Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks

Learning Micro-C from Hi-C with diffusion models

In the last few years, Micro-C has shown itself as an improved alternative to Hi-C. It replaced the restriction enzymes in Hi-C assays with micrococcal nuclease (MNase), resulting in capturing nucleosome resolution chromatin interactions. The signal-to-noise improvement of Micro-C allows it to detect more chromatin loops than high-resolution Hi-C. However, compared with massive Hi-C datasets available in the literature, there are only a limited number of Micro-C datasets. To take full advantage of these Hi-C datasets, we present HiC2MicroC, a computational method learning and then predicting Micro-C from Hi-C based on the denoising diffusion probabilistic models (DDPM). We trained our DDPM and other regression models in human foreskin fibroblast (HFFc6) cell line and evaluated these methods in six different cell types at 5-kb and 1-kb resolution. Our evaluations demonstrate that both HiC2MicroC and regression methods can markedly improve Hi-C towards Micro-C, and our DDPM-based HiC2MicroC outperforms regression in various terms. First, HiC2MicroC successfully recovers most of the Micro-C loops even those not detected in Hi-C maps. Second, a majority of the HiC2MicroC-recovered loops anchor CTCF binding sites in a convergent orientation. Third, HiC2MicroC loops share genomic and epigenetic properties with Micro-C loops, including linking promoters and enhancers, and their anchors are enriched for structural proteins (CTCF and cohesin) and histone modifications. Lastly, we find our recovered loops are also consistent with the loops identified from promoter capture Micro-C (PCMicro-C) and Chromatin Interaction Analysis by Paired-End Tag Sequencing (ChIA-PET). Overall, HiC2MicroC is an effective tool for further studying Hi-C data with Micro-C as a template. HiC2MicroC is publicly available at https://github.com/zwang-bioinformatics/HiC2MicroC/.

From tradition to innovation: conventional and deep learning frameworks in genome annotation

Following the milestone success of the Human Genome Project, the 'Encyclopedia of DNA Elements (ENCODE)' initiative was launched in 2003 to unearth information about the numerous functional elements within the genome. This endeavor coincided with the emergence of numerous novel technologies, accompanied by the provision of vast amounts of whole-genome sequences, high-throughput data such as ChIP-Seq and RNA-Seq. Extracting biologically meaningful information from this massive dataset has become a critical aspect of many recent studies, particularly in annotating and predicting the functions of unknown genes. The core idea behind genome annotation is to identify genes and various functional elements within the genome sequence and infer their biological functions. Traditional wet-lab experimental methods still rely on extensive efforts for functional verification. However, early bioinformatics algorithms and software primarily employed shallow learning techniques; thus, the ability to characterize data and features learning was limited. With the widespread adoption of RNA-Seq technology, scientists from the biological community began to harness the potential of machine learning and deep learning approaches for gene structure prediction and functional annotation. In this context, we reviewed both conventional methods and contemporary deep learning frameworks, and highlighted novel perspectives on the challenges arising during annotation underscoring the dynamic nature of this evolving scientific landscape.

Seq-RBPPred: Predicting RNA-Binding Proteins from Sequence

RNA-binding proteins (RBPs) can interact with RNAs to regulate RNA translation, modification, splicing, and other important biological processes. The accurate identification of RBPs is of paramount importance for gaining insights into the intricate mechanisms underlying organismal life activities. Traditional experimental methods to predict RBPs require a lot of time and money, so it is important to develop computational methods to predict RBPs. However, the existing approaches for RBP prediction still require further improvement due to unidentified RBPs in many species. In this study, we present Seq-RBPPred (predicting RBPs from sequence), a novel method that utilizes a comprehensive feature representation encompassing both biophysical properties and hidden-state features derived from protein sequences. In the results, comprehensive performance evaluations of Seq-RBPPred its superiority compare with state-of-the-art methods, yielding impressive performance including 0.922 for overall accuracy, 0.926 for sensitivity, 0.903 for specificity, and Matthew's correlation coefficient (MCC) of 0.757 as ascertained from the evaluation of the testing set. The data and code of Seq-RBPPred are available at https://github.com/yaoyao-11/Seq-RBPPred.

i5mC-DCGA: an improved hybrid network framework based on the CBAM attention mechanism for identifying promoter 5mC sites

BACKGROUND

5-Methylcytosine (5mC) plays a very important role in gene stability, transcription, and development. Therefore, accurate identification of the 5mC site is of key importance in genetic and pathological studies. However, traditional experimental methods for identifying 5mC sites are time-consuming and costly, so there is an urgent need to develop computational methods to automatically detect and identify these 5mC sites.

RESULTS

Deep learning methods have shown great potential in the field of 5mC sites, so we developed a deep learning combinatorial model called i5mC-DCGA. The model innovatively uses the Convolutional Block Attention Module (CBAM) to improve the Dense Convolutional Network (DenseNet), which is improved to extract advanced local feature information. Subsequently, we combined a Bidirectional Gated Recurrent Unit (BiGRU) and a Self-Attention mechanism to extract global feature information. Our model can learn feature representations of abstract and complex from simple sequence coding, while having the ability to solve the sample imbalance problem in benchmark datasets. The experimental results show that the i5mC-DCGA model achieves 97.02%, 96.52%, 96.58% and 85.58% in sensitivity (Sn), specificity (Sp), accuracy (Acc) and matthews correlation coefficient (MCC), respectively.

CONCLUSIONS

The i5mC-DCGA model outperforms other existing prediction tools in predicting 5mC sites, and it is currently the most representative promoter 5mC site prediction tool. The benchmark dataset and source code for the i5mC-DCGA model can be found in https://github.com/leirufeng/i5mC-DCGA .

Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models

The data explosion driven by advancements in genomic research, such as high-throughput sequencing techniques, is constantly challenging conventional methods used in genomics. In parallel with the urgent demand for robust algorithms, deep learning has succeeded in various fields such as vision, speech, and text processing. Yet genomics entails unique challenges to deep learning, since we expect a superhuman intelligence that explores beyond our knowledge to interpret the genome from deep learning. A powerful deep learning model should rely on the insightful utilization of task-specific knowledge. In this paper, we briefly discuss the strengths of different deep learning models from a genomic perspective so as to fit each particular task with proper deep learning-based architecture, and we remark on practical considerations of developing deep learning architectures for genomics. We also provide a concise review of deep learning applications in various aspects of genomic research and point out current challenges and potential research directions for future genomics applications. We believe the collaborative use of ever-growing diverse data and the fast iteration of deep learning models will continue to contribute to the future of genomics.

HiC4D: forecasting spatiotemporal Hi-C data with residual ConvLSTM

The Hi-C experiments have been extensively used for the studies of genomic structures. In the last few years, spatiotemporal Hi-C has largely contributed to the investigation of genome dynamic reorganization. However, computationally modeling and forecasting spatiotemporal Hi-C data still have not been seen in the literature. We present HiC4D for dealing with the problem of forecasting spatiotemporal Hi-C data. We designed and benchmarked a novel network and named it residual ConvLSTM (ResConvLSTM), which is a combination of residual network and convolutional long short-term memory (ConvLSTM). We evaluated our new ResConvLSTM networks and compared them with the other five methods, including a naïve network (NaiveNet) that we designed as a baseline method and four outstanding video-prediction methods from the literature: ConvLSTM, spatiotemporal LSTM (ST-LSTM), self-attention LSTM (SA-LSTM) and simple video prediction (SimVP). We used eight different spatiotemporal Hi-C datasets for the blind test, including two from mouse embryogenesis, one from somatic cell nuclear transfer (SCNT) embryos, three embryogenesis datasets from different species and two non-embryogenesis datasets. Our evaluation results indicate that our ResConvLSTM networks almost always outperform the other methods on the eight blind-test datasets in terms of accurately predicting the Hi-C contact matrices at future time-steps. Our benchmarks also indicate that all of the methods that we benchmarked can successfully recover the boundaries of topologically associating domains called on the experimental Hi-C contact matrices. Taken together, our benchmarks suggest that HiC4D is an effective tool for predicting spatiotemporal Hi-C data. HiC4D is publicly available at both http://dna.cs.miami.edu/HiC4D/ and https://github.com/zwang-bioinformatics/HiC4D/.

scHiMe: predicting single-cell DNA methylation levels based on single-cell Hi-C data

Recently a biochemistry experiment named methyl-3C was developed to simultaneously capture the chromosomal conformations and DNA methylation levels on individual single cells. However, the number of data sets generated from this experiment is still small in the scientific community compared with the greater amount of single-cell Hi-C data generated from separate single cells. Therefore, a computational tool to predict single-cell methylation levels based on single-cell Hi-C data on the same individual cells is needed. We developed a graph transformer named scHiMe to accurately predict the base-pair-specific (bp-specific) methylation levels based on both single-cell Hi-C data and DNA nucleotide sequences. We benchmarked scHiMe for predicting the bp-specific methylation levels on all of the promoters of the human genome, all of the promoter regions together with the corresponding first exon and intron regions, and random regions on the whole genome. Our evaluation showed a high consistency between the predicted and methyl-3C-detected methylation levels. Moreover, the predicted DNA methylation levels resulted in accurate classifications of cells into different cell types, which indicated that our algorithm successfully captured the cell-to-cell variability in the single-cell Hi-C data. scHiMe is freely available at http://dna.cs.miami.edu/scHiMe/.

Recall DNA methylation levels at low coverage sites using a CNN model in WGBS

DNA methylation is an important regulator of gene transcription. WGBS is the gold-standard approach for base-pair resolution quantitative of DNA methylation. It requires high sequencing depth. Many CpG sites with insufficient coverage in the WGBS data, resulting in inaccurate DNA methylation levels of individual sites. Many state-of-arts computation methods were proposed to predict the missing value. However, many methods required either other omics datasets or other cross-sample data. And most of them only predicted the state of DNA methylation. In this study, we proposed the RcWGBS, which can impute the missing (or low coverage) values from the DNA methylation levels on the adjacent sides. Deep learning techniques were employed for the accurate prediction. The WGBS datasets of H1-hESC and GM12878 were down-sampled. The average difference between the DNA methylation level at 12× depth predicted by RcWGBS and that at >50× depth in the H1-hESC and GM2878 cells are less than 0.03 and 0.01, respectively. RcWGBS performed better than METHimpute even though the sequencing depth was as low as 12×. Our work would help to process methylation data of low sequencing depth. It is beneficial for researchers to save sequencing costs and improve data utilization through computational methods.

DFHiC: a dilated full convolution model to enhance the resolution of Hi-C data

MOTIVATION

Hi-C technology has been the most widely used chromosome conformation capture (3C) experiment that measures the frequency of all paired interactions in the entire genome, which is a powerful tool for studying the 3D structure of the genome. The fineness of the constructed genome structure depends on the resolution of Hi-C data. However, due to the fact that high-resolution Hi-C data require deep sequencing and thus high experimental cost, most available Hi-C data are in low-resolution. Hence, it is essential to enhance the quality of Hi-C data by developing the effective computational methods.

RESULTS

In this work, we propose a novel method, so-called DFHiC, which generates the high-resolution Hi-C matrix from the low-resolution Hi-C matrix in the framework of the dilated convolutional neural network. The dilated convolution is able to effectively explore the global patterns in the overall Hi-C matrix by taking advantage of the information of the Hi-C matrix in a way of the longer genomic distance. Consequently, DFHiC can improve the resolution of the Hi-C matrix reliably and accurately. More importantly, the super-resolution Hi-C data enhanced by DFHiC is more in line with the real high-resolution Hi-C data than those done by the other existing methods, in terms of both chromatin significant interactions and identifying topologically associating domains.

AVAILABILITY AND IMPLEMENTATION

https://github.com/BinWangCSU/DFHiC.

