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.     

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.     

A Cascade Graph Convolutional Network for Predicting Protein–Ligand Binding Affinity

Accurate prediction of binding affinity between protein and ligand is a very important step in the field of drug discovery. Although there are many methods based on different assumptions and rules do exist, prediction performance of protein–ligand binding affinity is not satisfactory so far. This paper proposes a new cascade graph-based convolutional neural network architecture by dealing with non-Euclidean irregular data. We represent the molecule as a graph, and use a simple linear transformation to deal with the sparsity problem of the one-hot encoding of original data. The first stage adopts ARMA graph convolutional neural network to learn the characteristics of atomic space in the protein–ligand complex. In the second stage, one variant of the MPNN graph convolutional neural network is introduced with chemical bond information and interactive atomic features. Finally, the architecture passes through the global add pool and the fully connected layer, and outputs a constant value as the predicted binding affinity. Experiments on the PDBbind v2016 data set showed that our method is better than most of the current methods. Our method is also comparable to the state-of-the-art method on the data set, and is more intuitive and simple.     

Integration of Neighbor Topologies Based on Meta-Paths and Node Attributes for Predicting Drug-Related Diseases

Identifying new disease indications for existing drugs can help facilitate drug development and reduce development cost. The previous drug–disease association prediction methods focused on data about drugs and diseases from multiple sources. However, they did not deeply integrate the neighbor topological information of drug and disease nodes from various meta-path perspectives. We propose a prediction method called NAPred to encode and integrate meta-path-level neighbor topologies, multiple kinds of drug attributes, and drug-related and disease-related similarities and associations. The multiple kinds of similarities between drugs reflect the degrees of similarity between two drugs from different perspectives. Therefore, we constructed three drug–disease heterogeneous networks according to these drug similarities, respectively. A learning framework based on fully connected neural networks and a convolutional neural network with an attention mechanism is proposed to learn information of the neighbor nodes of a pair of drug and disease nodes. The multiple neighbor sets composed of different kinds of nodes were formed respectively based on meta-paths with different semantics and different scales. We established the attention mechanisms at the neighbor-scale level and at the neighbor topology level to learn enhanced neighbor feature representations and enhanced neighbor topological representations. A convolutional-autoencoder-based module is proposed to encode the attributes of the drug–disease pair in three heterogeneous networks. Extensive experimental results indicated that NAPred outperformed several state-of-the-art methods for drug–disease association prediction, and the improved recall rates demonstrated that NAPred was able to retrieve more actual drug–disease associations from the top-ranked candidates. Case studies on five drugs further demonstrated the ability of NAPred to identify potential drug-related disease candidates.     

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.     

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.     

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.     

Recent Applications of Deep Learning Methods on Evolution- and Contact-Based Protein Structure Prediction

The new advances in deep learning methods have influenced many aspects of scientific research, including the study of the protein system. The prediction of proteins’ 3D structural components is now heavily dependent on machine learning techniques that interpret how protein sequences and their homology govern the inter-residue contacts and structural organization. Especially, methods employing deep neural networks have had a significant impact on recent CASP13 and CASP14 competition. Here, we explore the recent applications of deep learning methods in the protein structure prediction area. We also look at the potential opportunities for deep learning methods to identify unknown protein structures and functions to be discovered and help guide drug–target interactions. Although significant problems still need to be addressed, we expect these techniques in the near future to play crucial roles in protein structural bioinformatics as well as in drug discovery.     

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.     

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.     

Binding Studies and Lead Generation of Pteridin-7(8H)-one Derivatives Targeting FLT3

Ligand modification by substituting chemical groups within the binding pocket is a popular strategy for kinase drug development. In this study, a series of pteridin-7(8H)-one derivatives targeting wild-type FMS-like tyrosine kinase-3 (FLT3) and its D835Y mutant (FL3_D835Y) were studied using a combination of molecular modeling techniques, such as docking, molecular dynamics (MD), binding energy calculation, and three-dimensional quantitative structure-activity relationship (3D-QSAR) studies. We determined the protein–ligand binding affinity by employing molecular mechanics Poisson–Boltzmann/generalized Born surface area (MM-PB/GBSA), fast pulling ligand (FPL) simulation, linear interaction energy (LIE), umbrella sampling (US), and free energy perturbation (FEP) scoring functions. The structure–activity relationship (SAR) study was conducted using comparative molecular field analysis (CoMFA) and comparative molecular similarity indices analysis (CoMSIA), and the results were emphasized as a SAR scheme. In both the CoMFA and CoMSIA models, satisfactory correlation statistics were obtained between the observed and predicted inhibitory activity. The MD and SAR models were co-utilized to design several new compounds, and their inhibitory activities were anticipated using the CoMSIA model. The designed compounds with higher predicted pIC₅₀ values than the most active compound were carried out for binding free energy evaluation to wild-type and mutant receptors using MM-PB/GBSA, LIE, and FEP methods.     

