Types Of Omics Data Research Articles

Unsupervised and supervised discovery of tissue cellular neighborhoods from cell phenotypes.

It is poorly understood how different cells in a tissue organize themselves to support tissue functions. We describe the CytoCommunity algorithm for the identification of tissue cellular neighborhoods (TCNs) based on cell phenotypes and their spatial distributions. CytoCommunity learns a mapping directly from the cell phenotype space to the TCN space using a graph neural network model without intermediate clustering of cell embeddings. By leveraging graph pooling, CytoCommunity enables de novo identification of condition-specific and predictive TCNs under the supervision of sample labels. Using several types of spatial omics data, we demonstrate that CytoCommunity can identify TCNs of variable sizes with substantial improvement over existing methods. By analyzing risk-stratified colorectal and breast cancer data, CytoCommunity revealed new granulocyte-enriched and cancer-associated fibroblast-enriched TCNs specific to high-risk tumors and altered interactions between neoplastic and immune or stromal cells within and between TCNs. CytoCommunity can perform unsupervised and supervised analyses of spatial omics maps and enable the discovery of condition-specific cell-cell communication patterns across spatial scales.

Functional selectivity of Receptor Tyrosine Kinases regulates distinct cellular outputs.

Functional selectivity refers to the activation of differential signalling and cellular outputs downstream of the same membrane-bound receptor when activated by two or more different ligands. Functional selectivity has been described and extensively studied for G-protein Coupled Receptors (GPCRs), leading to specific therapeutic options for dysregulated GPCRs functions. However, studies regarding the functional selectivity of Receptor Tyrosine Kinases (RTKs) remain sparse. Here, we will summarize recent data about RTK functional selectivity focusing on how the nature and the amount of RTK ligands and the crosstalk of RTKs with other membrane proteins regulate the specificity of RTK signalling. In addition, we will discuss how structural changes in RTKs upon ligand binding affects selective signalling pathways. Much remains to be known about the integration of different signals affecting RTK signalling specificity to orchestrate long-term cellular outcomes. Recent advancements in omics, specifically quantitative phosphoproteomics, and in systems biology methods to study, model and integrate different types of large-scale omics data have increased our ability to compare several signals affecting RTK functional selectivity in a global, system-wide fashion. We will discuss how such methods facilitate the exploration of important signalling hubs and enable data-driven predictions aiming at improving the efficacy of therapeutics for diseases like cancer, where redundant RTK signalling pathways often compromise treatment efficacy.

GNOMO2: a comprehensive and modular pipeline for integrated multi-omics analyses of microbiomes.

In recent years, omics technologies have offered an exceptional chance to gain a deeper insight into the structural and functional characteristics of microbial communities. As a result, there is a growing demand for user-friendly, reproducible, and versatile bioinformatic tools that can effectively harness multi-omics data to provide a holistic understanding of microbiomes. Previously, we introduced gNOMO, a bioinformatic pipeline tailored to analyze microbiome multi-omics data in an integrative manner. In response to the evolving demands within the microbiome field and the growing necessity for integrated multi-omics data analysis, we have implemented substantial enhancements to the gNOMO pipeline. Here, we present gNOMO2, a comprehensive and modular pipeline that can seamlessly manage various omics combinations, ranging from 2 to 4 distinct omics data types, including 16S ribosomal RNA (rRNA) gene amplicon sequencing, metagenomics, metatranscriptomics, and metaproteomics. Furthermore, gNOMO2 features a specialized module for processing 16S rRNA gene amplicon sequencing data to create a protein database suitable for metaproteomics investigations. Moreover, it incorporates new differential abundance, integration, and visualization approaches, enhancing the toolkit for a more insightful analysis of microbiomes. The functionality of these new features is showcased through the use of 4 microbiome multi-omics datasets encompassing various ecosystems and omics combinations. gNOMO2 not only replicated most of the primary findings from these studies but also offered further valuable perspectives. gNOMO2 enables the thorough integration of taxonomic and functional analyses in microbiome multi-omics data, offering novel insights in both host-associated and free-living microbiome research. gNOMO2 is available freely at https://github.com/muzafferarikan/gNOMO2.

