De Novo Prediction of Drug Targets and Candidates by Chemical Similarity-Guided Network-Based Inference

Identifying drug–target interactions is a crucial step in discovering novel drugs and for drug repositioning. Network-based methods have shown great potential thanks to the straightforward integration of information from different sources and the possibility of extracting novel information from the graph topology. However, despite recent advances, there is still an urgent need for efficient and robust prediction methods. Here, we present SimSpread, a novel method that combines network-based inference with chemical similarity. This method employs a tripartite drug–drug–target network constructed from protein–ligand interaction annotations and drug–drug chemical similarity on which a resource-spreading algorithm predicts potential biological targets for both known or failed drugs and novel compounds. We describe small molecules as vectors of similarity indices to other compounds, thereby providing a flexible means to explore diverse molecular representations. We show that our proposed method achieves high prediction performance through multiple cross-validation and time-split validation procedures over a series of datasets. In addition, we demonstrate that our method performed a balanced exploration of both chemical ligand space (scaffold hopping) and biological target space (target hopping). Our results suggest robust and balanced performance, and our method may be useful for predicting drug targets, virtual screening, and drug repositioning.     

SAG-DTA: Prediction of Drug–Target Affinity Using Self-Attention Graph Network

The prediction of drug–target affinity (DTA) is a crucial step for drug screening and discovery. In this study, a new graph-based prediction model named SAG-DTA (self-attention graph drug–target affinity) was implemented. Unlike previous graph-based methods, the proposed model utilized self-attention mechanisms on the drug molecular graph to obtain effective representations of drugs for DTA prediction. Features of each atom node in the molecular graph were weighted using an attention score before being aggregated as molecule representation. Various self-attention scoring methods were compared in this study. In addition, two pooing architectures, namely, global and hierarchical architectures, were presented and evaluated on benchmark datasets. Results of comparative experiments on both regression and binary classification tasks showed that SAG-DTA was superior to previous sequence-based or other graph-based methods and exhibited good generalization ability.     

Predicting Drug–Target Interactions Based on the Ensemble Models of Multiple Feature Pairs

Backgroud: The prediction of drug–target interactions (DTIs) is of great significance in drug development. It is time-consuming and expensive in traditional experimental methods. Machine learning can reduce the cost of prediction and is limited by the characteristics of imbalanced datasets and problems of essential feature selection. Methods: The prediction method based on the Ensemble model of Multiple Feature Pairs (Ensemble-MFP) is introduced. Firstly, three negative sets are generated according to the Euclidean distance of three feature pairs. Then, the negative samples of the validation set/test set are randomly selected from the union set of the three negative sets in the validation set/test set. At the same time, the ensemble model with weight is optimized and applied to the test set. Results: The area under the receiver operating characteristic curve (area under ROC, AUC) in three out of four sub-datasets in gold standard datasets was more than 94.0% in the prediction of new drugs. The effectiveness of the proposed method is also shown with the comparison of state-of-the-art methods and demonstration of predicted drug–target pairs. Conclusion: The Ensemble-MFP can weigh the existing feature pairs and has a good prediction effect for general prediction on new drugs.     

CSatDTA: Prediction of Drug–Target Binding Affinity Using Convolution Model with Self-Attention

Drug discovery, which aids to identify potential novel treatments, entails a broad range of fields of science, including chemistry, pharmacology, and biology. In the early stages of drug development, predicting drug–target affinity is crucial. The proposed model, the prediction of drug–target affinity using a convolution model with self-attention (CSatDTA), applies convolution-based self-attention mechanisms to the molecular drug and target sequences to predict drug–target affinity (DTA) effectively, unlike previous convolution methods, which exhibit significant limitations related to this aspect. The convolutional neural network (CNN) only works on a particular region of information, excluding comprehensive details. Self-attention, on the other hand, is a relatively recent technique for capturing long-range interactions that has been used primarily in sequence modeling tasks. The results of comparative experiments show that CSatDTA surpasses previous sequence-based or other approaches and has outstanding retention abilities.     

