Cell-to-cell communication (CCC) facilitates the coordination of various cellular behaviors in multicellular organisms. Many computational methods neglect downstream intracellular signaling and are limited by static and predefined ligand-receptor (L-R) databases. To address these limitations, we present CELLetter, a deep learning framework to identify potential L-R interactions through a novel feature learning model and decipher cellular signaling by integrating L-R co-expression with downstream transcription factor (TF) activity inferred from gene regulatory network. CELLetter begins by leveraging the protein large language model, ProstT5, for feature embedding. It then employs a dual-stream architecture for feature extraction and dimensionality reduction, a gate mechanism with dynamic weight adjustment for feature fusion, absolute difference, and element-wise product for feature interaction. After that, CELLetter combines interacting L-R pairs, single-cell RNA sequencing (scRNA-seq) data, and downstream TF activity to quantify communication strength. We comprehensively evaluated CELLetter using 11 evaluation metrics, benchmarking it against 4 state-of-the-art L-R classification models, 6 L-R validation tools, 10 CCC inference methods. CELLetter demonstrated superior L-R classification performance. Notably, we introduced a novel multi-faceted validation strategy employing colocalization distance, co-expression ratio, and co-detection probability on spatial transcriptomics data from human heart and distal lung epithelial tissues. CELLetter's predicted L-R pairs exhibited significant spatial relevance compared with other baselines. When applied to human head and neck squamous cell carcinoma (HNSCC) data, CELLetter produced CCC inferences broadly consistent with established methods. More importantly, ligand macrophage migration inhibitory factor (MIF) and receptor CD44 were predicted as a central signaling axis within HNSCC tumor microenvironment, suggesting their potentials as therapeutic targets . CELLetter is freely available at https://github.com/plhhnu/CELLetter.

Predicting potential drug-target interactions (DTIs) facilitates to accelerate drug discovery and reduce development cost. Current deep learning-based methods exhibit high-performance predictions, but three challenges remain: first, the absence of negative DTIs severely limits the model performance. Moreover, existing graph neural networks are beset with the scalability due to the model complexity and graph size. More importantly, most methods focus on learning the topological features while ignoring node features during DTI representation learning. To solve the limitations, here, we develop a multi-view neural network framework called DTI-MvSCA for DTI identification. This framework begins with constructing a drug-protein pair (DPP) network with matrix operation-based negative DTI selection, and then learns the DPP representations through aMulti-view neural network, finally classifies each DPP based on multilayer perceptron. Particularly, the multi-view neural network integrates graph topological feature learning based on the self-attention mechanism andSHADOW graph attention network, node feature learning based on 1DConvolutional neural network, and theAttention mechanism. An in-depth experiment on DrugBank V3.0 and V5.0 showed that DTI-MvSCA obtained precise and robust predictions against five state-of-the-art baseline methods. Furthermore, visualizing the feature distributions of the selected negative DTIs exhibits a more distinguishable and clearer boundary. In summary, DTI-MvSCA provides a useful deep learning tool to investigate potential DTIs.

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 in DTI prediction. However, how to precisely represent drug and protein features is a major challenge for DTI prediction. Here, we developed an end-to-end DTI identification framework called BINDTI based on bi-directional Intention network. First, drug features are encoded with graph convolutional networks based on its 2D molecular graph obtained by its SMILES string. Next, protein features are encoded based on its amino acid sequence through a mixed model called ACmix, which integrates self-attention mechanism and convolution. Third, drug and target features are fused through bi-directional Intention network, which combines Intention and multi-head attention. Finally, unknown drug-target (DT) pairs are classified through multilayer perceptron based on the fused DT features. The results demonstrate that BINDTI greatly outperformed four baseline methods (i.e., CPI-GNN, TransfomerCPI, MolTrans, and IIFDTI) on the BindingDB, BioSNAP, DrugBank, and Human datasets. More importantly, it was more appropriate to predict new DTIs than the four baseline methods on imbalanced datasets. Ablation experimental results elucidated that both bi-directional Intention and ACmix could greatly advance DTI prediction. The fused feature visualization and case studies manifested that the predicted results by BINDTI were basically consistent with the true ones. We anticipate that the proposed BINDTI framework can find new low-cost drug candidates, improve drugs' virtual screening, and further facilitate drug repositioning as well as drug discovery.