Comparison of multiple modalities for drug response prediction with learning curves using neural networks and XGBoost.

Anti-cancer drug response prediction is a central problem within stratified medicine. Transcriptomic profiles of cancer cell lines are typically used for drug response prediction, but we hypothesize that proteomics or phosphoproteomics might be more suitable as they give a more direct insight into cellular processes. However, there has not yet been a systematic comparison between all three of these datatypes using consistent evaluation criteria. Due to the limited number of cell lines with phosphoproteomics profiles we use learning curves, a plot of predictive performance as a function of dataset size, to compare the current performance and predict the future performance of the three omics datasets with more data. We use neural networks and XGBoost and compare them against a simple rule-based benchmark. We show that phosphoproteomics slightly outperforms RNA-seq and proteomics using the 38 cell lines with profiles of all three omics data types. Furthermore, using the 877 cell lines with proteomics and RNA-seq profiles, we show that RNA-seq slightly outperforms proteomics. With the learning curves we predict that the mean squared error using the phosphoproteomics dataset would decrease by if a dataset of the same size as the proteomics/transcriptomics was collected. For the cell lines with proteomics and RNA-seq profiles the learning curves reveal that for smaller dataset sizes neural networks outperform XGBoost and vice versa for larger datasets. Furthermore, the trajectory of the XGBoost curve suggests that it will improve faster than the neural networks as more data are collected. See https://github.com/Nik-BB/Learning-curves-for-DRP for the code used.

BioMOBS: A multi-omics visual analytics workflow for biomolecular insight generation

One of the challenges in multi-omics data analysis for precision medicine is the efficient exploration of undiscovered molecular interactions in disease processes. We present BioMOBS, a workflow consisting of two data visualization tools integrated with an open-source molecular information database to perform clinically relevant analyses (https://github.com/driesheylen123/BioMOBS). We performed exploratory pathway analysis with BioMOBS and demonstrate its ability to generate relevant molecular hypotheses, by reproducing recent findings in type 2 diabetes UK biobank data. The central visualisation tool, where data-driven and literature-based findings can be integrated, is available within the github link as well. BioMOBS is a workflow that leverages information from multiple data-driven interactive analyses and visually integrates it with established pathway knowledge. The demonstrated use cases place trust in the usage of BioMOBS as a procedure to offer clinically relevant insights in disease pathway analyses on various types of omics data.

Poly-omic risk scores predict inflammatory bowel disease diagnosis.

Inflammatory bowel disease (IBD) is characterized by complex etiology and a disrupted colonic ecosystem. We provide a framework for the analysis of multi-omic data, which we apply to study the gut ecosystem in IBD. Specifically, we train and validate models using data on the metagenome, metatranscriptome, virome, and metabolome from the Human Microbiome Project 2 IBD multi-omic database, with 1,785 repeated samples from 130 individuals (103 cases and 27 controls). After splitting the participants into training and testing groups, we used mixed-effects least absolute shrinkage and selection operator regression to select features for each omic. These features, with demographic covariates, were used to generate separate single-omic prediction scores. All four single-omic scores were then combined into a final regression to assess the relative importance of the individual omics and the predictive benefits when considered together. We identified several species, pathways, and metabolites known to be associated with IBD risk, and we explored the connections between data sets. Individually, metabolomic and viromic scores were more predictive than metagenomics or metatranscriptomics, and when all four scores were combined, we predicted disease diagnosis with a Nagelkerke's R2 of 0.46 and an area under the curve of 0.80 (95% confidence interval: 0.63, 0.98). Our work supports that some single-omic models for complex traits are more predictive than others, that incorporating multiple omic data sets may improve prediction, and that each omic data type provides a combination of unique and redundant information. This modeling framework can be extended to other complex traits and multi-omic data sets.IMPORTANCEComplex traits are characterized by many biological and environmental factors, such that multi-omic data sets are well-positioned to help us understand their underlying etiologies. We applied a prediction framework across multiple omics (metagenomics, metatranscriptomics, metabolomics, and viromics) from the gut ecosystem to predict inflammatory bowel disease (IBD) diagnosis. The predicted scores from our models highlighted key features and allowed us to compare the relative utility of each omic data set in single-omic versus multi-omic models. Our results emphasized the importance of metabolomics and viromics over metagenomics and metatranscriptomics for predicting IBD status. The greater predictive capability of metabolomics and viromics is likely because these omics serve as markers of lifestyle factors such as diet. This study provides a modeling framework for multi-omic data, and our results show the utility of combining multiple omic data types to disentangle complex disease etiologies and biological signatures.

