Abstract: BACKGROUND: Computational drug repositioning, which aims to find new applications for existing drugs, is gaining more attention from the pharmaceutical companies due to its low attrition rate, reduced cost, and shorter timelines for novel drug discovery. Nowadays, a growing number of researchers are utilizing the concept of recommendation systems to answer the question of drug repositioning. Nevertheless, there still lie some challenges to be addressed: 1) Learning ability deficiencies; the adopted model cannot learn a higher level of drug-disease associations from the data. 2) Data sparseness limits the generalization ability of the model. 3)Model is easy to overfit if the effect of negative samples is not taken into consideration. RESULTS: In this study, we propose a novel method for computational drug repositioning, Additional Neural Matrix Factorization (ANMF). The ANMF model makes use of drug-drug similarities and disease-disease similarities to enhance the representation information of drugs and diseases in order to overcome the matter of data sparsity. By means of a variant version of the autoencoder, we were able to uncover the hidden features of both drugs and diseases. The extracted hidden features will then participate in a collaborative filtering process by incorporating the Generalized Matrix Factorization (GMF) method, which will ultimately give birth to a model with a stronger learning ability. Finally, negative sampling techniques are employed to strengthen the training set in order to minimize the likelihood of model overfitting. The experimental results on the Gottlieb and Cdataset datasets show that the performance of the ANMF model outperforms state-of-the-art methods. CONCLUSIONS: Through performance on two real-world datasets, we believe that the proposed model will certainly play a role in answering to the major challenge in drug repositioning, which lies in predicting and choosing new therapeutic indications to prospectively test for a drug of interest.

Abstract: BACKGROUND: Recently, there has been an increasing tendency to go back to nature in search of new medicines. To facilitate this, a great deal of effort has been made to compile information on natural products worldwide, and as a result, many ethnic-based traditional medicine databases have been developed. In Ethiopia, there are more than 80 ethnic groups, each having their indigenous knowledge on the use of traditional medicine. About 80% of the population uses traditional medicine for primary health care. Despite this, there is no structured online database for Ethiopian traditional medicine, which limits natural products based drug discovery researches using natural products from this country. DESCRIPTION: To develop ETM-DB, online research articles, theses, books, and public databases containing Ethiopian herbal medicine and phytochemicals information were searched. These resources were thoroughly inspected and the necessary data were extracted. Then, we developed a comprehensive online relational database which contains information on 1054 Ethiopian medicinal herbs with 1465 traditional therapeutic uses, 573 multi-herb prescriptions, 4285 compounds, 11,621 human target gene/proteins, covering 5779 herb-phenotype, 1879 prescription-herb, 16,426 herb-compound, 105,202 compound-phenotype, 162,632 compound-gene/protein, and 16,584 phenotype-gene/protein relationships. Using various cheminformatics tools, we obtained predicted physicochemical and absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties of ETM-DB compounds. We also evaluated drug-likeness properties of these compounds using FAF-Drugs4 webserver. From the 4285 compounds, 4080 of them passed the FAF-Drugs4 input data curation stage, of which 876 were found to have acceptable drug-likeness properties. CONCLUSION: ETM-DB is the largest, freely accessible, web-based integrated resource on Ethiopian traditional medicine. It provides traditional herbal medicine entities and their relationships in well-structured forms including reference to the sources. The ETM-DB website interface allows users to search the entities using various options provided by the search menu. We hope that our database will expedite drug discovery and development researches from Ethiopian natural products as it contains information on the chemical composition and related human target gene/proteins. The current version of ETM-DB is openly accessible at http://biosoft.kaist.ac.kr/etm .

