Abstract: BACKGROUND: Detection of new drug-target interactions by computational algorithms is of crucial value to both old drug repositioning and new drug discovery. Existing machine-learning methods rely only on experimentally validated drug-target interactions (i.e., positive samples) for the predictions. Their performance is severely impeded by the lack of reliable negative samples. RESULTS: We propose a method to construct highly-reliable negative samples for drug target prediction by a pairwise drug-target similarity measurement and OCSVM with a high-recall constraint. On one hand, we measure the pairwise similarity between every two drug-target interactions by combining the chemical similarity between their drugs and the Gene Ontology-based similarity between their targets. Then we calculate the accumulative similarity with all known drug-target interactions for each unobserved drug-target interaction. On the other hand, we obtain the signed distance from OCSVM learned from the known interactions with high recall (>/=0.95) for each unobserved drug-target interaction. After normalizing all accumulative similarities and signed distances to the range [0,1], we compute the score for each unobserved drug-target interaction via averaging its accumulative similarity and signed distance. Unobserved interactions with lower scores are preferentially served as reliable negative samples for the classification algorithms. The performance of the proposed method is evaluated on the interaction data between 1094 drugs and 1556 target proteins. Extensive comparison experiments using four classical classifiers and one domain predictive method demonstrate the superior performance of the proposed method. A better decision boundary has been learned from the constructed reliable negative samples. CONCLUSIONS: Proper construction of highly-reliable negative samples can help the classification models learn a clear decision boundary which contributes to the performance improvement.

Abstract: BACKGROUND: Accurate identification of potential interactions between drugs and protein targets is a critical step to accelerate drug discovery. Despite many relative experimental researches have been done in the past decades, detecting drug-target interactions (DTIs) remains to be extremely resource-intensive and time-consuming. Therefore, many computational approaches have been developed for predicting drug-target associations on a large scale. RESULTS: In this paper, we proposed an deep learning-based method to predict DTIs only using the information of drug structures and protein sequences. The final results showed that our method can achieve good performance with the accuracies up to 92.0%, 90.0%, 92.0% and 90.7% for the target families of enzymes, ion channels, GPCRs and nuclear receptors of our created dataset, respectively. Another dataset derived from DrugBank was used to further assess the generalization of the model, which yielded an accuracy of 0.9015 and an AUC value of 0.9557. CONCLUSION: It was elucidated that our model shows improved performance in comparison with other state-of-the-art computational methods on the common benchmark datasets. Experimental results demonstrated that our model successfully extracted more nuanced yet useful features, and therefore can be used as a practical tool to discover new drugs. AVAILABILITY: http://deeplearner.ahu.edu.cn/web/CnnDTI.htm.

Abstract: BACKGROUND: Drug-drug interactions (DDIs) are a major concern in patients' medication. It's unfeasible to identify all potential DDIs using experimental methods which are time-consuming and expensive. Computational methods provide an effective strategy, however, facing challenges due to the lack of experimentally verified negative samples. RESULTS: To address this problem, we propose a novel positive-unlabeled learning method named DDI-PULearn for large-scale drug-drug-interaction predictions. DDI-PULearn first generates seeds of reliable negatives via OCSVM (one-class support vector machine) under a high-recall constraint and via the cosine-similarity based KNN (k-nearest neighbors) as well. Then trained with all the labeled positives (i.e., the validated DDIs) and the generated seed negatives, DDI-PULearn employs an iterative SVM to identify a set of entire reliable negatives from the unlabeled samples (i.e., the unobserved DDIs). Following that, DDI-PULearn represents all the labeled positives and the identified negatives as vectors of abundant drug properties by a similarity-based method. Finally, DDI-PULearn transforms these vectors into a lower-dimensional space via PCA (principal component analysis) and utilizes the compressed vectors as input for binary classifications. The performance of DDI-PULearn is evaluated on simulative prediction for 149,878 possible interactions between 548 drugs, comparing with two baseline methods and five state-of-the-art methods. Related experiment results show that the proposed method for the representation of DDIs characterizes them accurately. DDI-PULearn achieves superior performance owing to the identified reliable negatives, outperforming all other methods significantly. In addition, the predicted novel DDIs suggest that DDI-PULearn is capable to identify novel DDIs. CONCLUSIONS: The results demonstrate that positive-unlabeled learning paves a new way to tackle the problem caused by the lack of experimentally verified negatives in the computational prediction of DDIs.

