Unsupervised multiple kernel learning for heterogeneous data integration

Multi-OMICS approaches in cancer biology: New era in cancer therapy

Innovative multi-omics frameworks integrate diverse datasets from the same patients to enhance our understanding of the molecular and clinical aspects of cancers. Advanced omics and multi-view clustering algorithms present unprecedented opportunities for classifying cancers into subtypes, refining survival predictions and treatment outcomes, and unravelling key pathophysiological processes across various molecular layers. However, with the increasing availability of cost-effective high-throughput technologies (HTT) that generate vast amounts of data, analyzing single layers often falls short of establishing causal relations. Integrating multi-omics data spanning genomes, epigenomes, transcriptomes, proteomes, metabolomes, and microbiomes offers unique prospects to comprehend the underlying biology of complex diseases like cancer. This discussion explores algorithmic frameworks designed to uncover cancer subtypes, disease mechanisms, and methods for identifying pivotal genomic alterations. It also underscores the significance of multi-omics in tumor classifications, diagnostics, and prognostications. Despite its unparalleled advantages, the integration of multi-omics data has been slow to find its way into everyday clinics. A major hurdle is the uneven maturity of different omics approaches and the widening gap between the generation of large datasets and the capacity to process this data. Initiatives promoting the standardization of sample processing and analytical pipelines, as well as multidisciplinary training for experts in data analysis and interpretation, are crucial for translating theoretical findings into practical applications.

Application of Mass Cytometry Platforms to Solid Organ Transplantation

Transplantation serves as the cornerstone of treatment for patients with end-stage organ disease. The prevalence of complications, such as allograft rejection, infection, and malignancies, underscores the need to dissect the complex interactions of the immune system at the single-cell level. In this review, we discuss studies using mass cytometry or cytometry by time-of-flight, a cutting-edge technology enabling the characterization of immune populations and cell-to-cell interactions in granular detail. We review the application of mass cytometry in human and experimental animal studies in the context of transplantation, uncovering invaluable contributions of the tool to understanding rejection and other transplant-related complications. We discuss recent innovations that have the potential to streamline and standardize mass cytometry workflows for application to multisite clinical trials. Additionally, we introduce imaging mass cytometry, a technique that couples the power of mass cytometry with spatial context, thereby mapping cellular interactions within tissue microenvironments. The synergistic integration of mass cytometry and imaging mass cytometry data with other omics data sets and high-dimensional data platforms to further define immune dynamics is discussed. In conclusion, mass cytometry technologies, when integrated with other tools and data, shed light on the intricate landscape of the immune response in transplantation. This approach holds significant potential for enhancing patient outcomes by advancing our understanding and facilitating the development of new diagnostics and therapeutics.

Imaging and multi-omics datasets converge to define different neural progenitor origins for ATRT-SHH subgroups

Atypical teratoid rhabdoid tumors (ATRT) are divided into MYC, TYR and SHH subgroups, suggesting diverse lineages of origin. Here, we investigate the imaging of human ATRT at diagnosis and the precise anatomic origin of brain tumors in the Rosa26-CreERT2::Smarcb1flox/flox model. This cross-species analysis points to an extra-cerebral origin for MYC tumors. Additionally, we clearly distinguish SHH ATRT emerging from the cerebellar anterior lobe (CAL) from those emerging from the basal ganglia (BG) and intra-ventricular (IV) regions. Molecular characteristics point to the midbrain-hindbrain boundary as the origin of CAL SHH ATRT, and to the ganglionic eminence as the origin of BG/IV SHH ATRT. Single-cell RNA sequencing on SHH ATRT supports these hypotheses. Trajectory analyses suggest that SMARCB1 loss induces a de-differentiation process mediated by repressors of the neuronal program such as REST, ID and the NOTCH pathway.

Asterics: a simple tool for the ExploRation and Integration of omiCS data

BACKGROUND

The rapid development of omics acquisition techniques has induced the production of a large volume of heterogeneous and multi-level omics datasets, which require specific and sometimes complex analyses to obtain relevant biological information. Here, we present ASTERICS (version 2.5), a publicly available web interface for the analyses of omics datasets.

RESULTS

ASTERICS is designed to make both standard and complex exploratory and integration analysis workflows easily available to biologists and to provide high quality interactive plots. Special care has been taken to provide a comprehensive documentation of the implemented analyses and to guide users toward sound analysis choices regarding some specific omics data. Data and analyses are organized in a comprehensive graphical workflow within ASTERICS workspace to facilitate the understanding of successive data editions and analyses leading to a given result.

CONCLUSION

ASTERICS provides an easy to use platform for omics data exploration and integration. The modular organization of its open source code makes it easy to incorporate new workflows and analyses by external contributors. ASTERICS is available at https://asterics.miat.inrae.fr and can also be deployed using provided docker images.

AFEI: adaptive optimized vertical federated learning for heterogeneous multi-omics data integration

Vertical federated learning has gained popularity as a means of enabling collaboration and information sharing between different entities while maintaining data privacy and security. This approach has potential applications in disease healthcare, cancer prognosis prediction, and other industries where data privacy is a major concern. Although using multi-omics data for cancer prognosis prediction provides more information for treatment selection, collecting different types of omics data can be challenging due to their production in various medical institutions. Data owners must comply with strict data protection regulations such as European Union (EU) General Data Protection Regulation. To share patient data across multiple institutions, privacy and security issues must be addressed. Therefore, we propose an adaptive optimized vertical federated-learning-based framework adaptive optimized vertical federated learning for heterogeneous multi-omics data integration (AFEI) to integrate multi-omics data collected from multiple institutions for cancer prognosis prediction. AFEI enables participating parties to build an accurate joint evaluation model for learning more information related to cancer patients from different perspectives, based on the distributed and encrypted multi-omics features shared by multiple institutions. The experimental results demonstrate that AFEI achieves higher prediction accuracy (6.5% on average) than using single omics data by utilizing the encrypted multi-omics data from different institutions, and it performs almost as well as prognosis prediction by directly integrating multi-omics data. Overall, AFEI can be seen as an efficient solution for breaking down barriers to multi-institutional collaboration and promoting the development of cancer prognosis prediction.

Improvement of variables interpretability in kernel PCA

BACKGROUND

Kernel methods have been proven to be a powerful tool for the integration and analysis of high-throughput technologies generated data. Kernels offer a nonlinear version of any linear algorithm solely based on dot products. The kernelized version of principal component analysis is a valid nonlinear alternative to tackle the nonlinearity of biological sample spaces. This paper proposes a novel methodology to obtain a data-driven feature importance based on the kernel PCA representation of the data.

RESULTS

The proposed method, kernel PCA Interpretable Gradient (KPCA-IG), provides a data-driven feature importance that is computationally fast and based solely on linear algebra calculations. It has been compared with existing methods on three benchmark datasets. The accuracy obtained using KPCA-IG selected features is equal to or greater than the other methods' average. Also, the computational complexity required demonstrates the high efficiency of the method. An exhaustive literature search has been conducted on the selected genes from a publicly available Hepatocellular carcinoma dataset to validate the retained features from a biological point of view. The results once again remark on the appropriateness of the computed ranking.

