A fully Bayesian latent variable model for integrative clustering analysis of multi-type omics data

Integration of Multi-Omics Data for the Classification of Glioma Types and Identification of Novel Biomarkers

Glioma is currently one of the most prevalent types of primary brain cancer. Given its high level of heterogeneity along with the complex biological molecular markers, many efforts have been made to accurately classify the type of glioma in each patient, which, in turn, is critical to improve early diagnosis and increase survival. Nonetheless, as a result of the fast-growing technological advances in high-throughput sequencing and evolving molecular understanding of glioma biology, its classification has been recently subject to significant alterations. In this study, we integrate multiple glioma omics modalities (including mRNA, DNA methylation, and miRNA) from The Cancer Genome Atlas (TCGA), while using the revised glioma reclassified labels, with a supervised method based on sparse canonical correlation analysis (DIABLO) to discriminate between glioma types. We were able to find a set of highly correlated features distinguishing glioblastoma from lower-grade gliomas (LGGs) that were mainly associated with the disruption of receptor tyrosine kinases signaling pathways and extracellular matrix organization and remodeling. Concurrently, the discrimination of the LGG types was characterized primarily by features involved in ubiquitination and DNA transcription processes. Furthermore, we could identify several novel glioma biomarkers likely helpful in both diagnosis and prognosis of the patients, including the genes PPP1R8, GPBP1L1, KIAA1614, C14orf23, CCDC77, BVES, EXD3, CD300A, and HEPN1. Collectively, this comprehensive approach not only allowed a highly accurate discrimination of the different TCGA glioma patients but also presented a step forward in advancing our comprehension of the underlying molecular mechanisms driving glioma heterogeneity. Ultimately, our study also revealed novel candidate biomarkers that might constitute potential therapeutic targets, marking a significant stride toward personalized and more effective treatment strategies for patients with glioma.

A supervised Bayesian factor model for the identification of multi-omics signatures

MOTIVATION

Predictive biological signatures provide utility as biomarkers for disease diagnosis and prognosis, as well as prediction of responses to vaccination or therapy. These signatures are identified from high-throughput profiling assays through a combination of dimensionality reduction and machine learning techniques. The genes, proteins, metabolites, and other biological analytes that compose signatures also generate hypotheses on the underlying mechanisms driving biological responses, thus improving biological understanding. Dimensionality reduction is a critical step in signature discovery to address the large number of analytes in omics datasets, especially for multi-omics profiling studies with tens of thousands of measurements. Latent factor models, which can account for the structural heterogeneity across diverse assays, effectively integrate multi-omics data and reduce dimensionality to a small number of factors that capture correlations and associations among measurements. These factors provide biologically interpretable features for predictive modeling. However, multi-omics integration and predictive modeling are generally performed independently in sequential steps, leading to suboptimal factor construction. Combining these steps can yield better multi-omics signatures that are more predictive while still being biologically meaningful.

RESULTS

We developed a supervised variational Bayesian factor model that extracts multi-omics signatures from high-throughput profiling datasets that can span multiple data types. Signature-based multiPle-omics intEgration via lAtent factoRs (SPEAR) adaptively determines factor rank, emphasis on factor structure, data relevance and feature sparsity. The method improves the reconstruction of underlying factors in synthetic examples and prediction accuracy of coronavirus disease 2019 severity and breast cancer tumor subtypes.

AVAILABILITY AND IMPLEMENTATION

SPEAR is a publicly available R-package hosted at https://bitbucket.org/kleinstein/SPEAR.

A comprehensive review of machine learning techniques for multi-omics data integration: challenges and applications in precision oncology

Multi-omics data play a crucial role in precision medicine, mainly to understand the diverse biological interaction between different omics. Machine learning approaches have been extensively employed in this context over the years. This review aims to comprehensively summarize and categorize these advancements, focusing on the integration of multi-omics data, which includes genomics, transcriptomics, proteomics and metabolomics, alongside clinical data. We discuss various machine learning techniques and computational methodologies used for integrating distinct omics datasets and provide valuable insights into their application. The review emphasizes both the challenges and opportunities present in multi-omics data integration, precision medicine and patient stratification, offering practical recommendations for method selection in various scenarios. Recent advances in deep learning and network-based approaches are also explored, highlighting their potential to harmonize diverse biological information layers. Additionally, we present a roadmap for the integration of multi-omics data in precision oncology, outlining the advantages, challenges and implementation difficulties. Hence this review offers a thorough overview of current literature, providing researchers with insights into machine learning techniques for patient stratification, particularly in precision oncology. Contact:  anirban@klyuniv.ac.in.

Brain high-throughput multi-omics data reveal molecular heterogeneity in Alzheimer's disease

Unbiased data-driven omic approaches are revealing the molecular heterogeneity of Alzheimer disease. Here, we used machine learning approaches to integrate high-throughput transcriptomic, proteomic, metabolomic, and lipidomic profiles with clinical and neuropathological data from multiple human AD cohorts. We discovered 4 unique multimodal molecular profiles, one of them showing signs of poor cognitive function, a faster pace of disease progression, shorter survival with the disease, severe neurodegeneration and astrogliosis, and reduced levels of metabolomic profiles. We found this molecular profile to be present in multiple affected cortical regions associated with higher Braak tau scores and significant dysregulation of synapse-related genes, endocytosis, phagosome, and mTOR signaling pathways altered in AD early and late stages. AD cross-omics data integration with transcriptomic data from an SNCA mouse model revealed an overlapping signature. Furthermore, we leveraged single-nuclei RNA-seq data to identify distinct cell-types that most likely mediate molecular profiles. Lastly, we identified that the multimodal clusters uncovered cerebrospinal fluid biomarkers poised to monitor AD progression and possibly cognition. Our cross-omics analyses provide novel critical molecular insights into AD.

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.

Bayesian Multi-View Clustering given complex inter-view structure

Multi-view datasets are becoming increasingly prevalent. These datasets consist of different modalities that provide complementary characterizations of the same underlying system. They can include heterogeneous types of information with complex relationships, varying degrees of missingness, and assorted sample sizes, as is often the case in multi-omic biological studies. Clustering multi-view data allows us to leverage different modalities to infer underlying systematic structure, but most existing approaches are limited to contexts in which entities are the same across views or have clear one-to-one relationships across data types with a common sample size. Many methods also make strong assumptions about the similarities of clusterings across views. We propose a Bayesian multi-view clustering approach (BMVC) which can handle the realities of multi-view datasets that often have complex relationships and diverse structure. BMVC incorporates known and complex many-to-many relationships between entities via a probabilistic graphical model that enables the joint inference of clusterings specific to each view, but where each view informs the others. Additionally, BMVC estimates the strength of the relationships between each pair of views, thus moderating the degree to which it imposes dependence constraints. We benchmarked BMVC on simulated data to show that it accurately estimates varying degrees of inter-view dependence when inter-view relationships are not limited to one-to-one correspondence. Next, we demonstrated its ability to capture visually interpretable inter-view structure in a public health survey of individuals and households in Puerto Rico following Hurricane Maria. Finally, we showed that BMVC clusters integrate the complex relationships between multi-omic profiles of breast cancer patient data, improving the biological homogeneity of clusters and elucidating hypotheses for functional biological mechanisms. We found that BMVC leverages complex inter-view structure to produce higher quality clusters than those generated by standard approaches. We also showed that BMVC is a valuable tool for real-world discovery and hypothesis generation.