HLGNN-MDA: Heuristic Learning Based on Graph Neural Networks for miRNA–Disease Association Prediction

Identifying disease-related miRNAs can improve the understanding of complex diseases. However, experimentally finding the association between miRNAs and diseases is expensive in terms of time and resources. The computational screening of reliable miRNA–disease associations has thus become a necessary tool to guide biological experiments. “Similar miRNAs will be associated with the same disease” is the assumption on which most current miRNA–disease association prediction methods rely; however, biased prior knowledge, and incomplete and inaccurate miRNA similarity data and disease similarity data limit the performance of the model. Here, we propose heuristic learning based on graph neural networks to predict microRNA–disease associations (HLGNN-MDA). We learn the local graph topology features of the predicted miRNA–disease node pairs using graph neural networks. In particular, our improvements to the graph convolution layer of the graph neural network enable it to learn information among homogeneous nodes and among heterogeneous nodes. We illustrate the performance of HLGNN-MDA by performing tenfold cross-validation against excellent baseline models. The results show that we have promising performance in multiple metrics. We also focus on the role of the improvements to the graph convolution layer in the model. The case studies are supported by evidence on breast cancer, hepatocellular carcinoma and renal cell carcinoma. Given the above, the experiments demonstrate that HLGNN-MDA can serve as a reliable method to identify novel miRNA–disease associations.     

Identifying Drug Targets of Oral Squamous Cell Carcinoma through a Systems Biology Method and Genome-Wide Microarray Data for Drug Discovery by Deep Learning and Drug Design Specifications

In this study, we provide a systems biology method to investigate the carcinogenic mechanism of oral squamous cell carcinoma (OSCC) in order to identify some important biomarkers as drug targets. Further, a systematic drug discovery method with a deep neural network (DNN)-based drug–target interaction (DTI) model and drug design specifications is proposed to design a potential multiple-molecule drug for the medical treatment of OSCC before clinical trials. First, we use big database mining to construct the candidate genome-wide genetic and epigenetic network (GWGEN) including a protein–protein interaction network (PPIN) and a gene regulatory network (GRN) for OSCC and non-OSCC. In the next step, real GWGENs are identified for OSCC and non-OSCC by system identification and system order detection methods based on the OSCC and non-OSCC microarray data, respectively. Then, the principal network projection (PNP) method was used to extract core GWGENs of OSCC and non-OSCC from real GWGENs of OSCC and non-OSCC, respectively. Afterward, core signaling pathways were constructed through the annotation of KEGG pathways, and then the carcinogenic mechanism of OSCC was investigated by comparing the core signal pathways and their downstream abnormal cellular functions of OSCC and non-OSCC. Consequently, HES1, TCF, NF-κB and SP1 are identified as significant biomarkers of OSCC. In order to discover multiple molecular drugs for these significant biomarkers (drug targets) of the carcinogenic mechanism of OSCC, we trained a DNN-based drug–target interaction (DTI) model by DTI databases to predict candidate drugs for these significant biomarkers. Finally, drug design specifications such as adequate drug regulation ability, low toxicity and high sensitivity are employed to filter out the appropriate molecular drugs metformin, gefitinib and gallic-acid to combine as a potential multiple-molecule drug for the therapeutic treatment of OSCC.     

Substrates of the Human Brain Proton-Organic Cation Antiporter and Comparison with Organic Cation Transporter 1 Activities

Many organic cations (OCs) may be transported through membranes by a genetically still uncharacterized proton-organic cation (H + OC) antiporter. Here, we characterized an extended substrate spectrum of this antiporter. We studied the uptake of 72 drugs in hCMEC/D3 cells as a model of the human blood–brain barrier. All 72 drugs were tested with exchange transport assays and the transport of 26 of the drugs was studied in more detail concerning concentration-dependent uptake and susceptibility to specific inhibitors. According to exchange transport assays, 37 (51%) drugs were good substrates of the H + OC antiporter. From 26 drugs characterized in more detail, 23 were consistently identified as substrates of the H + OC antiporter in six different assays and transport kinetic constants could be identified with intrinsic clearances between 0.2 (ephedrine) and 201 (imipramine) mL × minute⁻¹ × g protein⁻¹. Excellent substrates of the H + OC antiporter were no substrates of organic cation transporter OCT1 and vice versa. Good substrates of the H + OC antiporter were more hydrophobic and had a lower topological polar surface area than non-substrates or OCT1 substrates. These data and further research on the H + OC antiporter may result in a better understanding of pharmacokinetics, drug–drug interactions and variations in pharmacokinetics.     

