact from the degradation problem by a novel deep residual learning. We extensively compare our method with some state-of-the-art methods, including NetPredATC, SPACE, and some multi-label-based methods. Our experimental results show that RNPredATC achieves better performances in five-fold and ten-fold cross validations. Furthermore, the visualization analysis of hidden layers and case studies of predicted associations at the fifth ATC classification level confirm that RNPredATC can effectively identify the potential ATC codes of drugs.

Guiding Drug Repositioning for Cancers Based on Drug Similarity Networks

Drug repositioning aims to discover novel clinical benefits of existing drugs, is an effective way to develop drugs for complex diseases such as cancer and may facilitate the process of traditional drug development. Meanwhile, network-based computational biology approaches, which allow the integration of information from different aspects to understand the relationships between biomolecules, has been successfully applied to drug repurposing. In this work, we developed a new strategy for network-based drug repositioning against cancer. Combining the mechanism of action and clinical efficacy of the drugs, a cancer-related drug similarity network was constructed, and the correlation score of each drug with a specific cancer was quantified. The top 5% of scoring drugs were reviewed for stability and druggable potential to identify potential repositionable drugs. Of the 11 potentially repurposable drugs for non-small cell lung cancer (NSCLC), 10 were confirmed by clinical trial articles and databases. The targets of these drugs were significantly enriched in cancer-related pathways and significantly associated with the prognosis of NSCLC. In light of the successful application of our approach to colorectal cancer as well, it provides an effective clue and valuable perspective for drug repurposing in cancer.

Identifying the kind behind SMILES-anatomical therapeutic chemical classification using structure-only representations

Anatomical Therapeutic Chemical (ATC) classification for compounds/drugs plays an important role in drug development and basic research. However, previous methods depend on interactions extracted from STITCH dataset which may make it depend on lab experiments. We present a pilot study to explore the possibility of conducting the ATC prediction solely based on the molecular structures. The motivation is to eliminate the reliance on the costly lab experiments so that the characteristics of a drug can be pre-assessed for better decision-making and effort-saving before the actual development. To this end, we construct a new benchmark consisting of 4545 compounds which is with larger scale than the one used in previous study. A light-weight prediction model is proposed. The model is with better explainability in the sense that it is consists of a straightforward tokenization that extracts and embeds statistically and physicochemically meaningful tokens, and a deep network backed by a set of pyramid kernels to capture multi-resolution chemical structural characteristics. Its efficacy has been validated in the experiments where it outperforms the state-of-the-art methods by 15.53% in accuracy and by 69.66% in terms of efficiency. We make the benchmark dataset, source code and web server open to ease the reproduction of this study.

Systematic optimization of host-directed therapeutic targets and preclinical validation of repositioned antiviral drugs

Inhibition of host protein functions using established drugs produces a promising antiviral effect with excellent safety profiles, decreased incidence of resistant variants and favorable balance of costs and risks. Genomic methods have produced a large number of robust host factors, providing candidates for identification of antiviral drug targets. However, there is a lack of global perspectives and systematic prioritization of known virus-targeted host proteins (VTHPs) and drug targets. There is also a need for host-directed repositioned antivirals. Here, we integrated 6140 VTHPs and grouped viral infection modes from a new perspective of enriched pathways of VTHPs. Clarifying the superiority of nonessential membrane and hub VTHPs as potential ideal targets for repositioned antivirals, we proposed 543 candidate VTHPs. We then presented a large-scale drug-virus network (DVN) based on matching these VTHPs and drug targets. We predicted possible indications for 703 approved drugs against 35 viruses and explored their potential as broad-spectrum antivirals. In vitro and in vivo tests validated the efficacy of bosutinib, maraviroc and dextromethorphan against human herpesvirus 1 (HHV-1), hepatitis B virus (HBV) and influenza A virus (IAV). Their drug synergy with clinically used antivirals was evaluated and confirmed. The results proved that low-dose dextromethorphan is better than high-dose in both single and combined treatments. This study provides a comprehensive landscape and optimization strategy for druggable VTHPs, constructing an innovative and potent pipeline to discover novel antiviral host proteins and repositioned drugs, which may facilitate their delivery to clinical application in translational medicine to combat fatal and spreading viral infections.