Application of Feature Selection and Deep Learning for Cancer Prediction Using DNA Methylation Markers

DNA methylation is a process that can affect gene accessibility and therefore gene expression. In this study, a machine learning pipeline is proposed for the prediction of breast cancer and the identification of significant genes that contribute to the prediction. The current study utilized breast cancer methylation data from The Cancer Genome Atlas (TCGA), specifically the TCGA-BRCA dataset. Feature engineering techniques have been utilized to reduce data volume and make deep learning scalable. A comparative analysis of the proposed approach on Illumina 27K and 450K methylation data reveals that deep learning methodologies for cancer prediction can be coupled with feature selection models to enhance prediction accuracy. Prediction using 450K methylation markers can be accomplished in less than 13 s with an accuracy of 98.75%. Of the list of 685 genes in the feature selected 27K dataset, 578 were mapped to Ensemble Gene IDs. This reduced set was significantly (FDR < 0.05) enriched in five biological processes and one molecular function. Of the list of 1572 genes in the feature selected 450K data set, 1290 were mapped to Ensemble Gene IDs. This reduced set was significantly (FDR < 0.05) enriched in 95 biological processes and 17 molecular functions. Seven oncogene/tumor suppressor genes were common between the 27K and 450K feature selected gene sets. These genes were RTN4IP1, MYO18B, ANP32A, BRF1, SETBP1, NTRK1, and IGF2R. Our bioinformatics deep learning workflow, incorporating imputation and data balancing methods, is able to identify important methylation markers related to functionally important genes in breast cancer with high accuracy compared to deep learning or statistical models alone.

Completing Single-Cell DNA Methylome Profiles via Transfer Learning Together With KL-Divergence

The high level of sparsity in methylome profiles obtained using whole-genome bisulfite sequencing in the case of low biological material amount limits its value in the study of systems in which large samples are difficult to assemble, such as mammalian preimplantation embryonic development. The recently developed computational methods for addressing the sparsity by imputing missing have their limits when the required minimum data coverage or profiles of the same tissue in other modalities are not available. In this study, we explored the use of transfer learning together with Kullback-Leibler (KL) divergence to train predictive models for completing methylome profiles with very low coverage (below 2%). Transfer learning was used to leverage less sparse profiles that are typically available for different tissues for the same species, while KL divergence was employed to maximize the usage of information carried in the input data. A deep neural network was adopted to extract both DNA sequence and local methylation patterns for imputation. Our study of training models for completing methylome profiles of bovine oocytes and early embryos demonstrates the effectiveness of transfer learning and KL divergence, with individual increase of 29.98 and 29.43%, respectively, in prediction performance and 38.70% increase when the two were used together. The drastically increased data coverage (43.80-73.6%) after imputation powers downstream analyses involving methylomes that cannot be effectively done using the very low coverage profiles (0.06-1.47%) before imputation.

scHiCEmbed: Bin-Specific Embeddings of Single-Cell Hi-C Data Using Graph Auto-Encoders

Most publicly accessible single-cell Hi-C data are sparse and cannot reach a higher resolution. Therefore, learning latent representations (bin-specific embeddings) of sparse single-cell Hi-C matrices would provide us with a novel way of mining valuable information hidden in the limited number of single-cell Hi-C contacts. We present scHiCEmbed, an unsupervised computational method for learning bin-specific embeddings of single-cell Hi-C data, and the computational system is applied to the tasks of 3D structure reconstruction of whole genomes and detection of topologically associating domains (TAD). The only input of scHiCEmbed is a raw or scHiCluster-imputed single-cell Hi-C matrix. The main process of scHiCEmbed is to embed each node/bin in a higher dimensional space using graph auto-encoders. The learned n-by-3 bin-specific embedding/latent matrix is considered the final reconstructed 3D genome structure. For TAD detection, we use constrained hierarchical clustering on the latent matrix to classify bins: S_Dbw is used to determine the optimal number of clusters, and each cluster is considered as one potential TAD. Our reconstructed 3D structures for individual chromatins at different cell stages reveal the expanding process of chromatins during the cell cycle. We observe that the TADs called from single-cell Hi-C data are not shared across individual cells and that the TAD boundaries called from raw or imputed single-cell Hi-C are significantly different from those called from bulk Hi-C, confirming the cell-to-cell variability in terms of TAD definitions. The source code for scHiCEmbed is publicly available, and the URL can be found in the conclusion section.

Artificial Intelligence and Cardiovascular Genetics

Polygenic diseases, which are genetic disorders caused by the combined action of multiple genes, pose unique and significant challenges for the diagnosis and management of affected patients. A major goal of cardiovascular medicine has been to understand how genetic variation leads to the clinical heterogeneity seen in polygenic cardiovascular diseases (CVDs). Recent advances and emerging technologies in artificial intelligence (AI), coupled with the ever-increasing availability of next generation sequencing (NGS) technologies, now provide researchers with unprecedented possibilities for dynamic and complex biological genomic analyses. Combining these technologies may lead to a deeper understanding of heterogeneous polygenic CVDs, better prognostic guidance, and, ultimately, greater personalized medicine. Advances will likely be achieved through increasingly frequent and robust genomic characterization of patients, as well the integration of genomic data with other clinical data, such as cardiac imaging, coronary angiography, and clinical biomarkers. This review discusses the current opportunities and limitations of genomics; provides a brief overview of AI; and identifies the current applications, limitations, and future directions of AI in genomics.

A guide to machine learning for biologists

The expanding scale and inherent complexity of biological data have encouraged a growing use of machine learning in biology to build informative and predictive models of the underlying biological processes. All machine learning techniques fit models to data; however, the specific methods are quite varied and can at first glance seem bewildering. In this Review, we aim to provide readers with a gentle introduction to a few key machine learning techniques, including the most recently developed and widely used techniques involving deep neural networks. We describe how different techniques may be suited to specific types of biological data, and also discuss some best practices and points to consider when one is embarking on experiments involving machine learning. Some emerging directions in machine learning methodology are also discussed.

