摘要 : Background: As we all know, finding new pharmaceuticals requires a lot of time and money, which has compelled people to think about adopting more effective approaches to locate drugs. Researchers have made significant progress recently when it comes to using Deep Learning (DL) to create DTI. Methods: Therefore, we propose a deep learning model that applies Transformer to DTI prediction. The model uses a Transformer and Graph Transformer to extract the feature information of protein and compound molecules, respectively, and combines their respective representations to predict interactions. Results: We used Human and C.elegans, the two benchmark datasets, evaluated the proposed method in different experimental settings and compared it with the latest DL model. Conclusion: The results show that the proposed model based on DL is an effective method for the classification and recognition of DTI prediction, and its performance on the two data sets is significantly better than other DL based methods.

摘要 : Drug target affinity prediction (DTA) is critical to the success of drug development. While numerous machine learning methods have been developed for this task, there remains a necessity to further enhance the accuracy and reliability of predictions. Considerable bias in drug target binding prediction may result due to missing structural information or missing information. In addition, current methods focus only on simulating individual non-covalent interactions between drugs and proteins, thereby neglecting the intricate interplay among different drugs and their interactions with proteins. GTAMP-DTA combines special Attention mechanisms, assigning each atom or amino acid an attention vector. Interactions between drug forms and protein forms were considered to capture information about their interactions. And fusion transformer was used to learn protein characterization from raw amino acid sequences, which were then merged with molecular map features extracted from SMILES. A self-supervised pre-trained embedding that uses pre-trained transformers to encode drug and protein attributes is introduced in order to address the lack of labeled data. Experimental results demonstrate that our model outperforms state-of-the-art methods on both the Davis and KIBA datasets. Additionally, the model's performance undergoes evaluation using three distinct pooling layers (max-pooling, mean-pooling, sum-pooling) along with variations of the attention mechanism. GTAMP-DTA shows significant performance improvements compared to other methods.

摘要 : The accurate prediction of drug-target affinity (DTA) is a crucial step in drug discovery and design. Traditional experiments are very expensive and time-consuming. Recently, deep learning methods have achieved notable performance improvements in DTA prediction. However, one challenge for deep learning-based models is appropriate and accurate representations of drugs and targets, especially the lack of effective exploration of target representations. Another challenge is how to comprehensively capture the interaction information between different instances, which is also important for predicting DTA. In this study, we propose AttentionMGT-DTA, a multi-modal attention-based model for DTA prediction. AttentionMGT-DTA represents drugs and targets by a molecular graph and binding pocket graph, respectively. Two attention mechanisms are adopted to integrate and interact information between different protein modalities and drug-target pairs. The experimental results showed that our proposed model outperformed state-of-the-art baselines on two benchmark datasets. In addition, AttentionMGT-DTA also had high interpretability by modeling the interaction strength between drug atoms and protein residues. Our code is available at https://github.com/JK-Liu7/AttentionMGT-DTA .

摘要 : Identification of new indications for existing drugs is crucial through the various stages of drug discovery. Computational methods are valuable in establishing meaningful associations between drugs and diseases. However, most methods predict the drug–disease associations based solely on similarity data, neglecting valuable biological and chemical information. These methods often use basic concatenation to integrate information from different modalities, limiting their ability to capture features from a comprehensive and in-depth perspective. Therefore, a novel multimodal framework called AMDGT was proposed to predict new drug associations based on dual-graph transformer modules. By combining similarity data and complex biochemical information, AMDGT understands the multimodal feature fusion of drugs and diseases effectively and comprehensively with an attention-aware modality interaction architecture. Extensive experimental results indicate that AMDGT surpasses state-of-the-art methods in real-world datasets. Moreover, case and molecular docking studies demonstrated that AMDGT is an effective tool for drug repositioning. Our code is available at GitHub: https://github.com/JK-Liu7/AMDGT. © 2023 The Author(s)

摘要 : DNA-protein binding is crucial for the normal development and function of organisms. The significance of accurately identifying DNA-protein binding sites lies in its role in disease prevention and the development of innovative approaches to disease treatment. In the present study, we introduce a precise and robust identifier for DNA-protein binding residues. In the context of protein representation, we combine the evolutionary information of the protein, represented by its position-specific scoring matrix, with the spatial information of the protein's secondary structure, enriching the overall informational content. This approach initially employs a combination of Bi-directional Long Short-Term Memory and Transformer encoder to jointly extract the interdependencies among residues within the protein sequence. Subsequently, convolutional operations are applied to the resulting feature matrix to capture local features of the residues. Experimental results on the benchmark dataset demonstrate that our method exhibits a higher level of competitiveness when compared to contemporary classifiers. Specifically, our method achieved an MCC of 0.349, SP of 96.50%, SN of 44.03% and ACC of 94.59% on the PDNA-41 dataset.