Integrating DNA methylation and gene expression data in a single gene network using the iNETgrate package

Analyzing different omics data types independently is often too restrictive to allow for detection of subtle, but consistent, variations that are coherently supported based upon different assays. Integrating multi-omics data in one model can increase statistical power. However, designing such a model is challenging because different omics are measured at different levels. We developed the iNETgrate package (https://bioconductor.org/packages/iNETgrate/) that efficiently integrates transcriptome and DNA methylation data in a single gene network. Applying iNETgrate on five independent datasets improved prognostication compared to common clinical gold standards and a patient similarity network approach.

Integrated omics analysis of coronary artery calcifications and myocardial infarction: the Framingham Heart Study

Gene function can be described using various measures. We integrated association studies of three types of omics data to provide insights into the pathophysiology of subclinical coronary disease and myocardial infarction (MI). Using multivariable regression models, we associated: (1) single nucleotide polymorphism, (2) DNA methylation, and (3) gene expression with coronary artery calcification (CAC) scores and MI. Among 3106 participants of the Framingham Heart Study, 65 (2.1%) had prevalent MI and 60 (1.9%) had incident MI, median CAC value was 67.8 [IQR 10.8, 274.9], and 1403 (45.2%) had CAC scores > 0 (prevalent CAC). Prevalent CAC was associated with AHRR (linked to smoking) and EXOC3 (affecting platelet function and promoting hemostasis). CAC score was associated with VWA1 (extracellular matrix protein associated with cartilage structure in endomysium). For prevalent MI we identified FYTTD1 (down-regulated in familial hypercholesterolemia) and PINK1 (linked to cardiac tissue homeostasis and ischemia–reperfusion injury). Incident MI was associated with IRX3 (enhancing browning of white adipose tissue) and STXBP3 (controlling trafficking of glucose transporter type 4 to plasma). Using an integrative trans-omics approach, we identified both putatively novel and known candidate genes associated with CAC and MI. Replication of findings is warranted.

Deep trans‐omic network fusion for altered functional interactions underlying Alzheimer’s Disease