Screening for Interacting Proteins with Peptide Biomarker of Blood–Brain Barrier Alteration under Inflammatory Conditions

Neurodegenerative diseases are characterized by increased permeability of the blood–brain barrier (BBB) due to alterations in cellular and structural components of the neurovascular unit, particularly in association with neuroinflammation. A previous screening study of peptide ligands to identify molecular alterations of the BBB in neuroinflammation by phage-display, revealed that phage clone 88 presented specific binding affinity to endothelial cells under inflammatory conditions in vivo and in vitro. Here, we aimed to identify the possible target receptor of the peptide ligand 88 expressed under inflammatory conditions. A cross-link test between phage-peptide-88 with IL-1β-stimulated human hCMEC cells, followed by mass spectrometry analysis, was used to identify the target of peptide-88. We modeled the epitope–receptor molecular interaction between peptide-88 and its target by using docking simulations. Three proteins were selected as potential target candidates and tested in enzyme-linked immunosorbent assays with peptide-88: fibronectin, laminin subunit α5 and laminin subunit β-1. Among them, only laminin subunit β-1 presented measurable interaction with peptide-88. Peptide-88 showed specific interaction with laminin subunit β-1, highlighting its importance as a potential biomarker of the laminin changes that may occur at the BBB endothelial cells under pathological inflammation conditions.     

Artificial Intelligence in Aptamer–Target Binding Prediction

Aptamers are short single-stranded DNA, RNA, or synthetic Xeno nucleic acids (XNA) molecules that can interact with corresponding targets with high affinity. Owing to their unique features, including low cost of production, easy chemical modification, high thermal stability, reproducibility, as well as low levels of immunogenicity and toxicity, aptamers can be used as an alternative to antibodies in diagnostics and therapeutics. Systematic evolution of ligands by exponential enrichment (SELEX), an experimental approach for aptamer screening, allows the selection and identification of in vitro aptamers with high affinity and specificity. However, the SELEX process is time consuming and characterization of the representative aptamer candidates from SELEX is rather laborious. Artificial intelligence (AI) could help to rapidly identify the potential aptamer candidates from a vast number of sequences. This review discusses the advancements of AI pipelines/methods, including structure-based and machine/deep learning-based methods, for predicting the binding ability of aptamers to targets. Structure-based methods are the most used in computer-aided drug design. For this part, we review the secondary and tertiary structure prediction methods for aptamers, molecular docking, as well as molecular dynamic simulation methods for aptamer–target binding. We also performed analysis to compare the accuracy of different secondary and tertiary structure prediction methods for aptamers. On the other hand, advanced machine-/deep-learning models have witnessed successes in predicting the binding abilities between targets and ligands in drug discovery and thus potentially offer a robust and accurate approach to predict the binding between aptamers and targets. The research utilizing machine-/deep-learning techniques for prediction of aptamer–target binding is limited currently. Therefore, perspectives for models, algorithms, and implementation strategies of machine/deep learning-based methods are discussed. This review could facilitate the development and application of high-throughput and less laborious in silico methods in aptamer selection and characterization.     

Integrated mRNA and miRNA Transcriptome Analysis Suggests a Regulatory Network for UV–B-Controlled Terpenoid Synthesis in Fragrant Woodfern (Dryopteris fragrans)

Fragrant woodfern (Dryopteris fragrans) is a medicinal plant rich in terpenoids. Ultraviolet-B (UV–B) light could increase concentration of terpenoids. The aim of this study was to analyze how UV–B regulates the terpenoid synthesis of the molecular regulatory mechanism in fragrant woodfern. In this study, compared with the control group, the content of the terpenes was significantly higher in fragrant woodfern leaves under UV–B treatment for 4 days (d). In order to identify how UV–B regulates the terpenoid metabolic mechanism in fragrant woodfern, we examined the mRNAs and small RNAs in fragrant woodfern leaves under UV–B treatment. mRNA and miRNA–seq identified 4533 DEGs and 17 DEMs in the control group compared with fragrant woodfern leaves under UV–B treatment for 4 d. mRNA–miRNA analysis identified miRNA target gene pairs consisting of 8 DEMs and 115 miRNAs. The target genes were subjected to GO and KEGG analyses. The results showed that the target genes were mainly enriched in diterpene biosynthesis, terpenoid backbone biosynthesis, plant hormone signal transduction, MEP pathway and MVA pathway, in which miR156 and miR160 regulate these pathways by targeting DfSPL and DfARF, respectively. The mRNA and miRNA datasets identified a subset of candidate genes. It provides the theoretical basis that UV–B regulates the terpenoid synthesis of the molecular regulatory mechanism in fragrant woodfern.     