CONCLUSIONS

The black-box nature of kernel PCA needs new methods to interpret the original features. Our proposed methodology KPCA-IG proved to be a valid alternative to select influential variables in high-dimensional high-throughput datasets, potentially unravelling new biological and medical biomarkers.

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.

The effect of synthetic silver nanoparticles on the antibiotic resistome and the removal efficiency of antibiotic resistance genes in a hybrid filter system treating municipal wastewater

Engineered nanoparticles, including silver nanoparticles (AgNPs), are released into the environment mainly through wastewater treatment systems. Knowledge of the impact of AgNPs on the abundance and removal efficiency of antibiotic resistance genes (ARGs) in wastewater treatment facilities, including constructed wetlands (CWs), is essential in the context of public health. This study evaluated the effect of increased (100-fold) collargol (protein-coated AgNPs) and ionic Ag⁺ in municipal wastewater on the structure, abundance, and removal efficiency of the antibiotic resistome, integron-integrase genes, and pathogens in a hybrid CW using quantitative PCR and metagenomic approaches. The abundance of ARGs in wastewater and the removal efficiency of ARGs in the hybrid system were significantly affected by higher Ag concentrations, especially with collargol treatment, resulting in an elevated ARG discharge of system effluent into the environment. The accumulated Ag in the filters had a more profound effect on the absolute and relative abundance of ARGs in the treated water than the Ag content in the water. This study recorded significantly enhanced relative abundance values for tetracycline (tetA, tetC, tetQ), sulfonamide (sul1, sul2), and aminoglycoside (aadA) resistance genes, which are frequently found on mobile genetic elements in collargol- and, to a lesser extent, AgNO₃-treated subsystems. Elevated plasmid and integron-integrase gene levels, especially intI1, in response to collargol presence indicated the substantial role of AgNPs in promoting horizontal gene transfer in the treatment system. The pathogenic segment of the prokaryotic community was similar to a typical sewage community, and strong correlations between pathogen and ARG proportions were recorded in vertical subsurface flow filters. Furthermore, the proportion of Salmonella enterica was positively related to the Ag content in these filter effluents. The effect of AgNPs on the nature and characteristics of prominent resistance genes carried by mobile genetic elements in CWs requires further investigation.

Metabolomics meets systems immunology

Metabolic processes play a critical role in immune regulation. Metabolomics is the systematic analysis of small molecules (metabolites) in organisms or biological samples, providing an opportunity to comprehensively study interactions between metabolism and immunity in physiology and disease. Integrating metabolomics into systems immunology allows the exploration of the interactions of multilayered features in the biological system and the molecular regulatory mechanism of these features. Here, we provide an overview on recent technological developments of metabolomic applications in immunological research. To begin, two widely used metabolomics approaches are compared: targeted and untargeted metabolomics. Then, we provide a comprehensive overview of the analysis workflow and the computational tools available, including sample preparation, raw spectra data preprocessing, data processing, statistical analysis, and interpretation. Third, we describe how to integrate metabolomics with other omics approaches in immunological studies using available tools. Finally, we discuss new developments in metabolomics and its prospects for immunology research. This review provides guidance to researchers using metabolomics and multiomics in immunity research, thus facilitating the application of systems immunology to disease research.

MEMMAL: A tool for expanding large-scale mechanistic models with machine learned associations and big datasets

Computational models that can explain and predict complex sub-cellular, cellular, and tissue-level drug response mechanisms could speed drug discovery and prioritize patient-specific treatments (i.e., precision medicine). Some models are mechanistic with detailed equations describing known (or supposed) physicochemical processes, while some are statistical or machine learning-based approaches, that explain datasets but have no mechanistic or causal guarantees. These two types of modeling are rarely combined, missing the opportunity to explore possibly causal but data-driven new knowledge while explaining what is already known. Here, we explore combining machine learned associations with mechanistic models to develop computational models that could more fully represent cellular behavior. In this proposed MEMMAL (MEchanistic Modeling with MAchine Learning) framework, machine learning/statistical models built using omics datasets provide predictions for new interactions between genes and proteins where there is physicochemical uncertainty. These interactions are used as a basis for new reactions in mechanistic models. As a test case, we focused on incorporating novel IFNγ/PD-L1 related associations into a large-scale mechanistic model for cell proliferation and death to better recapitulate the recently released NIH LINCS Consortium MCF10A dataset and enable description of the cellular response to checkpoint inhibitor immunotherapies. This work is a template for combining big-data-inferred interactions with mechanistic models, which could be more broadly applicable for building multi-scale precision medicine and whole cell models.

Missing data in multi-omics integration: Recent advances through artificial intelligence

Biological systems function through complex interactions between various 'omics (biomolecules), and a more complete understanding of these systems is only possible through an integrated, multi-omic perspective. This has presented the need for the development of integration approaches that are able to capture the complex, often non-linear, interactions that define these biological systems and are adapted to the challenges of combining the heterogenous data across 'omic views. A principal challenge to multi-omic integration is missing data because all biomolecules are not measured in all samples. Due to either cost, instrument sensitivity, or other experimental factors, data for a biological sample may be missing for one or more 'omic techologies. Recent methodological developments in artificial intelligence and statistical learning have greatly facilitated the analyses of multi-omics data, however many of these techniques assume access to completely observed data. A subset of these methods incorporate mechanisms for handling partially observed samples, and these methods are the focus of this review. We describe recently developed approaches, noting their primary use cases and highlighting each method's approach to handling missing data. We additionally provide an overview of the more traditional missing data workflows and their limitations; and we discuss potential avenues for further developments as well as how the missing data issue and its current solutions may generalize beyond the multi-omics context.

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.

Application of data integration for rice bacterial strain selection by combining their osmotic stress response and plant growth-promoting traits

Agricultural application of plant-beneficial bacteria to improve crop yield and alleviate the stress caused by environmental conditions, pests, and pathogens is gaining popularity. However, before using these bacterial strains in plant experiments, their environmental stress responses and plant health improvement potential should be examined. In this study, we explored the applicability of three unsupervised machine learning-based data integration methods, including principal component analysis (PCA) of concatenated data, multiple co-inertia analysis (MCIA), and multiple kernel learning (MKL), to select osmotic stress-tolerant plant growth-promoting (PGP) bacterial strains isolated from the rice phyllosphere. The studied datasets consisted of direct and indirect PGP activity measurements and osmotic stress responses of eight bacterial strains previously isolated from the phyllosphere of drought-tolerant rice cultivar. The production of phytohormones, such as indole-acetic acid (IAA), gibberellic acid (GA), abscisic acid (ABA), and cytokinin, were used as direct PGP traits, whereas the production of hydrogen cyanide and siderophore and antagonistic activity against the foliar pathogens Pyricularia oryzae and Helminthosporium oryzae were evaluated as measures of indirect PGP activity. The strains were subjected to a range of osmotic stress levels by adding PEG 6000 (0, 11, 21, and 32.6%) to their growth medium. The results of the osmotic stress response experiments showed that all bacterial strains accumulated endogenous proline and glycine betaine (GB) and exhibited an increase in growth, when osmotic stress levels were increased to a specific degree, while the production of IAA and GA considerably decreased. The three applied data integration methods did not provide a similar grouping of the strains. Especially deviant was the ordination of microbial strains based on the PCA of concatenated data. However, all three data integration methods indicated that the strains Bacillus altitudinis PB46 and B. megaterium PB50 shared high similarity in PGP traits and osmotic stress response. Overall, our results indicate that data integration methods complement the single-table data analysis approach and improve the selection process for PGP microbial strains.