AbstractBackgroundMulti‐omic data like genotype, gene expression and protein expression have been increasingly explored in post‐GWAS era to interpret GWAS findings and to gain more insight of the Alzheimer’s disease (AD) mechanism. However, each ‐omics data type is usually examined individually and identified genetic variations, genes and proteins are not necessarily functionally related.MethodWe used GWAS genotype, RNA‐Seq gene expression, and protein expression data from 133 subjects of ROS/MAP Project for original study and 121 subjects of Mount Sinai Brain Bank (MSBB) for replication (Fig. 1a). The multi‐omic data pre‐processing steps were shown in Fig. 1b. We proposed a new interpretable deep neural network MoFNet, extended from Varmole [1], to jointly model the prior knowledge of functional interactions using ROS/MAP cohort (Fig. 1c). It aimed to identify a subnetwork of functional interactions from prior knowledge that are both predictive of AD and evidenced by multi‐omic data. Particularly, prior functional interaction network was embedded into the architecture of MoFNet in a way that it resembles the information flow from DNA to gene and protein.ResultThe proposed model MoFNet significantly outperformed all other state‐of‐art classifiers when evaluated using multi‐omic data from ROS/MAP cohort (Table 1). It yielded three major multi‐omic sub‐networks related to innate immune system, clearance of mis‐folded proteins, and neurotransmitter release respectively (Fig. 2a). One subnetwork includes all the major members of the SNARE complex, an essential mediator of synaptic vesicle fusion. Majority of our identified genes/proteins are related to synaptic activities in neuronal, astrocyte and microglial cells. Differential expression analysis show MoFNet returned more genes and proteins due to functional connections (Fig. 2b). Around 50% of these findings were replicated in another independent cohort (MSBB).ConclusionOur identified gene/proteins are highly related to synaptic vesicle function. Altered regulation or expression of these genes/proteins could cause disruption in neuron‐neuron or neuron‐glia cross talk and further lead to neuronal and synapse loss in AD. Further investigation of these identified genes/proteins could possibly help decipher the mechanisms underlying synaptic dysfunction in AD, and ultimately inform therapeutic strategies to modify AD progression in the early stage. [1] Nguyen et al., Bioinformatics, 2021.

Identify Alzheimer’s disease subtypes and markers from multi‐omic data of human brain and blood with a subspace merging algorithm

AbstractBackgroundAlzheimer’s disease (AD) is a highly heterogeneous disease with different disease trajectory, brain pathological changes, and risk factors. Identifying subtypes of AD can have greatly impact AD diagnosis, treatment, and disease management. Our goal is to identify subtypes of AD by integrating multiple types of omics data from AD patients’ brain samples and blood samples.MethodWe applied a subspace merging algorithm on AD patient brain samples with matched transcriptomic, DNA methylation, and proteomics data collected from the ROSMAP study. This algorithm merges patient graphs generated from these three datasets on a Grassmann manifold followed by spectral clustering. Differential gene expression and pathway analysis were applied to establish the gene signatures between the subtypes (patient clusters) and to the transcriptomic data of the peripheral blood monocyte (PBMC) from the matching patients to identify possible blood markers.ResultOur analysis identified two patient clusters between which the cognitive test scores or the degree of AD pathology are significantly different. Differentially expressed genes between the two groups were identified from both brain and blood samples. Gene set enrichment analysis identified a group of genes significantly enriched with synaptic functions in the brain samples. The Ingenuity Pathway Analysis was used to examine any connections between the significantly differentially expressed genes in the brain samples with the ones identified from the PBMC samples. The low density lipoprotein receptor (LDLR) gene, which was an APOE receptor observed from the blood sample is connected with 12 genes from the brain sample. The results suggested that LDLR could be a novel blood biomarker for AD subtyping.ConclusionThe subspace merging algorithm integrated multimodal omics data from the patients and successfully identified two clusters with distinct clinical progression. Differential expression analysis identified 388 significant genes from the brain samples and 18 from the PBMC samples. The pathway analysis indicated that LDLR could be a novel blood biomarker for AD subtyping. Future work will focus on validating LDLR as a candidate blood marker for AD subtyping using other public datasets with similar study design. The clinical relevance and molecular mechanism basis for the findings will also be investigated.

