Modeling the causal regulatory network by integrating chromatin accessibility and transcriptome data

DeepCAGE: Incorporating Transcription Factors in Genome-wide Prediction of Chromatin Accessibility

Although computational approaches have been complementing high-throughput biological experiments for the identification of functional regions in the human genome, it remains a great challenge to systematically decipher interactions between transcription factors (TFs) and regulatory elements to achieve interpretable annotations of chromatin accessibility across diverse cellular contexts. To solve this problem, we propose DeepCAGE, a deep learning framework that integrates sequence information and binding statuses of TFs, for the accurate prediction of chromatin accessible regions at a genome-wide scale in a variety of cell types. DeepCAGE takes advantage of a densely connected deep convolutional neural network architecture to automatically learn sequence signatures of known chromatin accessible regions and then incorporates such features with expression levels and binding activities of human core TFs to predict novel chromatin accessible regions. In a series of systematic comparisons with existing methods, DeepCAGE exhibits superior performance in not only the classification but also the regression of chromatin accessibility signals. In a detailed analysis of TF activities, DeepCAGE successfully extracts novel binding motifs and measures the contribution of a TF to the regulation with respect to a specific locus in a certain cell type. When applied to whole-genome sequencing data analysis, our method successfully prioritizes putative deleterious variants underlying a human complex trait and thus provides insights into the understanding of disease-associated genetic variants. DeepCAGE can be downloaded from https://github.com/kimmo1019/DeepCAGE.

SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model

A large number of inorganic and organic compounds are able to bind DNA and form complexes, among which drug-related molecules are important. Chromatin accessibility changes not only directly affect drug–DNA interactions, but they can promote or inhibit the expression of the critical genes associated with drug resistance by affecting the DNA binding capacity of TFs and transcriptional regulators. However, the biological experimental techniques for measuring it are expensive and time-consuming. In recent years, several kinds of computational methods have been proposed to identify accessible regions of the genome. Existing computational models mostly ignore the contextual information provided by the bases in gene sequences. To address these issues, we proposed a new solution called SemanticCAP. It introduces a gene language model that models the context of gene sequences and is thus able to provide an effective representation of a certain site in a gene sequence. Basically, we merged the features provided by the gene language model into our chromatin accessibility model. During the process, we designed methods called SFA and SFC to make feature fusion smoother. Compared to DeepSEA, gkm-SVM, and k-mer using public benchmarks, our model proved to have better performance, showing a 1.25% maximum improvement in auROC and a 2.41% maximum improvement in auPRC.

Epigenetics of wheat-rust interaction: an update

The outcome of different host-pathogen interactions is influenced by both genetic and epigenetic systems, which determine the response of plants to pathogens and vice versa. This review highlights key molecular mechanisms and conceptual advances involved in epigenetic research and the progress made in epigenetics of wheat-rust interactions. Epigenetics implies the heritable changes in the way of gene expression as a consequence of the modification of DNA bases, histone proteins, and/or non-coding-RNA biogenesis without disturbing the underlying nucleotide sequence. The changes occurring between DNA and its surrounding chromatin without altering its DNA sequence and leading to significant changes in the genome of any organism are called epigenetic changes. Epigenetics has already been used successfully to explain the mechanism of human pathogens and in the identification of pathogen-induced modifications within various host plants. Wheat rusts are one of the most vital fungal diseases throughout the major wheat-growing areas of the world. The epigenome in plant pathogens causing diseases such as wheat rusts is mysterious. The investigations of host and pathogen epigenetics in the wheat rusts system can offer a piece of suitable evidence for elucidation of the molecular basis of host-pathogen interaction. Besides, the information on the epigenetic regulation of the genes involved in resistance or pathogenicity will provide better insights into the complex resistance signaling pathways and could provide answers to certain key questions, such as whether epigenetic regulation of certain genes is imparting resistance to host in response of certain pathogen elicitors or not. In the last few years, there has been an upsurge in research on the host as well as pathogen epigenetics and its outcome in plant-pathogen interactions. This review summarizes the progress made in the areas related to the epigenetic control of host-pathogen interaction with particular emphasis on wheat rusts.

Targeting Chromatin Complexes in Myeloid Malignancies and Beyond: From Basic Mechanisms to Clinical Innovation

The aberrant function of chromatin regulatory networks (epigenetics) is a hallmark of cancer promoting oncogenic gene expression. A growing body of evidence suggests that the disruption of specific chromatin-associated protein complexes has therapeutic potential in malignant conditions, particularly those that are driven by aberrant chromatin modifiers. Of note, a number of enzymatic inhibitors that block the catalytic function of histone modifying enzymes have been established and entered clinical trials. Unfortunately, many of these molecules do not have potent single-agent activity. One potential explanation for this phenomenon is the fact that those drugs do not profoundly disrupt the integrity of the aberrant network of multiprotein complexes on chromatin. Recent advances in drug development have led to the establishment of novel inhibitors of protein–protein interactions as well as targeted protein degraders that may provide inroads to longstanding effort to physically disrupt oncogenic multiprotein complexes on chromatin. In this review, we summarize some of the current concepts on the role epigenetic modifiers in malignant chromatin states with a specific focus on myeloid malignancies and recent advances in early-phase clinical trials.

