Netpredictor: R and Shiny package to perform drug-target network analysis and prediction of missing links

Network pharmacology and experimental validation for deciphering the action mechanism of Fritillaria cirrhosa D. Don constituents in suppressing breast carcinoma

Fritillaria cirrhosa D. Don is a well-known medicinal plant of Kashmir Himalaya. Traditionally, it has been used to treat several diseases, including cancer. However, the molecular mechanism behind anticancer activity remains unclear. Therefore, in the present study, we have performed high performance-liquid chromatography-mass spectrometry (HR-LC/MS), network pharmacology, molecular docking and molecular dynamic (MD) simulation methods were used to explore the underlying molecular mechanism of F. cirrhosa for the treatment of breast cancer (BC). The targets of F. cirrhosa for treating BC were predicted using databases like SwissTargetPrediction, Gene Cards and OMIM. Protein-protein interaction analysis and network construction were performed using the Search Tool for the Retrieval of Interacting Genes/Proteins programme, and analysis of Gene Ontology term enrichment and Kyoto Encyclopedia of Genes and Genomes pathway enrichment was done using the Cytoscape programme. In addition, molecular docking was used to investigate intermolecular interactions between the compounds and the proteins using the Autodock tool. MD simulations studies were also used to explore the stability of the representative AKT1 gene peiminine and Imperialine-3-β-glucoside. In addition, experimental treatment of F. cirrhosa was also verified. HR-LC/MS detected the presence of several secondary metabolites. Afterward, molecular docking was used to verify the effective activity of the active ingredients against the prospective targets. Additionally, Peiminine and Imperialine-3-β-glucoside showed the highest binding energy score against AKT-1 (-12.99 kcal/mol and -12.08 kcal/mol). AKT1 with Peiminine and Imperialine-3-β-glucoside was further explored for MD simulations. During the MD simulation study at 100 nanoseconds, a stable complex formation of AKT1 + Peiminine and Imperialine-3-β-glucoside was observed. The binding free energy calculations using MM/GBSA showed significant binding of the ligand with protein (ΔG: -79.83 ± 3.0 kcal/mol) between AKT1 + Peiminine was observed. The principal component analysis exhibited a stable converged structure by achieving global motion. Lastly, F. cirrhosa extracts also exhibited momentous anticancer activity through in vitro studies. Therefore, present study revealed the molecular mechanism of F. cirrhosa constituents for the effective treatment of BC by deactivating various multiple gene targets, multiple pathways particularly the PI3K-Akt signaling pathway. These findings emphasized the momentous anti-BC activity of F. cirrhosa constituents.Communicated by Ramaswamy H. Sarma.

Graph Transformer for Drug Response Prediction

BACKGROUND

Previous models have shown that learning drug features from their graph representation is more efficient than learning from their strings or numeric representations. Furthermore, integrating multi-omics data of cell lines increases the performance of drug response prediction. However, these models have shown drawbacks in extracting drug features from graph representation and incorporating redundancy information from multi-omics data. This paper proposes a deep learning model, GraTransDRP, to better drug representation and reduce information redundancy. First, the Graph transformer was utilized to extract the drug representation more efficiently. Next, Convolutional neural networks were used to learn the mutation, meth, and transcriptomics features. However, the dimension of transcriptomics features was up to 17737. Therefore, KernelPCA was applied to transcriptomics features to reduce the dimension and transform them into a dense presentation before putting them through the CNN model. Finally, drug and omics features were combined to predict a response value by a fully connected network. Experimental results show that our model outperforms some state-of-the-art methods, including GraphDRP and GraOmicDRP.

Artificial intelligence in cancer target identification and drug discovery

Artificial intelligence is an advanced method to identify novel anticancer targets and discover novel drugs from biology networks because the networks can effectively preserve and quantify the interaction between components of cell systems underlying human diseases such as cancer. Here, we review and discuss how to employ artificial intelligence approaches to identify novel anticancer targets and discover drugs. First, we describe the scope of artificial intelligence biology analysis for novel anticancer target investigations. Second, we review and discuss the basic principles and theory of commonly used network-based and machine learning-based artificial intelligence algorithms. Finally, we showcase the applications of artificial intelligence approaches in cancer target identification and drug discovery. Taken together, the artificial intelligence models have provided us with a quantitative framework to study the relationship between network characteristics and cancer, thereby leading to the identification of potential anticancer targets and the discovery of novel drug candidates.