Incorporating graph information in Bayesian factor analysis with robust and adaptive shrinkage priors

There has been an increasing interest in decomposing high-dimensional multi-omics data into a product of low-rank and sparse matrices for the purpose of dimension reduction and feature engineering. Bayesian factor models achieve such low-dimensional representation of the original data through different sparsity-inducing priors. However, few of these models can efficiently incorporate the information encoded by the biological graphs, which has been already proven to be useful in many analysis tasks. In this work, we propose a Bayesian factor model with novel hierarchical priors, which incorporate the biological graph knowledge as a tool of identifying a group of genes functioning collaboratively. The proposed model therefore enables sparsity within networks by allowing each factor loading to be shrunk adaptively and by considering additional layers to relate individual shrinkage parameters to the underlying graph information, both of which yield a more accurate structure recovery of factor loadings. Further, this new priors overcome the phase transition phenomenon, in contrast to existing graph-incorporated approaches, so that it is robust to noisy edges that are inconsistent with the actual sparsity structure of the factor loadings. Finally, our model can handle both continuous and discrete data types. The proposed method is shown to outperform several existing factor analysis methods through simulation experiments and real data analyses.

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.

TCGAnalyzeR: An Online Pan-Cancer Tool for Integrative Visualization of Molecular and Clinical Data of Cancer Patients for Cohort and Associated Gene Discovery

For humans, the parallel processing capability of visual recognition allows for faster comprehension of complex scenes and patterns. This is essential, especially for clinicians interpreting big data for whom the visualization tools play an even more vital role in transforming raw big data into clinical decision making by managing the inherent complexity and monitoring patterns interactively in real time. The Cancer Genome Atlas (TCGA) database's size and data variety challenge the effective utilization of this valuable resource by clinicians and biologists. We re-analyzed the five molecular data types, i.e., mutation, transcriptome profile, copy number variation, miRNA, and methylation data, of ~11,000 cancer patients with all 33 cancer types and integrated the existing TCGA patient cohorts from the literature into a free and efficient web application: TCGAnalyzeR. TCGAnalyzeR provides an integrative visualization of pre-analyzed TCGA data with several novel modules: (i) simple nucleotide variations with driver prediction; (ii) recurrent copy number alterations; (iii) differential expression in tumor versus normal, with pathway and the survival analysis; (iv) TCGA clinical data including metastasis and survival analysis; (v) external subcohorts from the literature, curatedTCGAData, and BiocOncoTK R packages; (vi) internal patient clusters determined using an iClusterPlus R package or signature-based expression analysis of five molecular data types. TCGAnalyzeR integrated the multi-omics, pan-cancer TCGA with ~120 subcohorts from the literature along with clipboard panels, thus allowing users to create their own subcohorts, compare against existing external subcohorts (MSI, Immune, PAM50, Triple Negative, IDH1, miRNA, metastasis, etc.) along with our internal patient clusters, and visualize cohort-centric or gene-centric results interactively using TCGAnalyzeR.

Hydrocortisone-associated death and hospital length of stay in patients with sepsis: A retrospective cohort of large-scale clinical care data

PURPOSE

Sepsis is one of the leading causes of morbidity and mortality worldwide with approximately 50 million annual cases. There is ongoing debate on the clinical benefit of hydrocortisone in the prevention of death in septic patients. Here we evaluated the association between hydrocortisone treatment and mortality in patients diagnosed with sepsis in a large-scale clinical dataset.

METHODS

Data from patients between 2008 and 2019 were extracted from the retrospective Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Patients who received hydrocortisone after diagnosis were matched using propensity-score matching with patients who did not, to balance confounding (by indication and contraindication) factors between the groups. 90-day mortality and survivors' length of hospital stay was compared between patients who did or did not receive hydrocortisone.

RESULTS

A total of 31,749 septic patients were included in the study (mean age: 67, men: 57.3%, in-hospital mortality: 15.6%). 90-day mortality was higher among the 1802 patients receiving hydrocortisone when compared with the 6348 matched non-users (hazard ratio: 1.35, 95% CI: 1.24-1.47). Hydrocortisone treatment was also associated with increased in-hospital mortality (40.9% vs. 27.6%, p < 0.0001) and prolonged hospital stay in those who survived until discharge (median 12.6 days vs. 10.8 days, p < 0.0001). Stratification for age, gender, ethnicity, occurrence of septic shock, and the need for vasopressor drug administration such as (nor)epinephrine did not reveal sub-population(s) benefiting of hydrocortisone use.

CONCLUSION

Hydrocortisone treatment is associated with increased risk of death as well as prolonged hospital stay in septic patients. Although residual confounding (by indication) cannot be ruled out completely due to the observational nature of the study, the present study suggests clinical implication of hydrocortisone use in patients with sepsis.

Joint clustering multiple longitudinal features: A comparison of methods and software packages with practical guidance

Clustering longitudinal features is a common goal in medical studies to identify distinct disease developmental trajectories. Compared to clustering a single longitudinal feature, integrating multiple longitudinal features allows additional information to be incorporated into the clustering process, which may reveal co-existing longitudinal patterns and generate deeper biological insight. Despite its increasing importance and popularity, there is limited practical guidance for implementing cluster analysis approaches for multiple longitudinal features and evaluating their comparative performance in medical datasets. In this paper, we provide an overview of several commonly used approaches to clustering multiple longitudinal features, with an emphasis on application and implementation through R software. These methods can be broadly categorized into two categories, namely model-based (including frequentist and Bayesian) approaches and algorithm-based approaches. To evaluate their performance, we compare these approaches using real-life and simulated datasets. These results provide practical guidance to applied researchers who are interested in applying these approaches for clustering multiple longitudinal features. Recommendations for applied researchers and suggestions for future research in this area are also discussed.

Identifying subgroups of childhood obesity by using multiplatform metabotyping

Introduction: Obesity results from an interplay between genetic predisposition and environmental factors such as diet, physical activity, culture, and socioeconomic status. Personalized treatments for obesity would be optimal, thus necessitating the identification of individual characteristics to improve the effectiveness of therapies. For example, genetic impairment of the leptin-melanocortin pathway can result in rare cases of severe early-onset obesity. Metabolomics has the potential to distinguish between a healthy and obese status; however, differentiating subsets of individuals within the obesity spectrum remains challenging. Factor analysis can integrate patient features from diverse sources, allowing an accurate subclassification of individuals. Methods: This study presents a workflow to identify metabotypes, particularly when routine clinical studies fail in patient categorization. 110 children with obesity (BMI > +2 SDS) genotyped for nine genes involved in the leptin-melanocortin pathway (CPE, MC3R, MC4R, MRAP2, NCOA1, PCSK1, POMC, SH2B1, and SIM1) and two glutamate receptor genes (GRM7 and GRIK1) were studied; 55 harboring heterozygous rare sequence variants and 55 with no variants. Anthropometric and routine clinical laboratory data were collected, and serum samples processed for untargeted metabolomic analysis using GC-q-MS and CE-TOF-MS and reversed-phase U(H)PLC-QTOF-MS/MS in positive and negative ionization modes. Following signal processing and multialignment, multivariate and univariate statistical analyses were applied to evaluate the genetic trait association with metabolomics data and clinical and routine laboratory features. Results and Discussion: Neither the presence of a heterozygous rare sequence variant nor clinical/routine laboratory features determined subgroups in the metabolomics data. To identify metabolomic subtypes, we applied Factor Analysis, by constructing a composite matrix from the five analytical platforms. Six factors were discovered and three different metabotypes. Subtle but neat differences in the circulating lipids, as well as in insulin sensitivity could be established, which opens the possibility to personalize the treatment according to the patients categorization into such obesity subtypes. Metabotyping in clinical contexts poses challenges due to the influence of various uncontrolled variables on metabolic phenotypes. However, this strategy reveals the potential to identify subsets of patients with similar clinical diagnoses but different metabolic conditions. This approach underscores the broader applicability of Factor Analysis in metabotyping across diverse clinical scenarios.

