EndoNet: an information resource about the intercellular signaling network

Predicting herb-disease associations using network-based measures in human protein interactome

BACKGROUND

Natural herbs are frequently used to treat diseases or to relieve symptoms in many countries. Moreover, as their safety has been proven for a long time, they are considered as main sources of new drug development. However, in many cases, the herbs are still prescribed relying on ancient records and/or traditional practices without scientific evidences. More importantly, the medicinal efficacy of the herbs has to be evaluated in the perspective of MCMT (multi-compound multi-target) effects, but most efforts focus on identifying and analyzing a single compound experimentally. To overcome these hurdles, computational approaches which are based on the scientific evidences and are able to handle the MCMT effects are needed to predict the herb-disease associations.

RESULTS

In this study, we proposed a network-based in silico method to predict the herb-disease associations. To this end, we devised a new network-based measure, WACP (weighted average closest path length), which not only quantifies proximity between herb-related genes and disease-related genes but also considers compound compositions of each herb. As a result, we confirmed that our method successfully predicts the herb-disease associations in the human protein interactome (AUROC = 0.777). In addition, we observed that our method is superior than the other simple network-based proximity measures (e.g. average shortest and closest path length). Additionally, we analyzed the associations between Brassica oleracea var. italica and its known associated diseases more specifically as case studies. Finally, based on the prediction results of the WACP, we suggested novel herb-disease pairs which are expected to have potential relations and their literature evidences.

CONCLUSIONS

This method could be a promising solution to modernize the use of the natural herbs by providing the scientific evidences about the molecular associations between the herb-related genes targeted by multiple compounds and the disease-related genes in the human protein interactome.

HormoNet: a deep learning approach for hormone-drug interaction prediction

Several experimental evidences have shown that the human endogenous hormones can interact with drugs in many ways and affect drug efficacy. The hormone drug interactions (HDI) are essential for drug treatment and precision medicine; therefore, it is essential to understand the hormone-drug associations. Here, we present HormoNet to predict the HDI pairs and their risk level by integrating features derived from hormone and drug target proteins. To the best of our knowledge, this is one of the first attempts to employ deep learning approach for prediction of HDI prediction. Amino acid composition and pseudo amino acid composition were applied to represent target information using 30 physicochemical and conformational properties of the proteins. To handle the imbalance problem in the data, we applied synthetic minority over-sampling technique technique. Additionally, we constructed novel datasets for HDI prediction and the risk level of their interaction. HormoNet achieved high performance on our constructed hormone-drug benchmark datasets. The results provide insights into the understanding of the relationship between hormone and a drug, and indicate the potential benefit of reducing risk levels of interactions in designing more effective therapies for patients in drug treatments. Our benchmark datasets and the source codes for HormoNet are available in: https://github.com/EmamiNeda/HormoNet .

Hmrbase2: a comprehensive database of hormones and their receptors

PURPOSE

Hormones play a critical role in regulating various physiological processes and any hormonal imbalances can lead to major endocrine disorders. Thus, studying hormones is essential for both the therapeutics and the diagnostics of hormonal diseases. To facilitate this need, we have developed Hmrbase2, a comprehensive platform that provides extensive information on hormones.

METHODS

Hmrbase2 is a web-based database which is an update of a previously published database, Hmrbase ( http://crdd.osdd.net/raghava/hmrbase/ ). We collected a large amount of information on peptide and non-peptide hormones and hormone receptors, this information being sourced from Hmrbase, HMDB, UniProt, HORDB, ENDONET, PubChem, and the medical literature.

RESULTS

Hmrbase2 contains a total of 12,056 entries, which is more than twice the number of entries contained in the previous version Hmrbase. These include 7406, 753, and 3897 entries for peptide hormones, non-peptide hormones, and hormone receptors, respectively, from 803 organisms compared to the 562 organisms in the previous version. The database also hosts 5662 hormone receptor pairs. The source organism, function, and subcellular location are provided for peptide hormones and receptors and properties such as melting point and water solubility is provided for non-peptide hormones. Besides browsing and keyword search, an advanced search option has also been supplied. Additionally, a similarity search module has been incorporated enabling users to run similarity searches against peptide hormone sequences using BLAST and Smith-Waterman.

CONCLUSIONS

To make the database accessible to various users, we designed a user-friendly, responsive website that can be easily used on smartphones, tablets, and desktop computers. The updated database version, Hmrbase2, offers improved data content compared to the previous version. Hmrbase2 is freely available at https://webs.iiitd.edu.in/raghava/hmrbase2 .

Predicting cross-tissue hormone-gene relations using balanced word embeddings

MOTIVATION

Inter-organ/inter-tissue communication is central to multi-cellular organisms including humans, and mapping inter-tissue interactions can advance system-level whole-body modeling efforts. Large volumes of biomedical literature have fostered studies that map within-tissue or tissue-agnostic interactions, but literature-mining studies that infer inter-tissue relations, such as between hormones and genes are solely missing.

RESULTS

We present a first study to predict from biomedical literature the hormone-gene associations mediating inter-tissue signaling in the human body. Our BioEmbedS* models use neural network-based Biomedical word Embeddings with a Support Vector Machine classifier to predict if a hormone-gene pair is associated or not, and whether an associated gene is involved in the hormone's production or response. Model training relies on our unified dataset Hormone-Gene version 1 of ground-truth associations between genes and endocrine hormones, which we compiled and carefully balanced in the embedded space to handle data disparities, such as between poorly- versus well-studied hormones. Our BioEmbedS model recapitulates known gene mediators of tissue-tissue signaling with 70.4% accuracy; predicts novel inter-tissue communication genes in humans, which are enriched for hormone-related disorders; and generalizes well to mouse, thereby holding promise for its extension to other multi-cellular organisms as well.

