Types Of Omics Data Research Articles

A subnetwork-based framework for prioritizing and evaluating prognostic gene modules from cancer transcriptome data

Cancer prognosis prediction is critical to the clinical decision-making process. Currently, the high availability of transcriptome datasets allows us to extract the gene modules with promising prognostic values. However, the biomarker identification is greatly challenged by tumor and patient heterogeneity. In this study, a framework of three subnetwork-based strategies is presented, incorporating hypothesis-driven, data-driven, and literature-based methods with informative visualization to prioritize candidate genes. By applying the proposed approaches to a head and neck squamous cell cancer (HNSCC) transcriptome dataset, we successfully identified multiple HNSCC-specific gene modules with improved prognostic values and mechanism information compared with the standard gene panel selection methods. The proposed framework is general and can be applied to any type of omics data. Overall, the study demonstrates and supports the use of the subnetwork-based approach for distilling reliable and biologically meaningful prognostic factors.

Advances in fermented foods revealed by multi-omics: A new direction toward precisely clarifying the roles of microorganisms.

Fermented foods generally comprise a complex micro-ecosystem with beneficial microbiota, functional products, and special flavors and qualities that are welcomed globally. Single-omics analysis allows for a comprehensive characterization of the main microbial factors influencing the function, flavor, and quality of fermented foods. However, the species, relative abundance, viability, growth patterns, and metabolic processes of microorganisms vary with changes in processing and environmental conditions during fermentation. Furthermore, the mechanisms underlying the complex interaction among microorganisms are still difficult to completely understand and analyze. Recently, multi-omics analysis and the integration of multiple types of omics data allowed researchers to more comprehensively explore microbial communities and understand the precise relationship between fermented foods and their functions, flavors, and qualities. Multi-omics approaches might help clarify the mechanisms underpinning the fermentation processes, metabolites, and functional components of these communities. This review clarified the recent advances in the roles of microorganisms in fermented foods based on multi-omics data. Current research achievements may allow for the precise control of the whole industrial processing technology of fermented foods, meeting consumers' expectations of healthy products.

Deep learning and multi-omics approach to predict drug responses in cancer

BackgroundCancers are genetically heterogeneous, so anticancer drugs show varying degrees of effectiveness on patients due to their differing genetic profiles. Knowing patient’s responses to numerous cancer drugs are needed for personalized treatment for cancer. By using molecular profiles of cancer cell lines available from Cancer Cell Line Encyclopedia (CCLE) and anticancer drug responses available in the Genomics of Drug Sensitivity in Cancer (GDSC), we will build computational models to predict anticancer drug responses from molecular features.ResultsWe propose a novel deep neural network model that integrates multi-omics data available as gene expressions, copy number variations, gene mutations, reverse phase protein array expressions, and metabolomics expressions, in order to predict cellular responses to known anti-cancer drugs. We employ a novel graph embedding layer that incorporates interactome data as prior information for prediction. Moreover, we propose a novel attention layer that effectively combines different omics features, taking their interactions into account. The network outperformed feedforward neural networks and reported 0.90 for R^2 values for prediction of drug responses from cancer cell lines data available in CCLE and GDSC.ConclusionThe outstanding results of our experiments demonstrate that the proposed method is capable of capturing the interactions of genes and proteins, and integrating multi-omics features effectively. Furthermore, both the results of ablation studies and the investigations of the attention layer imply that gene mutation has a greater influence on the prediction of drug responses than other omics data types. Therefore, we conclude that our approach can not only predict the anti-cancer drug response precisely but also provides insights into reaction mechanisms of cancer cell lines and drugs as well.

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.

Comprehensive analysis of TCGA data reveals correlation between DNA methylation and alternative splicing

The effect of DNA methylation on the regulation of gene expression has been extensively discussed in the literature. However, the potential association between DNA methylation and alternative splicing is not understood well. In this study, we integrated multiple omics data types from The Cancer Genome Atlas (TCGA) and systematically examined the relationship between DNA methylation and alternative splicing. Using the methylation data and exon expression data, we identified many CpG sites significantly associated with exon expression in various types of cancers. We further observed that the direction and strength of significant CpG-exon correlation tended to be consistent across different cancer contexts, indicating that some CpG-exon correlation patterns reflect fundamental biological mechanisms that transcend tissue- and cancer- types. We also discovered that CpG sites correlated with exon expressions were more likely to be associated with patient survival outcomes compared to CpG sites that did not correlate with exon expressions. Furthermore, we found that CpG sites were more strongly correlated with exon expression than expression of isoforms harboring the corresponding exons. This observation suggests that a major effect of CpG methylation on alternative splicing may be related to the inclusion or exclusion of exons, which subsequently impacts the relative usage of various isoforms. Overall, our study revealed correlation patterns between DNA methylation and alternative splicing, which provides new insights into the role of methylation in the transcriptional process.