Deep fusion learning facilitates anatomical therapeutic chemical recognition in drug repurposing and discovery

The advent of large-scale biomedical data and computational algorithms provides new opportunities for drug repurposing and discovery. It is of great interest to find an appropriate data representation and modeling method to facilitate these studies. The anatomical therapeutic chemical (ATC) classification system, proposed by the World Health Organization (WHO), is an essential source of information for drug repurposing and discovery. Besides, computational methods are applied to predict drug ATC classification. We conducted a systematic review of ATC computational prediction studies and revealed the differences in data sets, data representation, algorithm approaches, and evaluation metrics. We then proposed a deep fusion learning (DFL) framework to optimize the ATC prediction model, namely DeepATC. The methods based on graph convolutional network, inferring biological network and multimodel attentive fusion network were applied in DeepATC to extract the molecular topological information and low-dimensional representation from the molecular graph and heterogeneous biological networks. The results indicated that DeepATC achieved superior model performance with area under the curve (AUC) value at 0.968. Furthermore, the DFL framework was performed for the transcriptome data-based ATC prediction, as well as another independent task that is significantly relevant to drug discovery, namely drug-target interaction. The DFL-based model achieved excellent performance in the above-extended validation task, suggesting that the idea of aggregating the heterogeneous biological network and node's (molecule or protein) self-topological features will bring inspiration for broader drug repurposing and discovery research.

DeepDRK: a deep learning framework for drug repurposing through kernel-based multi-omics integration

Recent pharmacogenomic studies that generate sequencing data coupled with pharmacological characteristics for patient-derived cancer cell lines led to large amounts of multi-omics data for precision cancer medicine. Among various obstacles hindering clinical translation, lacking effective methods for multimodal and multisource data integration is becoming a bottleneck. Here we proposed DeepDRK, a machine learning framework for deciphering drug response through kernel-based data integration. To transfer information among different drugs and cancer types, we trained deep neural networks on more than 20 000 pan-cancer cell line-anticancer drug pairs. These pairs were characterized by kernel-based similarity matrices integrating multisource and multi-omics data including genomics, transcriptomics, epigenomics, chemical properties of compounds and known drug-target interactions. Applied to benchmark cancer cell line datasets, our model surpassed previous approaches with higher accuracy and better robustness. Then we applied our model on newly established patient-derived cancer cell lines and achieved satisfactory performance with AUC of 0.84 and AUPRC of 0.77. Moreover, DeepDRK was used to predict clinical response of cancer patients. Notably, the prediction of DeepDRK correlated well with clinical outcome of patients and revealed multiple drug repurposing candidates. In sum, DeepDRK provided a computational method to predict drug response of cancer cells from integrating pharmacogenomic datasets, offering an alternative way to prioritize repurposing drugs in precision cancer treatment. The DeepDRK is freely available via https://github.com/wangyc82/DeepDRK.

Identification of Carcinogenic Chemicals with Network Embedding and Deep Learning Methods

Background:

Cancer is the second leading cause of human death in the world. To date, many factors have been confirmed to be the cause of cancer. Among them, carcinogenic chemicals have been widely accepted as the important ones. Traditional methods for detecting carcinogenic chemicals are of low efficiency and high cost.

Objective:

The aim of this study was to design an efficient computational method for the identification of carcinogenic chemicals.

Methods:

A new computational model was proposed for detecting carcinogenic chemicals. As a data-driven model, carcinogenic and non-carcinogenic chemicals were obtained from Carcinogenic Potency Database (CPDB). These chemicals were represented by features extracted from five chemical networks, representing five types of chemical associations, via a network embedding method, Mashup. Obtained features were fed into a powerful deep learning method, recurrent neural network, to build the model.

Results:

The jackknife test on such model provided the F-measure of 0.971 and AUROC of 0.971.

Conclusion:

The proposed model was quite effective and was superior to the models with traditional machine learning algorithms, classic chemical encoding schemes or direct usage of chemical associations.

iATC-NRAKEL: an efficient multi-label classifier for recognizing anatomical therapeutic chemical classes of drugs

MOTIVATION

The anatomical therapeutic chemical (ATC) classification system plays an increasingly important role in drug repositioning and discovery. The correct identification of classes in each level of such system that a given drug may belong to is an essential problem. Several multi-label classifiers have been proposed in this regard. Although they provided satisfactory performance, the feature extraction procedures were still rough. More refined features may further improve the predicted quality.

RESULTS

In this article, we provide a novel multi-label classifier, called iATC-NRAKEL, to predict drug ATC classes in the first level. To obtain more informative drug features, we employed the drug association information in STITCH and KEGG, which was organized by seven drug networks. The powerful network embedding algorithm, Mashup, was adopted to extract informative drug features. The obtained features were fed into the RAndom k-labELsets (RAKEL) algorithm with support vector machine as the basic classification algorithm to construct the classifier. The 10-fold cross-validation of the benchmark dataset with 3883 drugs showed that the accuracy and absolute true were 76.56 and 74.51%, respectively. The comparison results indicated that iATC-NRAKEL was much superior to all previous reported classifiers. Finally, the contribution of each network was analyzed.

