DeepKEGG: a multi-omics data integration framework with biological insights for cancer recurrence prediction and biomarker discovery.

Deep learning-based multi-omics data integration methods have the capability to reveal the mechanisms of cancer development, discover cancer biomarkers and identify pathogenic targets. However, current methods ignore the potential correlations between samples in integrating multi-omics data. In addition, providing accurate biological explanations still poses significant challenges due to the complexity of deep learning models. Therefore, there is an urgent need for a deep learning-based multi-omics integration method to explore the potential correlations between samples and provide model interpretability. Herein, we propose a novel interpretable multi-omics data integration method (DeepKEGG) for cancer recurrence prediction and biomarker discovery. In DeepKEGG, a biological hierarchical module is designed for local connections of neuron nodes and model interpretability based on the biological relationship between genes/miRNAs and pathways. In addition, a pathway self-attention module is constructed to explore the correlation between different samples and generate the potential pathway feature representation for enhancing the prediction performance of the model. Lastly, an attribution-based feature importance calculation method is utilized to discover biomarkers related to cancer recurrence and provide a biological interpretation of the model. Experimental results demonstrate that DeepKEGG outperforms other state-of-the-art methods in 5-fold cross validation. Furthermore, case studies also indicate that DeepKEGG serves as an effective tool for biomarker discovery. The code is available at https://github.com/lanbiolab/DeepKEGG.

Deeply integrating latent consistent representations in high-noise multi-omics data for cancer subtyping.

Cancer is a complex and high-mortality disease regulated by multiple factors. Accurate cancer subtyping is crucial for formulating personalized treatment plans and improving patient survival rates. The underlying mechanisms that drive cancer progression can be comprehensively understood by analyzing multi-omics data. However, the high noise levels in omics data often pose challenges in capturing consistent representations and adequately integrating their information. This paper proposed a novel variational autoencoder-based deep learning model, named Deeply Integrating Latent Consistent Representations (DILCR). Firstly, multiple independent variational autoencoders and contrastive loss functions were designed to separate noise from omics data and capture latent consistent representations. Subsequently, an Attention Deep Integration Network was proposed to integrate consistent representations across different omics levels effectively. Additionally, we introduced the Improved Deep Embedded Clustering algorithm to make integrated variable clustering friendly. The effectiveness of DILCR was evaluated using 10 typical cancer datasets from The Cancer Genome Atlas and compared with 14 state-of-the-art integration methods. The results demonstrated that DILCR effectively captures the consistent representations in omics data and outperforms other integration methods in cancer subtyping. In the Kidney Renal Clear Cell Carcinoma case study, cancer subtypes were identified by DILCR with significant biological significance and interpretability.

Predicting RNA polymerase II transcriptional elongation pausing and associated histone code.

RNA Polymerase II (Pol II) transcriptional elongation pausing is an integral part of the dynamic regulation of gene transcription in the genome of metazoans. It plays a pivotal role in many vital biological processes and disease progression. However, experimentally measuring genome-wide Pol II pausing is technically challenging and the precise governing mechanism underlying this process is not fully understood. Here, we develop RP3 (RNA Polymerase II Pausing Prediction), a network regularized logistic regression machine learning method, to predict Pol II pausing events by integrating genome sequence, histone modification, gene expression, chromatin accessibility, and protein-protein interaction data. RP3 can accurately predict Pol II pausing in diverse cellular contexts and unveil the transcription factors that are associated with the Pol II pausing machinery. Furthermore, we utilize a forward feature selection framework to systematically identify the combination of histone modification signals associated with Pol II pausing. RP3 is freely available at https://github.com/AMSSwanglab/RP3.

Multiomics analysis identifies novel facilitators of human dopaminergic neuron differentiation.

Midbrain dopaminergic neurons (mDANs) control voluntary movement, cognition, and reward behavior under physiological conditions and are implicated in human diseases such as Parkinson's disease (PD). Many transcription factors (TFs) controlling human mDAN differentiation during development have been described, but much of the regulatory landscape remains undefined. Using a tyrosine hydroxylase (TH) human iPSC reporter line, we here generate time series transcriptomic and epigenomic profiles of purified mDANs during differentiation. Integrative analysis predicts novel regulators of mDAN differentiation and super-enhancers are used to identify key TFs. We find LBX1, NHLH1 and NR2F1/2 to promote mDAN differentiation and show that overexpression of either LBX1 or NHLH1 can also improve mDAN specification. A more detailed investigation of TF targets reveals that NHLH1 promotes the induction of neuronal miR-124, LBX1 regulates cholesterol biosynthesis, and NR2F1/2 controls neuronal activity.