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.

Modern views of machine learning for precision psychiatry

In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

Impact of synthetic silver nanoparticles on the biofilm microbial communities and wastewater treatment efficiency in experimental hybrid filter system treating municipal wastewater

Silver nanoparticles (AgNPs) threaten human and ecosystem health, and are among the most widely used engineered nanomaterials that reach wastewater during production, usage, and disposal phases. This study evaluated the effect of a 100-fold increase in collargol (protein-coated AgNP) and Ag⁺ ions concentrations in municipal wastewater on the microbial community composition of the filter material biofilms (FMB) and the purification efficiency of the hybrid treatment system consisting of vertical (VF) and horizontal (HF) subsurface flow filters. We found that increased amounts of collargol and AgNO₃ in wastewater had a modest effect on the prokaryotic community composition in FMB and did not significantly affect the performance of the studied system. Regardless of how Ag was introduced, 99.9% of it was removed by the system. AgNPs and AgNO₃ concentrations did not significantly affect the purification efficiency of the system. AgNO₃ induced a higher increase in the genetic potential of certain Ag resistance mechanisms in VFs than collargol; however, the increase in Ag resistance potential was similar for both substances in HF. Hence, the microbial community composition in biofilms of vertical and horizontal flow filters is largely resistant, resilient, or functionally redundant in response to AgNPs addition in the form of collargol.

Heterogeneous data integration methods for patient similarity networks

Patient similarity networks (PSNs), where patients are represented as nodes and their similarities as weighted edges, are being increasingly used in clinical research. These networks provide an insightful summary of the relationships among patients and can be exploited by inductive or transductive learning algorithms for the prediction of patient outcome, phenotype and disease risk. PSNs can also be easily visualized, thus offering a natural way to inspect complex heterogeneous patient data and providing some level of explainability of the predictions obtained by machine learning algorithms. The advent of high-throughput technologies, enabling us to acquire high-dimensional views of the same patients (e.g. omics data, laboratory data, imaging data), calls for the development of data fusion techniques for PSNs in order to leverage this rich heterogeneous information. In this article, we review existing methods for integrating multiple biomedical data views to construct PSNs, together with the different patient similarity measures that have been proposed. We also review methods that have appeared in the machine learning literature but have not yet been applied to PSNs, thus providing a resource to navigate the vast machine learning literature existing on this topic. In particular, we focus on methods that could be used to integrate very heterogeneous datasets, including multi-omics data as well as data derived from clinical information and medical imaging.

A Sparse Mixture-of-Experts Model With Screening of Genetic Associations to Guide Disease Subtyping

Motivation: Identifying new genetic associations in non-Mendelian complex diseases is an increasingly difficult challenge. These diseases sometimes appear to have a significant component of heritability requiring explanation, and this missing heritability may be due to the existence of subtypes involving different genetic factors. Taking genetic information into account in clinical trials might potentially have a role in guiding the process of subtyping a complex disease. Most methods dealing with multiple sources of information rely on data transformation, and in disease subtyping, the two main strategies used are 1) the clustering of clinical data followed by posterior genetic analysis and 2) the concomitant clustering of clinical and genetic variables. Both of these strategies have limitations that we propose to address. Contribution: This work proposes an original method for disease subtyping on the basis of both longitudinal clinical variables and high-dimensional genetic markers via a sparse mixture-of-regressions model. The added value of our approach lies in its interpretability in relation to two aspects. First, our model links both clinical and genetic data with regard to their initial nature (i.e., without transformation) and does not require post-processing where the original information is accessed a second time to interpret the subtypes. Second, it can address large-scale problems because of a variable selection step that is used to discard genetic variables that may not be relevant for subtyping. Results: The proposed method was validated on simulations. A dataset from a cohort of Parkinson's disease patients was also analyzed. Several subtypes of the disease and genetic variants that potentially have a role in this typology were identified. Software availability: The R code for the proposed method, named DiSuGen, and a tutorial are available for download (see the references).

High-throughput plant phenotyping: a role for metabolomics?

High-throughput (HTP) plant phenotyping approaches are developing rapidly and are already helping to bridge the genotype-phenotype gap. However, technologies should be developed beyond current physico-spectral evaluations to extend our analytical capacities to the subcellular level. Metabolites define and determine many key physiological and agronomic features in plants and an ability to integrate a metabolomics approach within current HTP phenotyping platforms has huge potential for added value. While key challenges remain on several fronts, novel technological innovations are upcoming yet under-exploited in a phenotyping context. In this review, we present an overview of the state of the art and how current limitations might be overcome to enable full integration of metabolomics approaches into a generic phenotyping pipeline in the near future.

Machine learning: its challenges and opportunities in plant system biology

Sequencing technologies are evolving at a rapid pace, enabling the generation of massive amounts of data in multiple dimensions (e.g., genomics, epigenomics, transcriptomic, metabolomics, proteomics, and single-cell omics) in plants. To provide comprehensive insights into the complexity of plant biological systems, it is important to integrate different omics datasets. Although recent advances in computational analytical pipelines have enabled efficient and high-quality exploration and exploitation of single omics data, the integration of multidimensional, heterogenous, and large datasets (i.e., multi-omics) remains a challenge. In this regard, machine learning (ML) offers promising approaches to integrate large datasets and to recognize fine-grained patterns and relationships. Nevertheless, they require rigorous optimizations to process multi-omics-derived datasets. In this review, we discuss the main concepts of machine learning as well as the key challenges and solutions related to the big data derived from plant system biology. We also provide in-depth insight into the principles of data integration using ML, as well as challenges and opportunities in different contexts including multi-omics, single-cell omics, protein function, and protein-protein interaction. KEY POINTS: • The key challenges and solutions related to the big data derived from plant system biology have been highlighted. • Different methods of data integration have been discussed. • Challenges and opportunities of the application of machine learning in plant system biology have been highlighted and discussed.

Kernel-based hierarchical structural component models for pathway analysis

MOTIVATION

Pathway analyses have led to more insight into the underlying biological functions related to the phenotype of interest in various types of omics data. Pathway-based statistical approaches have been actively developed, but most of them do not consider correlations among pathways. Because it is well known that there are quite a few biomarkers that overlap between pathways, these approaches may provide misleading results. In addition, most pathway-based approaches tend to assume that biomarkers within a pathway have linear associations with the phenotype of interest, even though the relationships are more complex.