Abstract: BACKGROUND: A drug-drug interaction (DDI) is defined as a drug effect modified by another drug, which is very common in treating complex diseases such as cancer. Many studies have evidenced that some DDIs could be an increase or a decrease of the drug effect. However, the adverse DDIs maybe result in severe morbidity and even morality of patients, which also cause some drugs to withdraw from the market. As the multi-drug treatment becomes more and more common, identifying the potential DDIs has become the key issue in drug development and disease treatment. However, traditional biological experimental methods, including in vitro and vivo, are very time-consuming and expensive to validate new DDIs. With the development of high-throughput sequencing technology, many pharmaceutical studies and various bioinformatics data provide unprecedented opportunities to study DDIs. RESULT: In this study, we propose a method to predict new DDIs, namely DDIGIP, which is based on Gaussian Interaction Profile (GIP) kernel on the drug-drug interaction profiles and the Regularized Least Squares (RLS) classifier. In addition, we also use the k-nearest neighbors (KNN) to calculate the initial relational score in the presence of new drugs via the chemical, biological, phenotypic data of drugs. We compare the prediction performance of DDIGIP with other competing methods via the 5-fold cross validation, 10-cross validation and de novo drug validation. CONLUSION: In 5-fold cross validation and 10-cross validation, DDRGIP method achieves the area under the ROC curve (AUC) of 0.9600 and 0.9636 which are better than state-of-the-art method (L1 Classifier ensemble method) of 0.9570 and 0.9599. Furthermore, for new drugs, the AUC value of DDIGIP in de novo drug validation reaches 0.9262 which also outperforms the other state-of-the-art method (Weighted average ensemble method) of 0.9073. Case studies and these results demonstrate that DDRGIP is an effective method to predict DDIs while being beneficial to drug development and disease treatment.

Abstract: Lipid based formulations (LBFs) are commonly employed to enhance the absorption of highly lipophilic, poorly water-soluble drugs. However, the utility of LBFs can be limited by low drug solubility in the formulation. Isolation of ionizable drugs as low melting, lipophilic salts or ionic liquids (ILs) provides one means to enhance drug solubility in LBFs. However, whether different ILs benefit from formulation in different LBFs is largely unknown. In the current studies, lumefantrine was isolated as a number of different lipophilic salt/ionic liquid forms and performance was assessed after formulation in a range of LBFs. The solubility of lumefantrine in LBF was enhanced 2- to 80-fold by isolation as the lumefantrine docusate IL when compared to lumefantrine free base. The increase in drug loading subsequently enhanced concentrations in the aqueous phase of model intestinal fluids during in vitro dispersion and digestion testing of the LBF. To assess in vivo performance, the systemic exposure of lumefantrine docusate after administration in Type II-MCF, IIIB-MCF, IIIB-LCF, and IV formulations was evaluated after oral administration to rats. In vivo exposure was compared to control lipid and aqueous suspension formulations of lumefantrine free base. Lumefantrine docusate in the Type IIIB-LCF showed significantly higher plasma exposure compared to all other formulations (up to 35-fold higher). The data suggest that isolation of a lipid-soluble IL, coupled with an appropriate formulation, is a viable means to increase drug dose in an oral formulation and to enhance exposure of lumefantrine in vivo.

Abstract: While the opportunities available for targeting RNA with small molecules have been widely appreciated, the challenges associated with achieving specific RNA recognition in biological systems have hindered progress and prevented many researchers from entering the field. To facilitate the discovery of RNA-targeted chemical probes and their subsequent applications, we curated the RNA-targeted BIoactive ligaNd Database (R-BIND). This collection contains an array of information on reported chemical probes that target non-rRNA and have biological activity, and analysis has led to the discovery of RNA-privileged properties. Herein, we developed an online platform to make this information freely available to the community, offering search options, a suite of tools for probe development, and an updated R-BIND data set with detailed experimental information for each probe. We repeated the previous cheminformatics analysis on the updated R-BIND list and found that the distinguishing physicochemical, structural, and spatial properties remained unchanged, despite an almost 50% increase in the database size. Further, we developed several user-friendly tools, including queries based on cheminformatic parameters, experimental details, functional groups, and substructures. In addition, a nearest neighbor algorithm can assess the similarity of user-uploaded molecules to R-BIND ligands. These tools and resources can be used to design small molecule libraries, optimize lead ligands, or select targets, probes, assays, and control experiments. Chemical probes are critical to the study and discovery of novel functions for RNA, and we expect this resource to greatly assist researchers in exploring and developing successful RNA-targeted probes.

Abstract: BACKGROUND: Computational prediction of a phenotypic response upon the chemical perturbation on a biological system plays an important role in drug discovery, and many other applications. Chemical fingerprints are a widely used feature to build machine learning models. However, the fingerprints that are derived from chemical structures ignore the biological context, thus, they suffer from several problems such as the activity cliff and curse of dimensionality. Fundamentally, the chemical modulation of biological activities is a multi-scale process. It is the genome-wide chemical-target interactions that modulate chemical phenotypic responses. Thus, the genome-scale chemical-target interaction profile will more directly correlate with in vitro and in vivo activities than the chemical structure. Nevertheless, the scope of direct application of the chemical-target interaction profile is limited due to the severe incompleteness, biasness, and noisiness of bioassay data. RESULTS: To address the aforementioned problems, we developed a novel chemical representation method: Latent Target Interaction Profile (LTIP). LTIP embeds chemicals into a low dimensional continuous latent space that represents genome-scale chemical-target interactions. Subsequently LTIP can be used as a feature to build machine learning models. Using the drug sensitivity of cancer cell lines as a benchmark, we have shown that the LTIP robustly outperforms chemical fingerprints regardless of machine learning algorithms. Moreover, the LTIP is complementary with the chemical fingerprints. It is possible for us to combine LTIP with other fingerprints to further improve the performance of bioactivity prediction. CONCLUSIONS: Our results demonstrate the potential of LTIP in particular and multi-scale modeling in general in predictive modeling of chemical modulation of biological activities.