Intricacies of single-cell multi-omics data integration.

A wealth of single-cell protocols makes it possible to characterize different molecular layers at unprecedented resolution. Integrating the resulting multimodal single-cell data to find cell-to-cell correspondences remains a challenge. We argue that data integration needs to happen at a meaningful biological level of abstraction and that it is necessary to consider the inherent discrepancies between modalities to strike a balance between biological discovery and noise removal. A survey of current methods reveals that a distinction between technical and biological origins of presumed unwanted variation between datasets is not yet commonly considered. The increasing availability of paired multimodal data will aid the development of improved methods by providing a ground truth on cell-to-cell matches.

Cancer subtyping with heterogeneous multi-omics data via hierarchical multi-kernel learning.

Differentiating cancer subtypes is crucial to guide personalized treatment and improve the prognosis for patients. Integrating multi-omics data can offer a comprehensive landscape of cancer biological process and provide promising ways for cancer diagnosis and treatment. Taking the heterogeneity of different omics data types into account, we propose a hierarchical multi-kernel learning (hMKL) approach, a novel cancer molecular subtyping method to identify cancer subtypes by adopting a two-stage kernel learning strategy. In stage 1, we obtain a composite kernel borrowing the cancer integration via multi-kernel learning (CIMLR) idea by optimizing the kernel parameters for individual omics data type. In stage 2, we obtain a final fused kernel through a weighted linear combination of individual kernels learned from stage 1 using an unsupervised multiple kernel learning method. Based on the final fusion kernel, k-means clustering is applied to identify cancer subtypes. Simulation studies show that hMKL outperforms the one-stage CIMLR method when there is data heterogeneity. hMKL can estimate the number of clusters correctly, which is the key challenge in subtyping. Application to two real data sets shows that hMKL identified meaningful subtypes and key cancer-associated biomarkers. The proposed method provides a novel toolkit for heterogeneous multi-omics data integration and cancer subtypes identification.

Unveiling the molecular landscape of cognitive aging: insights from polygenic risk scores, DNA methylation, and gene expression.

BACKGROUND: Aging represents a significant risk factor for the occurrence of cerebral small vessel disease, associated with white matter (WM) lesions, and to age-related cognitive alterations, though the precise mechanisms remain largely unknown. This study aimed to investigate the impact of polygenic risk scores (PRS) for WM integrity, together with age-related DNA methylation, and gene expression alterations, on cognitive aging in a cross-sectional healthy aging cohort. The PRSs were calculated using genome-wide association study (GWAS) summary statistics for magnetic resonance imaging (MRI) markers of WM integrity, including WM hyperintensities, fractional anisotropy (FA), and mean diffusivity (MD). These scores were utilized to predict age-related cognitive changes and evaluate their correlation with structural brain changes, which distinguish individuals with higher and lower cognitive scores. To reduce the dimensionality of the data and identify age-related DNA methylation and transcriptomic alterations, Sparse Partial Least Squares-Discriminant Analysis (sPLS-DA) was used. Subsequently, a canonical correlation algorithm was used to integrate the three types of omics data (PRS, DNA methylation, and gene expression data) and identify an individual "omics" signature that distinguishes subjects with varying cognitive profiles. RESULTS: We found a positive association between MD-PRS and long-term memory, as well as a correlation between MD-PRS and structural brain changes, effectively discriminating between individuals with lower and higher memory scores. Furthermore, we observed an enrichment of polygenic signals in genes related to both vascular and non-vascular factors. Age-related alterations in DNA methylation and gene expression indicated dysregulation of critical molecular features and signaling pathways involved in aging and lifespan regulation. The integration of multi-omics data underscored the involvement of synaptic dysfunction, axonal degeneration, microtubule organization, and glycosylation in the process of cognitive aging. CONCLUSIONS: These findings provide valuable insights into the biological mechanisms underlying the association between WM coherence and cognitive aging. Additionally, they highlight how age-associated DNA methylation and gene expression changes contribute to cognitive aging.