Elucidation of Biological Networks across Complex Diseases Using Single-Cell Omics

Single-cell multimodal omics (scMulti-omics) technologies have made it possible to trace cellular lineages during differentiation and to identify new cell types in heterogeneous cell populations. The derived information is especially promising for computing cell-type-specific biological networks encoded in complex diseases and improving our understanding of the underlying gene regulatory mechanisms. The integration of these networks could, therefore, give rise to a heterogeneous regulatory landscape (HRL) in support of disease diagnosis and drug therapeutics. In this review, we provide an overview of this field and pay particular attention to how diverse biological networks can be inferred in a specific cell type based on integrative methods. Then, we discuss how HRL can advance our understanding of regulatory mechanisms underlying complex diseases and aid in the prediction of prognosis and therapeutic responses. Finally, we outline challenges and future trends that will be central to bringing the field of HRL in complex diseases forward.

Global Role of Crop Genomics in the Face of Climate Change

The development of climate change resilient crops is necessary if we are to meet the challenge of feeding the growing world's population. We must be able to increase food production despite the projected decrease in arable land and unpredictable environmental conditions. This review summarizes the technological and conceptual advances that have the potential to transform plant breeding, help overcome the challenges of climate change, and initiate the next plant breeding revolution. Recent developments in genomics in combination with high-throughput and precision phenotyping facilitate the identification of genes controlling critical agronomic traits. The discovery of these genes can now be paired with genome editing techniques to rapidly develop climate change resilient crops, including plants with better biotic and abiotic stress tolerance and enhanced nutritional value. Utilizing the genetic potential of crop wild relatives (CWRs) enables the domestication of new species and the generation of synthetic polyploids. The high-quality crop plant genome assemblies and annotations provide new, exciting research targets, including long non-coding RNAs (lncRNAs) and cis-regulatory regions. Metagenomic studies give insights into plant-microbiome interactions and guide selection of optimal soils for plant cultivation. Together, all these advances will allow breeders to produce improved, resilient crops in relatively short timeframes meeting the demands of the growing population and changing climate.

From reads to insight: a hitchhiker's guide to ATAC-seq data analysis

Assay of Transposase Accessible Chromatin sequencing (ATAC-seq) is widely used in studying chromatin biology, but a comprehensive review of the analysis tools has not been completed yet. Here, we discuss the major steps in ATAC-seq data analysis, including pre-analysis (quality check and alignment), core analysis (peak calling), and advanced analysis (peak differential analysis and annotation, motif enrichment, footprinting, and nucleosome position analysis). We also review the reconstruction of transcriptional regulatory networks with multiomics data and highlight the current challenges of each step. Finally, we describe the potential of single-cell ATAC-seq and highlight the necessity of developing ATAC-seq specific analysis tools to obtain biologically meaningful insights.

Hierarchical graphical model reveals HFR1 bridging circadian rhythm and flower development in Arabidopsis thaliana

To study systems-level properties of the cell, it is necessary to go beyond individual regulators and target genes to study the regulatory network among transcription factors (TFs). However, it is difficult to directly dissect the TFs mediated genome-wide gene regulatory network (GRN) by experiment. Here, we proposed a hierarchical graphical model to estimate TF activity from mRNA expression by building TF complexes with protein cofactors and inferring TF's downstream regulatory network simultaneously. Then we applied our model on flower development and circadian rhythm processes in Arabidopsis thaliana. The computational results show that the sequence specific bHLH family TF HFR1 recruits the chromatin regulator HAC1 to flower development master regulator TF AG and further activates AG's expression by histone acetylation. Both independent data and experimental results supported this discovery. We also found a flower tissue specific H3K27ac ChIP-seq peak at AG gene body and a HFR1 motif in the center of this H3K27ac peak. Furthermore, we verified that HFR1 physically interacts with HAC1 by yeast two-hybrid experiment. This HFR1-HAC1-AG triplet relationship may imply that flower development and circadian rhythm are bridged by epigenetic regulation and enrich the classical ABC model in flower development. In addition, our TF activity network can serve as a general method to elucidate molecular mechanisms on other complex biological regulatory processes.

Constructing tissue-specific transcriptional regulatory networks via a Markov random field

BACKGROUND

Recent advances in sequencing technologies have enabled parallel assays of chromatin accessibility and gene expression for major human cell lines. Such innovation provides a great opportunity to decode phenotypic consequences of genetic variation via the construction of predictive gene regulatory network models. However, there still lacks a computational method to systematically integrate chromatin accessibility information with gene expression data to recover complicated regulatory relationships between genes in a tissue-specific manner.