A Bayesian framework for pathway-guided identification of cancer subgroups by integrating multiple types of genomic data

In recent years, comprehensive cancer genomics platforms, such as The Cancer Genome Atlas (TCGA), provide access to an enormous amount of high throughput genomic datasets for each patient, including gene expression, DNA copy number alterations, DNA methylation, and somatic mutation. While the integration of these multi-omics datasets has the potential to provide novel insights that can lead to personalized medicine, most existing approaches only focus on gene-level analysis and lack the ability to facilitate biological findings at the pathway-level. In this article, we propose Bayes-InGRiD (Bayesian Integrative Genomics Robust iDentification of cancer subgroups), a novel pathway-guided Bayesian sparse latent factor model for the simultaneous identification of cancer patient subgroups (clustering) and key molecular features (variable selection) within a unified framework, based on the joint analysis of continuous, binary, and count data. By utilizing pathway (gene set) information, Bayes-InGRiD does not only enhance the accuracy and robustness of cancer patient subgroup and key molecular feature identification, but also promotes biological understanding and interpretation. Finally, to facilitate an efficient posterior sampling, an alternative Gibbs sampler for logistic and negative binomial models is proposed using Pólya-Gamma mixtures of normal to represent latent variables for binary and count data, which yields a conditionally Gaussian representation of the posterior. The R package "INGRID" implementing the proposed approach is currently available in our research group GitHub webpage (https://dongjunchung.github.io/INGRID/).

netMUG: a novel network-guided multi-view clustering workflow for dissecting genetic and facial heterogeneity

Introduction: Multi-view data offer advantages over single-view data for characterizing individuals, which is crucial in precision medicine toward personalized prevention, diagnosis, or treatment follow-up. Methods: Here, we develop a network-guided multi-view clustering framework named netMUG to identify actionable subgroups of individuals. This pipeline first adopts sparse multiple canonical correlation analysis to select multi-view features possibly informed by extraneous data, which are then used to construct individual-specific networks (ISNs). Finally, the individual subtypes are automatically derived by hierarchical clustering on these network representations. Results: We applied netMUG to a dataset containing genomic data and facial images to obtain BMI-informed multi-view strata and showed how it could be used for a refined obesity characterization. Benchmark analysis of netMUG on synthetic data with known strata of individuals indicated its superior performance compared with both baseline and benchmark methods for multi-view clustering. The clustering derived from netMUG achieved an adjusted Rand index of 1 with respect to the synthesized true labels. In addition, the real-data analysis revealed subgroups strongly linked to BMI and genetic and facial determinants of these subgroups. Discussion: netMUG provides a powerful strategy, exploiting individual-specific networks to identify meaningful and actionable strata. Moreover, the implementation is easy to generalize to accommodate heterogeneous data sources or highlight data structures.

Identification of a brand intratumor microbiome signature for predicting prognosis of hepatocellular carcinoma

PURPOSE

Given that prognosis of hepatocellular carcinoma (HCC) differs dramatically, it is imperative to uncover effective and available prognostic biomarker(s). The intratumor microbiome plays a significant role in the response to tumor microenvironment, we aimed to identify an intratumor microbiome signature for predicting the prognosis of HCC patients accurately and investigate its possible mechanisms subsequently.

METHODS

The TCGA HCC microbiome data (TCGA-LIHC-microbiome) was downloaded from cBioPortal. To create an intratumor microbiome-related prognostic signature, univariate and multivariate Cox regression analyses were used to quantify the association of microbial abundance and patients' overall survival (OS), as well as their diseases specific survival (DSS). The performance of the scoring model was evaluated by the area under the ROC curve (AUC). Based on the microbiome-related signature, clinical factors, and multi-omics molecular subtypes on the basis of "icluster" algorithm, nomograms were established to predict OS and DSS. Patients were further clustered into three subtypes based on their microbiome-related characteristics by consensus clustering. Moreover, deconvolution algorithm, weighted correlation network analysis (WGCNA) and gene set variation analysis (GSVA) were used to investigate the potential mechanisms.

RESULTS

In TCGA LIHC microbiome data, the abundances of 166 genera among the total 1406 genera were considerably associated with HCC patients' OS. From that filtered dataset we identified a 27-microbe prognostic signature and developed a microbiome-related score (MRS) model. Compared with those in the relatively low-risk group, patients in higher-risk group own a much worse OS (P < 0.0001). Besides, the time-dependent ROC curves with MRS showed excellent predictive efficacy both in OS and DSS. Moreover, MRS is an independent prognostic factor for OS and DSS over clinical factors and multi-omics-based molecular subtypes. The integration of MRS into nomograms significantly improved the efficacy of prognosis prediction (1-year AUC:0.849, 3-year AUC: 0.825, 5-year AUC: 0.822). The analysis of microbiome-based subtypes on their immune characteristics and specific gene modules inferred that the intratumor microbiome may affect the HCC patients' prognosis via modulating the cancer stemness and immune response.

CONCLUSION

MRS, a 27 intratumor microbiome-related prognostic model, was successfully established to predict HCC patients overall survive independently. And the possible underlying mechanisms were also investigated to provide a potential intervention strategy.

An Integrated Multi-Omics and Artificial Intelligence Framework for Advance Plant Phenotyping in Horticulture

This review discusses the transformative potential of integrating multi-omics data and artificial intelligence (AI) in advancing horticultural research, specifically plant phenotyping. The traditional methods of plant phenotyping, while valuable, are limited in their ability to capture the complexity of plant biology. The advent of (meta-)genomics, (meta-)transcriptomics, proteomics, and metabolomics has provided an opportunity for a more comprehensive analysis. AI and machine learning (ML) techniques can effectively handle the complexity and volume of multi-omics data, providing meaningful interpretations and predictions. Reflecting the multidisciplinary nature of this area of research, in this review, readers will find a collection of state-of-the-art solutions that are key to the integration of multi-omics data and AI for phenotyping experiments in horticulture, including experimental design considerations with several technical and non-technical challenges, which are discussed along with potential solutions. The future prospects of this integration include precision horticulture, predictive breeding, improved disease and stress response management, sustainable crop management, and exploration of plant biodiversity. The integration of multi-omics and AI holds immense promise for revolutionizing horticultural research and applications, heralding a new era in plant phenotyping.

Deep multi-view contrastive learning for cancer subtype identification

Cancer heterogeneity has posed great challenges in exploring precise therapeutic strategies for cancer treatment. The identification of cancer subtypes aims to detect patients with distinct molecular profiles and thus could provide new clues on effective clinical therapies. While great efforts have been made, it remains challenging to develop powerful computational methods that can efficiently integrate multi-omics datasets for the task. In this paper, we propose a novel self-supervised learning model called Deep Multi-view Contrastive Learning (DMCL) for cancer subtype identification. Specifically, by incorporating the reconstruction loss, contrastive loss and clustering loss into a unified framework, our model simultaneously encodes the sample discriminative information into the extracted feature representations and well preserves the sample cluster structures in the embedded space. Moreover, DMCL is an end-to-end framework where the cancer subtypes could be directly obtained from the model outputs. We compare DMCL with eight alternatives ranging from classic cancer subtype identification methods to recently developed state-of-the-art systems on 10 widely used cancer multi-omics datasets as well as an integrated dataset, and the experimental results validate the superior performance of our method. We further conduct a case study on liver cancer and the analysis results indicate that different subtypes might have different responses to the selected chemotherapeutic drugs.

Machine learning for image-based multi-omics analysis of leaf veins

Veins are a critical component of the plant growth and development system, playing an integral role in supporting and protecting leaves, as well as transporting water, nutrients, and photosynthetic products. A comprehensive understanding of the form and function of veins requires a dual approach that combines plant physiology with cutting-edge image recognition technology. The latest advancements in computer vision and machine learning have facilitated the creation of algorithms that can identify vein networks and explore their developmental progression. Here, we review the functional, environmental, and genetic factors associated with vein networks, along with the current status of research on image analysis. In addition, we discuss the methods of venous phenotype extraction and multi-omics association analysis using machine learning technology, which could provide a theoretical basis for improving crop productivity by optimizing the vein network architecture.