Abstract: Natural products, including traditional herbal medicine (THM), are known to exert their therapeutic effects by acting on multiple targets, so researchers have employed network pharmacology methods to decipher the potential mechanisms of THM. To conduct THM-network pharmacology (THM-NP) studies, researchers have employed different tools and databases for constructing and analyzing herb-compound-target networks. In this study, we attempted to capture the methodological trends in THM-NP research. We identified the tools and databases employed to conduct THM-NP studies and visualized their combinatorial patterns. We also constructed co-author and affiliation networks to further understand how the methodologies are employed among researchers. The results showed that the number of THM-NP studies and employed databases/tools have been dramatically increased in the last decade, and there are characteristic patterns in combining methods of each analysis step in THM-NP studies. Overall, the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform (TCMSP) was the most frequently employed network pharmacology database in THM-NP studies. Among the processes involved in THM-NP research, the methodology for constructing a compound-target network has shown the greatest change over time. In summary, our analysis describes comprehensive methodological trends and current ideas in research design for network pharmacology researchers.

Abstract: Receptor tyrosine kinase (RTK)-mediated hyperactivation of the MAPK/Erk pathway is responsible for a large number of pathogenic outcomes including many cancers. Considerable effort has been directed at targeting this pathway with varying degrees of long term therapeutic success. Under non-stimulated conditions Erk is bound to the adaptor protein Shc preventing aberrant signalling by sequestering Erk from activation by Mek. Activated RTK recruits Shc, via its phosphotyrosine binding (PTB) domain (Shc(PTB)), precipitating the release of Erk to engage in a signalling response. Here we describe a novel approach to inhibition of MAP kinase signal transduction through attempting to preserve the Shc-Erk complex under conditions of activated receptor. A library of existing drug molecules was computationally screened for hits that would bind to the Shc(PTB) and block its interaction with the RTKs EGFR and ErbB2. The primary hit from the screen was indomethacin, a non-steroidal anti-inflammatory drug. Validation of this molecule in vitro and in cellular efficacy studies in cancer cells provides proof of principle of the approach to pathway down-regulation and a potential optimizable lead compound.

Abstract: PubChem is a chemical data repository that provides comprehensive information on various chemical entities. It contains a wealth of chemical information from hundreds of data sources. Programmatic access to this large amount of data provides researchers with new opportunities for data-intensive research. PubChem provides several programmatic access routes. One of these is PUG-View, which is a Representational State Transfer (REST)-style web service interface specialized for accessing annotation data contained in PubChem. The present paper describes various aspects of PUG-View, including the scope of data accessible through PUG-View, the syntax for formulating a PUG-View request URL, the difference of PUG-View from other web service interfaces in PubChem, and its limitations and usage policies.

Abstract: One key issue in the post-genomic era is how to systematically describe the associations between small molecule transcripts or translations inside cells. With the rapid development of high-throughput "omics" technologies, the achieved ability to detect and characterize molecules with other molecule targets opens the possibility of investigating the relationships between different molecules from a global perspective. In this article, a molecular association network (MAN) is constructed and comprehensively analyzed by integrating the associations among miRNA, lncRNA, protein, drug, and disease, in which any kind of potential associations can be predicted. More specifically, each node in MAN can be represented as a vector by combining two kinds of information including the attribute of the node itself (e.g., sequences of ncRNAs and proteins, semantics of diseases and molecular fingerprints of drugs) and the behavior of the node in the complex network (associations with other nodes). A random forest classifier is trained to classify and predict new interactions or associations between biomolecules. In the experiment, the proposed method achieved a superb performance with an area under curve (AUC) of 0.9735 under a five-fold cross-validation, which showed that the proposed method could provide new insight for exploration of the molecular mechanisms of disease and valuable clues for disease treatment.

Abstract: BACKGROUND: Predicting the effect of drug-drug interactions (DDIs) precisely is important for safer and more effective drug co-prescription. Many computational approaches to predict the effect of DDIs have been proposed, with the aim of reducing the effort of identifying these interactions in vivo or in vitro, but room remains for improvement in prediction performance. RESULTS: In this study, we propose a novel deep learning model to predict the effect of DDIs more accurately.. The proposed model uses autoencoders and a deep feed-forward network that are trained using the structural similarity profiles (SSP), Gene Ontology (GO) term similarity profiles (GSP), and target gene similarity profiles (TSP) of known drug pairs to predict the pharmacological effects of DDIs. The results show that GSP and TSP increase the prediction accuracy when using SSP alone, and the autoencoder is more effective than PCA for reducing the dimensions of each profile. Our model showed better performance than the existing methods, and identified a number of novel DDIs that are supported by medical databases or existing research. CONCLUSIONS: We present a novel deep learning model for more accurate prediction of DDIs and their effects, which may assist in future research to discover novel DDIs and their pharmacological effects.