Classifying breast cancer subtypes on multi-omics data via sparse canonical correlation analysis and deep learning.

BACKGROUND: Classifying breast cancer subtypes is crucial for clinical diagnosis and treatment. However, the early symptoms of breast cancer may not be apparent. Rapid advances in high-throughput sequencing technology have led to generating large number of multi-omics biological data. Leveraging and integrating the available multi-omics data can effectively enhance the accuracy of identifying breast cancer subtypes. However, few efforts focus on identifying the associations of different omics data to predict the breast cancer subtypes. RESULTS: In this paper, we propose a differential sparse canonical correlation analysis network (DSCCN) for classifying the breast cancer subtypes. DSCCN performs differential analysis on multi-omics expression data to identify differentially expressed (DE) genes and adopts sparse canonical correlation analysis (SCCA) to mine highly correlated features between multi-omics DE-genes. Meanwhile, DSCCN uses multi-task deep learning neural network separately to train the correlated DE-genes to predict breast cancer subtypes, which spontaneously tackle the data heterogeneity problem in integrating multi-omics data. CONCLUSIONS: The experimental results show that by mining the associations among multi-omics data, DSCCN is more capable of accurately classifying breast cancer subtypes than the existing methods.

Multi-omics analysis reveals epigenetically regulated processes and patient classification in lung adenocarcinoma.

Aberrant DNA methylation is a hallmark of many cancer types. Despite our knowledge of epigenetic and transcriptomic alterations in lung adenocarcinoma (LUAD), we lack robust multi-modal molecular classifications for patient stratification. This is partly because the impact of epigenetic alterations on lung cancer development and progression is still not fully understood. To that end, we identified disease-associated processes under epigenetic regulation in LUAD. We performed a genome-wide expression-methylation Quantitative Trait Loci (emQTL) analysis by integrating DNA methylation and gene expression data from 453 patients in the TCGA cohort. Using a community detection algorithm, we identified distinct communities of CpG-gene associations with diverse biological processes. Interestingly, we identified a community linked to hormone response and lipid metabolism; the identified CpGs in this community were enriched in enhancer regions and binding regions of transcription factors such as FOXA1/2, GRHL2, HNF1B, AR, and ESR1. Furthermore, the CpGs were connected to their associated genes through chromatin interaction loops. These findings suggest that the expression of genes involved in hormone response and lipid metabolism in LUAD is epigenetically regulated through DNA methylation and enhancer-promoter interactions. By applying consensus clustering on the integrated expression-methylation pattern of the emQTL-genes and CpGs linked to hormone response and lipid metabolism, we further identified subclasses of patients with distinct prognoses. This novel patient stratification was validated in an independent patient cohort of 135 patients and showed increased prognostic significance compared to previously defined molecular subtypes.

MDICC: novel method for multi-omics data integration and cancer subtype identification.

Each type of cancer usually has several subtypes with distinct clinical implications, and therefore the discovery of cancer subtypes is an important and urgent task in disease diagnosis and therapy. Using single-omics data to predict cancer subtypes is difficult because genomes are dysregulated and complicated by multiple molecular mechanisms, and therefore linking cancer genomes to cancer phenotypes is not an easy task. Using multi-omics data to effectively predict cancer subtypes is an area of much interest; however, integrating multi-omics data is challenging. Here, we propose a novel method of multi-omics data integration for clustering to identify cancer subtypes (MDICC) that integrates new affinity matrix and network fusion methods. Our experimental results show the effectiveness and generalization of the proposed MDICC model in identifying cancer subtypes, and its performance was better than those of currently available state-of-the-art clustering methods. Furthermore, the survival analysis demonstrates that MDICC delivered comparable or even better results than many typical integrative methods.

MODILM: towards better complex diseases classification using a novel multi-omics data integration learning model.