Multi-omics data integration using ratio-based quantitative profiling with Quartet reference materials

Characterization and integration of the genome, epigenome, transcriptome, proteome and metabolome of different datasets is difficult owing to a lack of ground truth. Here we develop and characterize suites of publicly available multi-omics reference materials of matched DNA, RNA, protein and metabolites derived from immortalized cell lines from a family quartet of parents and monozygotic twin daughters. These references provide built-in truth defined by relationships among the family members and the information flow from DNA to RNA to protein. We demonstrate how using a ratio-based profiling approach that scales the absolute feature values of a study sample relative to those of a concurrently measured common reference sample produces reproducible and comparable data suitable for integration across batches, labs, platforms and omics types. Our study identifies reference-free 'absolute' feature quantification as the root cause of irreproducibility in multi-omics measurement and data integration and establishes the advantages of ratio-based multi-omics profiling with common reference materials.

Correcting batch effects in large-scale multiomics studies using a reference-material-based ratio method

BACKGROUND

Batch effects are notoriously common technical variations in multiomics data and may result in misleading outcomes if uncorrected or over-corrected. A plethora of batch-effect correction algorithms are proposed to facilitate data integration. However, their respective advantages and limitations are not adequately assessed in terms of omics types, the performance metrics, and the application scenarios.

RESULTS

As part of the Quartet Project for quality control and data integration of multiomics profiling, we comprehensively assess the performance of seven batch effect correction algorithms based on different performance metrics of clinical relevance, i.e., the accuracy of identifying differentially expressed features, the robustness of predictive models, and the ability of accurately clustering cross-batch samples into their own donors. The ratio-based method, i.e., by scaling absolute feature values of study samples relative to those of concurrently profiled reference material(s), is found to be much more effective and broadly applicable than others, especially when batch effects are completely confounded with biological factors of study interests. We further provide practical guidelines for implementing the ratio based approach in increasingly large-scale multiomics studies.

CONCLUSIONS

Multiomics measurements are prone to batch effects, which can be effectively corrected using ratio-based scaling of the multiomics data. Our study lays the foundation for eliminating batch effects at a ratio scale.

Predictive overfitting in immunological applications: Pitfalls and solutions

Overfitting describes the phenomenon where a highly predictive model on the training data generalizes poorly to future observations. It is a common concern when applying machine learning techniques to contemporary medical applications, such as predicting vaccination response and disease status in infectious disease or cancer studies. This review examines the causes of overfitting and offers strategies to counteract it, focusing on model complexity reduction, reliable model evaluation, and harnessing data diversity. Through discussion of the underlying mathematical models and illustrative examples using both synthetic data and published real datasets, our objective is to equip analysts and bioinformaticians with the knowledge and tools necessary to detect and mitigate overfitting in their research.

Comparison of cancer subtype identification methods combined with feature selection methods in omics data analysis

BACKGROUND

Cancer subtype identification is important for the early diagnosis of cancer and the provision of adequate treatment. Prior to identifying the subtype of cancer in a patient, feature selection is also crucial for reducing the dimensionality of the data by detecting genes that contain important information about the cancer subtype. Numerous cancer subtyping methods have been developed, and their performance has been compared. However, combinations of feature selection and subtype identification methods have rarely been considered. This study aimed to identify the best combination of variable selection and subtype identification methods in single omics data analysis.

RESULTS

Combinations of six filter-based methods and six unsupervised subtype identification methods were investigated using The Cancer Genome Atlas (TCGA) datasets for four cancers. The number of features selected varied, and several evaluation metrics were used. Although no single combination was found to have a distinctively good performance, Consensus Clustering (CC) and Neighborhood-Based Multi-omics Clustering (NEMO) used with variance-based feature selection had a tendency to show lower p-values, and nonnegative matrix factorization (NMF) stably showed good performance in many cases unless the Dip test was used for feature selection. In terms of accuracy, the combination of NMF and similarity network fusion (SNF) with Monte Carlo Feature Selection (MCFS) and Minimum-Redundancy Maximum Relevance (mRMR) showed good overall performance. NMF always showed among the worst performances without feature selection in all datasets, but performed much better when used with various feature selection methods. iClusterBayes (ICB) had decent performance when used without feature selection.

CONCLUSIONS

Rather than a single method clearly emerging as optimal, the best methodology was different depending on the data used, the number of features selected, and the evaluation method. A guideline for choosing the best combination method under various situations is provided.

MOBILE pipeline enables identification of context-specific networks and regulatory mechanisms

Robust identification of context-specific network features that control cellular phenotypes remains a challenge. We here introduce MOBILE (Multi-Omics Binary Integration via Lasso Ensembles) to nominate molecular features associated with cellular phenotypes and pathways. First, we use MOBILE to nominate mechanisms of interferon-γ (IFNγ) regulated PD-L1 expression. Our analyses suggest that IFNγ-controlled PD-L1 expression involves BST2, CLIC2, FAM83D, ACSL5, and HIST2H2AA3 genes, which were supported by prior literature. We also compare networks activated by related family members transforming growth factor-beta 1 (TGFβ1) and bone morphogenetic protein 2 (BMP2) and find that differences in ligand-induced changes in cell size and clustering properties are related to differences in laminin/collagen pathway activity. Finally, we demonstrate the broad applicability and adaptability of MOBILE by analyzing publicly available molecular datasets to investigate breast cancer subtype specific networks. Given the ever-growing availability of multi-omics datasets, we envision that MOBILE will be broadly useful for identification of context-specific molecular features and pathways.

Alterations in the Epigenetic Machinery Associated with Prostate Cancer Health Disparities

Prostate cancer is driven by acquired genetic alterations, including those impacting the epigenetic machinery. With African ancestry as a significant risk factor for aggressive disease, we hypothesize that dysregulation among the roughly 656 epigenetic genes may contribute to prostate cancer health disparities. Investigating prostate tumor genomic data from 109 men of southern African and 56 men of European Australian ancestry, we found that African-derived tumors present with a longer tail of epigenetic driver gene candidates (72 versus 10). Biased towards African-specific drivers (63 versus 9 shared), many are novel to prostate cancer (18/63), including several putative therapeutic targets (CHD7, DPF3, POLR1B, SETD1B, UBTF, and VPS72). Through clustering of all variant types and copy number alterations, we describe two epigenetic PCa taxonomies capable of differentiating patients by ancestry and predicted clinical outcomes. We identified the top genes in African- and European-derived tumors representing a multifunctional "generic machinery", the alteration of which may be instrumental in epigenetic dysregulation and prostate tumorigenesis. In conclusion, numerous somatic alterations in the epigenetic machinery drive prostate carcinogenesis, but African-derived tumors appear to achieve this state with greater diversity among such alterations. The greater novelty observed in African-derived tumors illustrates the significant clinical benefit to be derived from a much needed African-tailored approach to prostate cancer healthcare aimed at reducing prostate cancer health disparities.

Deep multi-omics integration by learning correlation-maximizing representation identifies prognostically stratified cancer subtypes

Motivation

Molecular subtyping by integrative modeling of multi-omics and clinical data can help the identification of robust and clinically actionable disease subgroups; an essential step in developing precision medicine approaches.

Results

We developed a novel outcome-guided molecular subgrouping framework, called Deep Multi-Omics Integrative Subtyping by Maximizing Correlation (DeepMOIS-MC), for integrative learning from multi-omics data by maximizing correlation between all input -omics views. DeepMOIS-MC consists of two parts: clustering and classification. In the clustering part, the preprocessed high-dimensional multi-omics views are input into two-layer fully connected neural networks. The outputs of individual networks are subjected to Generalized Canonical Correlation Analysis loss to learn the shared representation. Next, the learned representation is filtered by a regression model to select features that are related to a covariate clinical variable, for example, a survival/outcome. The filtered features are used for clustering to determine the optimal cluster assignments. In the classification stage, the original feature matrix of one of the -omics view is scaled and discretized based on equal frequency binning, and then subjected to feature selection using RandomForest. Using these selected features, classification models (for example, XGBoost model) are built to predict the molecular subgroups that were identified at clustering stage. We applied DeepMOIS-MC on lung and liver cancers, using TCGA datasets. In comparative analysis, we found that DeepMOIS-MC outperformed traditional approaches in patient stratification. Finally, we validated the robustness and generalizability of the classification models on independent datasets. We anticipate that the DeepMOIS-MC can be adopted to many multi-omics integrative analyses tasks.