XL1R-Net: Explainable AI-driven improved [formula omitted]-regularized deep neural architecture for NSCLC biomarker identification

Background and Objective:Non-small cell lung cancer (NSCLC) exhibits intrinsic molecular heterogeneity, primarily driven by the mutation of specific biomarkers. Identification of these biomarkers would assist not only in distinguishing NSCLC into its major subtypes — Adenocarcinoma and Squamous Cell Carcinoma, but also in developing targeted therapy. Medical practitioners use one or more types of omic data to identify these biomarkers, copy number variation (CNV) being one such type. CNV provides a measure of genomic instability, which is considered a hallmark of carcinoma. However, the CNV data has not received much attention for biomarker identification. This paper aims to identify biomarkers for NSCLC using CNV data. Methods:An eXplainable AI (XAI)-driven L1-regularized deep learning architecture, XL1R-Net, is proposed that introduces a novel modification of the standard L1-regularized gradient descent algorithm to arrive at an improved deep neural classifier for NSCLC subtyping. Further, XAI-based feature identification has been used to leverage the trained classifier to uncover a set of twenty NCSLC-relevant biomarkers. Results:The identified biomarkers are evaluated based on their classification performance and clinical relevance. Using Multilayer Perceptron (MLP)-based model, a classification accuracy of 84.95% using 10-fold cross-validation is achieved. Moreover, the statistical significance test on the classification performance also revealed the superiority of the MLP model over the competitive machine learning models. Further, the publicly available Drug–Gene Interaction Database reveals twelve of the identified biomarkers as potentially druggable. The K–M Plotter tool was used to verify eighteen of the identified biomarkers with a high probability of predicting NSCLC patients’ likelihood of survival. While nine of the identified biomarkers confirm the recent literature, five find mention in the OncoKB Gene List. Conclusion:A set of seven novel biomarkers that have not been reported in the literature could be investigated for their potential contribution towards NSCLC therapy. Given NSCLC’s genetic diversity, using only one omics data type may not adequately capture the tumor’s complexity. Multiomics data and its integration with other sources will be examined in the future to better understand NSCLC heterogeneity.

DriverDBv4: a multi-omics integration database for cancer driver gene research.

Advancements in high-throughput technology offer researchers an extensive range of multi-omics data that provide deep insights into the complex landscape of cancer biology. However, traditional statistical models and databases are inadequate to interpret these high-dimensional data within a multi-omics framework. To address this limitation, we introduce DriverDBv4, an updated iteration of the DriverDB cancer driver gene database (http://driverdb.bioinfomics.org/). This updated version offers several significant enhancements: (i) an increase in the number of cohorts from 33 to 70, encompassing approximately 24 000 samples; (ii) inclusion of proteomics data, augmenting the existing types of omics data and thus expanding the analytical scope; (iii) implementation of multiple multi-omics algorithms for identification of cancer drivers; (iv) new visualization features designed to succinctly summarize high-context data and redesigned existing sections to accommodate the increased volume of datasets and (v) two new functions in Customized Analysis, specifically designed for multi-omics driver identification and subgroup expression analysis. DriverDBv4 facilitates comprehensive interpretation of multi-omics data across diverse cancer types, thereby enriching the understanding of cancer heterogeneity and aiding in the development of personalized clinical approaches. The database is designed to foster a more nuanced understanding of the multi-faceted nature of cancer.

Batch normalization followed by merging is powerful for phenotype prediction integrating multiple heterogeneous studies.

Heterogeneity in different genomic studies compromises the performance of machine learning models in cross-study phenotype predictions. Overcoming heterogeneity when incorporating different studies in terms of phenotype prediction is a challenging and critical step for developing machine learning algorithms with reproducible prediction performance on independent datasets. We investigated the best approaches to integrate different studies of the same type of omics data under a variety of different heterogeneities. We developed a comprehensive workflow to simulate a variety of different types of heterogeneity and evaluate the performances of different integration methods together with batch normalization by using ComBat. We also demonstrated the results through realistic applications on six colorectal cancer (CRC) metagenomic studies and six tuberculosis (TB) gene expression studies, respectively. We showed that heterogeneity in different genomic studies can markedly negatively impact the machine learning classifier's reproducibility. ComBat normalization improved the prediction performance of machine learning classifier when heterogeneous populations are present, and could successfully remove batch effects within the same population. We also showed that the machine learning classifier's prediction accuracy can be markedly decreased as the underlying disease model became more different in training and test populations. Comparing different merging and integration methods, we found that merging and integration methods can outperform each other in different scenarios. In the realistic applications, we observed that the prediction accuracy improved when applying ComBat normalization with merging or integration methods in both CRC and TB studies. We illustrated that batch normalization is essential for mitigating both population differences of different studies and batch effects. We also showed that both merging strategy and integration methods can achieve good performances when combined with batch normalization. In addition, we explored the potential of boosting phenotype prediction performance by rank aggregation methods and showed that rank aggregation methods had similar performance as other ensemble learning approaches.