AVAILABILITY AND IMPLEMENTATION

The codes of iATC-NRAKEL are available at https://github.com/zhou256/iATC-NRAKEL.

Drug repositioning by prediction of drug's anatomical therapeutic chemical code via network-based inference approaches

Drug discovery and development is a time-consuming and costly process. Therefore, drug repositioning has become an effective approach to address the issues by identifying new therapeutic or pharmacological actions for existing drugs. The drug's anatomical therapeutic chemical (ATC) code is a hierarchical classification system categorized as five levels according to the organs or systems that drugs act and the pharmacology, therapeutic and chemical properties of drugs. The 2nd-, 3rd- and 4th-level ATC codes reserved the therapeutic and pharmacological information of drugs. With the hypothesis that drugs with similar structures or targets would possess similar ATC codes, we exploited a network-based approach to predict the 2nd-, 3rd- and 4th-level ATC codes by constructing substructure drug-ATC (SD-ATC), target drug-ATC (TD-ATC) and Substructure&Target drug-ATC (STD-ATC) networks. After 10-fold cross validation and two external validations, the STD-ATC models outperformed the SD-ATC and TD-ATC ones. Furthermore, with KR as fingerprint, the STD-ATC model was identified as the optimal model with AUC values at 0.899 ± 0.015, 0.916 and 0.893 for 10-fold cross validation, external validation set 1 and external validation set 2, respectively. To illustrate the predictive capability of the STD-ATC model with KR fingerprint, as a case study, we predicted 25 FDA-approved drugs (22 drugs were actually purchased) to have potential activities on heart failure using that model. Experiments in vitro confirmed that 8 of the 22 old drugs have shown mild to potent cardioprotective activities on both hypoxia model and oxygen-glucose deprivation model, which demonstrated that our STD-ATC prediction model would be an effective tool for drug repositioning.

Computer-aided drug repurposing for cancer therapy: Approaches and opportunities to challenge anticancer targets

Despite huge efforts made in academic and pharmaceutical worldwide research, current anticancer therapies achieve effective treatment in a limited number of neoplasia cases only. Oncology terms such as big killers - to identify tumours with yet a high mortality rate - or undruggable cancer targets, and chemoresistance, represent the current therapeutic debacle of cancer treatments. In addition, metastases, tumour microenvironments, tumour heterogeneity, metabolic adaptations, and immunotherapy resistance are essential features controlling tumour response to therapies, but still, lack effective therapeutics or modulators. In this scenario, where the pharmaceutical productivity and drug efficacy in oncology seem to have reached a plateau, the so-called drug repurposing - i.e. the use of old drugs, already in clinical use, for a different therapeutic indication - is an appealing strategy to improve cancer therapy. Opportunities for drug repurposing are often based on occasional observations or on time-consuming pre-clinical drug screenings that are often not hypothesis-driven. In contrast, in-silico drug repurposing is an emerging, hypothesis-driven approach that takes advantage of the use of big-data. Indeed, the extensive use of -omics technologies, improved data storage, data meaning, machine learning algorithms, and computational modeling all offer unprecedented knowledge of the biological mechanisms of cancers and drugs' modes of action, providing extensive availability for both disease-related data and drugs-related data. This offers the opportunity to generate, with time and cost-effective approaches, computational drug networks to predict, in-silico, the efficacy of approved drugs against relevant cancer targets, as well as to select better responder patients or disease' biomarkers. Here, we will review selected disease-related data together with computational tools to be exploited for the in-silico repurposing of drugs against validated targets in cancer therapies, focusing on the oncogenic signaling pathways activation in cancer. We will discuss how in-silico drug repurposing has the promise to shortly improve our arsenal of anticancer drugs and, likely, overcome certain limitations of modern cancer therapies against old and new therapeutic targets in oncology.

The Association Between Serum Calcium Levels and Short-Term Mortality in Patients with Chronic Heart Failure

BACKGROUND

Patients with chronic heart failure have vulnerable myocardial function and are susceptible to electrolyte disturbances. In these patients, diuretic treatment is frequently prescribed, though it is known to cause electrolyte disturbances. Therefore, we investigated the association between altered calcium homeostasis and the risk of all-cause mortality in chronic heart failure patients.