Novel Transformer Networks for Improved Sequence Labeling in genomics

In genomics, a wide range of machine learning methodologies have been investigated to annotate biological sequences for positions of interest such as transcription start sites, translation initiation sites, methylation sites, splice sites and promoter start sites. In recent years, this area has been dominated by convolutional neural networks, which typically outperform previously-designed methods as a result of automated scanning for influential sequence motifs. However, those architectures do not allow for the efficient processing of the full genomic sequence. As an improvement, we introduce transformer architectures for whole genome sequence labeling tasks. We show that these architectures, recently introduced for natural language processing, are better suited for processing and annotating long DNA sequences. We apply existing networks and introduce an optimized method for the calculation of attention from input nucleotides. To demonstrate this, we evaluate our architecture on several sequence labeling tasks, and find it to achieve state-of-the-art performances when comparing it to specialized models for the annotation of transcription start sites, translation initiation sites and 4mC methylation in E. coli.

Predicting environmentally responsive transgenerational differential DNA methylated regions (epimutations) in the genome using a hybrid deep-machine learning approach

BACKGROUND

Deep learning is an active bioinformatics artificial intelligence field that is useful in solving many biological problems, including predicting altered epigenetics such as DNA methylation regions. Deep learning (DL) can learn an informative representation that addresses the need for defining relevant features. However, deep learning models are computationally expensive, and they require large training datasets to achieve good classification performance.

RESULTS

One approach to addressing these challenges is to use a less complex deep learning network for feature selection and Machine Learning (ML) for classification. In the current study, we introduce a hybrid DL-ML approach that uses a deep neural network for extracting molecular features and a non-DL classifier to predict environmentally responsive transgenerational differential DNA methylated regions (DMRs), termed epimutations, based on the extracted DL-based features. Various environmental toxicant induced epigenetic transgenerational inheritance sperm epimutations were used to train the model on the rat genome DNA sequence and use the model to predict transgenerational DMRs (epimutations) across the entire genome.

CONCLUSION

The approach was also used to predict potential DMRs in the human genome. Experimental results show that the hybrid DL-ML approach outperforms deep learning and traditional machine learning methods.

AI applications in functional genomics

We review the current applications of artificial intelligence (AI) in functional genomics. The recent explosion of AI follows the remarkable achievements made possible by "deep learning", along with a burst of "big data" that can meet its hunger. Biology is about to overthrow astronomy as the paradigmatic representative of big data producer. This has been made possible by huge advancements in the field of high throughput technologies, applied to determine how the individual components of a biological system work together to accomplish different processes. The disciplines contributing to this bulk of data are collectively known as functional genomics. They consist in studies of: i) the information contained in the DNA (genomics); ii) the modifications that DNA can reversibly undergo (epigenomics); iii) the RNA transcripts originated by a genome (transcriptomics); iv) the ensemble of chemical modifications decorating different types of RNA transcripts (epitranscriptomics); v) the products of protein-coding transcripts (proteomics); and vi) the small molecules produced from cell metabolism (metabolomics) present in an organism or system at a given time, in physiological or pathological conditions. After reviewing main applications of AI in functional genomics, we discuss important accompanying issues, including ethical, legal and economic issues and the importance of explainability.

Integrated Analysis of Whole Genome and Epigenome Data Using Machine Learning Technology: Toward the Establishment of Precision Oncology

With the completion of the International Human Genome Project, we have entered what is known as the post-genome era, and efforts to apply genomic information to medicine have become more active. In particular, with the announcement of the Precision Medicine Initiative by U.S. President Barack Obama in his State of the Union address at the beginning of 2015, "precision medicine," which aims to divide patients and potential patients into subgroups with respect to disease susceptibility, has become the focus of worldwide attention. The field of oncology is also actively adopting the precision oncology approach, which is based on molecular profiling, such as genomic information, to select the appropriate treatment. However, the current precision oncology is dominated by a method called targeted-gene panel (TGP), which uses next-generation sequencing (NGS) to analyze a limited number of specific cancer-related genes and suggest optimal treatments, but this method causes the problem that the number of patients who benefit from it is limited. In order to steadily develop precision oncology, it is necessary to integrate and analyze more detailed omics data, such as whole genome data and epigenome data. On the other hand, with the advancement of analysis technologies such as NGS, the amount of data obtained by omics analysis has become enormous, and artificial intelligence (AI) technologies, mainly machine learning (ML) technologies, are being actively used to make more efficient and accurate predictions. In this review, we will focus on whole genome sequencing (WGS) analysis and epigenome analysis, introduce the latest results of omics analysis using ML technologies for the development of precision oncology, and discuss the future prospects.

The impact of flanking sequence features on DNA CpG methylation

Epigenetics and DNA methylation play a pivotal role in many processes of the cell and we often observe that an aberrant methylation pattern characterizes pathologies. In this work we investigate the role that the flanking sequences of CGs play in the methylation process in human. We built four different CG datasets: methylated, unmethylated, and two randomly extracted ones. We evaluated features associated to the flanking sequences of those CG sets, for different size around the CG, through five measures accounting for different aspects of sequence composition complexity and structure. The analysis performed through those measures revealed evident different behaviors between methylated and unmethylated probe sets. Major differences were observed for GC content and CG dinucleotide frequency in a window size of 300-400 bp and for CG self-attraction in 3K bp. It is remarkable as the effect of methylated CG lasts much more than expected far from the CG.

Application of deep learning in genomics

In recent years, deep learning has been widely used in diverse fields of research, such as speech recognition, image classification, autonomous driving and natural language processing. Deep learning has showcased dramatically improved performance in complex classification and regression problems, where the intricate structure in the high-dimensional data is difficult to discover using conventional machine learning algorithms. In biology, applications of deep learning are gaining increasing popularity in predicting the structure and function of genomic elements, such as promoters, enhancers, or gene expression levels. In this review paper, we described the basic concepts in machine learning and artificial neural network, followed by elaboration on the workflow of using convolutional neural network in genomics. Then we provided a concise introduction of deep learning applications in genomics and synthetic biology at the levels of DNA, RNA and protein. Finally, we discussed the current challenges and future perspectives of deep learning in genomics.