GATNNCDA: A Method Based on Graph Attention Network and Multi-Layer Neural Network for Predicting circRNA-Disease Associations

Circular RNAs (circRNAs) are a new class of endogenous non-coding RNAs with covalent closed loop structure. Researchers have revealed that circRNAs play an important role in human diseases. As experimental identification of interactions between circRNA and disease is time-consuming and expensive, effective computational methods are an urgent need for predicting potential circRNA–disease associations. In this study, we proposed a novel computational method named GATNNCDA, which combines Graph Attention Network (GAT) and multi-layer neural network (NN) to infer disease-related circRNAs. Specially, GATNNCDA first integrates disease semantic similarity, circRNA functional similarity and the respective Gaussian Interaction Profile (GIP) kernel similarities. The integrated similarities are used as initial node features, and then GAT is applied for further feature extraction in the heterogeneous circRNA–disease graph. Finally, the NN-based classifier is introduced for prediction. The results of fivefold cross validation demonstrated that GATNNCDA achieved an average AUC of 0.9613 and AUPR of 0.9433 on the CircR2Disease dataset, and outperformed other state-of-the-art methods. In addition, case studies on breast cancer and hepatocellular carcinoma showed that 20 and 18 of the top 20 candidates were respectively confirmed in the validation datasets or published literature. Therefore, GATNNCDA is an effective and reliable tool for discovering circRNA–disease associations.     

Expression Profiles and Characteristics of Apple lncRNAs in Roots,Phloem, Leaves,Flowers, and Fruit

LncRNAs impart crucial effects on various biological processes, including biotic stress responses, abiotic stress responses, fertility and development. The apple tree is one of the four major fruit trees in the world. However, lncRNAs’s roles in different tissues of apple are unknown. We identified the lncRNAs in five tissues of apples including the roots, phloem, leaves, flowers, and fruit, and predicted the intricate regulatory networks. A total of 9440 lncRNAs were obtained. LncRNA target prediction revealed 10,628 potential lncRNA–messenger RNA (mRNA) pairs, 9410 pairs functioning in a cis-acting fashion, and 1218 acting in a trans-acting fashion. Functional enrichment analysis showed that the targets were significantly enriched in molecular functions related to photosynthesis-antenna proteins, single-organism metabolic process and glutathione metabolism. Additionally, a total of 88 lncRNAs have various functions related to microRNAs (miRNAs) as miRNA precursors. Interactions between lncRNAs and miRNAs were predicted, 1341 possible interrelations between 187 mdm-miRNAs and 174 lncRNAs (1.84%) were identified. MSTRG.121644.5, MSTRG.121644.8, MSTRG.2929.2, MSTRG.3953.2, MSTRG.63448.2, MSTRG.9870.2, and MSTRG.9870.3 could participate in the functions in roots as competing endogenous RNAs (ceRNAs). MSTRG.11457.2, MSTRG.138614.2, and MSTRG.60895.2 could adopt special functions in the fruit by working with miRNAs. A further analysis showed that different tissues formed special lncRNA–miRNA–mRNA networks. MSTRG.60895.2–mdm-miR393–MD17G1009000 may participate in the anthocyanin metabolism in the fruit. These findings provide a comprehensive view of potential functions for lncRNAs, corresponding target genes, and related lncRNA–miRNA–mRNA networks, which will increase our knowledge of the underlying development mechanism in apple.     

Residue–Residue Interaction Prediction via Stacked Meta-Learning

Protein–protein interactions (PPIs) are the basis of most biological functions determined by residue–residue interactions (RRIs). Predicting residue pairs responsible for the interaction is crucial for understanding the cause of a disease and drug design. Computational approaches that considered inexpensive and faster solutions for RRI prediction have been widely used to predict protein interfaces for further analysis. This study presents RRI-Meta, an ensemble meta-learning-based method for RRI prediction. Its hierarchical learning structure comprises four base classifiers and one meta-classifier to integrate predictive strengths from different classifiers. It considers multiple feature types, including sequence-, structure-, and neighbor-based features, for characterizing other properties of a residue interaction environment to better distinguish between noninteracting and interacting residues. We conducted the same experiments using the same data as previously reported in the literature to demonstrate RRI-Meta’s performance. Experimental results show that RRI-Meta is superior to several current prediction tools. Additionally, to analyze the factors that affect the performance of RRI-Meta, we conducted a comparative case study using different protein complexes.     

NEXGB: A Network Embedding Framework for Anticancer Drug Combination Prediction

Compared to single-drug therapy, drug combinations have shown great potential in cancer treatment. Most of the current methods employ genomic data and chemical information to construct drug–cancer cell line features, but there is still a need to explore methods to combine topological information in the protein interaction network (PPI). Therefore, we propose a network-embedding-based prediction model, NEXGB, which integrates the corresponding protein modules of drug–cancer cell lines with PPI network information. NEXGB extracts the topological features of each protein node in a PPI network by struc2vec. Then, we combine the topological features with the target protein information of drug–cancer cell lines, to generate drug features and cancer cell line features, and utilize extreme gradient boosting (XGBoost) to predict the synergistic relationship between drug combinations and cancer cell lines. We apply our model on two recently developed datasets, the Oncology-Screen dataset (Oncology-Screen) and the large drug combination dataset (DrugCombDB). The experimental results show that NEXGB outperforms five current methods, and it effectively improves the predictive power in discovering relationships between drug combinations and cancer cell lines. This further demonstrates that the network information is valid for detecting combination therapies for cancer and other complex diseases.     