METHODS

From Danish national registries, we identified patients with chronic heart failure with a serum calcium measurement within a minimum 90 days after initiated treatment with both loop diuretics and angiotensin-converting enzyme inhibitors or angiotensin II receptor blockers. Patients were divided into 3 groups according to serum calcium levels, and Cox regression was used to assess the mortality risk of <1.18 mmol/L (hypocalcemia) and >1.32 mmol/L (hypercalcemia) compared with 1.18 mmol/L-1.32 mmol/L (normocalcemia) as reference. Hazard ratios (HRs) with 95% confidence intervals (CIs) were calculated.

RESULTS

Of 2729 patients meeting the inclusion criteria, 32.6% had hypocalcemia, 63.1% normocalcemia, and 4.3% hypercalcemia. The highest mortality risk was present in early deaths (≤30 days), with a HR of 2.22 (95% CI; 1.74-2.82) in hypocalcemic patients and 1.67 (95% CI; 0.96-2.90) in hypercalcemic patients compared with normocalcemic patients. As for late deaths (>30 days), a HR of 1.52 (95% CI; 1.12-2.05) was found for hypocalcemic patients and a HR of 1.87 (95% CI; 1.03-3.41) for hypercalcemic patients compared with normocalcemic patients. In adjusted analyses, hypocalcemia and hypercalcemia remained associated with an increased mortality risk in both the short term (≤30 days) and longer term (>30 days).

CONCLUSION

Altered calcium homeostasis was associated with an increased short-term mortality risk. Almost one-third of all the heart failure patients suffered from hypocalcemia, having a poor prognosis.

Reverse Screening Methods to Search for the Protein Targets of Chemopreventive Compounds

This article is a systematic review of reverse screening methods used to search for the protein targets of chemopreventive compounds or drugs. Typical chemopreventive compounds include components of traditional Chinese medicine, natural compounds and Food and Drug Administration (FDA)-approved drugs. Such compounds are somewhat selective but are predisposed to bind multiple protein targets distributed throughout diverse signaling pathways in human cells. In contrast to conventional virtual screening, which identifies the ligands of a targeted protein from a compound database, reverse screening is used to identify the potential targets or unintended targets of a given compound from a large number of receptors by examining their known ligands or crystal structures. This method, also known as in silico or computational target fishing, is highly valuable for discovering the target receptors of query molecules from terrestrial or marine natural products, exploring the molecular mechanisms of chemopreventive compounds, finding alternative indications of existing drugs by drug repositioning, and detecting adverse drug reactions and drug toxicity. Reverse screening can be divided into three major groups: shape screening, pharmacophore screening and reverse docking. Several large software packages, such as Schrödinger and Discovery Studio; typical software/network services such as ChemMapper, PharmMapper, idTarget, and INVDOCK; and practical databases of known target ligands and receptor crystal structures, such as ChEMBL, BindingDB, and the Protein Data Bank (PDB), are available for use in these computational methods. Different programs, online services and databases have different applications and constraints. Here, we conducted a systematic analysis and multilevel classification of the computational programs, online services and compound libraries available for shape screening, pharmacophore screening and reverse docking to enable non-specialist users to quickly learn and grasp the types of calculations used in protein target fishing. In addition, we review the main features of these methods, programs and databases and provide a variety of examples illustrating the application of one or a combination of reverse screening methods for accurate target prediction.

Complex network theory for the identification and assessment of candidate protein targets

In this work we use complex network theory to provide a statistical model of the connectivity patterns of human proteins and their interaction partners. Our intention is to identify important proteins that may be predisposed to be potential candidates as drug targets for therapeutic interventions. Target proteins usually have more interaction partners than non-target proteins, but there are no hard-and-fast rules for defining the actual number of interactions. We devise a statistical measure for identifying hub proteins, we score our target proteins with gene ontology annotations. The important druggable protein targets are likely to have similar biological functions that can be assessed for their potential therapeutic value. Our system provides a statistical analysis of the local and distant neighborhood protein interactions of the potential targets using complex network measures. This approach builds a more accurate model of drug-to-target activity and therefore the likely impact on treating diseases. We integrate high quality protein interaction data from the HINT database and disease associated proteins from the DrugTarget database. Other sources include biological knowledge from Gene Ontology and drug information from DrugBank. The problem is a very challenging one since the data is highly imbalanced between target proteins and the more numerous nontargets. We use undersampling on the training data and build Random Forest classifier models which are used to identify previously unclassified target proteins. We validate and corroborate these findings from the available literature.