摘要 : Background: The prediction of drug-target interactions (DTIs) plays an essential role in drug discovery. Recently, deep learning methods have been widely applied in DTI prediction. However, most of the existing research does not fully utilize the molecular structures of drug compounds and the sequence structures of proteins, which makes these models unable to obtain precise and effective feature representations. Methods: In this study, we propose a novel deep learning framework combining transformer and graph neural networks for predicting DTIs. Our model utilizes graph convolutional neural networks to capture the global and local structure information of drugs, and convolutional neural networks are employed to capture the sequence feature of targets. In addition, the obtained drug and protein representations are input to multi-layer transformer encoders, respectively, to integrate their features and generate final representations. Results: The experiments on benchmark datasets demonstrated that our model outperforms previous graph-based and transformer-based methods, with 1.5% and 1.8% improvement in precision and 0.2% and 1.0% improvement in recall, respectively. The results indicate that the transformer encoders effectively extract feature information of both drug compounds and proteins. Conclusion: Overall, our proposed method validates the applicability of combining graph neural networks and transformer architecture in drug discovery, and due to the attention mechanisms, it can extract deep structure feature data of drugs and proteins.

摘要 : In recent years, research in the field of bioinformatics has focused on predicting the raw sequences of proteins, and some scholars consider DNA-binding protein prediction as a classification task . Many statistical and machine learning-based methods have been widely used in DNA-binding proteins research. The aforementioned methods are indeed more efficient than those based on manual classification, but there is still room for improvement in terms of prediction accuracy and speed. In this study, researchers used Average Blocks, Discrete Cosine Transform, Discrete Wavelet Transform, Global encoding, Normalized Moreau-Broto Autocorrelation and Pseudo position-specific scoring matrix to extract evolutionary features. A dynamic deep network based on lifelong learning architecture was then proposed in order to fuse six features and thus allow for more efficient classification of DNA-binding proteins. The multi-feature fusion allows for a more accurate description of the desired protein information than single features. This model offers a fresh perspective on the dichotomous classification problem in bioinformatics and broadens the application field of lifelong learning. The researchers ran trials on three datasets and contrasted them with other classification techniques to show the model's effectiveness in this study. The findings demonstrated that the model used in this research was superior to other approaches in terms of single-sample specificity (81.0%, 83.0%) and single-sample sensitivity (82.4%, 90.7%), and achieves high accuracy on the benchmark dataset (88.4%, 80.0%, and 76.6%).

摘要 : Klebsiella pneumoniae is an important multidrug-resistant (MDR) pathogen that can cause a range of infections in hospitalized patients. With the growing use of antibiotics, MDR K. pneumoniae is more prevalent, posing additional difficulties and obstacles in clinical therapy. To provide a valuable reference to deeply understand K. pneumoniae, and also to provide the theoretical basis for clinical prevention of such bacteria infections, the antibiotic resistance and mechanism of K. pneumoniae are discussed in this article. We conducted a literature review on antibiotic resistance of K. pneumoniae. We ran a thorough literature search of PubMed, Web of Science, and Scopus, among other databases. We also thoroughly searched the literature listed in the papers. We searched all antibiotic resistance mechanisms and genes of seven important antibiotics used to treat K. pneumoniae infections. Antibiotics such as β-lactams, aminoglycosides, and quinolones are used in the treatment of K. pneumoniae infection. With both chromosomal and plasmid-encoded ARGs, this pathogen has diverse resistance genes. Carbapenem resistance genes, enlarged-spectrum β-lactamase genes, and AmpC genes are the most often β-lactamase resistance genes. K. pneumoniae is a major contributor to antibiotic resistance worldwide. Understanding K. pneumoniae antibiotic resistance mechanisms and molecular characteristics will be important for the design of targeted prevention and novel control strategies against this pathogen.

摘要 : A membrane protein's functions are significantly associated with its type, so it is crucial to identify the types of membrane proteins. Conventional computational methods for identifying the species of membrane proteins tend to ignore two issues: High-order correlation among membrane proteins and the scenarios of multi-modal representations of membrane proteins, which leads to information loss. To tackle those two issues, we proposed a deep residual hypergraph neural network (DRHGNN), which enhances the hypergraph neural network (HGNN) with initial residual and identity mapping in this paper. We carried out extensive experiments on four benchmark datasets of membrane proteins. In the meantime, we compared the DRHGNN with recently developed advanced methods. Experimental results showed the better performance of DRHGNN on the membrane protein classification task on four datasets. Experiments also showed that DRHGNN can handle the over-smoothing issue with the increase of the number of model layers compared with HGNN. The code is available at https://github.com/yunfighting/Identification-of-Membrane-Protein-Types-via-deep-residual-hypergraph-neural-network.

摘要 : Nowadays, millions of patients suffer from physical disabilities, including lower-limb disabilities. Researchers have adopted a variety of physical therapies based on the lower-limb exoskeleton, in which it is difficult to adjust equipment parameters in a timely fashion. Therefore, intelligent control methods, for example, deep reinforcement learning (DRL), have been used to control the medical equipment used in human gait adjustment. In this study, based on the key-value attention mechanism, we reconstructed the agent’s observations by capturing the self-dependent feature information for decision-making in regard to each state sampled from the replay buffer. Moreover, based on Softmax Deep Double Deterministic policy gradients (SD3), a novel DRL-based framework, key-value attention-based SD3 (AT_SD3), has been proposed for gait adjustment. We demonstrated the effectiveness of our proposed framework in gait adjustment by comparing different gait trajectories, including the desired trajectory and the adjusted trajectory. The results showed that the simulated trajectories were closer to the desired trajectory, both in their shapes and values. Furthermore, by comparing the results of our experiments with those of other state-of-the-art methods, the results proved that our proposed framework exhibited better performance. © 2022 by the authors.