RESULTS

To model complex effects including nonlinear effects, we propose a new approach, Hierarchical structural CoMponent analysis using Kernel (HisCoM-Kernel). The proposed method models nonlinear associations between biomarkers and phenotype by extending the kernel machine regression and analyzes entire pathways simultaneously by using the biomarker-pathway hierarchical structure. HisCoM-Kernel is a flexible model that can be applied to various omics data. It was successfully applied to three omics datasets generated by different technologies. Our simulation studies showed that HisCoM-Kernel provided higher statistical power than other existing pathway-based methods in all datasets. The application of HisCoM-Kernel to three types of omics dataset showed its superior performance compared to existing methods in identifying more biologically meaningful pathways, including those reported in previous studies.

AVAILABILITY AND IMPLEMENTATION

Freely available at http://statgen.snu.ac.kr/software/HisCom-Kernel/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Unsupervised Multi-Omics Data Integration Methods: A Comprehensive Review

Through the developments of Omics technologies and dissemination of large-scale datasets, such as those from The Cancer Genome Atlas, Alzheimer’s Disease Neuroimaging Initiative, and Genotype-Tissue Expression, it is becoming increasingly possible to study complex biological processes and disease mechanisms more holistically. However, to obtain a comprehensive view of these complex systems, it is crucial to integrate data across various Omics modalities, and also leverage external knowledge available in biological databases. This review aims to provide an overview of multi-Omics data integration methods with different statistical approaches, focusing on unsupervised learning tasks, including disease onset prediction, biomarker discovery, disease subtyping, module discovery, and network/pathway analysis. We also briefly review feature selection methods, multi-Omics data sets, and resources/tools that constitute critical components for carrying out the integration.

Current progress and open challenges for applying deep learning across the biosciences

Deep Learning (DL) has recently enabled unprecedented advances in one of the grand challenges in computational biology: the half-century-old problem of protein structure prediction. In this paper we discuss recent advances, limitations, and future perspectives of DL on five broad areas: protein structure prediction, protein function prediction, genome engineering, systems biology and data integration, and phylogenetic inference. We discuss each application area and cover the main bottlenecks of DL approaches, such as training data, problem scope, and the ability to leverage existing DL architectures in new contexts. To conclude, we provide a summary of the subject-specific and general challenges for DL across the biosciences.

Feature selection for kernel methods in systems biology

The substantial development of high-throughput biotechnologies has rendered large-scale multi-omics datasets increasingly available. New challenges have emerged to process and integrate this large volume of information, often obtained from widely heterogeneous sources. Kernel methods have proven successful to handle the analysis of different types of datasets obtained on the same individuals. However, they usually suffer from a lack of interpretability since the original description of the individuals is lost due to the kernel embedding. We propose novel feature selection methods that are adapted to the kernel framework and go beyond the well-established work in supervised learning by addressing the more difficult tasks of unsupervised learning and kernel output learning. The method is expressed under the form of a non-convex optimization problem with a ℓ₁ penalty, which is solved with a proximal gradient descent approach. It is tested on several systems biology datasets and shows good performances in selecting relevant and less redundant features compared to existing alternatives. It also proved relevant for identifying important governmental measures best explaining the time series of Covid-19 reproducing number evolution during the first months of 2020. The proposed feature selection method is embedded in the R package mixKernel version 0.8, published on CRAN. Installation instructions are available at http://mixkernel.clementine.wf/.

Computational approaches leveraging integrated connections of multi-omic data toward clinical applications

In line with the advances in high-throughput technologies, multiple omic datasets have accumulated to study biological systems and diseases coherently. No single omics data type is capable of fully representing cellular activity. The complexity of the biological processes arises from the interactions between omic entities such as genes, proteins, and metabolites. Therefore, multi-omic data integration is crucial but challenging. The impact of the molecular alterations in multi-omic data is not local in the neighborhood of the altered gene or protein; rather, the impact diffuses in the network and changes the functionality of multiple signaling pathways and regulation of the gene expression. Additionally, multi-omic data is high-dimensional and has background noise. Several integrative approaches have been developed to accurately interpret the multi-omic datasets, including machine learning, network-based methods, and their combination. In this review, we overview the most recent integrative approaches and tools with a focus on network-based methods. We then discuss these approaches according to their specific applications, from disease-network and biomarker identification to patient stratification, drug discovery, and repurposing.

Identifying Molecular Biomarkers for Diseases With Machine Learning Based on Integrative Omics

Molecular biomarkers are certain molecules or set of molecules that can be of help for diagnosis or prognosis of diseases or disorders. In the past decades, thanks to the advances in high-throughput technologies, a huge amount of molecular 'omics' data, e.g., transcriptomics and proteomics, have been accumulated. The availability of these omics data makes it possible to screen biomarkers for diseases or disorders. Accordingly, a number of computational approaches have been developed to identify biomarkers by exploring the omics data. In this review, we present a comprehensive survey on the recent progress of identification of molecular biomarkers with machine learning approaches. Specifically, we categorize the machine learning approaches into supervised, un-supervised and recommendation approaches, where the biomarkers including single genes, gene sets and small gene networks. In addition, we further discuss potential problems underlying bio-medical data that may pose challenges for machine learning, and provide possible directions for future biomarker identification.

Evaluation and comparison of multi-omics data integration methods for cancer subtyping

Computational integrative analysis has become a significant approach in the data-driven exploration of biological problems. Many integration methods for cancer subtyping have been proposed, but evaluating these methods has become a complicated problem due to the lack of gold standards. Moreover, questions of practical importance remain to be addressed regarding the impact of selecting appropriate data types and combinations on the performance of integrative studies. Here, we constructed three classes of benchmarking datasets of nine cancers in TCGA by considering all the eleven combinations of four multi-omics data types. Using these datasets, we conducted a comprehensive evaluation of ten representative integration methods for cancer subtyping in terms of accuracy measured by combining both clustering accuracy and clinical significance, robustness, and computational efficiency. We subsequently investigated the influence of different omics data on cancer subtyping and the effectiveness of their combinations. Refuting the widely held intuition that incorporating more types of omics data always produces better results, our analyses showed that there are situations where integrating more omics data negatively impacts the performance of integration methods. Our analyses also suggested several effective combinations for most cancers under our studies, which may be of particular interest to researchers in omics data analysis.

Cancer is one of the most heterogeneous diseases, characterized by diverse morphological, phenotypic, and genomic profiles between tumors and their subtypes. Identifying cancer subtypes can help patients receive precise treatments. With the development of high-throughput technologies, genomics, epigenomics, and transcriptomics data have been generated for large cancer patient cohorts. It is believed that the more omics data we use, the more accurate identification of cancer subtypes. To examine this assumption, we first constructed three classes of benchmarking datasets to conduct a comprehensive evaluation and comparison of ten representative multi-omics data integration methods for cancer subtyping by considering their accuracy, robustness, and computational efficiency. Then, we investigated the influence of different omics data and their various combinations on the effectiveness of cancer subtyping. Our analyses showed that there are situations where integrating more omics data negatively impacts the performance of integration methods. We hope that our work may help researchers choose a proper method and an effective data combination when identifying cancer subtypes using data integration methods.