Inferring anatomical therapeutic chemical (ATC) class of drugs using shortest path and random walk with restart algorithms

The anatomical therapeutic chemical (ATC) classification system is a widely accepted drug classification scheme. This system comprises five levels and includes several classes in each level. Drugs are classified into classes according to their therapeutic effects and characteristics. The first level includes 14 main classes. In this study, we proposed two network-based models to infer novel potential chemicals deemed to belong in the first level of ATC classification. To build these models, two large chemical networks were constructed using the chemical-chemical interaction information retrieved from the Search Tool for Interactions of Chemicals (STITCH). Two classic network algorithms, shortest path (SP) and random walk with restart (RWR) algorithms, were executed on the corresponding network to mine novel chemicals for each ATC class using the validated drugs in a class as seed nodes. Then, the obtained chemicals yielded by these two algorithms were further evaluated by a permutation test and an association test. The former can exclude chemicals produced by the structure of the network, i.e., false positive discoveries. By contrast, the latter identifies the most important chemicals that have strong associations with the ATC class. Comparisons indicated that the two models can provide quite dissimilar results, suggesting that the results yielded by one model can be essential supplements for those obtained by the other model. In addition, several representative inferred chemicals were analyzed to confirm the reliability of the results generated by the two models. This article is part of a Special Issue entitled: Accelerating Precision Medicine through Genetic and Genomic Big Data Analysis edited by Yudong Cai & Tao Huang.

Comparing structural and transcriptional drug networks reveals signatures of drug activity and toxicity in transcriptional responses

We performed an integrated analysis of drug chemical structures and drug-induced transcriptional responses. We demonstrated that a network representing three-dimensional structural similarities among 5452 compounds can be used to automatically group together drugs with similar scaffolds, physicochemical parameters and mode-of-action. We compared the structural network to a network representing transcriptional similarities among a subset of 1309 drugs for which transcriptional response were available in the Connectivity Map data set. Analysis of structurally similar, but transcriptionally different drugs sharing the same MOA enabled us to detect and remove weak and noisy transcriptional responses, greatly enhancing the reliability of transcription-based approaches to drug discovery and drug repositioning. Cardiac glycosides exhibited the strongest transcriptional responses with a significant induction of pathways related to epigenetic regulation, which suggests an epigenetic mechanism of action for these drugs. Drug classes with the weakest transcriptional responses tended to induce expression of cytochrome P450 enzymes, hinting at drug-induced drug resistance. Analysis of transcriptionally similar, but structurally different drugs with unrelated MOA, led us to the identification of a 'toxic' transcriptional signature indicative of lysosomal stress (lysosomotropism) and lipid accumulation (phospholipidosis) partially masking the target-specific transcriptional effects of these drugs. We found that this transcriptional signature is shared by 258 compounds and it is associated to the activation of the transcription factor TFEB, a master regulator of lysosomal biogenesis and autophagy. Finally, we built a predictive Random Forest model of these 258 compounds based on 128 physicochemical parameters, which should help in the early identification of potentially toxic drug candidates.

Transcriptional responses to drug treatment can reveal mechanism of action and off-target effects thus enabling drug repositioning, but only if measured in the appropriate cells at clinically relevant concentrations. A team led by Diego di Bernardo and Diego Medina generated a network representing structural similarities among compounds to automatically group together drugs with similar scaffolds and MOA. By comparing the structural drug network with a transcriptional drug network based on similarities in transcriptional response, the team observed broad differences between the two. This observation led to the identification of a transcriptional signature related lysosomal stress and phospholipidosis, and a physicochemical model to identify such compounds. These results provide general guidelines to prevent erroneous conclusion when using transcriptional responses of small molecules for drug discovery and drug repositioning

Classification and analysis of a large collection of in vivo bioassay descriptions

Testing potential drug treatments in animal disease models is a decisive step of all preclinical drug discovery programs. Yet, despite the importance of such experiments for translational medicine, there have been relatively few efforts to comprehensively and consistently analyze the data produced by in vivo bioassays. This is partly due to their complexity and lack of accepted reporting standards-publicly available animal screening data are only accessible in unstructured free-text format, which hinders computational analysis. In this study, we use text mining to extract information from the descriptions of over 100,000 drug screening-related assays in rats and mice. We retrieve our dataset from ChEMBL-an open-source literature-based database focused on preclinical drug discovery. We show that in vivo assay descriptions can be effectively mined for relevant information, including experimental factors that might influence the outcome and reproducibility of animal research: genetic strains, experimental treatments, and phenotypic readouts used in the experiments. We further systematize extracted information using unsupervised language model (Word2Vec), which learns semantic similarities between terms and phrases, allowing identification of related animal models and classification of entire assay descriptions. In addition, we show that random forest models trained on features generated by Word2Vec can predict the class of drugs tested in different in vivo assays with high accuracy. Finally, we combine information mined from text with curated annotations stored in ChEMBL to investigate the patterns of usage of different animal models across a range of experiments, drug classes, and disease areas.

