HiChIPdb: a comprehensive database of HiChIP regulatory interactions.

Elucidating the role of 3D architecture of DNA in gene regulation is crucial for understanding cell differentiation, tissue homeostasis and disease development. Among various chromatin conformation capture methods, HiChIP has received increasing attention for its significant improvement over other methods in profiling of regulatory (e.g. H3K27ac) and structural (e.g. cohesin) interactions. To facilitate the studies of 3D regulatory interactions, we developed a HiChIP interactions database, HiChIPdb (http://health.tsinghua.edu.cn/hichipdb/). The current version of HiChIPdb contains ∼262M annotated HiChIP interactions from 200 high-throughput HiChIP samples across 108 cell types. The functionalities of HiChIPdb include: (i) standardized categorization of HiChIP interactions in a hierarchical structure based on organ, tissue and cell line and (ii) comprehensive annotations of HiChIP interactions with regulatory genes and GWAS Catalog SNPs. To the best of our knowledge, HiChIPdb is the first comprehensive database that utilizes a unified pipeline to map the functional interactions across diverse cell types and tissues in different resolutions. We believe this database has the potential to advance cutting-edge research in regulatory mechanisms in development and disease by removing the barrier in data aggregation, preprocessing, and analysis.

REDDA: Integrating multiple biological relations to heterogeneous graph neural network for drug-disease association prediction.

Computational drug repositioning is an effective way to find new indications for existing drugs, thus can accelerate drug development and reduce experimental costs. Recently, various deep learning-based repurposing methods have been established to identify the potential drug-disease associations (DDA). However, effective utilization of the relations of biological entities to capture the biological interactions to enhance the drug-disease association prediction is still challenging. To resolve the above problem, we proposed a heterogeneous graph neural network called REDDA (Relations-Enhanced Drug-Disease Association prediction). Assembled with three attention mechanisms, REDDA can sequentially learn drug/disease representations by a general heterogeneous graph convolutional network-based node embedding block, a topological subnet embedding block, a graph attention block, and a layer attention block. Performance comparisons on our proposed benchmark dataset show that REDDA outperforms 8 advanced drug-disease association prediction methods, achieving relative improvements of 0.76% on the area under the receiver operating characteristic curve (AUC) score and 13.92% on the precision-recall curve (AUPR) score compared to the suboptimal method. On the other benchmark dataset, REDDA also obtains relative improvements of 2.48% on the AUC score and 4.93% on the AUPR score. Specifically, case studies also indicate that REDDA can give valid predictions for the discovery of -new indications for drugs and new therapies for diseases. The overall results provide an inspiring potential for REDDA in the in silico drug development. The proposed benchmark dataset and source code are available in https://github.com/gu-yaowen/REDDA.

PRKAR1A and SDCBP Serve as Potential Predictors of Heart Failure Following Acute Myocardial Infarction.

Background and Objectives: Early diagnosis of patients with acute myocardial infarction (AMI) who are at a high risk of heart failure (HF) progression remains controversial. This study aimed at identifying new predictive biomarkers of post-AMI HF and at revealing the pathogenesis of HF involving these marker genes. Methods and Results: A transcriptomic dataset of whole blood cells from AMI patients with HF progression (post-AMI HF, n = 16) and without progression (post-AMI non-HF, n = 16) was analyzed using the weighted gene co-expression network analysis (WGCNA). The results indicated that one module consisting of 720 hub genes was significantly correlated with post-AMI HF. The hub genes were validated in another transcriptomic dataset of peripheral blood mononuclear cells (post-AMI HF, n = 9; post-AMI non-HF, n = 8). PRKAR1A, SDCBP, SPRED2, and VAMP3 were upregulated in the two datasets. Based on a single-cell RNA sequencing dataset of leukocytes from heart tissues of normal and infarcted mice, PRKAR1A was further verified to be upregulated in monocytes/macrophages on day 2, while SDCBP was highly expressed in neutrophils on day 2 and in monocytes/macrophages on day 3 after AMI. Cell-cell communication analysis via the "CellChat" package showed that, based on the interaction of ligand-receptor (L-R) pairs, there were increased autocrine/paracrine cross-talk networks of monocytes/macrophages and neutrophils in the acute stage of MI. Functional enrichment analysis of the abovementioned L-R genes together with PRKAR1A and SDCBP performed through the Metascape platform suggested that PRKAR1A and SDCBP were mainly involved in inflammation, apoptosis, and angiogenesis. The receiver operating characteristic (ROC) curve analysis demonstrated that PRKAR1A and SDCBP, as well as their combination, had a promising prognostic value in the identification of AMI patients who were at a high risk of HF progression. Conclusion: This study identified that PRKAR1A and SDCBP may serve as novel biomarkers for the early diagnosis of post-AMI HF and also revealed their potentially regulatory mechanism during HF progression.