Availability and implementation

Source codes for PyTorch implementation of DGCCA and other DeepMOIS-MC modules are available at GitHub (https://github.com/duttaprat/DeepMOIS-MC).

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

Learning vector quantized representation for cancer subtypes identification

BACKGROUND AND OBJECTIVE

Defining and separating cancer subtypes is essential for facilitating personalized therapy modality and prognosis of patients. The definition of subtypes has been constantly recalibrated as a result of our deepened understanding. During this recalibration, researchers often rely on clustering of cancer data to provide an intuitive visual reference that could reveal the intrinsic characteristics of subtypes. The data being clustered are often omics data such as transcriptomics that have strong correlations to the underlying biological mechanism. However, while existing studies have shown promising results, they suffer from issues associated with omics data: sample scarcity and high dimensionality while they impose unrealistic assumptions to extract useful features from the data while avoiding overfitting to spurious correlations.

METHODS

This paper proposes to leverage a recent strong generative model, Vector-Quantized Variational AutoEncoder, to tackle the data issues and extract discrete representations that are crucial to the quality of subsequent clustering by retaining only information relevant to reconstructing the input.

RESULTS

Extensive experiments and medical analysis on multiple datasets comprising 10 distinct cancers demonstrate the proposed clustering results can significantly and robustly improve prognosis over prevalent subtyping systems.

CONCLUSION

Our proposal does not impose strict assumptions on data distribution; while, its latent features are better representations of the transcriptomic data in different cancer subtypes, capable of yielding superior clustering performance with any mainstream clustering method.

Integrative multi-omics analysis reveals novel idiopathic pulmonary fibrosis endotypes associated with disease progression

BACKGROUND

Idiopathic pulmonary fibrosis (IPF) is characterized by the accumulation of extracellular matrix in the pulmonary interstitium and progressive functional decline. We hypothesized that integration of multi-omics data would identify clinically meaningful molecular endotypes of IPF.

METHODS

The IPF-PRO Registry is a prospective registry of patients with IPF. Proteomic and transcriptomic (including total RNA [toRNA] and microRNA [miRNA]) analyses were performed using blood collected at enrollment. Molecular data were integrated using Similarity Network Fusion, followed by unsupervised spectral clustering to identify molecular subtypes. Cox proportional hazards models tested the relationship between these subtypes and progression-free and transplant-free survival. The molecular subtypes were compared to risk groups based on a previously described 52-gene (toRNA expression) signature. Biological characteristics of the molecular subtypes were evaluated via linear regression differential expression and canonical pathways (Ingenuity Pathway Analysis [IPA]) over-representation analyses.

RESULTS

Among 232 subjects, two molecular subtypes were identified. Subtype 1 (n = 105, 45.3%) and Subtype 2 (n = 127, 54.7%) had similar distributions of age (70.1 +/- 8.1 vs. 69.3 +/- 7.6 years; p = 0.31) and sex (79.1% vs. 70.1% males, p = 0.16). Subtype 1 had more severe disease based on composite physiologic index (CPI) (55.8 vs. 51.2; p = 0.002). After adjusting for CPI and antifibrotic treatment at enrollment, subtype 1 experienced shorter progression-free survival (HR 1.79, 95% CI 1.28,2.56; p = 0.0008) and similar transplant-free survival (HR 1.30, 95% CI 0.87,1.96; p = 0.20) as subtype 2. There was little agreement in the distribution of subjects to the molecular subtypes and the risk groups based on 52-gene signature (kappa = 0.04, 95% CI= -0.08, 0.17), and the 52-gene signature risk groups were associated with differences in transplant-free but not progression-free survival. Based on heatmaps and differential expression analyses, proteins and miRNAs (but not toRNA) contributed to classification of subjects to the molecular subtypes. The IPA showed enrichment in pulmonary fibrosis-relevant pathways, including mTOR, VEGF, PDGF, and B-cell receptor signaling.

CONCLUSIONS

Integration of transcriptomic and proteomic data from blood enabled identification of clinically meaningful molecular endotypes of IPF. If validated, these endotypes could facilitate identification of individuals likely to experience disease progression and enrichment of clinical trials.

TRIAL REGISTRATION

NCT01915511.

Consensus clustering methodology to improve molecular stratification of non-small cell lung cancer

Recent advances in machine learning research, combined with the reduced sequencing costs enabled by modern next-generation sequencing, paved the way to the implementation of precision medicine through routine multi-omics molecular profiling of tumours. Thus, there is an emerging need of reliable models exploiting such data to retrieve clinically useful information. Here, we introduce an original consensus clustering approach, overcoming the intrinsic instability of common clustering methods based on molecular data. This approach is applied to the case of non-small cell lung cancer (NSCLC), integrating data of an ongoing clinical study (PROMOLE) with those made available by The Cancer Genome Atlas, to define a molecular-based stratification of the patients beyond, but still preserving, histological subtyping. The resulting subgroups are biologically characterized by well-defined mutational and gene-expression profiles and are significantly related to disease-free survival (DFS). Interestingly, it was observed that (1) cluster B, characterized by a short DFS, is enriched in KEAP1 and SKP2 mutations, that makes it an ideal candidate for further studies with inhibitors, and (2) over- and under-representation of inflammation and immune systems pathways in squamous-cell carcinomas subgroups could be potentially exploited to stratify patients treated with immunotherapy.

Multivariate functional mixed model with MRI data: An application to Alzheimer's disease

Alzheimer's Disease (AD) is the leading cause of dementia and impairment in various domains. Recent AD studies, (ie, Alzheimer's Disease Neuroimaging Initiative (ADNI) study), collect multimodal data, including longitudinal neurological assessments and magnetic resonance imaging (MRI) data, to better study the disease progression. Adopting early interventions is essential to slow AD progression for subjects with mild cognitive impairment (MCI). It is of particular interest to develop an AD predictive model that leverages multimodal data and provides accurate personalized predictions. In this article, we propose a multivariate functional mixed model with MRI data (MFMM-MRI) that simultaneously models longitudinal neurological assessments, baseline MRI data, and the survival outcome (ie, dementia onset) for subjects with MCI at baseline. Two functional forms (the random-effects model and instantaneous model) linking the longitudinal and survival process are investigated. We use Markov Chain Monte Carlo (MCMC) method based on No-U-Turn Sampling (NUTS) algorithm to obtain posterior samples. We develop a dynamic prediction framework that provides accurate personalized predictions of longitudinal trajectories and survival probability. We apply MFMM-MRI to the ADNI study and identify significant associations among longitudinal outcomes, MRI data, and the risk of dementia onset. The instantaneous model with voxels from the whole brain has the best prediction performance among all candidate models. The simulation study supports the validity of the estimation and dynamic prediction method.

netMUG: a novel network-guided multi-view clustering workflow for dissecting genetic and facial heterogeneity

Multi-view data offer advantages over single-view data for characterizing individuals, which is crucial in precision medicine toward personalized prevention, diagnosis, or treatment follow-up. Here, we develop a network-guided multi-view clustering framework named netMUG to identify actionable subgroups of individuals. This pipeline first adopts sparse multiple canonical correlation analysis to select multi-view features possibly informed by extraneous data, which are then used to construct individual-specific networks (ISNs). Finally, the individual subtypes are automatically derived by hierarchical clustering on these network representations. We applied netMUG to a dataset containing genomic data and facial images to obtain BMI-informed multi-view strata and showed how it could be used for a refined obesity characterization. Benchmark analysis of netMUG on synthetic data with known strata of individuals indicated its superior performance compared with both baseline and benchmark methods for multi-view clustering. In addition, the real-data analysis revealed subgroups strongly linked to BMI and genetic and facial determinants of these classes. NetMUG provides a powerful strategy, exploiting individual-specific networks to identify meaningful and actionable strata. Moreover, the implementation is easy to generalize to accommodate heterogeneous data sources or highlight data structures.