Predicting anatomic therapeutic chemical classification codes using tiered learning

BACKGROUND

The low success rate and high cost of drug discovery requires the development of new paradigms to identify molecules of therapeutic value. The Anatomical Therapeutic Chemical (ATC) Code System is a World Health Organization (WHO) proposed classification that assigns multi-level codes to compounds based on their therapeutic, pharmacological and chemical characteristics as well as the in-vivo sites(s) of activity. The ability to predict ATC codes of compounds can assist in creation of high-quality chemical libraries for drug screening and in applications such as drug repositioning. We propose a machine learning architecture called tiered learning for prediction of ATC codes that relies on the prediction results of the higher levels of the ATC code to simplify the predictions of the lower levels.

RESULTS

The proposed approach was validated using a number of compounds in both cross-validation and test setting. The validation experiments compared chemical descriptors, initialization methods and classification algorithms. The prediction accuracy obtained with tiered learning was found to be either comparable or better than that of established methods. Additionally, the experiments demonstrated the generalizability of the tiered learning architecture, in that its use was found to improve prediction rates for a majority of machine learning algorithms when compared to their stand-alone application.

CONCLUSION

The basis of our approach lies in the observation that anatomical-therapeutic biological activity of certain types typically precludes activities of many other types. Thus, there exists a characteristic distribution of the ATC codes, which can be leveraged to limit the search-space of possible codes that can be ascribed at a particular level once the codes at the preceding levels are known. Tiered learning utilizes this observation to constrain the learning space for ATC codes at a particular level based on the ATC code at higher levels. This simplifies the prediction and allows for improved accuracy.

Exploration and analysis of drug modes of action through feature integration

Identifying drug modes of action (MoA) is of paramount importance for having a good grasp of drug indications in clinical tests.

New strategy for drug discovery by large-scale association analysis of molecular networks of different species

The development of modern omics technology has not significantly improved the efficiency of drug development. Rather precise and targeted drug discovery remains unsolved. Here a large-scale cross-species molecular network association (CSMNA) approach for targeted drug screening from natural sources is presented. The algorithm integrates molecular network omics data from humans and 267 plants and microbes, establishing the biological relationships between them and extracting evolutionarily convergent chemicals. This technique allows the researcher to assess targeted drugs for specific human diseases based on specific plant or microbe pathways. In a perspective validation, connections between the plant Halliwell-Asada (HA) cycle and the human Nrf2-ARE pathway were verified and the manner by which the HA cycle molecules act on the human Nrf2-ARE pathway as antioxidants was determined. This shows the potential applicability of this approach in drug discovery. The current method integrates disparate evolutionary species into chemico-biologically coherent circuits, suggesting a new cross-species omics analysis strategy for rational drug development.

Short-term mortality risk of serum potassium levels in acute heart failure following myocardial infarction

AIMS

Diuretic treatment is often needed in acute heart failure following myocardial infarction (MI) and carries a risk of abnormal potassium levels. We examined the relation between different levels of potassium and mortality.

METHODS AND RESULTS

From Danish national registries we identified 2596 patients treated with loop diuretics after their first MI episode where potassium measurement was available within 3 months. All-cause mortality was examined according to seven predefined potassium levels: hypokalaemia <3.5 mmol/L, low normal potassium 3.5-3.8 mmol/L, normal potassium 3.9-4.2 mmol/L, normal potassium 4.3-4.5 mmol/L, high normal potassium 4.6-5.0 mmol/L, mild hyperkalaemia 5.1-5.5 mmol/L, and severe hyperkalaemia: >5.5 mmol/L. Follow-up was 90 days and using normal potassium 3.9-4.2 mmol/L as a reference, we estimated the risk of death with a multivariable-adjusted Cox proportional hazard model. After 90 days, the mortality rates in the seven potassium intervals were 15.7, 13.6, 7.3, 8.1, 10.6, 15.5, and 38.3%, respectively. Multivariable-adjusted risk for death was statistically significant for patients with hypokalaemia [hazard ratio (HR): 1.91, confidence interval (95%CI): 1.14-3.19], and mild and severe hyperkalaemia (HR: 2, CI: 1.25-3.18 and HR: 5.6, CI: 3.38-9.29, respectively). Low and high normal potassium were also associated with increased mortality (HR: 1.84, CI: 1.23-2.76 and HR: 1.55, CI: 1.09-2.22, respectively).