BACKGROUND: Accurately classifying complex diseases is crucial for diagnosis and personalized treatment. Integrating multi-omics data has been demonstrated to enhance the accuracy of analyzing and classifying complex diseases. This can be attributed to the highly correlated nature of the data with various diseases, as well as the comprehensive and complementary information it provides. However, integrating multi-omics data for complex diseases is challenged by data characteristics such as high imbalance, scale variation, heterogeneity, and noise interference. These challenges further emphasize the importance of developing effective methods for multi-omics data integration. RESULTS: We proposed a novel multi-omics data learning model called MODILM, which integrates multiple omics data to improve the classification accuracy of complex diseases by obtaining more significant and complementary information from different single-omics data. Our approach includes four key steps: 1) constructing a similarity network for each omics data using the cosine similarity measure, 2) leveraging Graph Attention Networks to learn sample-specific and intra-association features from similarity networks for single-omics data, 3) using Multilayer Perceptron networks to map learned features to a new feature space, thereby strengthening and extracting high-level omics-specific features, and 4) fusing these high-level features using a View Correlation Discovery Network to learn cross-omics features in the label space, which results in unique class-level distinctiveness for complex diseases. To demonstrate the effectiveness of MODILM, we conducted experiments on six benchmark datasets consisting of miRNA expression, mRNA, and DNA methylation data. Our results show that MODILM outperforms state-of-the-art methods, effectively improving the accuracy of complex disease classification. CONCLUSIONS: Our MODILM provides a more competitive way to extract and integrate important and complementary information from multiple omics data, providing a very promising tool for supporting decision-making for clinical diagnosis.

Assisted clustering of gene expression data using regulatory data from partially overlapping sets of individuals.

BACKGROUND: As omics measurements profiled on different molecular layers are interconnected, integrative approaches that incorporate the regulatory effect from multi-level omics data are needed. When the multi-level omics data are from the same individuals, gene expression (GE) clusters can be identified using information from regulators like genetic variants and DNA methylation. When the multi-level omics data are from different individuals, the choice of integration approaches is limited. METHODS: We developed an approach to improve GE clustering from microarray data by integrating regulatory data from different but partially overlapping sets of individuals. We achieve this through (1) decomposing gene expression into the regulated component and the other component that is not regulated by measured factors, (2) optimizing the clustering goodness-of-fit objective function. We do not require the availability of different omics measurements on all individuals. A certain amount of individual overlap between GE data and the regulatory data is adequate for modeling the regulation, thus improving GE clustering. RESULTS: A simulation study shows that the performance of the proposed approach depends on the strength of the GE-regulator relationship, degree of missingness, data dimensionality, sample size, and the number of clusters. Across the various simulation settings, the proposed method shows competitive performance in terms of accuracy compared to the alternative K-means clustering method, especially when the clustering structure is due mostly to the regulated component, rather than the unregulated component. We further validate the approach with an application to 8,902 Framingham Heart Study participants with data on up to 17,873 genes and regulation information of DNA methylation and genotype from different but partially overlapping sets of participants. We identify clustering structures of genes associated with pulmonary function while incorporating the predicted regulation effect from the measured regulators. We further investigate the over-representation of these GE clusters in pathways of other diseases that may be related to lung function and respiratory health. CONCLUSION: We propose a novel approach for clustering GE with the assistance of regulatory data that allowed for different but partially overlapping sets of individuals to be included in different omics data.

TPQCI: A topology potential-based method to quantify functional influence of copy number variations.

Copy number variation (CNV) is a major type of chromosomal structural variation that play important roles in many diseases including cancers. Due to genome instability, a large number of CNV events can be detected in diseases such as cancer. Therefore, it is important to identify the functionally important CNVs in diseases, which currently still poses a challenge in genomics. One of the critical steps to solve the problem is to define the influence of CNV. In this paper, we provide a topology potential based method, TPQCI, to quantify this kind of influence by integrating statistics, gene regulatory associations, and biological function information. We used this metric to detect functionally enriched genes on genomic segments with CNV in breast cancer and multiple myeloma and discovered biological functions influenced by CNV. Our results demonstrate that, by using our proposed TPQCI metric, we can detect disease-specific genes that are influenced by CNVs. Source codes of TPQCI are provided in Github (https://github.com/usos/TPQCI).

ReactomeGSA - Efficient Multi-Omics Comparative Pathway Analysis.

