Recent advances in spatially resolved transcriptomics have enabled comprehensive measurements of gene expression patterns while retaining the spatial context of the tissue microenvironment. Deciphering the spatial context of spots in a tissue needs to use their spatial information carefully. To this end, we develop a graph attention auto-encoder framework STAGATE to accurately identify spatial domains by learning low-dimensional latent embeddings via integrating spatial information and gene expression profiles. To better characterize the spatial similarity at the boundary of spatial domains, STAGATE adopts an attention mechanism to adaptively learn the similarity of neighboring spots, and an optional cell type-aware module through integrating the pre-clustering of gene expressions. We validate STAGATE on diverse spatial transcriptomics datasets generated by different platforms with different spatial resolutions. STAGATE could substantially improve the identification accuracy of spatial domains, and denoise the data while preserving spatial expression patterns. Importantly, STAGATE could be extended to multiple consecutive sections to reduce batch effects between sections and extracting three-dimensional (3D) expression domains from the reconstructed 3D tissue effectively.

Motivation: It is well known that microRNAs (miRNAs) and genes work cooperatively to form the key part of gene regulatory networks. However, the specific functional roles of most miRNAs and their combinatorial effects in cellular processes are still unclear. The availability of multiple types of functional genomic data provides unprecedented opportunities to study the miRNA–gene regulation. A major challenge is how to integrate the diverse genomic data to identify the regulatory modules of miRNAs and genes. Results: Here we propose an effective data integration framework to identify the miRNA–gene regulatory comodules. The miRNA and gene expression profiles are jointly analyzed in a multiple non-negative matrix factorization framework, and additional network data are simultaneously integrated in a regularized manner. Meanwhile, we employ the sparsity penalties to the variables to achieve modular solutions. The mathematical formulation can be effectively solved by an iterative multiplicative updating algorithm. We apply the proposed method to integrate a set of heterogeneous data sources including the expression profiles of miRNAs and genes on 385 human ovarian cancer samples, computationally predicted miRNA–gene interactions, and gene–gene interactions. We demonstrate that the miRNAs and genes in 69% of the regulatory comodules are significantly associated. Moreover, the comodules are significantly enriched in known functional sets such as miRNA clusters, GO biological processes and KEGG pathways, respectively. Furthermore, many miRNAs and genes in the comodules are related with various cancers including ovarian cancer. Finally, we show that comodules can stratify patients (samples) into groups with significant clinical characteristics. Availability: The program and supplementary materials are available at http://zhoulab.usc.edu/SNMNMF/. Contact:xjzhou@usc.edu; zsh@amss.ac.cn Supplementary information: Supplementary data are available at Bioinformatics online.

Background: The treatment of complex diseases by taking multiple drugs becomes increasingly popular. However, drug-drug interactions (DDIs) may give rise to the risk of unanticipated adverse effects and even unknown toxicity. DDI detection in the wet lab is expensive and time-consuming. Thus, it is highly desired to develop the computational methods for predicting DDIs. Generally, most of the existing computational methods predict DDIs by extracting the chemical and biological features of drugs from diverse drug-related properties, however some drug properties are costly to obtain and not available in many cases.Results: In this work, we presented a novel method (namely DPDDI) to predict DDIs by extracting the network structure features of drugs from DDI network with graph convolution network (GCN), and the deep neural network (DNN) model as a predictor. GCN learns the low-dimensional feature representations of drugs by capturing the topological relationship of drugs in DDI network. DNN predictor concatenates the latent feature vectors of any two drugs as the feature vector of the corresponding drug pairs to train a DNN for predicting the potential drug-drug interactions. Experiment results show that, the newly proposed DPDDI method outperforms four other state-of-the-art methods; the GCN-derived latent features include more DDI information than other features derived from chemical, biological or anatomical properties of drugs; and the concatenation feature aggregation operator is better than two other feature aggregation operators (i.e., inner product and summation). The results in case studies confirm that DPDDI achieves reasonable performance in predicting new DDIs.Conclusion: We proposed an effective and robust method DPDDI to predict the potential DDIs by utilizing the DDI network information without considering the drug properties (i.e., drug chemical and biological properties). The method should also be useful in other DDI-related scenarios, such as the detection of unexpected side effects, and the guidance of drug combination.