CONCLUSION

Potassium levels outside the interval 3.9-4.5 mmol/L were associated with a substantial risk of death in patients requiring diuretic treatment after an MI.

Large-scale exploration and analysis of drug combinations

MOTIVATION

Drug combinations are a promising strategy for combating complex diseases by improving the efficacy and reducing corresponding side effects. Currently, a widely studied problem in pharmacology is to predict effective drug combinations, either through empirically screening in clinic or pure experimental trials. However, the large-scale prediction of drug combination by a systems method is rarely considered.

RESULTS

We report a systems pharmacology framework to predict drug combinations (PreDCs) on a computational model, termed probability ensemble approach (PEA), for analysis of both the efficacy and adverse effects of drug combinations. First, a Bayesian network integrating with a similarity algorithm is developed to model the combinations from drug molecular and pharmacological phenotypes, and the predictions are then assessed with both clinical efficacy and adverse effects. It is illustrated that PEA can predict the combination efficacy of drugs spanning different therapeutic classes with high specificity and sensitivity (AUC = 0.90), which was further validated by independent data or new experimental assays. PEA also evaluates the adverse effects (AUC = 0.95) quantitatively and detects the therapeutic indications for drug combinations. Finally, the PreDC database includes 1571 known and 3269 predicted optimal combinations as well as their potential side effects and therapeutic indications.

AVAILABILITY AND IMPLEMENTATION

The PreDC database is available at http://sm.nwsuaf.edu.cn/lsp/predc.php.

Systematic analysis of new drug indications by drug-gene-disease coherent subnetworks

Drug targets and disease genes may work as driver factors at the transcriptional level, which propagate signals through gene regulatory network and cause the downstream genes' differential expression. How to analyze transcriptional response data to identify meaningful gene modules shared by both drugs and diseases is still a critical issue for drug-disease associations and molecular mechanism. In this article, we propose the drug-gene-disease coherent subnetwork concept to group the biological function related drugs, diseases, and genes. It was defined as the subnetwork with drug, gene, and disease as nodes and their interactions coherently crossing three data layers as edges. Integrating differential expression profiles of 418 drugs and 84 diseases, we develop a computational framework and identify 13 coherent subnetworks such as inflammatory bowel disease and melanoma relevant subnetwork. The results demonstrate that our coherent subnetwork approach is able to identify novel drug indications and highlight their molecular basis.

SuperPred: update on drug classification and target prediction

The SuperPred web server connects chemical similarity of drug-like compounds with molecular targets and the therapeutic approach based on the similar property principle. Since the first release of this server, the number of known compound–target interactions has increased from 7000 to 665 000, which allows not only a better prediction quality but also the estimation of a confidence. Apart from the addition of quantitative binding data and the statistical consideration of the similarity distribution in all drug classes, new approaches were implemented to improve the target prediction. The 3D similarity as well as the occurrence of fragments and the concordance of physico-chemical properties is also taken into account. In addition, the effect of different fingerprints on the prediction was examined. The retrospective prediction of a drug class (ATC code of the WHO) allows the evaluation of methods and descriptors for a well-characterized set of approved drugs. The prediction is improved by 7.5% to a total accuracy of 75.1%. For query compounds with sufficient structural similarity, the web server allows prognoses about the medical indication area of novel compounds and to find new leads for known targets. SuperPred is publicly available without registration at: http://prediction.charite.de.

Toward more realistic drug-target interaction predictions

A number of supervised machine learning models have recently been introduced for the prediction of drug-target interactions based on chemical structure and genomic sequence information. Although these models could offer improved means for many network pharmacology applications, such as repositioning of drugs for new therapeutic uses, the prediction models are often being constructed and evaluated under overly simplified settings that do not reflect the real-life problem in practical applications. Using quantitative drug-target bioactivity assays for kinase inhibitors, as well as a popular benchmarking data set of binary drug-target interactions for enzyme, ion channel, nuclear receptor and G protein-coupled receptor targets, we illustrate here the effects of four factors that may lead to dramatic differences in the prediction results: (i) problem formulation (standard binary classification or more realistic regression formulation), (ii) evaluation data set (drug and target families in the application use case), (iii) evaluation procedure (simple or nested cross-validation) and (iv) experimental setting (whether training and test sets share common drugs and targets, only drugs or targets or neither). Each of these factors should be taken into consideration to avoid reporting overoptimistic drug-target interaction prediction results. We also suggest guidelines on how to make the supervised drug-target interaction prediction studies more realistic in terms of such model formulations and evaluation setups that better address the inherent complexity of the prediction task in the practical applications, as well as novel benchmarking data sets that capture the continuous nature of the drug-target interactions for kinase inhibitors.