Nano–Liposomes Double Loaded with Curcumin and Tetrandrine: Preparation,Characterization, Hepatotoxicity and Anti–Tumor Effects

(1) Background: Curcumin (CUR) and tetrandrine (TET) are natural compounds with various bioactivities, but have problems with low solubility, stability, and absorption rate, resulting in low bioavailability, and limited applications in food, medicine, and other fields. It is very important to improve the solubility while maintaining the high activity of drugs. Liposomes are micro–vesicles synthesized from cholesterol and lecithin. With high biocompatibility and biodegradability, liposomes can significantly improve drug solubility, efficacy, and bioavailability. (2) Methods: In this work, CUR and TET were encapsulated with nano–liposomes and g DSPE–MPEG 2000 (DP)was added as a stabilizer to achieve better physicochemical properties, biosafety, and anti–tumor effects. (3) Results: The nano–liposome (CT–DP–Lip) showed stable particle size (under 100 nm) under different conditions, high solubility, drug encapsulation efficiency (EE), loading capacity (LC), release rate in vitro, and stability. In addition, in vivo studies demonstrated CT–DP–Lip had no significant toxicity on zebrafish. Tumor cytotoxicity test showed that CT–DP–Lip had a strong inhibitory effect on a variety of cancer cells. (4) Conclusions: This work showed that nano–liposomes can significantly improve the physical and chemical properties of CUR and TET and make them safer and more efficient.     

Rational Design of CYP3A4 Inhibitors: A One-Atom Linker Elongation in Ritonavir-Like Compounds Leads to a Marked Improvement in the Binding Strength

Inhibition of the major human drug-metabolizing cytochrome P450 3A4 (CYP3A4) by pharmaceuticals and other xenobiotics could lead to toxicity, drug–drug interactions and other adverse effects, as well as pharmacoenhancement. Despite serious clinical implications, the structural basis and attributes required for the potent inhibition of CYP3A4 remain to be established. We utilized a rational inhibitor design to investigate the structure–activity relationships in the analogues of ritonavir, the most potent CYP3A4 inhibitor in clinical use. This study elucidated the optimal length of the head-group spacer using eleven (series V) analogues with the R₁/R₂ side-groups as phenyls or R₁–phenyl/R₂–indole/naphthalene in various stereo configurations. Spectral, functional and structural characterization of the inhibitory complexes showed that a one-atom head-group linker elongation, from pyridyl–ethyl to pyridyl–propyl, was beneficial and markedly improved K_s, IC₅₀ and thermostability of CYP3A4. In contrast, a two-atom linker extension led to a multi-fold decrease in the binding and inhibitory strength, possibly due to spatial and/or conformational constraints. The lead compound, 3h, was among the best inhibitors designed so far and overall, the strongest binder (K_s and IC₅₀ of 0.007 and 0.090 µM, respectively). 3h was the fourth structurally simpler inhibitor superior to ritonavir, which further demonstrates the power of our approach.     

Novel Algorithm of Network Calcium Dynamics Analysis for Studying the Role of Astrocytes in Neuronal Activity in Alzheimer’s Disease Models

Accumulated experimental data strongly suggest that astrocytes play an important role in the pathogenesis of neurodegeneration, including Alzheimer’s disease (AD). The effect of astrocytes on the calcium activity of neuron–astroglia networks in AD modelling was the object of the present study. We have expanded and improved our approach’s capabilities to analyze calcium activity. We have developed a novel algorithm to construct dynamic directed graphs of both astrocytic and neuronal networks. The proposed algorithm allows us not only to identify functional relationships between cells and determine the presence of network activity, but also to characterize the spread of the calcium signal from cell to cell. Our study showed that Alzheimer’s astrocytes can change the functional pattern of the calcium activity of healthy nerve cells. When healthy nerve cells were cocultivated with astrocytes treated with Aβ42, activation of calcium signaling was found. When healthy nerve cells were cocultivated with 5xFAD astrocytes, inhibition of calcium signaling was observed. In this regard, it seems relevant to further study astrocytic–neuronal interactions as an important factor in the regulation of the functional activity of brain cells during neurodegenerative processes. The approach to the analysis of streaming imaging data developed by the authors is a promising tool for studying the collective calcium dynamics of nerve cells.     