An efficient curriculum learning-based strategy for molecular graph learning.

Computational methods have been widely applied to resolve various core issues in drug discovery, such as molecular property prediction. In recent years, a data-driven computational method-deep learning had achieved a number of impressive successes in various domains. In drug discovery, graph neural networks (GNNs) take molecular graph data as input and learn graph-level representations in non-Euclidean space. An enormous amount of well-performed GNNs have been proposed for molecular graph learning. Meanwhile, efficient use of molecular data during training process, however, has not been paid enough attention. Curriculum learning (CL) is proposed as a training strategy by rearranging training queue based on calculated samples' difficulties, yet the effectiveness of CL method has not been determined in molecular graph learning. In this study, inspired by chemical domain knowledge and task prior information, we proposed a novel CL-based training strategy to improve the training efficiency of molecular graph learning, called CurrMG. Consisting of a difficulty measurer and a training scheduler, CurrMG is designed as a plug-and-play module, which is model-independent and easy-to-use on molecular data. Extensive experiments demonstrated that molecular graph learning models could benefit from CurrMG and gain noticeable improvement on five GNN models and eight molecular property prediction tasks (overall improvement is 4.08%). We further observed CurrMG's encouraging potential in resource-constrained molecular property prediction. These results indicate that CurrMG can be used as a reliable and efficient training strategy for molecular graph learning. Availability: The source code is available in https://github.com/gu-yaowen/CurrMG.

scGraph: a graph neural network-based approach to automatically identify cell types.

MOTIVATION: Single-cell technologies play a crucial role in revolutionizing biological research over the past decade, which strengthens our understanding in cell differentiation, development and regulation from a single-cell level perspective. Single-cell RNA sequencing (scRNA-seq) is one of the most common single cell technologies, which enables probing transcriptional states in thousands of cells in one experiment. Identification of cell types from scRNA-seq measurements is a fundamental and crucial question to answer. Most previous studies directly take gene expression as input while ignoring the comprehensive gene-gene interactions. RESULTS: We propose scGraph, an automatic cell identification algorithm leveraging gene interaction relationships to enhance the performance of the cell-type identification. scGraph is based on a graph neural network to aggregate the information of interacting genes. In a series of experiments, we demonstrate that scGraph is accurate and outperforms eight comparison methods in the task of cell-type identification. Moreover, scGraph automatically learns the gene interaction relationships from biological data and the pathway enrichment analysis shows consistent findings with previous analysis, providing insights on the analysis of regulatory mechanism. AVAILABILITY AND IMPLEMENTATION: scGraph is freely available at https://github.com/QijinYin/scGraph and https://figshare.com/articles/software/scGraph/17157743. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Identification of monocyte-associated genes as predictive biomarkers of heart failure after acute myocardial infarction.

