The identification of drug-target interactions (DTIs) is an essential step in drug discovery. In vitro experimental methods are expensive, laborious, and time-consuming. Deep learning has witnessed promising progress DTI prediction. However, how to precisely represent protein features a major challenge for Here, we developed end-to-end framework called BINDTI based on bi-directional Intention network. First, encoded with graph convolutional networks its 2D molecular obtained by SMILES...

Lonicera japonica is a typical Chinese herbal medicine. We previously reported method to isolate polysaccharides from (LJP). In this study, we first performed qualitative analysis of LJP using the Fourier Transform Infrared Spectrometer (FT-IR) and explored monosaccharide composition pre-column derivatization high performance liquid chromatography (HPLC) method. then investigated immunomodulatory function in cyclophosphamide (CTX)-induced immunosuppressed mouse models. The results showed...

Carcinomas are complex ecosystems composed of cancer, stromal and immune cells. Communication between these cells their microenvironments induces cancer progression causes therapy resistance. In order to improve the treatment cancers, it is essential quantify crosstalk within various cell types in a tumour microenvironment. Focusing on coordinated expression patterns ligands cognate receptors, cell-cell communication can be inferred through ligand-receptor interactions (LRIs). this...

Cell-to-cell communication (CCC) plays important roles in multicellular organisms. The identification of between cancer cells themselves and one normal tumor microenvironment helps understand genesis, development metastasis. CCC is usually mediated by Ligand-Receptor Interactions (LRIs). In this manuscript, we developed a Boosting-based LRI model (CellEnBoost) for inference. First, potential LRIs are predicted data collection, feature extraction, dimensional reduction, classification based...

Intercellular communication significantly influences tumor progression, metastasis, and therapy resistance. An intercellular inference method includes two main procedures: ligand-receptor interaction (LRI) curation LRI-mediated strength measurement. The construction of a comprehensive, high-confident well-organized LRI database contributes to inference. Here, we developed computational framework named CellDialog reconstruct an connectivity network based on the combined expression ligands...

Abstract Long noncoding RNAs (lncRNAs) participate in various biological processes and have close linkages with diseases. In vivo vitro experiments validated many associations between lncRNAs However, are time-consuming expensive. Here, we introduce LDA-VGHB, an lncRNA–disease association (LDA) identification framework, by incorporating feature extraction based on singular value decomposition variational graph autoencoder LDA classification heterogeneous Newton boosting machine. LDA-VGHB was...

Identifying potential associations between drugs and targets is a critical prerequisite for modern drug discovery repurposing. However, predicting these difficult because of the limitations existing computational methods. Most models only consider chemical structures protein sequences, other are oversimplified. Moreover, datasets used analysis contain true-positive interactions, experimentally validated negative samples unavailable. To overcome limitations, we developed semi-supervised based...

There are countless microbes in the human body, and they play various roles physiological process. is growing evidence that closely associated with diseases. Researching disease-related helps us understand mechanisms of diseases provides new strategies for diagnosis treatment. Many computational models have been proposed to predict microbes, this paper, we developed a model Adaptive Boosting Human Microbe-Disease Association prediction (ABHMDA) reveal associations between by calculating...

Single-cell RNA sequencing (scRNA-seq) technologies allow numerous opportunities for revealing novel and potentially unexpected biological discoveries. scRNA-seq clustering helps elucidate cell-to-cell heterogeneity uncover cell subgroups dynamics at the group level. Two important aspects of data analysis were introduced discussed in present review: relevant datasets analytical tools. In particular, we reviewed popular models including K-means clustering, hierarchical consensus so on. Seven...

Abstract The outbreak of a novel febrile respiratory disease called COVID-19, caused by newfound coronavirus SARS-CoV-2, has brought worldwide attention. Prioritizing approved drugs is critical for quick clinical trials against COVID-19. In this study, we first manually curated three Virus-Drug Association (VDA) datasets. By incorporating VDAs with the similarity between and that viruses, constructed heterogeneous network. A Random Walk Restart method (VDA-RWR) was then developed to identify...

The quantitative accuracy of positron emission tomography (PET) is affected by several factors, including the intrinsic resolution imaging system and inherently noisy data, which result in a low signal-to-noise ratio (SNR) PET image. To address this problem, paper, we proposed novel deep learning denoising framework aiming to enhance dynamic images via introduction image prior (DIP) combined with Regularization Denoising (RED), as such method labeled DeepRED denoising. network structure...

The identification of lncRNA-protein interactions (LPIs) is important to understand the biological functions and molecular mechanisms lncRNAs. However, most computational models are evaluated on a unique dataset, thereby resulting in prediction bias. Furthermore, previous have not uncovered potential proteins (or lncRNAs) interacting with new lncRNA protein). Finally, performance these can be improved. In this study, we develop Deep Learning framework Dual-net Neural architecture find LPIs...

Drug-Target Interaction (DTI) prediction facilitates acceleration of drug discovery and promotes repositioning. Most existing deep learning-based DTI methods can better extract discriminative features for drugs proteins, but they rarely consider multimodal drugs. Moreover, learning the interaction representations between targets needs further exploration. Here, we proposed a simple M ulti-modal G ating N etwork prediction, MGNDTI, based on representation gating mechanism. MGNDTI first learns...

DNA-binding proteins play critical roles in various cellular biological processes, such as gene expression and transcription. However, the experimental methods to identify these like ChIP-sequencing are expensive time-consuming, which presents need for silico methods, especially machine learning-based methods. In recent years, accuracy of protein prediction has been increasing significantly. there still some problems be solved how convert sequences into an appropriate discrete model or...

Identifying drug-target interaction (DTI) candidates is crucial for drug repositioning. However, usually only positive DTIs are deposited in known databases, which challenges computational methods to predict novel due the lack of negative samples. To overcome this dilemma, researchers randomly select samples from unlabeled pairs, introduces a lot false-positives. In study, sample extraction method named NDTISE first developed screen strong DTI examples based on positive-unlabeled learning. A...

Abstract Background Long noncoding RNAs (lncRNAs) play important roles in various biological and pathological processes. Discovery of lncRNA–protein interactions (LPIs) contributes to understand the functions mechanisms lncRNAs. Although wet experiments find a few between lncRNAs proteins, experimental techniques are costly time-consuming. Therefore, computational methods increasingly exploited uncover possible associations. However, existing have several limitations. First, majority them...