Identifying Regulatory Elements via Deep Learning

Deep neural networks have been revolutionizing the field of machine learning for the past several years. They have been applied with great success in many domains of the biomedical data sciences and are outperforming extant methods by a large margin. The ability of deep neural networks to pick up local image features and model the interactions between them makes them highly applicable to regulatory genomics. Instead of an image, the networks analyze DNA and RNA sequences and additional epigenomic data. In this review, we survey the successes of deep learning in the field of regulatory genomics. We first describe the fundamental building blocks of deep neural networks, popular architectures used in regulatory genomics, and their training process on molecular sequence data. We then review several key methods in different gene regulation domains. We start with the pioneering method DeepBind and its successors, which were developed to predict protein–DNA binding. We then review methods developed to predict and model epigenetic information, such as histone marks and nucleosome occupancy. Following epigenomics, we review methods to predict protein–RNA binding with its unique challenge of incorporating RNA structure information. Finally, we provide our overall view of the strengths and weaknesses of deep neural networks and prospects for future developments.

Prediction of RNA Methylation Status From Gene Expression Data Using Classification and Regression Methods

RNA N⁶-methyladenosine (m⁶A) has emerged as an important epigenetic modification for its role in regulating the stability, structure, processing, and translation of RNA. Instability of m⁶A homeostasis may result in flaws in stem cell regulation, decrease in fertility, and risk of cancer. To this day, experimental detection and quantification of RNA m⁶A modification are still time-consuming and labor-intensive. There is only a limited number of epitranscriptome samples in existing databases, and a matched RNA methylation profile is not often available for a biological problem of interests. As gene expression data are usually readily available for most biological problems, it could be appealing if we can estimate the RNA methylation status from gene expression data using in silico methods. In this study, we explored the possibility of computational prediction of RNA methylation status from gene expression data using classification and regression methods based on mouse RNA methylation data collected from 73 experimental conditions. Elastic Net-regularized Logistic Regression (ENLR), Support Vector Machine (SVM), and Random Forests (RF) were constructed for classification. Both SVM and RF achieved the best performance with the mean area under the curve (AUC) = 0.84 across samples; SVM had a narrower AUC spread. Gene Site Enrichment Analysis was conducted on those sites selected by ENLR as predictors to access the biological significance of the model. Three functional annotation terms were found statistically significant: phosphoprotein, SRC Homology 3 (SH3) domain, and endoplasmic reticulum. All 3 terms were found to be closely related to m⁶A pathway. For regression analysis, Elastic Net was implemented, which yielded a mean Pearson correlation coefficient = 0.68 and a mean Spearman correlation coefficient = 0.64. Our exploratory study suggested that gene expression data could be used to construct predictors for m⁶A methylation status with adequate accuracy. Our work showed for the first time that RNA methylation status may be predicted from the matched gene expression data. This finding may facilitate RNA modification research in various biological contexts when a matched RNA methylation profile is not available, especially in the very early stage of the study.

HiCNN: a very deep convolutional neural network to better enhance the resolution of Hi-C data

Motivation

High-resolution Hi-C data are indispensable for the studies of three-dimensional (3D) genome organization at kilobase level. However, generating high-resolution Hi-C data (e.g. 5 kb) by conducting Hi-C experiments needs millions of mammalian cells, which may eventually generate billions of paired-end reads with a high sequencing cost. Therefore, it will be important and helpful if we can enhance the resolutions of Hi-C data by computational methods.

Results

We developed a new computational method named HiCNN that used a 54-layer very deep convolutional neural network to enhance the resolutions of Hi-C data. The network contains both global and local residual learning with multiple speedup techniques included resulting in fast convergence. We used mean squared errors and Pearson’s correlation coefficients between real high-resolution and computationally predicted high-resolution Hi-C data to evaluate the method. The evaluation results show that HiCNN consistently outperforms HiCPlus, the only existing tool in the literature, when training and testing data are extracted from the same cell type (i.e. GM12878) and from two different cell types in the same or different species (i.e. GM12878 as training with K562 as testing, and GM12878 as training with CH12-LX as testing). We further found that the HiCNN-enhanced high-resolution Hi-C data are more consistent with real experimental high-resolution Hi-C data than HiCPlus-enhanced data in terms of indicating statistically significant interactions. Moreover, HiCNN can efficiently enhance low-resolution Hi-C data, which eventually helps recover two chromatin loops that were confirmed by 3D-FISH.

Availability and implementation

HiCNN is freely available at http://dna.cs.miami.edu/HiCNN/.

Supplementary information

Supplementary data are available at Bioinformatics online.

Machine learning and clinical epigenetics: a review of challenges for diagnosis and classification

BACKGROUND

Machine learning is a sub-field of artificial intelligence, which utilises large data sets to make predictions for future events. Although most algorithms used in machine learning were developed as far back as the 1950s, the advent of big data in combination with dramatically increased computing power has spurred renewed interest in this technology over the last two decades.

MAIN BODY

Within the medical field, machine learning is promising in the development of assistive clinical tools for detection of e.g. cancers and prediction of disease. Recent advances in deep learning technologies, a sub-discipline of machine learning that requires less user input but more data and processing power, has provided even greater promise in assisting physicians to achieve accurate diagnoses. Within the fields of genetics and its sub-field epigenetics, both prime examples of complex data, machine learning methods are on the rise, as the field of personalised medicine is aiming for treatment of the individual based on their genetic and epigenetic profiles.

CONCLUSION

We now have an ever-growing number of reported epigenetic alterations in disease, and this offers a chance to increase sensitivity and specificity of future diagnostics and therapies. Currently, there are limited studies using machine learning applied to epigenetics. They pertain to a wide variety of disease states and have used mostly supervised machine learning methods.