Long noncoding RNAs (lncRNAs) participate in various biological processes and have close linkages with diseases. In vivo and in vitro experiments have validated many associations between lncRNAs and diseases. However, biological experiments are time-consuming and expensive. Here, we introduce LDA-VGHB, an lncRNA-disease association (LDA) identification framework, by incorporating feature extraction based on singular value decomposition and variational graph autoencoder and LDA classification based on heterogeneous Newton boosting machine. LDA-VGHB was compared with four classical LDA prediction methods (i.e. SDLDA, LDNFSGB, IPCARF and LDASR) and four popular boosting models (XGBoost, AdaBoost, CatBoost and LightGBM) under 5-fold cross-validations on lncRNAs, diseases, lncRNA-disease pairs and independent lncRNAs and independent diseases, respectively. It greatly outperformed the other methods with its prominent performance under four different cross-validations on the lncRNADisease and MNDR databases. We further investigated potential lncRNAs for lung cancer, breast cancer, colorectal cancer and kidney neoplasms and inferred the top 20 lncRNAs associated with them among all their unobserved lncRNAs. The results showed that most of the predicted top 20 lncRNAs have been verified by biomedical experiments provided by the Lnc2Cancer 3.0, lncRNADisease v2.0 and RNADisease databases as well as publications. We found that HAR1A, KCNQ1DN, ZFAT-AS1 and HAR1B could associate with lung cancer, breast cancer, colorectal cancer and kidney neoplasms, respectively. The results need further biological experimental validation. We foresee that LDA-VGHB was capable of identifying possible lncRNAs for complex diseases. LDA-VGHB is publicly available at https://github.com/plhhnu/LDA-VGHB.

Intercellular communication significantly influences tumor progression, metastasis, and therapy resistance. An intercellular communication inference method includes two main procedures: ligand-receptor interaction (LRI) curation and LRI-mediated intercellular communication strength measurement. The construction of a comprehensive, high-confident and well-organized LRI database contributes to intercellular communication inference. Here, we developed a computational framework named CellDialog to reconstruct an intercellular connectivity network based on the combined expression of ligands and receptors involved in sender and receiver cells. CellDialog first captures high-confident LRIs through LRI feature extraction, feature selection, and classification. Furthermore, CellDialog uses a three-point estimation approach to measure the LRI-mediated intercellular communication strength by combining LRI filtering and single-cell RNA sequencing data. A comparison analysis of CellDialog and the other tools was conducted, and it was found that CellDialog can efficiently decode intercellular communications. Additionally, CellDialog offers a heatmap view and network view for intercellular communication visualization. In summary, CellDialog provides a tool that allows researchers to analyze intercellular signal transduction. It is freely available at https://github.com/plhhnu/CellDialog.

lncRNAs are involved in many biological processes, and their mutations and disorders are closely related to many diseases. Identification of LncRNA-Disease Associations (LDAs) helps us understand the pathogenesis of diseases and improve their diagnosis and treatment. However, experiments to determine LDAs are expensive, so it is essential to exploit effective computational methods to screen possible LDAs. In this study, we developed an LDA prediction model (LDA-DLPU) based on deep learning and positive-unlabeled (PU) learning. First, LDA-DLPU extracted features of lncRNAs and diseases based on singular value decomposition and regression model. Second, it selected negative LDAs based on PU learning and graph autoencoder. Finally, it classified unknown lncRNA-disease pairs based on deep neural network. LDA-DLPU obtained the best performance on two datasets. We predict that BCYRN1 and IFNG-AS1 may associate with leukemia.