Subtype-DCC: decoupled contrastive clustering method for cancer subtype identification based on multi-omics data

Due to the high heterogeneity and complexity of cancers, patients with different cancer subtypes often have distinct groups of genomic and clinical characteristics. Therefore, the discovery and identification of cancer subtypes are crucial to cancer diagnosis, prognosis and treatment. Recent technological advances have accelerated the increasing availability of multi-omics data for cancer subtyping. To take advantage of the complementary information from multi-omics data, it is necessary to develop computational models that can represent and integrate different layers of data into a single framework. Here, we propose a decoupled contrastive clustering method (Subtype-DCC) based on multi-omics data integration for clustering to identify cancer subtypes. The idea of contrastive learning is introduced into deep clustering based on deep neural networks to learn clustering-friendly representations. Experimental results demonstrate the superior performance of the proposed Subtype-DCC model in identifying cancer subtypes over the currently available state-of-the-art clustering methods. The strength of Subtype-DCC is also supported by the survival and clinical analysis.

Molecular and clinical diversity in primary central nervous system lymphoma

BACKGROUND

Primary central nervous system lymphoma (PCNSL) is a rare and distinct entity within diffuse large B-cell lymphoma presenting with variable response rates probably to underlying molecular heterogeneity.

PATIENTS AND METHODS

To identify and characterize PCNSL heterogeneity and facilitate clinical translation, we carried out a comprehensive multi-omic analysis [whole-exome sequencing, RNA sequencing (RNA-seq), methylation sequencing, and clinical features] in a discovery cohort of 147 fresh-frozen (FF) immunocompetent PCNSLs and a validation cohort of formalin-fixed, paraffin-embedded (FFPE) 93 PCNSLs with RNA-seq and clinico-radiological data.

RESULTS

Consensus clustering of multi-omic data uncovered concordant classification of four robust, non-overlapping, prognostically significant clusters (CS). The CS1 and CS2 groups presented an immune-cold hypermethylated profile but a distinct clinical behavior. The 'immune-hot' CS4 group, enriched with mutations increasing the Janus kinase (JAK)-signal transducer and activator of transcription (STAT) and nuclear factor-κB activity, had the most favorable clinical outcome, while the heterogeneous-immune CS3 group had the worse prognosis probably due to its association with meningeal infiltration and enriched HIST1H1E mutations. CS1 was characterized by high Polycomb repressive complex 2 activity and CDKN2A/B loss leading to higher proliferation activity. Integrated analysis on proposed targets suggests potential use of immune checkpoint inhibitors/JAK1 inhibitors for CS4, cyclin D-Cdk4,6 plus phosphoinositide 3-kinase (PI3K) inhibitors for CS1, lenalidomide/demethylating drugs for CS2, and enhancer of zeste 2 polycomb repressive complex 2 subunit (EZH2) inhibitors for CS3. We developed an algorithm to identify the PCNSL subtypes using RNA-seq data from either FFPE or FF tissue.

CONCLUSIONS

The integration of genome-wide data from multi-omic data revealed four molecular patterns in PCNSL with a distinctive prognostic impact that provides a basis for future clinical stratification and subtype-based targeted interventions.

Multi-omics data integration methods and their applications in psychiatric disorders

To study mental illness and health, in the past researchers have often broken down their complexity into individual subsystems (e.g., genomics, transcriptomics, proteomics, clinical data) and explored the components independently. Technological advancements and decreasing costs of high throughput sequencing has led to an unprecedented increase in data generation. Furthermore, over the years it has become increasingly clear that these subsystems do not act in isolation but instead interact with each other to drive mental illness and health. Consequently, individual subsystems are now analysed jointly to promote a holistic understanding of the underlying biological complexity of health and disease. Complementing the increasing data availability, current research is geared towards developing novel methods that can efficiently combine the information rich multi-omics data to discover biologically meaningful biomarkers for diagnosis, treatment, and prognosis. However, clinical translation of the research is still challenging. In this review, we summarise conventional and state-of-the-art statistical and machine learning approaches for discovery of biomarker, diagnosis, as well as outcome and treatment response prediction through integrating multi-omics and clinical data. In addition, we describe the role of biological model systems and in silico multi-omics model designs in clinical translation of psychiatric research from bench to bedside. Finally, we discuss the current challenges and explore the application of multi-omics integration in future psychiatric research. The review provides a structured overview and latest updates in the field of multi-omics in psychiatry.

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.

Multi-view spectral clustering with latent representation learning for applications on multi-omics cancer subtyping

Driven by multi-omics data, some multi-view clustering algorithms have been successfully applied to cancer subtypes prediction, aiming to identify subtypes with biometric differences in the same cancer, thereby improving the clinical prognosis of patients and designing personalized treatment plan. Due to the fact that the number of patients in omics data is much smaller than the number of genes, multi-view spectral clustering based on similarity learning has been widely developed. However, these algorithms still suffer some problems, such as over-reliance on the quality of pre-defined similarity matrices for clustering results, inability to reasonably handle noise and redundant information in high-dimensional omics data, ignoring complementary information between omics data, etc. This paper proposes multi-view spectral clustering with latent representation learning (MSCLRL) method to alleviate the above problems. First, MSCLRL generates a corresponding low-dimensional latent representation for each omics data, which can effectively retain the unique information of each omics and improve the robustness and accuracy of the similarity matrix. Second, the obtained latent representations are assigned appropriate weights by MSCLRL, and global similarity learning is performed to generate an integrated similarity matrix. Third, the integrated similarity matrix is used to feed back and update the low-dimensional representation of each omics. Finally, the final integrated similarity matrix is used for clustering. In 10 benchmark multi-omics datasets and 2 separate cancer case studies, the experiments confirmed that the proposed method obtained statistically and biologically meaningful cancer subtypes.

Statistical Methods for Integrative Clustering of Multi-omics Data

Cancers are heterogeneous diseases caused by accumulated mutations or abnormal alterations at multi-levels of biological processes including genomics, epigenomics, transcriptomics, and proteomics. There is a great clinical interest in identifying cancer molecular subtypes for disease prognosis and personalized medicine. Integrative clustering is a powerful unsupervised learning method that has been increasingly used to identify cancer molecular subtypes using multi-omics data including somatic mutations, DNA copy numbers, DNA methylation, and gene expression. Integrative clustering methods are generally classified into model-based or nonparametric approaches. In this chapter, we will give an overview of the frequently used model-based methods, including iCluster, iClusterPlus, and iClusterBayes, and the nonparametric method, integrative nonnegative matrix factorization (intNMF). We will use the integrative analyses of uveal melanoma and lower-grade glioma to illustrate these representative methods. Finally, we will discuss the strengths and limitations of these representative methods and give suggestions for performing integrative analyses of cancer multi-omics data in practice.

Multi-omics Data Deconvolution and Integration: New Methods, Insights, and Translational Implications

In the current era of multi-omics, new sequencing and molecular profiling technologies have facilitated our quest for a deeper and broader understanding of the variations and dynamic regulations in human genomes. However, analyzing and integrating data generated from diverse platforms, modalities, and large-scale heterogeneous samples to extract functional and clinically valuable information remains a significant challenge. Here, we first discuss recent advances in methods and algorithms for analyzing data at the genome, transcriptome, proteome, metabolome, and microbiome levels, followed by emerging methods for leveraging single-cell sequencing and spatial transcriptomic data. We also highlight the mechanistic insights that these advances can bring to the field, as well as the current challenges and outlooks relating to their translational and reproducible adoption at the population level. It is evident that novel statistical methods, which were inspired by new assays, will enable the associated molecular profiling pipelines and experimental designs to continuously improve our understanding of the human genome and the downstream consequences in the transcriptome, epigenome, proteome, metabolome, regulome, and microbiome.