A unified framework for the integration of multiple hierarchical clusterings or networks from multi-source data

Background

Integrating data from different sources is a recurring question in computational biology. Much effort has been devoted to the integration of data sets of the same type, typically multiple numerical data tables. However, data types are generally heterogeneous: it is a common place to gather data in the form of trees, networks or factorial maps, as these representations all have an appealing visual interpretation that helps to study grouping patterns and interactions between entities. The question we aim to answer in this paper is that of the integration of such representations.

Results

To this end, we provide a simple procedure to compare data with various types, in particular trees or networks, that relies essentially on two steps: the first step projects the representations into a common coordinate system; the second step then uses a multi-table integration approach to compare the projected data. We rely on efficient and well-known methodologies for each step: the projection step is achieved by retrieving a distance matrix for each representation form and then applying multidimensional scaling to provide a new set of coordinates from all the pairwise distances. The integration step is then achieved by applying a multiple factor analysis to the multiple tables of the new coordinates. This procedure provides tools to integrate and compare data available, for instance, as tree or network structures. Our approach is complementary to kernel methods, traditionally used to answer the same question.

Conclusion

Our approach is evaluated on simulation and used to analyze two real-world data sets: first, we compare several clusterings for different cell-types obtained from a transcriptomics single-cell data set in mouse embryos; second, we use our procedure to aggregate a multi-table data set from the TCGA breast cancer database, in order to compare several protein networks inferred for different breast cancer subtypes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04303-4.

A generalized kernel machine approach to identify higher-order composite effects in multi-view datasets, with application to adolescent brain development and osteoporosis

In recent years, a comprehensive study of complex disease with multi-view datasets (e.g., multi-omics and imaging scans) has been a focus and forefront in biomedical research. State-of-the-art biomedical technologies are enabling us to collect multi-view biomedical datasets for the study of complex diseases. While all the views of data tend to explore complementary information of disease, analysis of multi-view data with complex interactions is challenging for a deeper and holistic understanding of biological systems. In this paper, we propose a novel generalized kernel machine approach to identify higher-order composite effects in multi-view biomedical datasets (GKMAHCE). This generalized semi-parametric (a mixed-effect linear model) approach includes the marginal and joint Hadamard product of features from different views of data. The proposed kernel machine approach considers multi-view data as predictor variables to allow a more thorough and comprehensive modeling of a complex trait. We applied GKMAHCE approach to both synthesized datasets and real multi-view datasets from adolescent brain development and osteoporosis study. Our experiments demonstrate that the proposed method can effectively identify higher-order composite effects and suggest that corresponding features (genes, region of interests, and chemical taxonomies) function in a concerted effort. We show that the proposed method is more generalizable than existing ones. To promote reproducible research, the source code of the proposed method is available at.

Integration strategies of multi-omics data for machine learning analysis

Increased availability of high-throughput technologies has generated an ever-growing number of omics data that seek to portray many different but complementary biological layers including genomics, epigenomics, transcriptomics, proteomics, and metabolomics. New insight from these data have been obtained by machine learning algorithms that have produced diagnostic and classification biomarkers. Most biomarkers obtained to date however only include one omic measurement at a time and thus do not take full advantage of recent multi-omics experiments that now capture the entire complexity of biological systems.

Multi-omics data integration strategies are needed to combine the complementary knowledge brought by each omics layer. We have summarized the most recent data integration methods/ frameworks into five different integration strategies: early, mixed, intermediate, late and hierarchical. In this mini-review, we focus on challenges and existing multi-omics integration strategies by paying special attention to machine learning applications.

Statistical Integration of 'Omics Data Increases Biological Knowledge Extracted from Metabolomics Data: Application to Intestinal Exposure to the Mycotoxin Deoxynivalenol

The effects of low doses of toxicants are often subtle and information extracted from metabolomic data alone may not always be sufficient. As end products of enzymatic reactions, metabolites represent the final phenotypic expression of an organism and can also reflect gene expression changes caused by this exposure. Therefore, the integration of metabolomic and transcriptomic data could improve the extracted biological knowledge on these toxicants induced disruptions. In the present study, we applied statistical integration tools to metabolomic and transcriptomic data obtained from jejunal explants of pigs exposed to the food contaminant, deoxynivalenol (DON). Canonical correlation analysis (CCA) and self-organizing map (SOM) were compared for the identification of correlated transcriptomic and metabolomic features, and O2-PLS was used to model the relationship between exposure and selected features. The integration of both 'omics data increased the number of discriminant metabolites discovered (39) by about 10 times compared to the analysis of the metabolomic dataset alone (3). Besides the disturbance of energy metabolism previously reported, assessing correlations between both functional levels revealed several other types of damage linked to the intestinal exposure to DON, including the alteration of protein synthesis, oxidative stress, and inflammasome activation. This confirms the added value of integration to enrich the biological knowledge extracted from metabolomics.

A review of AI and Data Science support for cancer management

INTRODUCTION

Thanks to improvement of care, cancer has become a chronic condition. But due to the toxicity of treatment, the importance of supporting the quality of life (QoL) of cancer patients increases. Monitoring and managing QoL relies on data collected by the patient in his/her home environment, its integration, and its analysis, which supports personalization of cancer management recommendations. We review the state-of-the-art of computerized systems that employ AI and Data Science methods to monitor the health status and provide support to cancer patients managed at home.

OBJECTIVE

Our main objective is to analyze the literature to identify open research challenges that a novel decision support system for cancer patients and clinicians will need to address, point to potential solutions, and provide a list of established best-practices to adopt.

METHODS

We designed a review study, in compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, analyzing studies retrieved from PubMed related to monitoring cancer patients in their home environments via sensors and self-reporting: what data is collected, what are the techniques used to collect data, semantically integrate it, infer the patient's state from it and deliver coaching/behavior change interventions.

RESULTS

Starting from an initial corpus of 819 unique articles, a total of 180 papers were considered in the full-text analysis and 109 were finally included in the review. Our findings are organized and presented in four main sub-topics consisting of data collection, data integration, predictive modeling and patient coaching.

CONCLUSION

Development of modern decision support systems for cancer needs to utilize best practices like the use of validated electronic questionnaires for quality-of-life assessment, adoption of appropriate information modeling standards supplemented by terminologies/ontologies, adherence to FAIR data principles, external validation, stratification of patients in subgroups for better predictive modeling, and adoption of formal behavior change theories. Open research challenges include supporting emotional and social dimensions of well-being, including PROs in predictive modeling, and providing better customization of behavioral interventions for the specific population of cancer patients.