Spatially resolved transcriptomic data provide a large quantity of high-throughput gene expression and spatial structure information of tissues. Spatial clusters obtained by spatial transcriptome helps us to identify co-expressed regions and gene modules corresponding to cell types. In this study, we developed a Deep learning-based spatial clustering algorithm (RkDeep) by combining Ratio-cut and k-means. We first preprocessed spatial transcriptome data using graph neural network, and conducted dimensional reduction on the preprocessed data with denoising autoencoder. Finally, we clustered spatial transcriptome data by combining ratio cut and k-means. We compared our proposed RkDeep method with the other two spatial clustering methods, Seurat and Panoview. The results show that RkDeep computed the smallest Davide-Bouldin index and the largest Caliniski Harabaz index, adjusted rand index and normalized mutual information. Moreover, RkDeep was applied to analyze spatial transcriptome data of adult mouse brain, adult mouse kidney, and breast cancer. The results show that RkDeep can more accurately identify cell types from spatial transcriptome data.

Cell-to-cell communication (CCC) plays essential roles in multicellular organisms. the identification of CCC between cancer cells themselves and one between cancer cells and normal cells in tumor microenvironment contributes to the understanding of carcinogenesis, cancer development and metastasis. CCC is usually mediated by Ligand-Receptor Interactions (LRIs). In this manuscript, we developed an LRI-mediated CCC estimation framework (LRI-EnABCLG) by incorporating LRI collection, prediction and filtering, CCC inference and visualization. First, four LRI datasets were collected. Second, LRIs were predicted by a heterogeneous deep ensemble model. Third, LRIs were filtered by combining single-cell sequencing (scRNA-seq) data. Fourth, CCC was inferred by combining the filtered LRIs and scRNA-seq data. Finally, the proposed CCC prediction framework was applied to CCC analysis in colorectal tumor tissues. Our proposed LRI-EnABCLG model obtained better LRI prediction performance. Case study demonstrated that fibroblasts was more likely to communicate with colorectal cancer cells, which was in accord with the results from iTALK (a classical CCC analysis pipeline). We anticipate that this work can contribute to diagnosis and treatment of cancers.

Carcinomas are complex ecosystems composed of cancer, stromal and immune cells. Communication between these cells and their microenvironments induces cancer progression and causes therapy resistance. In order to improve the treatment of cancers, it is essential to quantify crosstalk between and within various cell types in a tumour microenvironment. Focusing on the coordinated expression patterns of ligands and cognate receptors, cell-cell communication can be inferred through ligand-receptor interactions (LRIs). In this manuscript, we carry out the following work: (i) introduce pipeline for ligand-receptor-mediated intercellular communication estimation from single-cell transcriptomics and list a few available LRI-related databases and visualization tools; (ii) demonstrate seven classical intercellular communication scoring strategies, highlight four types of representative intercellular communication inference methods, including network-based approaches, machine learning-based approaches, spatial information-based approaches and other approaches; (iii) summarize the evaluation and validation avenues for intercellular communication inference and analyze the advantages and limitations for the above four types of cell-cell communication methods; (iv) comment several major challenges while provide further research directions for intercellular communication analysis in the tumour microenvironments. We anticipate that this work helps to better understand intercellular crosstalk and to further develop powerful cell-cell communication estimation tools for tumor-targeted therapy.

The identification of lncRNA-protein interactions (LPIs) is important to understand the biological functions and molecular mechanisms of lncRNAs. However, most computational models are evaluated on a unique dataset, thereby resulting in prediction bias. Furthermore, previous models have not uncovered potential proteins (or lncRNAs) interacting with a new lncRNA (or protein). Finally, the performance of these models can be improved. In this study, we develop a Deep Learning framework with Dual-net Neural architecture to find potential LPIs (LPI-DLDN). First, five LPI datasets are collected. Second, the features of lncRNAs and proteins are extracted by Pyfeat and BioTriangle, respectively. Third, these features are concatenated as a vector after dimension reduction. Finally, a deep learning model with dual-net neural architecture is designed to classify lncRNA-protein pairs. LPI-DLDN is compared with six state-of-the-art LPI prediction methods (LPI-XGBoost, LPI-HeteSim, LPI-NRLMF, PLIPCOM, LPI-CNNCP, and Capsule-LPI) under four cross validations. The results demonstrate the powerful LPI classification performance of LPI-DLDN. Case study analyses show that there may be interactions between RP11-439E19.10 and Q15717, and between RP11-196G18.22 and Q9NUL5. The novelty of LPI-DLDN remains, integrating various biological features, designing a novel deep learning-based LPI identification framework, and selecting the optimal LPI feature subset based on feature importance ranking.