Multiview Robust Graph-Based Clustering for Cancer Subtype Identification

Cancer subtype identification is to classify cancer into groups according to their molecular characteristics and clinical manifestations and is the basis for more personalized diagnosis and therapy. Public datasets such as The Cancer Genome Atlas (TCGA) have collected a massive number of multi-omics data. The accumulation of these datasets provides unprecedented opportunities to study the mechanism of cancers and further identify cancer subtypes at a comprehensive level. In this paper, we propose a multi-view robust graph-based clustering (MRGC) method to effectively identify cancer subtypes. Our method first learns robust latent representations from the raw omics data to alleviate the influences of the noise, where a set of similarity matrices are then adaptively learned based on these new representations. Finally, a global similarity graph is obtained by exploiting the consensus structure from the graphs. As a result, the three parts in our method can reinforce each other in a mutual iterative manner. We conduct extensive experiments on both generic machine learning datasets and cancer datasets. The experimental results confirm that our model can achieve satisfactory clustering performance compared to several state-of-the-art approaches. Moreover, we convey the practicability of MRGC by carrying out a case study on hepatocellular carcinoma.

A molecular classification of gastric cancer associated with distinct clinical outcomes and validated by an XGBoost-based prediction model

Gastric cancer (GC) is a heterogeneous disease and a leading cause of cancer-related deaths. Discovering robust, clinically relevant molecular classifications is critical for guiding personalized therapies for GC. Here, we propose a refined molecular classification scheme for GC using integrated optimal algorithms and multi-omics data. Based on the important features of mRNA, microRNA, and DNA methylation data selected by the multivariate Cox regression model, three subtypes linked to distinct clinical outcomes were identified by combining similarity network fusion and consensus clustering methods. Three subtypes were validated by an extreme gradient boosting machine learning prediction model with 125 differentially expressed genes in multiple independent cohorts. The molecular characteristics of mutation signatures, characteristic gene sets, driver genes, and chemotherapy sensitivity for each subtype were also identified: subtype 1 was associated with favorable prognosis and characterized by high ARID1A and PIK3CA mutations, subtype 2 was associated with a poor prognosis and harbored high recurrent TP53 mutations, and subtype 3 was associated with high CHD1, APOA1 mutations, and a poor prognosis. The proposed three-subtype scheme achieved a better clinical prediction performance (area under the curve value = 0.71) than The Cancer Genome Atlas classification, which may provide a practical subtyping framework to improve the treatment of GC.

A guide to multi-omics data collection and integration for translational medicine

The emerging high-throughput technologies have led to the shift in the design of translational medicine projects towards collecting multi-omics patient samples and, consequently, their integrated analysis. However, the complexity of integrating these datasets has triggered new questions regarding the appropriateness of the available computational methods. Currently, there is no clear consensus on the best combination of omics to include and the data integration methodologies required for their analysis. This article aims to guide the design of multi-omics studies in the field of translational medicine regarding the types of omics and the integration method to choose. We review articles that perform the integration of multiple omics measurements from patient samples. We identify five objectives in translational medicine applications: (i) detect disease-associated molecular patterns, (ii) subtype identification, (iii) diagnosis/prognosis, (iv) drug response prediction, and (v) understand regulatory processes. We describe common trends in the selection of omic types combined for different objectives and diseases. To guide the choice of data integration tools, we group them into the scientific objectives they aim to address. We describe the main computational methods adopted to achieve these objectives and present examples of tools. We compare tools based on how they deal with the computational challenges of data integration and comment on how they perform against predefined objective-specific evaluation criteria. Finally, we discuss examples of tools for downstream analysis and further extraction of novel insights from multi-omics datasets.

MCluster-VAEs: An end-to-end variational deep learning-based clustering method for subtype discovery using multi-omics data

The discovery of cancer subtypes based on unsupervised clustering helps in providing a precise diagnosis, guide treatment, and improve patients' prognoses. Instead of single-omics data, multi-omics data can improve the clustering performance because it obtains a comprehensive landscape for understanding biological systems and mechanisms. However, heterogeneous data from multiple sources raises high complexity and different kinds of noise, which are detrimental to the extraction of clustering information. We propose an end-to-end deep learning based method, called Multi-omics Clustering Variational Autoencoders (MCluster-VAEs), that can extract cluster-friendly representations on multi-omics data. First, a unified network architecture with an attention mechanism was developed for accurately modeling multi-omics data. Then, using a novel objective function built from the Variational Bayes technique, the model was trained to effectively obtain the posterior estimation of the clustering assignments. Compared with 12 other state-of-the-art multi-omics clustering methods, MCluster-VAEs achieved an outstanding performance on benchmark datasets from the TCGA database. On the Pan Cancer dataset, MCluster-VAEs achieved an adjusted Rand index of approximately 0.78 for cancer category recognition, an increase of more than 18% compared with other methods. Furthermore, a survival analysis and clinical parameter enrichment tests conducted on 10 cancer datasets demonstrated that MCluster-VAEs provides comparable and even better results than many common integrative approaches. These results demonstrate that MCluster-VAEs are a powerful new tool for dissecting complex multi-omics relationships and providing new insights for cancer subtype discovery.

Multi-omics research strategies in ischemic stroke: A multidimensional perspective

Ischemic stroke (IS) is a multifactorial and heterogeneous neurological disorder with high rate of death and long-term impairment. Despite years of studies, there are still no stroke biomarkers for clinical practice, and the molecular mechanisms of stroke remain largely unclear. The high-throughput omics approach provides new avenues for discovering biomarkers of IS and explaining its pathological mechanisms. However, single-omics approaches only provide a limited understanding of the biological pathways of diseases. The integration of multiple omics data means the simultaneous analysis of thousands of genes, RNAs, proteins and metabolites, revealing networks of interactions between multiple molecular levels. Integrated analysis of multi-omics approaches will provide helpful insights into stroke pathogenesis, therapeutic target identification and biomarker discovery. Here, we consider advances in genomics, transcriptomics, proteomics and metabolomics and outline their use in discovering the biomarkers and pathological mechanisms of IS. We then delineate strategies for achieving integration at the multi-omics level and discuss how integrative omics and systems biology can contribute to our understanding and management of IS.

A Multiview Clustering Method With Low-Rank and Sparsity Constraints for Cancer Subtyping

Multiomics data clustering is one of the major challenges in the field of precision medicine. Integration of multiomics data for cancer subtyping can improve the understanding on cancer and reveal systems-level insights. How to integrate multiomics data for accurate cancer subtyping is an interesting and challenging research problem. To capture the global and the local structure of omics data, a novel framework for integrating multiomics data is proposed for cancer subtyping. Multiview clustering with low-rank and sparsity constraints (MVCLRS) can measure the local similarities of samples in each omics data and obtain global consensus structures by integrating the multiomics data. The main insight provided by MVCLRS is that low-rank sparse subspace clustering for the construction of an affinity matrix can best capture the local similarities in omics data. Extensive testing is conducted on 10 real world cancer datasets with multiomics from The Cancer Genome Atlas. Compared with 10 state-of-the-art multiomics clustering algorithms, the MVCLRS performs better in the 10 cancer datasets by providing its clustering results with at least one enriched clinical label in nine of ten cancer subtypes, the most of any method.