Brain Disposition of Antibody-Based Therapeutics: Dogma,Approaches and Perspectives

Due to their high specificity, monoclonal antibodies have been widely investigated for their application in drug delivery to the central nervous system (CNS) for the treatment of neurological diseases such as stroke, Alzheimer’s, and Parkinson’s disease. Research in the past few decades has revealed that one of the biggest challenges in the development of antibodies for drug delivery to the CNS is the presence of blood–brain barrier (BBB), which acts to restrict drug delivery and contributes to the limited uptake (0.1–0.2% of injected dose) of circulating antibodies into the brain. This article reviews the various methods currently used for antibody delivery to the CNS at the preclinical stage of development and the underlying mechanisms of BBB penetration. It also describes efforts to improve or modulate the physicochemical and biochemical properties of antibodies (e.g., charge, Fc receptor binding affinity, and target affinity), to adapt their pharmacokinetics (PK), and to influence their distribution and disposition into the brain. Finally, a distinction is made between approaches that seek to modify BBB permeability and those that use a physiological approach or antibody engineering to increase uptake in the CNS. Although there are currently inherent difficulties in developing safe and efficacious antibodies that will cross the BBB, the future prospects of brain-targeted delivery of antibody-based agents are believed to be excellent.     

Polyaminoacid Based Core@shell Nanocarriers of 5-Fluorouracil: Synthesis,Properties and Theranostics Application

Cancer is one of the most important health problems of our population, and one of the common anticancer treatments is chemotherapy. The disadvantages of chemotherapy are related to the drug’s toxic effects, which act on cancer cells and the healthy part of the body. The solution of the problem is drug encapsulation and drug targeting. The present study aimed to develop a novel method of preparing multifunctional 5-Fluorouracil (5-FU) nanocarriers and their in vitro characterization. 5-FU polyaminoacid-based core@shell nanocarriers were formed by encapsulation drug-loaded nanocores with polyaminoacids multilayer shell via layer-by-layer method. The size of prepared nanocarriers ranged between 80–200 nm. Biocompatibility of our nanocarriers as well as activity of the encapsulated drug were confirmed by MTT tests. Moreover, the ability to the real-time observation of developed nanocarriers and drug accumulation inside the target was confirmed by fluorine magnetic resonance imaging (¹⁹F-MRI).     

A 3D–Predicted Structure of the Amine Oxidase Domain of Lysyl Oxidase–Like 2

Lysyl oxidase–like 2 (LOXL2) has been recognized as an attractive drug target for anti–fibrotic and anti–tumor therapies. However, the structure–based drug design of LOXL2 has been very challenging due to the lack of structural information of the catalytically–competent LOXL2. In this study; we generated a 3D–predicted structure of the C–terminal amine oxidase domain of LOXL2 containing the lysine tyrosylquinone (LTQ) cofactor from the 2.4Å crystal structure of the Zn²⁺–bound precursor (lacking LTQ; PDB:5ZE3); this was achieved by molecular modeling and molecular dynamics simulation based on our solution studies of a mature LOXL2 that is inhibited by 2–hydrazinopyridine. The overall structures of the 3D–modeled mature LOXL2 and the Zn²⁺–bound precursor are very similar (RMSD = 1.070Å), and disulfide bonds are conserved. The major difference of the mature and the precursor LOXL2 is the secondary structure of the pentapeptide (His652–Lys653–Ala654–Ser655–Phe656) containing Lys653 (the precursor residue of the LTQ cofactor). We anticipate that this peptide is flexible in solution to accommodate the conformation that enables the LTQ cofactor formation as opposed to the β–sheet observed in 5ZE3. We discuss the active site environment surrounding LTQ and Cu²⁺ of the 3D–predicted structure.     

The Use of Molecular Dynamics Simulation Method to Quantitatively Evaluate the Affinity between HBV Antigen T Cell Epitope Peptides and HLA-A Molecules

Chronic hepatitis B virus (HBV), a potentially life-threatening liver disease, makes people vulnerable to serious diseases such as cancer. T lymphocytes play a crucial role in clearing HBV virus, while the pathway depends on the strong binding of T cell epitope peptide and HLA. However, the experimental identification of HLA-restricted HBV antigenic peptides is extremely time-consuming. In this study, we provide a novel prediction strategy based on structure to assess the affinity between the HBV antigenic peptide and HLA molecule. We used residue scanning, peptide docking and molecular dynamics methods to obtain the molecular docking model of HBV peptide and HLA, and then adopted the MM-GBSA method to calculate the binding affinity of the HBV peptide–HLA complex. Overall, we collected 59 structures of HLA-A from Protein Data Bank, and finally obtained 352 numerical affinity results to figure out the optimal bind choice between the HLA-A molecules and 45 HBV T cell epitope peptides. The results were highly consistent with the qualitative affinity level determined by the competitive peptide binding assay, which confirmed that our affinity prediction process based on an HLA structure is accurate and also proved that the homologous modeling strategy for HLA-A molecules in this study was reliable. Hence, our work highlights an effective way by which to predict and screen for HLA-peptide binding that would improve the treatment of HBV infection.