Motivation: The first step for clinical diagnostics, prognostics and targeted therapeutics of cancer is to comprehensively understand its molecular mechanisms. Large-scale cancer genomics projects are providing a large volume of data about genomic, epigenomic and gene expression aberrations in multiple cancer types. One of the remaining challenges is to identify driver mutations, driver genes and driver pathways promoting cancer proliferation and filter out the unfunctional and passenger ones. Results: In this study, we propose two methods to solve the so-called maximum weight submatrix problem, which is designed to de novo identify mutated driver pathways from mutation data in cancer. The first one is an exact method that can be helpful for assessing other approximate or/and heuristic algorithms. The second one is a stochastic and flexible method that can be employed to incorporate other types of information to improve the first method. Particularly, we propose an integrative model to combine mutation and expression data. We first apply our methods onto simulated data to show their efficiency. We further apply the proposed methods onto several real biological datasets, such as the mutation profiles of 74 head and neck squamous cell carcinomas samples, 90 glioblastoma tumor samples and 313 ovarian carcinoma samples. The gene expression profiles were also considered for the later two data. The results show that our integrative model can identify more biologically relevant gene sets. We have implemented all these methods and made a package called mutated driver pathway finder, which can be easily used for other researchers. Availability: A MATLAB package of MDPFinder is available at http://zhangroup.aporc.org/ShiHuaZhang Contact:zsh@amss.ac.cn Supplementary information: Supplementary data are available at Bioinformatics online.

The inference of gene regulatory networks (GRNs) from expression data can mine the direct regulations among genes and gain deep insights into biological processes at a network level. During past decades, numerous computational approaches have been introduced for inferring the GRNs. However, many of them still suffer from various problems, e.g., Bayesian network (BN) methods cannot handle large-scale networks due to their high computational complexity, while information theory-based methods cannot identify the directions of regulatory interactions and also suffer from false positive/negative problems. To overcome the limitations, in this work we present a novel algorithm, namely local Bayesian network (LBN), to infer GRNs from gene expression data by using the network decomposition strategy and false-positive edge elimination scheme. Specifically, LBN algorithm first uses conditional mutual information (CMI) to construct an initial network or GRN, which is decomposed into a number of local networks or GRNs. Then, BN method is employed to generate a series of local BNs by selecting the k-nearest neighbors of each gene as its candidate regulatory genes, which significantly reduces the exponential search space from all possible GRN structures. Integrating these local BNs forms a tentative network or GRN by performing CMI, which reduces redundant regulations in the GRN and thus alleviates the false positive problem. The final network or GRN can be obtained by iteratively performing CMI and local BN on the tentative network. In the iterative process, the false or redundant regulations are gradually removed. When tested on the benchmark GRN datasets from DREAM challenge as well as the SOS DNA repair network in E.coli, our results suggest that LBN outperforms other state-of-the-art methods (ARACNE, GENIE3 and NARROMI) significantly, with more accurate and robust performance. In particular, the decomposition strategy with local Bayesian networks not only effectively reduce the computational cost of BN due to much smaller sizes of local GRNs, but also identify the directions of the regulations. Gene regulatory network (GRN) represents how some genes encode regulatory molecules such as transcription factors or microRNAs for regulating the expression of other genes. Accurate inference of GRN is an important task to understand the biological activity from signal emulsion to metabolic dynamics, prioritize potential drug targets of various diseases, devise effective therapeutics, and discover the novel pathways. In this paper, we propose a novel local Bayesian network (LBN) algorithm to improve the accuracy of GRN inference from gene expression data by exploring advantages of Bayesian network (BN) and conditional mutual information (CMI) methods. BNs with kNN network decomposition and CMI are respectively introduced to reduce the high computational complexity of BN and remove the false or redundant regulation interactions. The superior performance of the proposed LBN approach is demonstrated on GRN datasets from DREAM challenge as well as the SOS DNA repair network in E. coli.