Gene-based mediation analysis in epigenetic studies

Mediation analysis has been a useful tool for investigating the effect of mediators that lie in the path from the independent variable to the outcome. With the increasing dimensionality of mediators such as in (epi)genomics studies, high-dimensional mediation model is needed. In this work, we focus on epigenetic studies with the goal to identify important DNA methylations that act as mediators between an exposure disease outcome. Specifically, we focus on gene-based high-dimensional mediation analysis implemented with kernel principal component analysis to capture potential nonlinear mediation effect. We first review the current high-dimensional mediation models and then propose two gene-based analytical approaches: gene-based high-dimensional mediation analysis based on linearity assumption between mediators and outcome (gHMA-L) and gene-based high-dimensional mediation analysis based on nonlinearity assumption (gHMA-NL). Since the underlying true mediation relationship is unknown in practice, we further propose an omnibus test of gene-based high-dimensional mediation analysis (gHMA-O) by combing gHMA-L and gHMA-NL. Extensive simulation studies show that gHMA-L performs better under the model linear assumption and gHMA-NL does better under the model nonlinear assumption, while gHMA-O is a more powerful and robust method by combining the two. We apply the proposed methods to two datasets to investigate genes whose methylation levels act as important mediators in the relationship: (1) between alcohol consumption and epithelial ovarian cancer risk using data from the Mayo Clinic Ovarian Cancer Case-Control Study and (2) between childhood maltreatment and comorbid post-traumatic stress disorder and depression in adulthood using data from the Gray Trauma Project.

Integrating multi-omics data through deep learning for accurate cancer prognosis prediction

BACKGROUND

Genomic information is nowadays widely used for precise cancer treatments. Since the individual type of omics data only represents a single view that suffers from data noise and bias, multiple types of omics data are required for accurate cancer prognosis prediction. However, it is challenging to effectively integrate multi-omics data due to the large number of redundant variables but relatively small sample size. With the recent progress in deep learning techniques, Autoencoder was used to integrate multi-omics data for extracting representative features. Nevertheless, the generated model is fragile from data noises. Additionally, previous studies usually focused on individual cancer types without making comprehensive tests on pan-cancer. Here, we employed the denoising Autoencoder to get a robust representation of the multi-omics data, and then used the learned representative features to estimate patients' risks.

RESULTS

By applying to 15 cancers from The Cancer Genome Atlas (TCGA), our method was shown to improve the C-index values over previous methods by 6.5% on average. Considering the difficulty to obtain multi-omics data in practice, we further used only mRNA data to fit the estimated risks by training XGboost models, and found the models could achieve an average C-index value of 0.627. As a case study, the breast cancer prognosis prediction model was independently tested on three datasets from the Gene Expression Omnibus (GEO), and shown able to significantly separate high-risk patients from low-risk ones (C-index>0.6, p-values<0.05). Based on the risk subgroups divided by our method, we identified nine prognostic markers highly associated with breast cancer, among which seven genes have been proved by literature review.

CONCLUSION

Our comprehensive tests indicated that we have constructed an accurate and robust framework to integrate multi-omics data for cancer prognosis prediction. Moreover, it is an effective way to discover cancer prognosis-related genes.

An Efficient Multiple Kernel Support Vector Regression Model for Assessing Dry Weight of Hemodialysis Patients

Background:

Dry Weight (DW) is the lowest weight after dialysis, and patients with lower weight usually have symptoms of hypotension and shock. Several clinical-based approaches have been presented to assess the dry weight of hemodialysis patients. However, these traditional methods all depend on special instruments and professional technicians.

Objective:

In order to avoid this limitation, we need to find a machine-independent way to assess dry weight, therefore we collected some clinical influencing characteristic data and constructed a Machine Learning-based (ML) model to predict the dry weight of hemodialysis patients.

Methods::

In this paper, 476 hemodialysis patients' demographic data, anthropometric measurements, and Bioimpedance spectroscopy (BIS) were collected. Among them, these patients' age, sex, Body Mass Index (BMI), Blood Pressure (BP) and Heart Rate (HR) and Years of Dialysis (YD) were closely related to their dry weight. All these relevant data were used to enter the regression equation. Multiple Kernel Support Vector Regression-based on Maximizes the Average Similarity (MKSVRMAS) model was proposed to predict the dry weight of hemodialysis patients.

Result:

The experimental results show that dry weight is positively correlated with BMI and HR. And age, sex, systolic blood pressure, diastolic blood pressure and hemodialysis time are negatively correlated with dry weight. Moreover, the Root Mean Square Error (RMSE) of our model was 1.3817.

Conclusion:

Our proposed model could serve as a viable alternative for dry weight estimation of hemodialysis patients, thus providing a new way for clinical practice. Our proposed model could serve as a viable alternative of dry weight estimation for hemodialysis patients, thus providing a new way for the clinic.

Metabolic Homeostasis in Chronic Helminth Infection Is Sustained by Organ-Specific Metabolic Rewiring

Opisthorchiasis, is a hepatobiliary disease caused by flukes of the trematode family Opisthorchiidae. A chronic form of the disease implies a prolonged coexistence of a host and the parasite. The pathological changes inflicted by the worm to the host's hepatobiliary system are well documented. Yet, the response to the infection also triggers a deep remodeling of the host systemic metabolism reaching a new homeostasis and affecting the organs beyond the worm location. Understanding the metabolic alternation in chronic opisthorchiasis, could help us to pinpoint pathways that underlie infection opening possibilities for the development of more selective treatment strategies. Here, with this report we apply an integrative, multicompartment metabolomics analysis, using multiple biofluids, stool samples and tissue extracts to describe metabolic changes in Opisthorchis felineus infected animals at the chronic stage. We show that the shift in lipid metabolism in the serum, a depletion of the amino acids pool, an alteration of the ketogenic pathways in the jejunum and a suppressed metabolic activity of the spleen are the key features of the metabolic host adaptation at the chronic stage of O. felineus infection. We describe this combination of the metabolic changes as a "metabolically mediated immunosuppressive status of organism" which develops during a chronic infection. This status in combination with other factors (e.g., parasite-derived immunomodulators) might increase risk of infection-related malignancy.

Subtypes identification on heart failure with preserved ejection fraction via network enhancement fusion using multi-omics data

Heart failure with preserved ejection fraction (HFpEF) is associated with multiple etiologic and pathophysiologic factors. HFpEF leads to significant cardiovascular morbidity and mortality. There are various reasons that fail to identify effective therapeutic interventions for HFpEF, primarily due to its clinical heterogeneity causing significant difficulties in determining physiologic and prognostic implications for this syndrome. Thus, identifying clinical subtypes using multi-omics data has great implications for efficient treatment and prognosis of HFpEF patients. Here we proposed to integrate mRNA, DNA methylation and microRNA (miRNA) expression data of HFpEF with a similarity network fusion (SNF) method following a network enhancement (ne-SNF) denoising technique to form a fused network. A spectral clustering method was then used to obtain clusters of patient subtypes. Experiments on HFpEF datasets demonstrated that ne-SNF significantly outperforms single data subtype analysis and other integrated methods. The identified subgroups were shown to have statistically significant differences in survival. Two HFpEF subtypes were defined: a high-risk group (16.8%) and a low-risk group (83.2%). The 5-year mortality rates were 63.3% and 33.0% for the high- and low-risk group, respectively. After adjusting for the effects of clinical covariates, HFpEF patients in the high-risk group were 2.43 times more likely to die than the low-risk group. A total of 157 differentially expressed (DE) mRNAs, 2199 abnormal methylations and 121 DE miRNAs were identified between two subtypes. They were also enriched in many HFpEF-related biological processes or pathways. The ne-SNF method provides a novel pipeline for subtype identification in integrated analysis of multi-omics data.