Enablers and challenges of spatial omics, a melting pot of technologies.

Spatial omics has emerged as a rapidly growing and fruitful field with hundreds of publications presenting novel methods for obtaining spatially resolved information for any omics data type on spatial scales ranging from subcellular to organismal. From a technology development perspective, spatial omics is a highly interdisciplinary field that integrates imaging and omics, spatial and molecular analyses, sequencing and mass spectrometry, and image analysis and bioinformatics. The emergence of this field has not only opened a window into spatial biology, but also created multiple novel opportunities, questions, and challenges for method developers. Here, we provide the perspective of technology developers on what makes the spatial omics field unique. After providing a brief overview of the state of the art, we discuss technological enablers and challenges and present our vision about the future applications and impact of this melting pot.

Integration of incomplete multi-omics data using Knowledge Distillation and Supervised Variational Autoencoders for disease progression prediction

Objective:The rapid advancement of high-throughput technologies in the biomedical field has resulted in the accumulation of diverse omics data types, such as mRNA expression, DNA methylation, and microRNA expression, for studying various diseases. Integrating these multi-omics datasets enables a comprehensive understanding of the molecular basis of cancer and facilitates accurate prediction of disease progression. Methods:However, conventional approaches face challenges due to the dimensionality curse problem. This paper introduces a novel framework called Knowledge Distillation and Supervised Variational AutoEncoders utilizing View Correlation Discovery Network (KD-SVAE-VCDN) to address the integration of high-dimensional multi-omics data with limited common samples. Through our experimental evaluation, we demonstrate that the proposed KD-SVAE-VCDN architecture accurately predicts the progression of breast and kidney carcinoma by effectively classifying patients as long- or short-term survivors. Furthermore, our approach outperforms other state-of-the-art multi-omics integration models. Results:Our findings highlight the efficacy of the KD-SVAE-VCDN architecture in predicting the disease progression of breast and kidney carcinoma. By enabling the classification of patients based on survival outcomes, our model contributes to personalized and targeted treatments. The favorable performance of our approach in comparison to several existing models suggests its potential to contribute to the advancement of cancer understanding and management. Conclusion:The development of a robust predictive model capable of accurately forecasting disease progression at the time of diagnosis holds immense promise for advancing personalized medicine. By leveraging multi-omics data integration, our proposed KD-SVAE-VCDN framework offers an effective solution to this challenge, paving the way for more precise and tailored treatment strategies for patients with different types of cancer.

Multi-Omics Revealed Peanut Root Metabolism Regulated by Exogenous Calcium under Salt Stress.

High salinity severely inhibits plant seedling root development and metabolism. Although plant salt tolerance can be improved by exogenous calcium supplementation, the metabolism molecular mechanisms involved remain unclear. In this study, we integrated three types of omics data (transcriptome, metabolome, and phytohormone absolute quantification) to analyze the metabolic profiles of peanut seedling roots as regulated by exogenous calcium under salt stress. (1) exogenous calcium supplementation enhanced the allocation of carbohydrates to the TCA cycle and plant cell wall biosynthesis rather than the shikimate pathway influenced by up-regulating the gene expression of antioxidant enzymes under salt stress; (2) exogenous calcium induced further ABA accumulation under salt stress by up-regulating the gene expression of ABA biosynthesis key enzymes AAO2 and AAO3 while down-regulating ABA glycosylation enzyme UGT71C5 expression; (3) exogenous calcium supplementation under salt stress restored the trans-zeatin absolute content to unstressed levels while inhibiting the root cis-zeatin biosynthesis.