Is There Justification to Treat Neurodegenerative Disorders by Repurposing Drugs? The Case of Alzheimer’s Disease,Lithium, and Autophagy

Lithium is the prototype mood-stabilizer used for acute and long-term treatment of bipolar disorder. Cumulated translational research of lithium indicated the drug’s neuroprotective characteristics and, thereby, has raised the option of repurposing it as a drug for neurodegenerative diseases. Lithium’s neuroprotective properties rely on its modulation of homeostatic mechanisms such as inflammation, mitochondrial function, oxidative stress, autophagy, and apoptosis. This myriad of intracellular responses are, possibly, consequences of the drug’s inhibition of the enzymes inositol-monophosphatase (IMPase) and glycogen-synthase-kinase (GSK)-3. Here we review lithium’s neurobiological properties as evidenced by its neurotrophic and neuroprotective properties, as well as translational studies in cells in culture, in animal models of Alzheimer’s disease (AD) and in patients, discussing the rationale for the drug’s use in the treatment of AD.     

Systems Approach to Pathogenic Mechanism of Type 2 Diabetes and Drug Discovery Design Based on Deep Learning and Drug Design Specifications

In this study, we proposed a systems biology approach to investigate the pathogenic mechanism for identifying significant biomarkers as drug targets and a systematic drug discovery strategy to design a potential multiple-molecule targeting drug for type 2 diabetes (T2D) treatment. We first integrated databases to construct the genome-wide genetic and epigenetic networks (GWGENs), which consist of protein–protein interaction networks (PPINs) and gene regulatory networks (GRNs) for T2D and non-T2D (health), respectively. Second, the relevant “real GWGENs” are identified by system identification and system order detection methods performed on the T2D and non-T2D RNA-seq data. To simplify network analysis, principal network projection (PNP) was thereby exploited to extract core GWGENs from real GWGENs. Then, with the help of KEGG pathway annotation, core signaling pathways were constructed to identify significant biomarkers. Furthermore, in order to discover potential drugs for the selected pathogenic biomarkers (i.e., drug targets) from the core signaling pathways, not only did we train a deep neural network (DNN)-based drug–target interaction (DTI) model to predict candidate drug’s binding with the identified biomarkers but also considered a set of design specifications, including drug regulation ability, toxicity, sensitivity, and side effects to sieve out promising drugs suitable for T2D.     

Investigating Pathogenetic Mechanisms of Alzheimer’s Disease by Systems Biology Approaches for Drug Discovery

Alzheimer’s disease (AD) is the most common cause of dementia, characterized by progressive cognitive decline and neurodegenerative disorder. Abnormal aggregations of intracellular neurofibrillary tangles (NFTs) and unusual accumulations of extracellular amyloid-β (Aβ) peptides are two important pathological features in AD brains. However, in spite of large-scale clinical studies and computational simulations, the molecular mechanisms of AD development and progression are still unclear. In this study, we divided all of the samples into two groups: early stage (Braak score I–III) and later stage (Braak score IV–VI). By big database mining, the candidate genetic and epigenetic networks (GEN) have been constructed. In order to find out the real GENs for two stages of AD, we performed systems identification and system order detection scheme to prune false positives with the help of corresponding microarray data. Applying the principal network projection (PNP) method, core GENs were extracted from real GENs based on the projection values. By the annotation of KEGG pathway, we could obtain core pathways from core GENs and investigate pathogenetic mechanisms for the early and later stage of AD, respectively. Consequently, according to pathogenetic mechanisms, several potential biomarkers are identified as drug targets for multiple-molecule drug design in the treatment of AD.     

Exploiting Radiation Induction of Antigens in Cancer: Targeted Drug Delivery

Therapeutic antibodies used to treat cancer are effective in patients with advanced-stage disease. For example, antibodies that activate T-lymphocytes improve survival in many cancer subtypes. In addition, antibody–drug conjugates effectively target cytotoxic agents that are specific to cancer. This review discusses radiation-inducible antigens, which are stress-regulated proteins that are over-expressed in cancer. These inducible cell surface proteins become accessible to antibody binding during the cellular response to genotoxic stress. The lead antigens are induced in all histologic subtypes and nearly all advanced-stage cancers, but show little to no expression in normal tissues. Inducible antigens are exploited by using therapeutic antibodies that bind specifically to these stress-regulated proteins. Antibodies that bind to the inducible antigens GRP78 and TIP1 enhance the efficacy of radiotherapy in preclinical cancer models. The conjugation of cytotoxic drugs to the antibodies further improves cancer response. This review focuses on the use of radiotherapy to control the cancer-specific binding of therapeutic antibodies and antibody–drug conjugates.