Pathway analyses are key methods to analyze 'omics experiments. Nevertheless, integrating data from different 'omics technologies and different species still requires considerable bioinformatics knowledge.Here we present the novel ReactomeGSA resource for comparative pathway analyses of multi-omics datasets. ReactomeGSA can be used through Reactome's existing web interface and the novel ReactomeGSA R Bioconductor package with explicit support for scRNA-seq data. Data from different species is automatically mapped to a common pathway space. Public data from ExpressionAtlas and Single Cell ExpressionAtlas can be directly integrated in the analysis. ReactomeGSA greatly reduces the technical barrier for multi-omics, cross-species, comparative pathway analyses.We used ReactomeGSA to characterize the role of B cells in anti-tumor immunity. We compared B cell rich and poor human cancer samples from five of the Cancer Genome Atlas (TCGA) transcriptomics and two of the Clinical Proteomic Tumor Analysis Consortium (CPTAC) proteomics studies. B cell-rich lung adenocarcinoma samples lacked the otherwise present activation through NFkappaB. This may be linked to the presence of a specific subset of tumor associated IgG+ plasma cells that lack NFkappaB activation in scRNA-seq data from human melanoma. This showcases how ReactomeGSA can derive novel biomedical insights by integrating large multi-omics datasets.

IOAT: an interactive tool for statistical analysis of omics data and clinical data.

BACKGROUND: With the development of high-throughput sequencing technology, a huge amount of multi-omics data has been accumulated. Although there are many software tools for statistical analysis and visual development of omics data, these tools are not suitable for private data and non-technical users. Besides, most of these tools have specialized in only one or perhaps a few data typesare, without combining clinical information. What's more, users could not choose data processing and model selection flexibly when using these tools. RESULTS: To help non-technical users to understand and analyze private multi-omics data and ensure data security, we developed an interactive desk tool for statistical analysis and visualization of omics and clinical data (shortly IOAT). Our mainly targets csv format data, and combines clinical data with high-dimensional multi-omics data. It also contains various operations, such as data preprocessing, feature selection, risk assessment, clustering, and survival analysis. By using this tool, users can safely and conveniently try a combination of various methods on their private multi-omics data to find a model suitable for their data, conduct risk assessment and determine their cancer subtypes. At the same time, the tool can also provide them with references to genes that are closely related to tumor staging, facilitating the development of precision oncology. We review IOAT's main features and demonstrate its analysis capabilities on a lung from TCGA. CONCLUSIONS: IOAT is a local desktop tool, which provides a set of multi-omics data integration solutions. It can quickly perform a complete analysis of cancer genome data for subtype discovery and biomarker identification without security issues and writing any code. Thus, our tool can enable cancer biologists and biomedicine researchers to analyze their data more easily and safely. IOAT can be downloaded for free from https://github.com/WlSunshine/IOAT-software .

Stingray Venom Proteins: Mechanisms of Action Revealed Using a Novel Network Pharmacology Approach.

Animal venoms offer a valuable source of potent new drug leads, but their mechanisms of action are largely unknown. We therefore developed a novel network pharmacology approach based on multi-omics functional data integration to predict how stingray venom disrupts the physiological systems of target animals. We integrated 10 million transcripts from five stingray venom transcriptomes and 848,640 records from three high-content venom bioactivity datasets into a large functional data network. The network featured 216 signaling pathways, 29 of which were shared and targeted by 70 transcripts and 70 bioactivity hits. The network revealed clusters for single envenomation outcomes, such as pain, cardiotoxicity and hemorrhage. We carried out a detailed analysis of the pain cluster representing a primary envenomation symptom, revealing bibrotoxin and cholecystotoxin-like transcripts encoding pain-inducing candidate proteins in stingray venom. The cluster also suggested that such pain-inducing toxins primarily activate the inositol-3-phosphate receptor cascade, inducing intracellular calcium release. We also found strong evidence for synergistic activity among these candidates, with nerve growth factors cooperating with the most abundant translationally-controlled tumor proteins to activate pain signaling pathways. Our network pharmacology approach, here applied to stingray venom, can be used as a template for drug discovery in neglected venomous species.

A Detailed Catalogue of Multi-Omics Methodologies for Identification of Putative Biomarkers and Causal Molecular Networks in Translational Cancer Research.