Integrated multi-omics analysis of brain aging in female nonhuman primates reveals altered signaling pathways relevant to age-related disorders

The prefrontal cortex (PFC) has been implicated as a key brain region responsible for age-related cognitive decline. Little is known about aging-related molecular changes in PFC that may mediate these effects. To date, no studies have used untargeted discovery methods with integrated analyses to determine PFC molecular changes in healthy female primates. We quantified PFC changes associated with healthy aging in female baboons by integrating multiple omics data types (transcriptomics, proteomics, metabolomics) from samples across the adult age span. Our integrated omics approach using unbiased weighted gene co-expression network analysis to integrate data and treat age as a continuous variable, revealed highly interconnected known and novel pathways associated with PFC aging. We found Gamma-aminobutyric acid (GABA) tissue content associated with these signaling pathways, providing 1 potential biomarker to assess PFC changes with age. These highly coordinated pathway changes during aging may represent early steps for aging-related decline in PFC functions, such as learning and memory, and provide potential biomarkers to assess cognitive status in humans.

Multiomics: A user-friendly multi-omics data harmonisation R pipeline

Data from multiple omics layers of a biological system is growing in quantity, heterogeneity and dimensionality. Simultaneous multi-omics data integration is of immense interest to researchers as it has potential to unlock previously hidden biomolecular relationships leading to early diagnosis, prognosis, and expedited treatments. Many tools for multi-omics data integration are developed. However, these tools are often restricted to highly specific experimental designs, types of omics data, and specific data formats. A major limitation of the field is the lack of a pipeline that can accept data in unrefined form to preserve maximum biology in an individual dataset prior to integration. We fill this gap by developing a flexible, generic multi-omics pipeline called multiomics, to facilitate general-purpose data exploration and analysis of heterogeneous data. The pipeline takes unrefined multi-omics data as input, sample information and user-specified parameters to generate a list of output plots and data tables for quality control and downstream analysis. We have demonstrated its application on a sepsis case study. We enabled limited checkpointing functionality where intermediate output is staged to allow continuation after errors or interruptions in the pipeline and generate a script for reproducing the analysis to improve reproducibility. Our pipeline can be installed as an R package or manually from the git repository, and is accompanied by detailed documentation with walkthroughs on three case studies.

Integration of multi-omics data using adaptive graph learning and attention mechanism for patient classification and biomarker identification

With the rapid development and accumulation of high-throughput sequencing technology and omics data, many studies have conducted a more comprehensive understanding of human diseases from a multi-omics perspective. Meanwhile, graph-based methods have been widely used to process multi-omics data due to its powerful expressive ability. However, most existing graph-based methods utilize fixed graphs to learn sample embedding representations, which often leads to sub-optimal results. Furthermore, treating embedding representations of different omics equally usually cannot obtain more reasonable integrated information. In addition, the complex correlation between omics is not fully taken into account. To this end, we propose an end-to-end interpretable multi-omics integration method, named MOGLAM, for disease classification prediction. Dynamic graph convolutional network with feature selection is first utilized to obtain higher quality omic-specific embedding information by adaptively learning the graph structure and discover important biomarkers. Then, multi-omics attention mechanism is applied to adaptively weight the embedding representations of different omics, thereby obtaining more reasonable integrated information. Finally, we propose omic-integrated representation learning to capture complex common and complementary information between omics while performing multi-omics integration. Experimental results on three datasets show that MOGLAM achieves superior performance than other state-of-the-art multi-omics integration methods. Moreover, MOGLAM can identify important biomarkers from different omics data types in an end-to-end manner.

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.