A hybrid method for prediction and repositioning of drug Anatomical Therapeutic Chemical classes

In the Anatomical Therapeutic Chemical (ATC) classification system, therapeutic drugs are divided into 14 main classes according to the organ or system on which they act and their chemical, pharmacological and therapeutic properties. This system, recommended by the World Health Organization (WHO), provides a global standard for classifying medical substances and serves as a tool for international drug utilization research to improve quality of drug use. In view of this, it is necessary to develop effective computational prediction methods to identify the ATC-class of a given drug, which thereby could facilitate further analysis of this system. In this study, we initiated an attempt to develop a prediction method and to gain insights from it by utilizing ontology information of drug compounds. Since only about one-fourth of drugs in the ATC classification system have ontology information, a hybrid prediction method combining the ontology information, chemical interaction information and chemical structure information of drug compounds was proposed for the prediction of drug ATC-classes. As a result, by using the Jackknife test, the 1st prediction accuracies for identifying the 14 main ATC-classes in the training dataset, the internal validation dataset and the external validation dataset were 75.90%, 75.70% and 66.36%, respectively. Analysis of some samples with false-positive predictions in the internal and external validation datasets indicated that some of them may even have a relationship with the false-positive predicted ATC-class, suggesting novel uses of these drugs. It was conceivable that the proposed method could be used as an efficient tool to identify ATC-classes of novel drugs or to discover novel uses of known drugs.

Computational Study of Drugs by Integrating Omics Data with Kernel Methods

With the rapid development of genomic and chemogenomic techniques, many omics data sources for drugs have been publicly available. These data sources illustrate drug's biological function in the living cell from different levels and different aspects. One straightforward idea is to learn understandable rules via computational models and algorithms to mine and integrate these data sources. Here, we review our recent efforts on developing kernel-based methods to integrate drug related omics data sources. Three promising applications of our framework are shown to predict drug targets, assign drug's ATC-code annotation, and reveal drug repositioning. We demonstrate that data integration does provide more information and improve the accuracy by recovering more experimentally observed target proteins, ATC-codes, and drug repositioning. Importantly, data integration can indicate novel predictions which are supported by database search and functional annotation analysis and worthy of further experimental validation. In conclusion, kernel methods can efficiently integrate heterogeneous data sources to computationally study drugs, and will promote the further research in drug discovery in a low-cost way.

Drug repositioning by kernel-based integration of molecular structure, molecular activity, and phenotype data

Computational inference of novel therapeutic values for existing drugs, i.e., drug repositioning, offers the great prospect for faster and low-risk drug development. Previous researches have indicated that chemical structures, target proteins, and side-effects could provide rich information in drug similarity assessment and further disease similarity. However, each single data source is important in its own way and data integration holds the great promise to reposition drug more accurately. Here, we propose a new method for drug repositioning, PreDR (Predict Drug Repositioning), to integrate molecular structure, molecular activity, and phenotype data. Specifically, we characterize drug by profiling in chemical structure, target protein, and side-effects space, and define a kernel function to correlate drugs with diseases. Then we train a support vector machine (SVM) to computationally predict novel drug-disease interactions. PreDR is validated on a well-established drug-disease network with 1,933 interactions among 593 drugs and 313 diseases. By cross-validation, we find that chemical structure, drug target, and side-effects information are all predictive for drug-disease relationships. More experimentally observed drug-disease interactions can be revealed by integrating these three data sources. Comparison with existing methods demonstrates that PreDR is competitive both in accuracy and coverage. Follow-up database search and pathway analysis indicate that our new predictions are worthy of further experimental validation. Particularly several novel predictions are supported by clinical trials databases and this shows the significant prospects of PreDR in future drug treatment. In conclusion, our new method, PreDR, can serve as a useful tool in drug discovery to efficiently identify novel drug-disease interactions. In addition, our heterogeneous data integration framework can be applied to other problems.