MethylNet: an automated and modular deep learning approach for DNA methylation analysis

BACKGROUND

DNA methylation (DNAm) is an epigenetic regulator of gene expression programs that can be altered by environmental exposures, aging, and in pathogenesis. Traditional analyses that associate DNAm alterations with phenotypes suffer from multiple hypothesis testing and multi-collinearity due to the high-dimensional, continuous, interacting and non-linear nature of the data. Deep learning analyses have shown much promise to study disease heterogeneity. DNAm deep learning approaches have not yet been formalized into user-friendly frameworks for execution, training, and interpreting models. Here, we describe MethylNet, a DNAm deep learning method that can construct embeddings, make predictions, generate new data, and uncover unknown heterogeneity with minimal user supervision.

RESULTS

The results of our experiments indicate that MethylNet can study cellular differences, grasp higher order information of cancer sub-types, estimate age and capture factors associated with smoking in concordance with known differences.

CONCLUSION

The ability of MethylNet to capture nonlinear interactions presents an opportunity for further study of unknown disease, cellular heterogeneity and aging processes.

A comprehensive review of computational prediction of genome-wide features

There are significant correlations among different types of genetic, genomic and epigenomic features within the genome. These correlations make the in silico feature prediction possible through statistical or machine learning models. With the accumulation of a vast amount of high-throughput data, feature prediction has gained significant interest lately, and a plethora of papers have been published in the past few years. Here we provide a comprehensive review on these published works, categorized by the prediction targets, including protein binding site, enhancer, DNA methylation, chromatin structure and gene expression. We also provide discussions on some important points and possible future directions.

Drug-Drug Interaction Predicting by Neural Network Using Integrated Similarity

Drug-Drug Interaction (DDI) prediction is one of the most critical issues in drug development and health. Proposing appropriate computational methods for predicting unknown DDI with high precision is challenging. We proposed "NDD: Neural network-based method for drug-drug interaction prediction" for predicting unknown DDIs using various information about drugs. Multiple drug similarities based on drug substructure, target, side effect, off-label side effect, pathway, transporter, and indication data are calculated. At first, NDD uses a heuristic similarity selection process and then integrates the selected similarities with a nonlinear similarity fusion method to achieve high-level features. Afterward, it uses a neural network for interaction prediction. The similarity selection and similarity integration parts of NDD have been proposed in previous studies of other problems. Our novelty is to combine these parts with new neural network architecture and apply these approaches in the context of DDI prediction. We compared NDD with six machine learning classifiers and six state-of-the-art graph-based methods on three benchmark datasets. NDD achieved superior performance in cross-validation with AUPR ranging from 0.830 to 0.947, AUC from 0.954 to 0.994 and F-measure from 0.772 to 0.902. Moreover, cumulative evidence in case studies on numerous drug pairs, further confirm the ability of NDD to predict unknown DDIs. The evaluations corroborate that NDD is an efficient method for predicting unknown DDIs. The data and implementation of NDD are available at https://github.com/nrohani/NDD.

Identification of DNA motifs that regulate DNA methylation

DNA methylation is an important epigenetic mark but how its locus-specificity is decided in relation to DNA sequence is not fully understood. Here, we have analyzed 34 diverse whole-genome bisulfite sequencing datasets in human and identified 313 motifs, including 92 and 221 associated with methylation (methylation motifs, MMs) and unmethylation (unmethylation motifs, UMs), respectively. The functionality of these motifs is supported by multiple lines of evidence. First, the methylation levels at the MM and UM motifs are respectively higher and lower than the genomic background. Second, these motifs are enriched at the binding sites of methylation modifying enzymes including DNMT3A and TET1, indicating their possible roles of recruiting these enzymes. Third, these motifs significantly overlap with "somatic QTLs" (quantitative trait loci) of methylation and expression. Fourth, disruption of these motifs by mutation is associated with significantly altered methylation level of the CpGs in the neighbor regions. Furthermore, these motifs together with somatic mutations are predictive of cancer subtypes and patient survival. We revealed some of these motifs were also associated with histone modifications, suggesting a possible interplay between the two types of epigenetic modifications. We also found some motifs form feed forward loops to contribute to DNA methylation dynamics.

Predicting protein residue-residue contacts using random forests and deep networks

BACKGROUND

The ability to predict which pairs of amino acid residues in a protein are in contact with each other offers many advantages for various areas of research that focus on proteins. For example, contact prediction can be used to reduce the computational complexity of predicting the structure of proteins and even to help identify functionally important regions of proteins. These predictions are becoming especially important given the relatively low number of experimentally determined protein structures compared to the amount of available protein sequence data.

RESULTS

Here we have developed and benchmarked a set of machine learning methods for performing residue-residue contact prediction, including random forests, direct-coupling analysis, support vector machines, and deep networks (stacked denoising autoencoders). These methods are able to predict contacting residue pairs given only the amino acid sequence of a protein. According to our own evaluations performed at a resolution of +/- two residues, the predictors we trained with the random forest algorithm were our top performing methods with average top 10 prediction accuracy scores of 85.13% (short range), 74.49% (medium range), and 54.49% (long range). Our ensemble models (stacked denoising autoencoders combined with support vector machines) were our best performing deep network predictors and achieved top 10 prediction accuracy scores of 75.51% (short range), 60.26% (medium range), and 43.85% (long range) using the same evaluation. These tests were blindly performed on targets from the CASP11 dataset; and the results suggested that our models achieved comparable performance to contact predictors developed by groups that participated in CASP11.

CONCLUSIONS

Due to the challenging nature of contact prediction, it is beneficial to develop and benchmark a variety of different prediction methods. Our work has produced useful tools with a simple interface that can provide contact predictions to users without requiring a lengthy installation process. In addition to this, we have released our C++ implementation of the direct-coupling analysis method as a standalone software package. Both this tool and our RFcon web server are freely available to the public at http://dna.cs.miami.edu/RFcon /.