Systems biology reveals anatabine to be an NRF2 activator.

Anatabine, an alkaloid present in plants of the So lanaceae family (including tobacco and eggplant), has been shown to ameliorate chronic inflammatory conditions in mouse models, such as Alzheimer's disease, Hashimoto's thyroiditis, multiple sclerosis, and intestinal inflammation. However, the mechanisms of action of anatabine remain unclear. To understand the impact of anatabine on cellular systems and identify the molecular pathways that are perturbed, we designed a study to examine the concentration-dependent effects of anatabine on various cell types by using a systems pharmacology approach. The resulting dataset, consisting of measurements of various omics data types at different time points, was analyzed by using multiple computational techniques. To identify concentration-dependent activated pathways, we performed linear modeling followed by gene set enrichment. To predict the functional partners of anatabine and the involved pathways, we harnessed the LINCS L1000 dataset's wealth of information and implemented integer linear programming on directed graphs, respectively. Finally, we experimentally verified our key computational predictions. Using an appropriate luciferase reporter cell system, we were able to demonstrate that anatabine treatment results in NRF2 (nuclear factor-erythroid factor 2-related factor 2) translocation, and our systematic phosphoproteomic assays showed that anatabine treatment results in activation of MAPK signaling. While there are certain areas to be explored in deciphering the exact anti-inflammatory mechanisms of action of anatabine and other NRF2 activators, we believe that anatabine constitutes an interesting molecule for its therapeutic potential in NRF2-related diseases.

Abstract A038: High-dimensional, multi-omics analyses of proteins, metabolites, transcripts, and genes enable biomarker discovery in early- and late-stage pancreatic cancer

Abstract Pancreatic cancer is the third leading cause of cancer-related deaths in the United States. Disease biomarkers quantified from blood-based assays may help reduce mortality by enabling early detection, treatment selection, or response and resistance assessment. PrognomiQ has developed a multi-omics assay and analysis platform that comprehensively profiles blood samples to detect proteins, metabolites, lipids, mRNA, miRNA, cfDNA fragments, and methylation at CpG sites. This platform can provide deep insights into the biology of pancreatic cancer and could enable the development of high sensitivity and specificity tests for the early detection of pancreatic cancer. We conducted a case-control study comprising 196 subjects: 92 with untreated pancreatic cancer and 104 matched controls without pancreatic cancer. For each subject, blood was collected in assay-specific tubes and processed to provide 7 different `omics readouts. cfDNA and mRNA were isolated from samples and assayed following standard NGS protocols. cfDNA fragments were processed to estimate fragment-length disorder and copy-number variation along with CpG site methylation. In addition, targeted and untargeted LCMS were used to detect and quantify proteins, metabolites, and lipids. After normalization, non-parametric univariate analyses of cases versus controls were performed to identify differentially abundant features on all available samples for each assay. Unsupervised learning was used to investigate the separation of subjects into groups based on disease status for the subset of 157 subjects for which complete data on all 7 readouts were available. We detected 2,812 proteins, 811 lipids, 373 metabolites, and 110,864 mRNA transcripts in all samples where data for each assay was available. Of these, 275 proteins, 232 lipids, 49 metabolites, and 3385 mRNA transcripts were significantly different (FWER < 0.05) in cases versus controls. From cfDNA data, we identified 35 non-contiguous genomic regions associated with fragment-length disorder, 557 with copy-number variation, and 5 with multiple, differentially methylated CpGs (FWER < 0.05) that aggregately span 307 protein-coding genes; of these, the overlap with the differentially expressed proteins included E-cadherin (tumor suppressor) and N-cadherin (involved in epithelial-to-mesenchymal transition). Statistically significant genes and proteins were found to be associated with processes including Wnt signaling, regulation of focal adhesion assembly, and actin cytoskeleton organization. Multi-omics, unsupervised learning showed separation of early- and late-stage cases and controls. High-dimensional bioinformatics analyses systematically decomposed each `omics data type into joint and orthogonal components associated with pancreatic cancer. Ongoing multivariate analyses, including supervised machine learning, will further elucidate the biology of pancreatic cancer development, and serve as the foundation for high-sensitivity blood tests for the early detection and monitoring of pancreatic cancer. Citation Format: Ehdieh Khaledian, Preethi Prasad, John Blume, Ghristine Bundalian, Connie Chao-Shern, Jinlyung Choi, Rea Cuaresma, Jared Deyarmin, Jun Heok Jang, Manoj Khadka, Thidar Khin, Yuya Kodama, Ajinkya Kokate, Joon-Yong Lee, Manway Liu, Nithya Mudaliar, Madhuvanthi Ramaiah, Saividya Ramaswamy, Peter Spiro, Kavya Swaminathan, Preston Williams, Mi Yang, James Yee, Brian Young, Robert Zawada, Susan Zhang, Chinmay Belthangady, Bruce Wilcox, Philip Ma. High-dimensional, multi-omics analyses of proteins, metabolites, transcripts, and genes enable biomarker discovery in early- and late-stage pancreatic cancer [abstract]. In: Proceedings of the AACR Special Conference on Pancreatic Cancer; 2022 Sep 13-16; Boston, MA. Philadelphia (PA): AACR; Cancer Res 2022;82(22 Suppl):Abstract nr A038.