Recent advances in sequencing and biotechnological methodologies have led to the generation of large volumes of molecular data of different omics layers, such as genomics, transcriptomics, proteomics and metabolomics. Integration of these data with clinical information provides new opportunities to discover how perturbations in biological processes lead to disease. Using data-driven approaches for the integration and interpretation of multi-omics data could stably identify links between structural and functional information and propose causal molecular networks with potential impact on cancer pathophysiology. This knowledge can then be used to improve disease diagnosis, prognosis, prevention, and therapy. This review will summarize and categorize the most current computational methodologies and tools for integration of distinct molecular layers in the context of translational cancer research and personalized therapy. Additionally, the bioinformatics tools Multi-Omics Factor Analysis (MOFA) and netDX will be tested using omics data from public cancer resources, to assess their overall robustness, provide reproducible workflows for gaining biological knowledge from multi-omics data, and to comprehensively understand the significantly perturbed biological entities in distinct cancer types. We show that the performed supervised and unsupervised analyses result in meaningful and novel findings.

Molecular signature of eutopic endometrium in endometriosis based on the multi-omics integrative synthesis.

PURPOSE: To synthesise data from genome-wide studies reporting molecular signature of eutopic endometrium through the phases of the menstrual cycle in endometriosis. METHODS: Extraction of data from publications reporting genetic signatures characterising endometrium associated with endometriosis. The nomenclature of extracted differentially expressed transcripts and proteins was adopted according to the HUGO Gene Nomenclature Committee (HGNC). Loci were further sorted according to the different phases of the menstrual cycle, i.e. menstrual (M), proliferative (P), secretory (S), early-secretory (ES), mid-secretory (MS), late-secretory (LS), and not specified (N/S) if the endometrial dating was not available. Enrichment analysis was performed using the DAVID bioinformatics tool. RESULTS: Altered molecular changes were reported by 21 studies, including 13 performed at the transcriptomic, 6 at proteomic, and 2 at epigenomic level. Extracted data resulted in a catalogue of total 670 genetic causes with available 591 official gene symbols, i.e. M = 3, P = 188, S = 81, ES = 82, MS = 173, LS = 36, and N/S = 28. Enriched pathways included oestrogen signalling pathway, extracellular matrix organization, and endothelial cell chemotaxis. Our study revealed that knowledge of endometrium biology in endometriosis is fragmented due to heterogeneity of published data. However, 15 genes reported as dysregulated by at least two studies within the same phase and 33 significantly enriched GO-BP terms/KEGG pathways associated with different phases of the menstrual cycle were identified. CONCLUSIONS: A multi-omics insight into molecular patterns underlying endometriosis could contribute towards identification of endometrial pathological mechanisms that impact fertility capacities of women with endometriosis.

Unveiling network-based functional features through integration of gene expression into protein networks.

Decoding health and disease phenotypes is one of the fundamental objectives in biomedicine. Whereas high-throughput omics approaches are available, it is evident that any single omics approach might not be adequate to capture the complexity of phenotypes. Therefore, integrated multi-omics approaches have been used to unravel genotype-phenotype relationships such as global regulatory mechanisms and complex metabolic networks in different eukaryotic organisms. Some of the progress and challenges associated with integrated omics studies have been reviewed previously in comprehensive studies. In this work, we highlight and review the progress, challenges and advantages associated with emerging approaches, integrating gene expression and protein-protein interaction networks to unravel network-based functional features. This includes identifying disease related genes, gene prioritization, clustering protein interactions, developing the modules, extract active subnetworks and static protein complexes or dynamic/temporal protein complexes. We also discuss how these approaches contribute to our understanding of the biology of complex traits and diseases. This article is part of a Special Issue entitled: Cardiac adaptations to obesity, diabetes and insulin resistance, edited by Professors Jan F.C. Glatz, Jason R.B. Dyck and Christine Des Rosiers.

Dimension reduction techniques for the integrative analysis of multi-omics data.

State-of-the-art next-generation sequencing, transcriptomics, proteomics and other high-throughput 'omics' technologies enable the efficient generation of large experimental data sets. These data may yield unprecedented knowledge about molecular pathways in cells and their role in disease. Dimension reduction approaches have been widely used in exploratory analysis of single omics data sets. This review will focus on dimension reduction approaches for simultaneous exploratory analyses of multiple data sets. These methods extract the linear relationships that best explain the correlated structure across data sets, the variability both within and between variables (or observations) and may highlight data issues such as batch effects or outliers. We explore dimension reduction techniques as one of the emerging approaches for data integration, and how these can be applied to increase our understanding of biological systems in normal physiological function and disease.