A Risk Signature Consisting of Eight m6A Methylation Regulators Predicts the Prognosis of Glioma

Glioma progression seriously correlates to the epigenetic context. This study aims to identify glioma subtypes by clustering analysis of patients using the multi-omics data of N6-methyladenosine (m⁶A) methylation regulators and to construct a risk signature for investigating the role of m⁶A methylation regulators in the prognosis of glioma. Multi-omics data of glioma and normal control tissues were obtained through The Cancer Genome Atlas (TCGA) database. The clustering analysis of multi-omics data of patients was conducted using the R package iClusterPlus software. The risk model was constructed by univariate and multivariate Cox analysis, and the glioma expression data and related clinical data were obtained by Chinese Glioma Genome Atlas (CGGA) datasets to verify the risk model. By analyzing the glioma data in TCGA, we found that the risk signature could be constructed according to the eight genes with m⁶A methylation modification function, including ALKBH5, HNRNPA2B1, IGF2BP2, IGF2BP3, RBM15, WTAP, YTHDF1, and YTHDF2. Meanwhile, we found that IGF2BP2 and IGF2BP3 were highly expressed in glioma subtypes with high-risk scores and closely related to the prognosis of glioma patients. m⁶A methylation regulators, especially IGF2BP2 and IGF2BP3, play important roles in the malignant progression of glioma. The risk signature constructed by eight m⁶A methylation regulators can predict the prognosis of glioma. IGF2BP2 and IGF2BP3 may be the key regulatory factors of m⁶A methylation regulators involved in the occurrence and development of glioma, and can serve as molecular markers for the prognosis of glioma.

Multi-omics analysis: Paving the path toward achieving precision medicine in cancer treatment and immuno-oncology

The acceleration of large-scale sequencing and the progress in high-throughput computational analyses, defined as omics, was a hallmark for the comprehension of the biological processes in human health and diseases. In cancerology, the omics approach, initiated by genomics and transcriptomics studies, has revealed an incredible complexity with unsuspected molecular diversity within a same tumor type as well as spatial and temporal heterogeneity of tumors. The integration of multiple biological layers of omics studies brought oncology to a new paradigm, from tumor site classification to pan-cancer molecular classification, offering new therapeutic opportunities for precision medicine. In this review, we will provide a comprehensive overview of the latest innovations for multi-omics integration in oncology and summarize the largest multi-omics dataset available for adult and pediatric cancers. We will present multi-omics techniques for characterizing cancer biology and show how multi-omics data can be combined with clinical data for the identification of prognostic and treatment-specific biomarkers, opening the way to personalized therapy. To conclude, we will detail the newest strategies for dissecting the tumor immune environment and host–tumor interaction. We will explore the advances in immunomics and microbiomics for biomarker identification to guide therapeutic decision in immuno-oncology.

Immune depletion of the methylated phenotype of colon cancer is closely related to resistance to immune checkpoint inhibitors

Background

Molecular typing based on single omics data has its limitations and requires effective integration of multiple omics data for tumor typing of colorectal cancer (CRC).

Methods

Transcriptome expression, DNA methylation, somatic mutation, clinicopathological information, and copy number variation were retrieved from TCGA, UCSC Xena, cBioPortal, FireBrowse, or GEO. After pre-processing and calculating the clustering prediction index (CPI) with gap statistics, integrative clustering analysis was conducted via MOVICS. The tumor microenvironment (TME) was deconvolved using several algorithms such as GSVA, MCPcounter, ESTIMATE, and PCA. The metabolism-relevant pathways were extracted through ssGSEA. Differential analysis was based on limma and enrichment analysis was carried out by Enrichr. DNA methylation and transcriptome expression were integrated via ELMER. Finally, nearest template or hemotherapeutic sensitivity prediction was conducted using NTP or pRRophetic.

Results

Three molecular subtypes (CS1, CS2, and CS3) were recognized by integrating transcriptome, DNA methylation, and driver mutations. CRC patients in CS3 had the most favorable prognosis. A total of 90 differentially mutated genes among the three CSs were obtained, and CS3 displayed the highest tumor mutation burden (TMB), while significant instability across the entire chromosome was observed in the CS2 group. A total of 30 upregulated mRNAs served as classifiers were identified and the similar diversity in clinical outcomes of CS3 was validated in four external datasets. The heterogeneity in the TME and metabolism-related pathways were also observed in the three CSs. Furthermore, we found CS2 tended to loss methylations while CS3 tended to gain methylations. Univariate and multivariate Cox regression revealed that the subtypes were independent prognostic factors. For the drug sensitivity analysis, we found patients in CS2 were more sensitive to ABT.263, NSC.87877, BIRB.0796, and PAC.1. By Integrating with the DNA mutation and RNA expression in CS3, we identified that SOX9, a specific marker of CS3, was higher in the tumor than tumor adjacent by IHC in the in-house cohort and public cohort.

Conclusion

The molecular subtypes based on integrated multi-omics uncovered new insights into the prognosis, mechanisms, and clinical therapeutic targets for CRC.

HSSG: Identification of Cancer Subtypes Based on Heterogeneity Score of A Single Gene

Cancer is a highly heterogeneous disease, which leads to the fact that even the same cancer can be further classified into different subtypes according to its pathology. With the multi-omics data widely used in cancer subtypes identification, effective feature selection is essential for accurately identifying cancer subtypes. However, the feature selection in the existing cancer subtypes identification methods has the problem that the most helpful features cannot be selected from a biomolecular perspective, and the relationship between the selected features cannot be reflected. To solve this problem, we propose a method for feature selection to identify cancer subtypes based on the heterogeneity score of a single gene: HSSG. In the proposed method, the sample-similarity network of a single gene is constructed, and pseudo-F statistics calculates the heterogeneity score for cancer subtypes identification of each gene. Finally, we construct gene-gene networks using genes with higher heterogeneity scores and mine essential genes from the networks. From the seven TCGA data sets for three experiments, including cancer subtypes identification in single-omics data, the performance in feature selection of multi-omics data, and the effectiveness and stability of the selected features, HSSG achieves good performance in all. This indicates that HSSG can effectively select features for subtypes identification.

Multimodal Dimension Reduction and Subtype Classification of Head and Neck Squamous Cell Tumors

Traditional analysis of genomic data from bulk sequencing experiments seek to group and compare sample cohorts into biologically meaningful groups. To accomplish this task, large scale databases of patient-derived samples, like that of TCGA, have been established, giving the ability to interrogate multiple data modalities per tumor. We have developed a computational strategy employing multimodal integration paired with spectral clustering and modern dimension reduction techniques such as PHATE to provide a more robust method for cancer sub-type classification. Using this integrated approach, we have examined 514 Head and Neck Squamous Carcinoma (HNSC) tumor samples from TCGA across gene-expression, DNA-methylation, and microbiome data modalities. We show that these approaches, primarily developed for single-cell sequencing can be efficiently applied to bulk tumor sequencing data. Our multimodal analysis captures the dynamic heterogeneity, identifies new and refines subtypes of HNSC, and orders tumor samples along well-defined cellular trajectories. Collectively, these results showcase the inherent molecular complexity of tumors and offer insights into carcinogenesis and importance of targeted therapy. Computational techniques as highlighted in our study provide an organic and powerful approach to identify granular patterns in large and noisy datasets that may otherwise be overlooked.

The molecular pathophysiology of mood disorders: From the analysis of single molecular layers to multi-omic integration

Next-generation sequencing now enables the rapid and affordable production of reliable biological data at multiple molecular levels, collectively referred to as "omics". To maximize the potential for discovery, computational biologists have created and adapted integrative multi-omic analytical methods. When applied to diseases with traceable pathophysiology such as cancer, these new algorithms and statistical approaches have enabled the discovery of clinically relevant molecular mechanisms and biomarkers. In contrast, these methods have been much less applied to the field of molecular psychiatry, although diagnostic and prognostic biomarkers are similarly needed. In the present review, we first briefly summarize main findings from two decades of studies that investigated single molecular processes in relation to mood disorders. Then, we conduct a systematic review of multi-omic strategies that have been proposed and used more recently. We also list databases and types of data available to researchers for future work. Finally, we present the newest methodologies that have been employed for multi-omics integration in other medical fields, and discuss their potential for molecular psychiatry studies.