BACKGROUND: Acute myocardial infarction (AMI) is a major contributor of heart failure (HF). Peripheral blood mononuclear cells (PBMCs), mainly monocytes, are the essential initiators of AMI-induced HF. The powerful biomarkers for early identification of AMI patients at risk of HF remain elusive. We aimed to identify monocyte-related critical genes as predictive biomarkers for post-AMI HF. METHODS: We performed weighted gene co-expression network analysis (WGCNA) on transcriptomics of PBMCs from AMI patients who developed HF or did not. Functional enrichment analysis of genes in significant modules was performed via Metascape. Then we obtained the single-cell RNA-sequencing data of recruited monocytes/macrophages from AMI and control mice using the Scanpy and screened 381 differentially expressed genes (DEGs) between the two groups. We validated the expression changes of the 25 genes in cardiac macrophages from AMI mice based on bulk RNA-sequencing data and PBMCs data mentioned above. RESULTS: In our study, the results of WGCNA showed that two modules containing 827 hub genes were most significantly associated with post-AMI HF, which mainly participated in cell migration, inflammation, immunity, and apoptosis. There were 25 common genes between DEGs and hub genes, showing close relationship with inflammation and collagen metabolism. CUX1, CTSD and ADD3 exhibited consistent changes in three independent studies. Receiver operating characteristic curve analysis showed that each of the three genes had excellent performance in recognizing post-AMI HF patients. CONCLUSION: Our findings provided a set of three monocyte-related biomarkers for the early prediction of HF development after AMI as well as potential therapeutic targets of post-AMI HF.

DeepHistone: a deep learning approach to predicting histone modifications.

MOTIVATION: Quantitative detection of histone modifications has emerged in the recent years as a major means for understanding such biological processes as chromosome packaging, transcriptional activation, and DNA damage. However, high-throughput experimental techniques such as ChIP-seq are usually expensive and time-consuming, prohibiting the establishment of a histone modification landscape for hundreds of cell types across dozens of histone markers. These disadvantages have been appealing for computational methods to complement experimental approaches towards large-scale analysis of histone modifications. RESULTS: We proposed a deep learning framework to integrate sequence information and chromatin accessibility data for the accurate prediction of modification sites specific to different histone markers. Our method, named DeepHistone, outperformed several baseline methods in a series of comprehensive validation experiments, not only within an epigenome but also across epigenomes. Besides, sequence signatures automatically extracted by our method was consistent with known transcription factor binding sites, thereby giving insights into regulatory signatures of histone modifications. As an application, our method was shown to be able to distinguish functional single nucleotide polymorphisms from their nearby genetic variants, thereby having the potential to be used for exploring functional implications of putative disease-associated genetic variants. CONCLUSIONS: DeepHistone demonstrated the possibility of using a deep learning framework to integrate DNA sequence and experimental data for predicting epigenomic signals. With the state-of-the-art performance, DeepHistone was expected to shed light on a variety of epigenomic studies. DeepHistone is freely available in https://github.com/QijinYin/DeepHistone .

Chromatin accessibility prediction via a hybrid deep convolutional neural network.

Motivation: A majority of known genetic variants associated with human-inherited diseases lie in non-coding regions that lack adequate interpretation, making it indispensable to systematically discover functional sites at the whole genome level and precisely decipher their implications in a comprehensive manner. Although computational approaches have been complementing high-throughput biological experiments towards the annotation of the human genome, it still remains a big challenge to accurately annotate regulatory elements in the context of a specific cell type via automatic learning of the DNA sequence code from large-scale sequencing data. Indeed, the development of an accurate and interpretable model to learn the DNA sequence signature and further enable the identification of causative genetic variants has become essential in both genomic and genetic studies. Results: We proposed Deopen, a hybrid framework mainly based on a deep convolutional neural network, to automatically learn the regulatory code of DNA sequences and predict chromatin accessibility. In a series of comparison with existing methods, we show the superior performance of our model in not only the classification of accessible regions against background sequences sampled at random, but also the regression of DNase-seq signals. Besides, we further visualize the convolutional kernels and show the match of identified sequence signatures and known motifs. We finally demonstrate the sensitivity of our model in finding causative noncoding variants in the analysis of a breast cancer dataset. We expect to see wide applications of Deopen with either public or in-house chromatin accessibility data in the annotation of the human genome and the identification of non-coding variants associated with diseases. Availability and implementation: Deopen is freely available at https://github.com/kimmo1019/Deopen. Contact: ruijiang@tsinghua.edu.cn. Supplementary information: Supplementary data are available at Bioinformatics online.