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.

kernInt: A Kernel Framework for Integrating Supervised and Unsupervised Analyses in Spatio-Temporal Metagenomic Datasets

The advent of next-generation sequencing technologies allowed relative quantification of microbiome communities and their spatial and temporal variation. In recent years, supervised learning (i.e., prediction of a phenotype of interest) from taxonomic abundances has become increasingly common in the microbiome field. However, a gap exists between supervised and classical unsupervised analyses, based on computing ecological dissimilarities for visualization or clustering. Despite this, both approaches face common challenges, like the compositional nature of next-generation sequencing data or the integration of the spatial and temporal dimensions. Here we propose a kernel framework to place on a common ground the unsupervised and supervised microbiome analyses, including the retrieval of microbial signatures (taxa importances). We define two compositional kernels (Aitchison-RBF and compositional linear) and discuss how to transform non-compositional beta-dissimilarity measures into kernels. Spatial data is integrated with multiple kernel learning, while longitudinal data is evaluated by specific kernels. We illustrate our framework through a single point soil dataset, a human dataset with a spatial component, and a previously unpublished longitudinal dataset concerning pig production. The proposed framework and the case studies are freely available in the kernInt package at https://github.com/elies-ramon/kernInt.

Integrating multi-OMICS data through sparse canonical correlation analysis for the prediction of complex traits: a comparison study

Motivation

Recent developments in technology have enabled researchers to collect multiple OMICS datasets for the same individuals. The conventional approach for understanding the relationships between the collected datasets and the complex trait of interest would be through the analysis of each OMIC dataset separately from the rest, or to test for associations between the OMICS datasets. In this work we show that integrating multiple OMICS datasets together, instead of analysing them separately, improves our understanding of their in-between relationships as well as the predictive accuracy for the tested trait. Several approaches have been proposed for the integration of heterogeneous and high-dimensional (p≫n) data, such as OMICS. The sparse variant of canonical correlation analysis (CCA) approach is a promising one that seeks to penalize the canonical variables for producing sparse latent variables while achieving maximal correlation between the datasets. Over the last years, a number of approaches for implementing sparse CCA (sCCA) have been proposed, where they differ on their objective functions, iterative algorithm for obtaining the sparse latent variables and make different assumptions about the original datasets.

Results

Through a comparative study we have explored the performance of the conventional CCA proposed by Parkhomenko et al., penalized matrix decomposition CCA proposed by Witten and Tibshirani and its extension proposed by Suo et al. The aforementioned methods were modified to allow for different penalty functions. Although sCCA is an unsupervised learning approach for understanding of the in-between relationships, we have twisted the problem as a supervised learning one and investigated how the computed latent variables can be used for predicting complex traits. The approaches were extended to allow for multiple (more than two) datasets where the trait was included as one of the input datasets. Both ways have shown improvement over conventional predictive models that include one or multiple datasets.

Availability and implementation

https://github.com/theorod93/sCCA.

Supplementary information

Supplementary data are available at Bioinformatics online.

Artificial Intelligence (AI)-Based Systems Biology Approaches in Multi-Omics Data Analysis of Cancer

Cancer is the manifestation of abnormalities of different physiological processes involving genes, DNAs, RNAs, proteins, and other biomolecules whose profiles are reflected in different omics data types. As these bio-entities are very much correlated, integrative analysis of different types of omics data, multi-omics data, is required to understanding the disease from the tumorigenesis to the disease progression. Artificial intelligence (AI), specifically machine learning algorithms, has the ability to make decisive interpretation of "big"-sized complex data and, hence, appears as the most effective tool for the analysis and understanding of multi-omics data for patient-specific observations. In this review, we have discussed about the recent outcomes of employing AI in multi-omics data analysis of different types of cancer. Based on the research trends and significance in patient treatment, we have primarily focused on the AI-based analysis for determining cancer subtypes, disease prognosis, and therapeutic targets. We have also discussed about AI analysis of some non-canonical types of omics data as they have the capability of playing the determiner role in cancer patient care. Additionally, we have briefly discussed about the data repositories because of their pivotal role in multi-omics data storing, processing, and analysis.

Group-based local adaptive deep multiple kernel learning with lp norm

The deep multiple kernel Learning (DMKL) method has attracted wide attention due to its better classification performance than shallow multiple kernel learning. However, the existing DMKL methods are hard to find suitable global model parameters to improve classification accuracy in numerous datasets and do not take into account inter-class correlation and intra-class diversity. In this paper, we present a group-based local adaptive deep multiple kernel learning (GLDMKL) method with lp norm. Our GLDMKL method can divide samples into multiple groups according to the multiple kernel k-means clustering algorithm. The learning process in each well-grouped local space is exactly adaptive deep multiple kernel learning. And our structure is adaptive, so there is no fixed number of layers. The learning model in each group is trained independently, so the number of layers of the learning model maybe different. In each local space, adapting the model by optimizing the SVM model parameter α and the local kernel weight β in turn and changing the proportion of the base kernel of the combined kernel in each layer by the local kernel weight, and the local kernel weight is constrained by the lp norm to avoid the sparsity of basic kernel. The hyperparameters of the kernel are optimized by the grid search method. Experiments on UCI and Caltech 256 datasets demonstrate that the proposed method is more accurate in classification accuracy than other deep multiple kernel learning methods, especially for datasets with relatively complex data.

Link-HD: a versatile framework to explore and integrate heterogeneous microbial communities

MOTIVATION

We present Link-HD, an approach to integrate multiple datasets. Link-HD is a generalization of 'Structuration des Tableaux A Trois Indices de la Statistique-Analyse Conjointe de Tableaux', a family of methods designed to integrate information from heterogeneous data. Here, we extend the classical approach to deal with broader datasets (e.g. compositional data), methods for variable selection and taxon-set enrichment analysis.

RESULTS

The methodology is demonstrated by integrating rumen microbial communities from cows for which methane yield (CH4y) was individually measured. Our approach reproduces the significant link between rumen microbiota structure and CH4 emission. When analyzing the TARA's ocean data, Link-HD replicates published results, highlighting the relevance of temperature with members of phyla Proteobacteria on the structure and functionality of this ecosystem.

AVAILABILITY AND IMPLEMENTATION

The source code, examples and a complete manual are freely available in GitHub https://github.com/lauzingaretti/LinkHD and in Bioconductor https://bioconductor.org/packages/release/bioc/html/LinkHD.html.