Abstract: BACKGROUND: Individualized drug response prediction is vital for achieving personalized treatment of cancer and moving precision medicine forward. Large-scale multi-omics profiles provide unprecedented opportunities for precision cancer therapy. METHODS: In this study, we propose a pipeline to identify subpathway signatures for anticancer drug response of individuals by integrating the comprehensive contributions of multiple genetic and epigenetic (gene expression, copy number variation and DNA methylation) alterations. RESULTS: Totally, 46 subpathway signatures associated with individual responses to different anticancer drugs were identified based on five cancer-drug response datasets. We have validated the reliability of subpathway signatures in two independent datasets. Furthermore, we also demonstrated these multi-omics subpathway signatures could significantly improve the performance of anticancer drug response prediction. In-depth analysis of these 46 subpathway signatures uncovered the essential roles of three omics types and the functional associations underlying different anticancer drug responses. Patient stratification based on subpathway signatures involved in anticancer drug response identified subtypes with different clinical outcomes, implying their potential roles as prognostic biomarkers. In addition, a landscape of subpathways associated with cellular responses to 191 anticancer drugs from CellMiner was provided and the mechanism similarity of drug action was accurately unclosed based on these subpathways. Finally, we constructed a user-friendly web interface-CancerDAP ( http://bio-bigdata.hrbmu.edu.cn/CancerDAP/ ) available to explore 2751 subpathways relevant with 191 anticancer drugs response. CONCLUSIONS: Taken together, our study identified and systematically characterized subpathway signatures for individualized anticancer drug response prediction, which may promote the precise treatment of cancer and the study for molecular mechanisms of drug actions.

Abstract: Uncovering drug-target interactions (DTIs) is pivotal to understand drug mode-of-action (MoA), avoid adverse drug reaction (ADR), and seek opportunities for drug repositioning (DR). For decades, in silico predictions for DTIs have largely depended on structural information of both targets and compounds, e.g., docking or ligand-based virtual screening. Recently, the application of deep neural network (DNN) is opening a new path to uncover novel DTIs for thousands of targets. One important question is which features for targets are most relevant to DTI prediction. As an early attempt to answer this question, we objectively compared three canonical target features extracted from: (i) the expression profiles by gene knockdown (GEPs); (ii) the protein-protein interaction network (PPI network); and (iii) the pathway membership (PM) of a target gene. For drug features, the large-scale drug-induced transcriptome dataset, or the Library of Integrated Network-based Cellular Signatures (LINCS) L1000 dataset was used. All these features are closely related to protein function or drug MoA, of which utility is only sparsely investigated. In particular, few studies have compared the three types of target features in DNN-based DTI prediction under the same evaluation scheme. Among the three target features, the PM and the PPI network show similar performances superior to GEPs. DNN models based on both features consistently outperformed other machine learning methods such as naive Bayes, random forest, or logistic regression.

Abstract: Recent advances in DNA/RNA sequencing have made it possible to identify new targets rapidly and to repurpose approved drugs for treating heterogeneous diseases by the 'precise' targeting of individualized disease modules. In this study, we develop a Genome-wide Positioning Systems network (GPSnet) algorithm for drug repurposing by specifically targeting disease modules derived from individual patient's DNA and RNA sequencing profiles mapped to the human protein-protein interactome network. We investigate whole-exome sequencing and transcriptome profiles from ~5,000 patients across 15 cancer types from The Cancer Genome Atlas. We show that GPSnet-predicted disease modules can predict drug responses and prioritize new indications for 140 approved drugs. Importantly, we experimentally validate that an approved cardiac arrhythmia and heart failure drug, ouabain, shows potential antitumor activities in lung adenocarcinoma by uniquely targeting a HIF1alpha/LEO1-mediated cell metabolism pathway. In summary, GPSnet offers a network-based, in silico drug repurposing framework for more efficacious therapeutic selections.