Computational approaches for network-based integrative multi-omics analysis.

Advances in omics technologies allow for holistic studies into biological systems. These studies rely on integrative data analysis techniques to obtain a comprehensive view of the dynamics of cellular processes, and molecular mechanisms. Network-based integrative approaches have revolutionized multi-omics analysis by providing the framework to represent interactions between multiple different omics-layers in a graph, which may faithfully reflect the molecular wiring in a cell. Here we review network-based multi-omics/multi-modal integrative analytical approaches. We classify these approaches according to the type of omics data supported, the methods and/or algorithms implemented, their node and/or edge weighting components, and their ability to identify key nodes and subnetworks. We show how these approaches can be used to identify biomarkers, disease subtypes, crosstalk, causality, and molecular drivers of physiological and pathological mechanisms. We provide insight into the most appropriate methods and tools for research questions as showcased around the aetiology and treatment of COVID-19 that can be informed by multi-omics data integration. We conclude with an overview of challenges associated with multi-omics network-based analysis, such as reproducibility, heterogeneity, (biological) interpretability of the results, and we highlight some future directions for network-based integration.

Leveraging omics data to boost the power of genome-wide association studies.

SummaryGenome-wide association studies (GWASs) have successfully identified many genetic variants and risk loci for complex traits and common diseases in the last 15 years. However, these identified variants, in general, can explain only a small to moderate proportion of the heritability, thus the task of improving GWAS power for more discoveries remains both critical and challenging. In addition to the usual but costly or even infeasible route of continuing to increase the sample size, many approaches have been proposed to incorporate functional annotations to prioritize SNPs but with only limited success. Here, by taking advantage of increasing availability of various types of omics data, we propose a new and orthogonal approach by integrating individual-level omics data with GWASs. The premise is that since omics data reflect both genetic and environmental (such as diet and other lifestyle) effects on individuals, they can be used to account for (otherwise unexplained) variations among individuals in GWAS analysis, leading to more precise/efficient estimation and thus higher power. As a concrete example, we propose boosting GWAS power by adjusting for metabolomics data in GWAS analysis. We applied the method to the UK Biobank subcohort of n = 90,000 individuals with both GWAS and metabolomics data. The analysis of 7 quantitative traits and one binary trait demonstrated clear power gains. For example, the new method (after adjusting for metabolomics data) identified 13 new loci for diastolic blood pressure that were all missed by the standard GWAS, and most or all of the 13 new signals were validated in two much larger GWAS datasets (n = 340,000 and 700,000); the improved estimation efficiency was equivalent to a 38.4% gain of GWAS sample size. The proposed method is both simple and promising and broadly applicable to integrating GWASs with other omics data.