RESULTS

We propose a Markov random field (MRF) model for constructing tissue-specific transcriptional regulatory networks via integrative analysis of DNase-seq and RNA-seq data. Our method, named CSNets (cell-line specific regulatory networks), first infers regulatory networks for individual cell lines using chromatin accessibility information, and then fine-tunes these networks using the MRF based on pairwise similarity between cell lines derived from gene expression data. Using this method, we constructed regulatory networks specific to 110 human cell lines and 13 major tissues with the use of ENCODE data. We demonstrated the high quality of these networks via comprehensive statistical analysis based on ChIP-seq profiles, functional annotations, taxonomic analysis, and literature surveys. We further applied these networks to analyze GWAS data of Crohn's disease and prostate cancer. Results were either consistent with the literature or provided biological insights into regulatory mechanisms of these two complex diseases. The website of CSNets is freely available at http://bioinfo.au.tsinghua.edu.cn/jianglab/CSNETS/ .

CONCLUSIONS

CSNets demonstrated the power of joint analysis on epigenomic and transcriptomic data towards the accurate construction of gene regulatory network. Our work provides not only a useful resource of regulatory networks to the community, but also valuable experiences in methodology development for multi-omics data integration.

Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding

Motivation

Experimental techniques for measuring chromatin accessibility are expensive and time consuming, appealing for the development of computational approaches to predict open chromatin regions from DNA sequences. Along this direction, existing methods fall into two classes: one based on handcrafted k-mer features and the other based on convolutional neural networks. Although both categories have shown good performance in specific applications thus far, there still lacks a comprehensive framework to integrate useful k-mer co-occurrence information with recent advances in deep learning.

Results

We fill this gap by addressing the problem of chromatin accessibility prediction with a convolutional Long Short-Term Memory (LSTM) network with k-mer embedding. We first split DNA sequences into k-mers and pre-train k-mer embedding vectors based on the co-occurrence matrix of k-mers by using an unsupervised representation learning approach. We then construct a supervised deep learning architecture comprised of an embedding layer, three convolutional layers and a Bidirectional LSTM (BLSTM) layer for feature learning and classification. We demonstrate that our method gains high-quality fixed-length features from variable-length sequences and consistently outperforms baseline methods. We show that k-mer embedding can effectively enhance model performance by exploring different embedding strategies. We also prove the efficacy of both the convolution and the BLSTM layers by comparing two variations of the network architecture. We confirm the robustness of our model to hyper-parameters by performing sensitivity analysis. We hope our method can eventually reinforce our understanding of employing deep learning in genomic studies and shed light on research regarding mechanisms of chromatin accessibility.

Availability and implementation

The source code can be downloaded from https://github.com/minxueric/ismb2017_lstm.

Supplementary information

Supplementary materials are available at Bioinformatics online.

Improved anticancer drug response prediction in cell lines using matrix factorization with similarity regularization

BACKGROUND

Human cancer cell lines are used in research to study the biology of cancer and to test cancer treatments. Recently there are already some large panels of several hundred human cancer cell lines which are characterized with genomic and pharmacological data. The ability to predict drug responses using these pharmacogenomics data can facilitate the development of precision cancer medicines. Although several methods have been developed to address the drug response prediction, there are many challenges in obtaining accurate prediction.

METHODS

Based on the fact that similar cell lines and similar drugs exhibit similar drug responses, we adopted a similarity-regularized matrix factorization (SRMF) method to predict anticancer drug responses of cell lines using chemical structures of drugs and baseline gene expression levels in cell lines. Specifically, chemical structural similarity of drugs and gene expression profile similarity of cell lines were considered as regularization terms, which were incorporated to the drug response matrix factorization model.

RESULTS

We first demonstrated the effectiveness of SRMF using a set of simulation data and compared it with two typical similarity-based methods. Furthermore, we applied it to the Genomics of Drug Sensitivity in Cancer (GDSC) and Cancer Cell Line Encyclopedia (CCLE) datasets, and performance of SRMF exceeds three state-of-the-art methods. We also applied SRMF to estimate the missing drug response values in the GDSC dataset. Even though SRMF does not specifically model mutation information, it could correctly predict drug-cancer gene associations that are consistent with existing data, and identify novel drug-cancer gene associations that are not found in existing data as well. SRMF can also aid in drug repositioning. The newly predicted drug responses of GDSC dataset suggest that mTOR inhibitor rapamycin was sensitive to non-small cell lung cancer (NSCLC), and expression of AK1RC3 and HINT1 may be adjunct markers of cell line sensitivity to rapamycin.

CONCLUSIONS

Our analysis showed that the proposed data integration method is able to improve the accuracy of prediction of anticancer drug responses in cell lines, and can identify consistent and novel drug-cancer gene associations compared to existing data as well as aid in drug repositioning.