BACKGROUND: Long noncoding RNAs (lncRNAs) have dense linkages with a plethora of important cellular activities. lncRNAs exert functions by linking with corresponding RNA-binding proteins. Since experimental techniques to detect lncRNA-protein interactions (LPIs) are laborious and time-consuming, a few computational methods have been reported for LPI prediction. However, computation-based LPI identification methods have the following limitations: (1) Most methods were evaluated on a single dataset, and researchers may thus fail to measure their generalization ability. (2) The majority of methods were validated under cross validation on lncRNA-protein pairs, did not investigate the performance under other cross validations, especially for cross validation on independent lncRNAs and independent proteins. (3) lncRNAs and proteins have abundant biological information, how to select informative features need to further investigate. RESULTS: Under a hybrid framework (LPI-HyADBS) integrating feature selection based on AdaBoost, and classification models including deep neural network (DNN), extreme gradient Boost (XGBoost), and SVM with a penalty Coefficient of misclassification (C-SVM), this work focuses on finding new LPIs. First, five datasets are arranged. Each dataset contains lncRNA sequences, protein sequences, and an LPI network. Second, biological features of lncRNAs and proteins are acquired based on Pyfeat. Third, the obtained features of lncRNAs and proteins are selected based on AdaBoost and concatenated to depict each LPI sample. Fourth, DNN, XGBoost, and C-SVM are used to classify lncRNA-protein pairs based on the concatenated features. Finally, a hybrid framework is developed to integrate the classification results from the above three classifiers. LPI-HyADBS is compared to six classical LPI prediction approaches (LPI-SKF, LPI-NRLMF, Capsule-LPI, LPI-CNNCP, LPLNP, and LPBNI) on five datasets under 5-fold cross validations on lncRNAs, proteins, lncRNA-protein pairs, and independent lncRNAs and independent proteins. The results show LPI-HyADBS has the best LPI prediction performance under four different cross validations. In particular, LPI-HyADBS obtains better classification ability than other six approaches under the constructed independent dataset. Case analyses suggest that there is relevance between ZNF667-AS1 and Q15717. CONCLUSIONS: Integrating feature selection approach based on AdaBoost, three classification techniques including DNN, XGBoost, and C-SVM, this work develops a hybrid framework to identify new linkages between lncRNAs and proteins.

BACKGROUND: Long noncoding RNAs (lncRNAs) play important roles in various biological and pathological processes. Discovery of lncRNA-protein interactions (LPIs) contributes to understand the biological functions and mechanisms of lncRNAs. Although wet experiments find a few interactions between lncRNAs and proteins, experimental techniques are costly and time-consuming. Therefore, computational methods are increasingly exploited to uncover the possible associations. However, existing computational methods have several limitations. First, majority of them were measured based on one simple dataset, which may result in the prediction bias. Second, few of them are applied to identify relevant data for new lncRNAs (or proteins). Finally, they failed to utilize diverse biological information of lncRNAs and proteins. RESULTS: Under the feed-forward deep architecture based on gradient boosting decision trees (LPI-deepGBDT), this work focuses on classify unobserved LPIs. First, three human LPI datasets and two plant LPI datasets are arranged. Second, the biological features of lncRNAs and proteins are extracted by Pyfeat and BioProt, respectively. Thirdly, the features are dimensionally reduced and concatenated as a vector to represent an lncRNA-protein pair. Finally, a deep architecture composed of forward mappings and inverse mappings is developed to predict underlying linkages between lncRNAs and proteins. LPI-deepGBDT is compared with five classical LPI prediction models (LPI-BLS, LPI-CatBoost, PLIPCOM, LPI-SKF, and LPI-HNM) under three cross validations on lncRNAs, proteins, lncRNA-protein pairs, respectively. It obtains the best average AUC and AUPR values under the majority of situations, significantly outperforming other five LPI identification methods. That is, AUCs computed by LPI-deepGBDT are 0.8321, 0.6815, and 0.9073, respectively and AUPRs are 0.8095, 0.6771, and 0.8849, respectively. The results demonstrate the powerful classification ability of LPI-deepGBDT. Case study analyses show that there may be interactions between GAS5 and Q15717, RAB30-AS1 and O00425, and LINC-01572 and P35637. CONCLUSIONS: Integrating ensemble learning and hierarchical distributed representations and building a multiple-layered deep architecture, this work improves LPI prediction performance as well as effectively probes interaction data for new lncRNAs/proteins.