Kernel Fusion Method for Detecting Cancer Subtypes via Selecting Relevant Expression Data

Recently, cancer has been characterized as a heterogeneous disease composed of many different subtypes. Early diagnosis of cancer subtypes is an important study of cancer research, which can be of tremendous help to patients after treatment. In this paper, we first extract a novel dataset, which contains gene expression, miRNA expression, and isoform expression of five cancers from The Cancer Genome Atlas (TCGA). Next, to avoid the effect of noise existing in 60, 483 genes, we select a small number of genes by using LASSO that employs gene expression and survival time of patients. Then, we construct one similarity kernel for each expression data by using Chebyshev distance. And also, We used SKF to fused the three similarity matrix composed of gene, Iso, and miRNA, and finally clustered the fused similarity matrix with spectral clustering. In the experimental results, our method has better P-value in the Cox model than other methods on 10 cancer data from Jiang Dataset and Novel Dataset. We have drawn different survival curves for different cancers and found that some genes play a key role in cancer. For breast cancer, we find out that HSPA2A, RNASE1, CLIC6, and IFITM1 are highly expressed in some specific groups. For lung cancer, we ensure that C4BPA, SESN3, and IRS1 are highly expressed in some specific groups. The code and all supporting data files are available from https://github.com/guofei-tju/Uncovering-Cancer-Subtypes-via-LASSO.

Integrated Multi-Omics Analyses in Oncology: A Review of Machine Learning Methods and Tools

In recent years, high-throughput sequencing technologies provide unprecedented opportunity to depict cancer samples at multiple molecular levels. The integration and analysis of these multi-omics datasets is a crucial and critical step to gain actionable knowledge in a precision medicine framework. This paper explores recent data-driven methodologies that have been developed and applied to respond major challenges of stratified medicine in oncology, including patients' phenotyping, biomarker discovery, and drug repurposing. We systematically retrieved peer-reviewed journals published from 2014 to 2019, select and thoroughly describe the tools presenting the most promising innovations regarding the integration of heterogeneous data, the machine learning methodologies that successfully tackled the complexity of multi-omics data, and the frameworks to deliver actionable results for clinical practice. The review is organized according to the applied methods: Deep learning, Network-based methods, Clustering, Features Extraction, and Transformation, Factorization. We provide an overview of the tools available in each methodological group and underline the relationship among the different categories. Our analysis revealed how multi-omics datasets could be exploited to drive precision oncology, but also current limitations in the development of multi-omics data integration.

Heterogeneous multiple kernel learning for breast cancer outcome evaluation

Background

Breast cancer is one of the common kinds of cancer among women, and it ranks second among all cancers in terms of incidence, after lung cancer. Therefore, it is of great necessity to study the detection methods of breast cancer. Recent research has focused on using gene expression data to predict outcomes, and kernel methods have received a lot of attention regarding the cancer outcome evaluation. However, selecting the appropriate kernels and their parameters still needs further investigation.

Results

We utilized heterogeneous kernels from a specific kernel set including the Hadamard, RBF and linear kernels. The mixed coefficients of the heterogeneous kernel were computed by solving the standard convex quadratic programming problem of the quadratic constraints. The algorithm is named the heterogeneous multiple kernel learning (HMKL). Using the particle swarm optimization (PSO) in HMKL, we selected the kernel parameters, then we employed HMKL to perform the breast cancer outcome evaluation. By testing real-world microarray datasets, the HMKL method outperforms the methods of the random forest, decision tree, GA with Rotation Forest, BFA + RF, SVM and MKL.

Conclusions

On one hand, HMKL is effective for the breast cancer evaluation and can be utilized by physicians to better understand the patient’s condition. On the other hand, HMKL can choose the function and parameters of the kernel. At the same time, this study proves that the Hadamard kernel is effective in HMKL. We hope that HMKL could be applied as a new method to more actual problems.

A U-statistics for integrative analysis of multilayer omics data

MOTIVATION

The emerging multilayer omics data provide unprecedented opportunities for detecting biomarkers that are associated with complex diseases at various molecular levels. However, the high-dimensionality of multiomics data and the complex disease etiologies have brought tremendous analytical challenges.

RESULTS

We developed a U-statistics-based non-parametric framework for the association analysis of multilayer omics data, where consensus and permutation-based weighting schemes are developed to account for various types of disease models. Our proposed method is flexible for analyzing different types of outcomes as it makes no assumptions about their distributions. Moreover, it explicitly accounts for various types of underlying disease models through weighting schemes and thus provides robust performance against them. Through extensive simulations and the application to dataset obtained from the Alzheimer's Disease Neuroimaging Initiatives, we demonstrated that our method outperformed the commonly used kernel regression-based methods.

AVAILABILITY AND IMPLEMENTATION

The R-package is available at https://github.com/YaluWen/Uomic.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Clustering and variable selection evaluation of 13 unsupervised methods for multi-omics data integration

Recent advances in NGS sequencing, microarrays and mass spectrometry for omics data production have enabled the generation and collection of different modalities of high-dimensional molecular data. The integration of multiple omics datasets is a statistical challenge, due to the limited number of individuals, the high number of variables and the heterogeneity of the datasets to integrate. Recently, a lot of tools have been developed to solve the problem of integrating omics data including canonical correlation analysis, matrix factorization and SM. These commonly used techniques aim to analyze simultaneously two or more types of omics. In this article, we compare a panel of 13 unsupervised methods based on these different approaches to integrate various types of multi-omics datasets: iClusterPlus, regularized generalized canonical correlation analysis, sparse generalized canonical correlation analysis, multiple co-inertia analysis (MCIA), integrative-NMF (intNMF), SNF, MoCluster, mixKernel, CIMLR, LRAcluster, ConsensusClustering, PINSPlus and multi-omics factor analysis (MOFA). We evaluate the ability of the methods to recover the subgroups and the variables that drive the clustering on eight benchmarks of simulation. MOFA does not provide any results on these benchmarks. For clustering, SNF, MoCluster, CIMLR, LRAcluster, ConsensusClustering and intNMF provide the best results. For variable selection, MoCluster outperforms the others. However, the performance of the methods seems to depend on the heterogeneity of the datasets (especially for MCIA, intNMF and iClusterPlus). Finally, we apply the methods on three real studies with heterogeneous data and various phenotypes. We conclude that MoCluster is the best method to analyze these omics data. Availability: An R package named CrIMMix is available on GitHub at https://github.com/CNRGH/crimmix to reproduce all the results of this article.

DIABLO: an integrative approach for identifying key molecular drivers from multi-omics assays

MOTIVATION

In the continuously expanding omics era, novel computational and statistical strategies are needed for data integration and identification of biomarkers and molecular signatures. We present Data Integration Analysis for Biomarker discovery using Latent cOmponents (DIABLO), a multi-omics integrative method that seeks for common information across different data types through the selection of a subset of molecular features, while discriminating between multiple phenotypic groups.

RESULTS

Using simulations and benchmark multi-omics studies, we show that DIABLO identifies features with superior biological relevance compared with existing unsupervised integrative methods, while achieving predictive performance comparable to state-of-the-art supervised approaches. DIABLO is versatile, allowing for modular-based analyses and cross-over study designs. In two case studies, DIABLO identified both known and novel multi-omics biomarkers consisting of mRNAs, miRNAs, CpGs, proteins and metabolites.

AVAILABILITY AND IMPLEMENTATION

DIABLO is implemented in the mixOmics R Bioconductor package with functions for parameters' choice and visualization to assist in the interpretation of the integrative analyses, along with tutorials on http://mixomics.org and in our Bioconductor vignette.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.