AVAILABILITY AND IMPLEMENTATION

Freely available at https://cross-tissue-signaling.herokuapp.com are our model predictions & datasets; https://github.com/BIRDSgroup/BioEmbedS has all relevant code.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Learning of Signaling Networks: Molecular Mechanisms

Molecular processes of neuronal learning have been well described. However, learning mechanisms of non-neuronal cells are not yet fully understood at the molecular level. Here, we discuss molecular mechanisms of cellular learning, including conformational memory of intrinsically disordered proteins (IDPs) and prions, signaling cascades, protein translocation, RNAs [miRNA and long noncoding RNA (lncRNA)], and chromatin memory. We hypothesize that these processes constitute the learning of signaling networks and correspond to a generalized Hebbian learning process of single, non-neuronal cells, and we discuss how cellular learning may open novel directions in drug design and inspire new artificial intelligence methods.

CODA-ML: context-specific biological knowledge representation for systemic physiology analysis

Background

Computational analysis of complex diseases involving multiple organs requires the integration of multiple different models into a unified model. Different models are often constructed in heterogeneous formats. Thus, the integration of the models requires a standard language format that can effectively represent essential biological information. However, the previously introduced formats have limitations that prevent from adequately representing essential biological information, particularly specifications of bio-molecules and biological contexts.

Results

We defined an XML-based markup language called context-oriented directed association markup language (CODA-ML), which better represents essential biological information. The CODA-ML has two major strengths in designating molecular specifications and biological contexts. It can cover heterogeneous entity types involved in biological events (e.g. gene/protein, compound, cellular function, disease). Molecular types of entities can have molecular specifications which include detailed information of a molecule from isoforms to modifications, enabling high-resolution representation of molecules. In addition, it can distinguish biological events that vary depending on different biological contexts such as cell types or disease conditions. Especially representation of inter-cellular events as well as intra-cellular events is available. These two major strengths can resolve contradictory associations when different models are integrated into one unified model, which improves the accuracy of the model.

Conclusions

With the CODA-ML, diverse models such as signaling pathways, metabolic pathways, and gene regulatory pathways can be represented in a unified language format. Heterogeneous entity types can be covered by the CODA-ML, thus it enables detailed description for the mechanisms of diseases or drugs from multiple perspectives (e.g., molecule, function or disease). The CODA-ML is expected to help integrate different models into one systemic model in an efficient and effective. The unified model can be used to perform computational analysis not only for cancer but also for other complex diseases involving multiple organs beyond a single cell.

Electronic supplementary material

The online version of this article (10.1186/s12859-019-2812-7) contains supplementary material, which is available to authorized users.

Meta-path Based Prioritization of Functional Drug Actions with Multi-Level Biological Networks

Functional drug actions refer to drug-affected GO terms. They aid in the investigation of drug effects that are therapeutic or adverse. Previous studies have utilized the linkage information between drugs and functions in molecular level biological networks. Since the current knowledge of molecular level mechanisms of biological functions is still limited, such previous studies were incomplete. We expected that the multi-level biological networks would allow us to more completely investigate the functional drug actions. We constructed multi-level biological networks with genes, GO terms, and diseases. Meta-paths were utilized to extract the features of each GO term. We trained 39 SVM models to prioritize the functional drug actions of the various 39 drugs. Through the multi-level networks, more functional drug actions were utilized for the 39 models and inferred by the models. Multi-level based features improved the performance of the models, and the average AUROC value in the cross-validation was 0.86. Moreover, 60% of the candidates were true.

HIDEEP: a systems approach to predict hormone impacts on drug efficacy based on effect paths

Experimental evidence has shown that some of the human endogenous hormones significantly affect drug efficacy. Since hormone status varies with individual physiological states, it is essential to understand the interplay of hormones and drugs for precision medicine. Here, we developed an in silico method to predict interactions between 283 human endogenous hormones and 590 drugs for 20 diseases including cancers and non-cancer diseases. We extracted hormone effect paths and drug effect paths from a large-scale molecular network that contains protein interactions, transcriptional regulations, and signaling interactions. If two kinds of effect paths for a hormone-drug pair intersect closely, we expect that the influence of the hormone on the drug efficacy is significant. It has been shown that the proposed method correctly distinguishes hormone-drug pairs with known interactions from random pairs in blind experiments. In addition, the method can suggest underlying interaction mechanisms at the molecular level so that it helps us to better understand the interplay of hormones and drugs.

CODA: Integrating multi-level context-oriented directed associations for analysis of drug effects

In silico network-based methods have shown promising results in the field of drug development. Yet, most of networks used in the previous research have not included context information even though biological associations actually do appear in the specific contexts. Here, we reconstruct an anatomical context-specific network by assigning contexts to biological associations using protein expression data and scientific literature. Furthermore, we employ the context-specific network for the analysis of drug effects with a proximity measure between drug targets and diseases. Distinct from previous context-specific networks, intercellular associations and phenomic level entities such as biological processes are included in our network to represent the human body. It is observed that performances in inferring drug-disease associations are increased by adding context information and phenomic level entities. In particular, hypertension, a disease related to multiple organs and associated with several phenomic level entities, is analyzed in detail to investigate how our network facilitates the inference of drug-disease associations. Our results indicate that the inclusion of context information, intercellular associations, and phenomic level entities can contribute towards a better prediction of drug-disease associations and provide detailed insight into understanding of how drugs affect diseases in the human body.