Identifying potential associations between drugs and targets is a critical prerequisite for modern drug discovery and repurposing. However, predicting these associations is difficult because of the limitations of existing computational methods. Most models only consider chemical structures and protein sequences, and other models are oversimplified. Moreover, datasets used for analysis contain only true-positive interactions, and experimentally validated negative samples are unavailable. To overcome these limitations, we developed a semi-supervised based learning framework called NormMulInf through collaborative filtering theory by using labeled and unlabeled interaction information. The proposed method initially determines similarity measures, such as similarities among samples and local correlations among the labels of the samples, by integrating biological information. The similarity information is then integrated into a robust principal component analysis model, which is solved using augmented Lagrange multipliers. Experimental results on four classes of drug-target interaction networks suggest that the proposed approach can accurately classify and predict drug-target interactions. Part of the predicted interactions are reported in public databases. The proposed method can also predict possible targets for new drugs and can be used to determine whether atropine may interact with alpha1B- and beta1- adrenergic receptors. Furthermore, the developed technique identifies potential drugs for new targets and can be used to assess whether olanzapine and propiomazine may target 5HT2B. Finally, the proposed method can potentially address limitations on studies of multitarget drugs and multidrug targets.

Efficient mining of high-throughput data has become one of the popular themes in the big data era. Existing biology-related feature ranking methods mainly focus on statistical and annotation information. In this study, two efficient feature ranking methods are presented. Multi-target regression and graph embedding are incorporated in an optimization framework, and feature ranking is achieved by introducing structured sparsity norm. Unlike existing methods, the presented methods have two advantages: (1) the feature subset simultaneously account for global margin information as well as locality manifold information. Consequently, both global and locality information are considered. (2) Features are selected by batch rather than individually in the algorithm framework. Thus, the interactions between features are considered and the optimal feature subset can be guaranteed. In addition, this study presents a theoretical justification. Empirical experiments demonstrate the effectiveness and efficiency of the two algorithms in comparison with some state-of-the-art feature ranking methods through a set of real-world gene expression data sets.

Low-rank coding (LRC), originated from matrix decomposition, is recently introduced into image classification. Following the standard bag-of-words (BOW) pipeline, when coding the data matrix in the sense of low-rankness incorporates contextual information into the traditional BOW model, this can capture the dependency relationship among neighbor patches. It differs from the traditional sparse coding paradigms which encode patches independently. Current LRC-based methods use l_1 norm to increase the discrimination and sparseness of the learned codes. However, such methods fail to consider the local manifold structure between dataspace and dictionary space. To solve this problem, we propose a locality-constrained low-rank coding (LCLR) algorithm for image representations. By using the geometric structure information as a regularization term,we can obtain more discriminative representations. In addition, we present a fast and stable online algorithmto solve the optimization problem. In the experiments,we evaluate LCLR with four benchmarks, including one face recognition dataset (extended Yale B), one handwrittendigit recognition dataset (USPS), and two image datasets (Scene13 for scene recognition and Caltech101 for object recognition). Experimental results show thatour approach outperforms many state-of-the-art algorithmseven with a linear classifier.

FAST TCP is a new transmission control protocol designed for high speed networks. In this paper, we mainly address the stability issue of FAST TCP with time-delay. We first establish the nonlinear delay differential model of the transmission system made up of FAST TCP and the routers. Then, using the stability criterion for double time-delay system, we give the local stability condition of FAST TCP in single-link multi-source networks with time-delay. The conclusion gained here is more accurate than the existing one. Based on the stability conclusion, we further discuss the parameter setting of FAST TCP and propose a method to adjust the parameter. The simulation results confirm the correctness of the conclusion and the effectiveness of the new algorithm.