Delta: a new web-based 3D genome visualization and analysis platform

Summary

Delta is an integrative visualization and analysis platform to facilitate visually annotating and exploring the 3D physical architecture of genomes. Delta takes Hi-C or ChIA-PET contact matrix as input and predicts the topologically associating domains and chromatin loops in the genome. It then generates a physical 3D model which represents the plausible consensus 3D structure of the genome. Delta features a highly interactive visualization tool which enhances the integration of genome topology/physical structure with extensive genome annotation by juxtaposing the 3D model with diverse genomic assay outputs. Finally, by visually comparing the 3D model of the β-globin gene locus and its annotation, we speculated a plausible transitory interaction pattern in the locus. Experimental evidence was found to support this speculation by literature survey. This served as an example of intuitive hypothesis testing with the help of Delta.

Availability and implementation

Delta is freely accessible from http://delta.big.ac.cn, and the source code is available at https://github.com/zhangzhwlab/delta.

Contact

zhangzhihua@big.ac.cn.

Supplementary information

Supplementary data are available at Bioinformatics online.

A primer on deep learning in genomics

Deep learning methods are a class of machine learning techniques capable of identifying highly complex patterns in large datasets. Here, we provide a perspective and primer on deep learning applications for genome analysis. We discuss successful applications in the fields of regulatory genomics, variant calling and pathogenicity scores. We include general guidance for how to effectively use deep learning methods as well as a practical guide to tools and resources. This primer is accompanied by an interactive online tutorial.

Reconstructing high-resolution chromosome three-dimensional structures by Hi-C complex networks

BACKGROUND

Hi-C data have been widely used to reconstruct chromosomal three-dimensional (3D) structures. One of the key limitations of Hi-C is the unclear relationship between spatial distance and the number of Hi-C contacts. Many methods used a fixed parameter when converting the number of Hi-C contacts to wish distances. However, a single parameter cannot properly explain the relationship between wish distances and genomic distances or the  locations of topologically associating domains (TADs).

RESULTS

We have addressed one of the key issues of using Hi-C data, that is, the unclear relationship between spatial distances and the number of Hi-C contacts, which is crucial to understand significant biological functions, such as the enhancer-promoter interactions. Specifically, we developed a new method to infer this converting parameter and pairwise Euclidean distances based on the topology of the Hi-C complex network (HiCNet). The inferred distances were modeled by clustering coefficient and multiple other types of constraints. We found that our inferred distances between bead-pairs within the same TAD were apparently smaller than those distances between bead-pairs from different TADs. Our inferred distances had a higher correlation with fluorescence in situ hybridization (FISH) data, fitted the localization patterns of Xist transcripts on DNA, and better matched 156 pairs of protein-enabled long-range chromatin interactions detected by ChIA-PET. Using the inferred distances and another round of optimization, we further reconstructed 40 kb high-resolution 3D chromosomal structures of mouse male ES cells. The high-resolution structures successfully illustrate TADs and DNA loops (peaks in Hi-C contact heatmaps) that usually indicate enhancer-promoter interactions.

CONCLUSIONS

We developed a novel method to infer the wish distances between DNA bead-pairs from Hi-C contacts. High-resolution 3D structures of chromosomes were built based on the newly-inferred wish distances. This whole process has been implemented as a tool named HiCNet, which is publicly available at http://dna.cs.miami.edu/HiCNet/ .

DIRECTION: a machine learning framework for predicting and characterizing DNA methylation and hydroxymethylation in mammalian genomes

Motivation

5-Methylcytosine and 5-Hydroxymethylcytosine in DNA are major epigenetic modifications known to significantly alter mammalian gene expression. High-throughput assays to detect these modifications are expensive, labor-intensive, unfeasible in some contexts and leave a portion of the genome unqueried. Hence, we devised a novel, supervised, integrative learning framework to perform whole-genome methylation and hydroxymethylation predictions in CpG dinucleotides. Our framework can also perform imputation of missing or low quality data in existing sequencing datasets. Additionally, we developed infrastructure to perform in silico, high-throughput hypotheses testing on such predicted methylation or hydroxymethylation maps.

Results

We test our approach on H1 human embryonic stem cells and H1-derived neural progenitor cells. Our predictive model is comparable in accuracy to other state-of-the-art DNA methylation prediction algorithms. We are the first to predict hydroxymethylation in silico with high whole-genome accuracy, paving the way for large-scale reconstruction of hydroxymethylation maps in mammalian model systems. We designed a novel, beam-search driven feature selection algorithm to identify the most discriminative predictor variables, and developed a platform for performing integrative analysis and reconstruction of the epigenome. Our toolkit DIRECTION provides predictions at single nucleotide resolution and identifies relevant features based on resource availability. This offers enhanced biological interpretability of results potentially leading to a better understanding of epigenetic gene regulation.

Availability and implementation

http://www.pradiptaray.com/direction, under CC-by-SA license.

Contacts

pradiptaray@gmail.com or mchen@utdallas.edu or michael.zhang@utdallas.edu.

Supplementary information

Supplementary data are available at Bioinformatics online.

BoostMe accurately predicts DNA methylation values in whole-genome bisulfite sequencing of multiple human tissues

Background

Bisulfite sequencing is widely employed to study the role of DNA methylation in disease; however, the data suffer from biases due to coverage depth variability. Imputation of methylation values at low-coverage sites may mitigate these biases while also identifying important genomic features associated with predictive power.

Results

Here we describe BoostMe, a method for imputing low-quality DNA methylation estimates within whole-genome bisulfite sequencing (WGBS) data. BoostMe uses a gradient boosting algorithm, XGBoost, and leverages information from multiple samples for prediction. We find that BoostMe outperforms existing algorithms in speed and accuracy when applied to WGBS of human tissues. Furthermore, we show that imputation improves concordance between WGBS and the MethylationEPIC array at low WGBS depth, suggesting improved WGBS accuracy after imputation.

Conclusions

Our findings support the use of BoostMe as a preprocessing step for WGBS analysis.

Electronic supplementary material

The online version of this article (10.1186/s12864-018-4766-y) contains supplementary material, which is available to authorized users.