Abstract: BACKGROUND: Current approaches to identifying drug-drug interactions (DDIs), include safety studies during drug development and post-marketing surveillance after approval, offer important opportunities to identify potential safety issues, but are unable to provide complete set of all possible DDIs. Thus, the drug discovery researchers and healthcare professionals might not be fully aware of potentially dangerous DDIs. Predicting potential drug-drug interaction helps reduce unanticipated drug interactions and drug development costs and optimizes the drug design process. Methods for prediction of DDIs have the tendency to report high accuracy but still have little impact on translational research due to systematic biases induced by networked/paired data. In this work, we aimed to present realistic evaluation settings to predict DDIs using knowledge graph embeddings. We propose a simple disjoint cross-validation scheme to evaluate drug-drug interaction predictions for the scenarios where the drugs have no known DDIs. RESULTS: We designed different evaluation settings to accurately assess the performance for predicting DDIs. The settings for disjoint cross-validation produced lower performance scores, as expected, but still were good at predicting the drug interactions. We have applied Logistic Regression, Naive Bayes and Random Forest on DrugBank knowledge graph with the 10-fold traditional cross validation using RDF2Vec, TransE and TransD. RDF2Vec with Skip-Gram generally surpasses other embedding methods. We also tested RDF2Vec on various drug knowledge graphs such as DrugBank, PharmGKB and KEGG to predict unknown drug-drug interactions. The performance was not enhanced significantly when an integrated knowledge graph including these three datasets was used. CONCLUSION: We showed that the knowledge embeddings are powerful predictors and comparable to current state-of-the-art methods for inferring new DDIs. We addressed the evaluation biases by introducing drug-wise and pairwise disjoint test classes. Although the performance scores for drug-wise and pairwise disjoint seem to be low, the results can be considered to be realistic in predicting the interactions for drugs with limited interaction information.

Abstract: Salvia miltiorrhiza-Dalbergia odorifera coupled-herbs (SMDOCH) has been used to treat coronary heart disease (CHD) for thousands of years, but its unclear bioactive components and mechanisms greatly limit its clinical application. In this study, for the first time, we used network pharmacology to elucidate the mechanisms of action of SMDOCH on CHD. We collected 270 SMDOCH-related targets from 74 bioactive components and 375 CHD-related targets, with 58 overlapping common targets. Next, we performed enrichment analysis for common-target network and protein-protein interaction (PPI) network. The results showed that SMDOCH affected CHD mainly through 10 significant signaling pathways in three biological processes: 'vascular endothelial function regulation', 'inflammatory response', and 'lipid metabolism'. Six pathways belonged to the 'vascular endothelial function regulation' model, which primarily regulated hormone (renin, angiotensin, oestrogen) activity, and included three key upstream pathways that influence vascular endothelial function, namely KEGG:04933, KEGG:05418, and KEGG:04066. Three pathways, namely KEGG:04668, KEGG:04064, and KEGG:04620, belonged to the 'inflammatory response' model. One pathway (KEGG:04920) belonged to the 'lipid metabolism' model. To some extent, this study revealed the potential bioactive components and pharmacological mechanisms of SMDOCH on CHD, and provided a new direction for the development of new drugs for the treatment of CHD.

Abstract: Long noncoding RNAs (lncRNAs) have multiple regulatory roles and are involved in many human diseases. A potential therapeutic strategy based on targeting lncRNAs was recently developed. To gain insight into the global relationship between small molecule drugs and their affected lncRNAs, we constructed a small molecule lncRNA network consisting of 1206 nodes (1033 drugs and 173 lncRNAs) and 4770 drug-lncRNA associations using LNCmap, which reannotated the microarray data from the Connectivity Map (CMap) database. Based on network biology, we found that the connected drug pairs tended to share the same targets, indications, and side effects. In addition, the connected drug pairs tended to have a similar structure. By inferring the functions of lncRNAs through their co-expressing mRNAs, we found that lncRNA functions related to the modular interface were associated with the mode of action or side effects of the corresponding connected drugs, suggesting that lncRNAs may directly/indirectly participate in specific biological processes after drug administration. Finally, we investigated the tissue-specificity of drug-affected lncRNAs and found that some kinds of drugs tended to have a broader influence (e.g. antineoplastic and immunomodulating drugs), whereas some tissue-specific lncRNAs (nervous system) tended to be affected by multiple types of drugs.