Integrating Molecular Graph Data of Drugs and Multiple -Omic Data of Cell Lines for Drug Response Prediction

Previous studies have either learned drug's features from their string or numeric representations, which are not natural forms of drugs, or only used genomic data of cell lines for the drug response prediction problem. Here, we proposed a deep learning model, GraOmicDRP, to learn drug's features from their graph representation and integrate multiple -omic data of cell lines. In GraOmicDRP, drugs are represented as graphs of bindings among atoms; meanwhile, cell lines are depicted by not only genomic but also transcriptomic and epigenomic data. Graph convolutional and convolutional neural networks were used to learn the representation of drugs and cell lines, respectively. A combination of the two representations was then used to be representative of each pair of drug-cell line. Finally, the response value of each pair was predicted by a fully connected network. Experimental results indicate that transcriptomic data shows the best among single -omic data; meanwhile, the combinations of transcriptomic and other -omic data achieved the best performance overall in terms of both Root Mean Square Error and Pearson correlation coefficient. In addition, we also show that GraOmicDRP outperforms some state-of-the-art methods, including ones integrating -omic data with drug information such as GraphDRP, and ones using -omic data without drug information such as DeepDR and MOLI.

Machine learning approaches and databases for prediction of drug-target interaction: a survey paper

The task of predicting the interactions between drugs and targets plays a key role in the process of drug discovery. There is a need to develop novel and efficient prediction approaches in order to avoid costly and laborious yet not-always-deterministic experiments to determine drug–target interactions (DTIs) by experiments alone. These approaches should be capable of identifying the potential DTIs in a timely manner. In this article, we describe the data required for the task of DTI prediction followed by a comprehensive catalog consisting of machine learning methods and databases, which have been proposed and utilized to predict DTIs. The advantages and disadvantages of each set of methods are also briefly discussed. Lastly, the challenges one may face in prediction of DTI using machine learning approaches are highlighted and we conclude by shedding some lights on important future research directions.

DTI-CDF: a cascade deep forest model towards the prediction of drug-target interactions based on hybrid features

Drug-target interactions (DTIs) play a crucial role in target-based drug discovery and development. Computational prediction of DTIs can effectively complement experimental wet-lab techniques for the identification of DTIs, which are typically time- and resource-consuming. However, the performances of the current DTI prediction approaches suffer from a problem of low precision and high false-positive rate. In this study, we aim to develop a novel DTI prediction method for improving the prediction performance based on a cascade deep forest (CDF) model, named DTI-CDF, with multiple similarity-based features between drugs and the similarity-based features between target proteins extracted from the heterogeneous graph, which contains known DTIs. In the experiments, we built five replicates of 10-fold cross-validation under three different experimental settings of data sets, namely, corresponding DTI values of certain drugs (SD), targets (ST), or drug-target pairs (SP) in the training sets are missed but existed in the test sets. The experimental results demonstrate that our proposed approach DTI-CDF achieves a significantly higher performance than that of the traditional ensemble learning-based methods such as random forest and XGBoost, deep neural network, and the state-of-the-art methods such as DDR. Furthermore, there are 1352 newly predicted DTIs which are proved to be correct by KEGG and DrugBank databases. The data sets and source code are freely available at https://github.com//a96123155/DTI-CDF.

Regulation of cell-type-specific transcriptomes by microRNA networks during human brain development

MicroRNAs (miRNAs) regulate many cellular events during brain development by interacting with hundreds of mRNA transcripts. However, miRNAs operate nonuniformly upon the transcriptional profile with an as yet unknown logic. Shortcomings in defining miRNA-mRNA networks include limited knowledge of in vivo miRNA targets and their abundance in single cells. By combining multiple complementary approaches, high-throughput sequencing of RNA isolated by cross-linking immunoprecipitation with an antibody to AGO2 (AGO2-HITS-CLIP), single-cell profiling and computational analyses using bipartite and coexpression networks, we show that miRNA-mRNA interactions operate as functional modules that often correspond to cell-type identities and undergo dynamic transitions during brain development. These networks are highly dynamic during development and over the course of evolution. One such interaction is between radial-glia-enriched ORC4 and miR-2115, a great-ape-specific miRNA, which appears to control radial glia proliferation rates during human brain development.

Bipartite graphs in systems biology and medicine: a survey of methods and applications

The latest advances in high-throughput techniques during the past decade allowed the systems biology field to expand significantly. Today, the focus of biologists has shifted from the study of individual biological components to the study of complex biological systems and their dynamics at a larger scale. Through the discovery of novel bioentity relationships, researchers reveal new information about biological functions and processes. Graphs are widely used to represent bioentities such as proteins, genes, small molecules, ligands, and others such as nodes and their connections as edges within a network. In this review, special focus is given to the usability of bipartite graphs and their impact on the field of network biology and medicine. Furthermore, their topological properties and how these can be applied to certain biological case studies are discussed. Finally, available methodologies and software are presented, and useful insights on how bipartite graphs can shape the path toward the solution of challenging biological problems are provided.