A deep ensemble model to predict miRNA-disease association

Cumulative evidence from biological experiments has confirmed that microRNAs (miRNAs) are related to many types of human diseases through different biological processes. It is anticipated that precise miRNA-disease association prediction could not only help infer potential disease-related miRNA but also boost human diagnosis and disease prevention. Considering the limitations of previous computational models, a more effective computational model needs to be implemented to predict miRNA-disease associations. In this work, we first constructed a human miRNA-miRNA similarity network utilizing miRNA-miRNA functional similarity data and heterogeneous miRNA Gaussian interaction profile kernel similarities based on the assumption that similar miRNAs with similar functions tend to be associated with similar diseases, and vice versa. Then, we constructed disease-disease similarity using disease semantic information and heterogeneous disease-related interaction data. We proposed a deep ensemble model called DeepMDA that extracts high-level features from similarity information using stacked autoencoders and then predicts miRNA-disease associations by adopting a 3-layer neural network. In addition to five-fold cross-validation, we also proposed another cross-validation method to evaluate the performance of the model. The results show that the proposed model is superior to previous methods with high robustness.

Deep learning of the regulatory grammar of yeast 5' untranslated regions from 500,000 random sequences

Our ability to predict protein expression from DNA sequence alone remains poor, reflecting our limited understanding of cis-regulatory grammar and hampering the design of engineered genes for synthetic biology applications. Here, we generate a model that predicts the protein expression of the 5′ untranslated region (UTR) of mRNAs in the yeast Saccharomyces cerevisiae. We constructed a library of half a million 50-nucleotide-long random 5′ UTRs and assayed their activity in a massively parallel growth selection experiment. The resulting data allow us to quantify the impact on protein expression of Kozak sequence composition, upstream open reading frames (uORFs), and secondary structure. We trained a convolutional neural network (CNN) on the random library and showed that it performs well at predicting the protein expression of both a held-out set of the random 5′ UTRs as well as native S. cerevisiae 5′ UTRs. The model additionally was used to computationally evolve highly active 5′ UTRs. We confirmed experimentally that the great majority of the evolved sequences led to higher protein expression rates than the starting sequences, demonstrating the predictive power of this model.

Machine learning for epigenetics and future medical applications

Understanding epigenetic processes holds immense promise for medical applications. Advances in Machine Learning (ML) are critical to realize this promise. Previous studies used epigenetic data sets associated with the germline transmission of epigenetic transgenerational inheritance of disease and novel ML approaches to predict genome-wide locations of critical epimutations. A combination of Active Learning (ACL) and Imbalanced Class Learning (ICL) was used to address past problems with ML to develop a more efficient feature selection process and address the imbalance problem in all genomic data sets. The power of this novel ML approach and our ability to predict epigenetic phenomena and associated disease is suggested. The current approach requires extensive computation of features over the genome. A promising new approach is to introduce Deep Learning (DL) for the generation and simultaneous computation of novel genomic features tuned to the classification task. This approach can be used with any genomic or biological data set applied to medicine. The application of molecular epigenetic data in advanced machine learning analysis to medicine is the focus of this review.

A novel framework for the identification of drug target proteins: Combining stacked auto-encoders with a biased support vector machine

The identification of drug target proteins (IDTP) plays a critical role in biometrics. The aim of this study was to retrieve potential drug target proteins (DTPs) from a collected protein dataset, which represents an overwhelming task of great significance. Previously reported methodologies for this task generally employ protein-protein interactive networks but neglect informative biochemical attributes. We formulated a novel framework utilizing biochemical attributes to address this problem. In the framework, a biased support vector machine (BSVM) was combined with the deep embedded representation extracted using a deep learning model, stacked auto-encoders (SAEs). In cases of non-drug target proteins (NDTPs) contaminated by DTPs, the framework is beneficial due to the efficient representation of the SAE and relief of the imbalance effect by the BSVM. The experimental results demonstrated the effectiveness of our framework, and the generalization capability was confirmed via comparisons to other models. This study is the first to exploit a deep learning model for IDTP. In summary, nearly 23% of the NDTPs were predicted as likely DTPs, which are awaiting further verification based on biomedical experiments.

Genome-Wide Prediction of DNA Methylation Using DNA Composition and Sequence Complexity in Human

DNA methylation plays a significant role in transcriptional regulation by repressing activity. Change of the DNA methylation level is an important factor affecting the expression of target genes and downstream phenotypes. Because current experimental technologies can only assay a small proportion of CpG sites in the human genome, it is urgent to develop reliable computational models for predicting genome-wide DNA methylation. Here, we proposed a novel algorithm that accurately extracted sequence complexity features (seven features) and developed a support-vector-machine-based prediction model with integration of the reported DNA composition features (trinucleotide frequency and GC content, 65 features) by utilizing the methylation profiles of embryonic stem cells in human. The prediction results from 22 human chromosomes with size-varied windows showed that the 600-bp window achieved the best average accuracy of 94.7%. Moreover, comparisons with two existing methods further showed the superiority of our model, and cross-species predictions on mouse data also demonstrated that our model has certain generalization ability. Finally, a statistical test of the experimental data and the predicted data on functional regions annotated by ChromHMM found that six out of 10 regions were consistent, which implies reliable prediction of unassayed CpG sites. Accordingly, we believe that our novel model will be useful and reliable in predicting DNA methylation.

Machine learning and computer vision approaches for phenotypic profiling

Grys et al. review computer vision and machine-learning methods that have been applied to phenotypic profiling of image-based data. Descriptions are provided for segmentation, feature extraction, selection, and dimensionality reduction, as well as clustering, outlier detection, and classification of data.

With recent advances in high-throughput, automated microscopy, there has been an increased demand for effective computational strategies to analyze large-scale, image-based data. To this end, computer vision approaches have been applied to cell segmentation and feature extraction, whereas machine-learning approaches have been developed to aid in phenotypic classification and clustering of data acquired from biological images. Here, we provide an overview of the commonly used computer vision and machine-learning methods for generating and categorizing phenotypic profiles, highlighting the general biological utility of each approach.