Tuning a high performing multiplexed-CRISPRi Pseudomonas putida strain to further enhance indigoidine production

In this study, a 14-gene edited Pseudomonas putida KT2440 strain for heterologous indigoidine production was examined using three distinct omic datasets. Transcriptomic data indicated that CRISPR/dCpf1-interference (CRISPRi) mediated multiplex repression caused global gene expression changes, implying potential undesirable changes in metabolic flux. 13C-metabolic flux analysis (13C-MFA) revealed that the core P. putida flux network after CRISPRi repression was conserved, with moderate reduction of TCA cycle and pyruvate shunt activity along with glyoxylate shunt activation during glucose catabolism. Metabolomic results identified a change in intracellular TCA metabolites and extracellular metabolite secretion profiles (sugars and succinate overflow) in the engineered strains. These omic analyses guided further strain engineering, with a random mutagenesis screen first identifying an optimal ribosome binding site (RBS) for Cpf1 that enabled stronger product-substrate pairing (1.6–fold increase). Then, deletion strains were constructed with excision of the PHA operon (ΔphaAZC-IID) resulting in a 2.2–fold increase in indigoidine titer over the optimized Cpf1-RBS construct at the end of the growth phase (∼6 h). The maximum indigoidine titer (at 72 h) in the ΔphaAZC-IID strain had a 1.5–fold and 1.8–fold increase compared to the optimized Cpf1-RBS construct and the original strain, respectively. Overall, this study demonstrated that integration of omic data types is essential for understanding responses to complex metabolic engineering designs and directly quantified the effect of such modifications on central metabolism.

A Multi-omics Data Analysis Workflow Packaged as a FAIR Digital Object

In current biomedical and complex trait research, increasing numbers of large molecular profiling (omics) data sets are being generated. At the same time, many studies fail to be reproduced (Baker 2016, Kim 2018). In order to improve study reproducibility and data reuse, including integration of data sets of different types and origins, it is imperative to work with omics data that is findable, accessible, interoperable, and reusable (FAIR, Wilkinson 2016) at the source. The data analysis, integration and stewardship pillar of the Netherlands X-omics Initiative aims to facilitate multi-omics research by providing tools to create, analyze and integrate FAIR omics data. We here report a joint activity of X-omics and the Netherlands Twin Register demonstrating the FAIRification of a multi-omics data set and the development of a FAIR multi-omics data analysis workflow. The implementation of FAIR principles (Wilkinson 2016) can improve scientific transparency and facilitate data reuse. However, Kim (2018) showed in a case study that the availability of data and code are required but not sufficient to reproduce data analyses. They highlighted the importance of interoperable and open formats, and structured metadata. In order to increase research reproducibility on the data analysis level, additional practices such as version-control, code licensing, and documentation have been proposed. These include recommendations for FAIR software by the Netherlands eScience Center and the Dutch Data Archiving and Networked Services (DANS), and FAIR principles for research software proposed by the Research Data Alliance (Chue Hong 2022). Data analysis in biomedical research usually comprises multiple steps often resulting in complex data analysis workflows and requiring additional practices, such as containerization, to ensure transparency and reproducibility (Goble 2020, Stoudt 2021). We apply these practices to a multi-omics data set that comprises genome-wide DNA methylation profiles, targeted metabolomics, and behavioral data of two cohorts that participated in the ACTION Biomarker Study (ACTION, Aggression in Children: Unraveling gene-environment interplay to inform Treatment and InterventiON strategies, see consortium members in Suppl. material 1) (Boomsma 2015, Bartels 2018, Hagenbeek 2020, van Dongen 2021, Hagenbeek 2022). The ACTION-NTR cohort consists of twins that are either longitudinally concordant or discordant for childhood aggression. The ACTION-Curium-LUMC cohort consists of children referred to the Dutch LUMC Curium academic center for child and youth psychiatry. With the joint analysis of multi-omics data and behavioral data, we aim to identify substructures in the ACTION-NTR cohort and link them to aggressive behavior. First, the individuals are clustered using Similarity Network Fusion (SNF, Wang 2014), and latent feature dimensions are uncovered using different unsupervised methods including Multi-Omics Factor Analysis (MOFA) (Argelaguet 2018) and Multiple Correspondence Analysis (MCA, Lê 2008, Husson 2017). In a second step, we determine correlations between -omics and phenotype dimensions, and use them to explain the subgroups of individuals from the ACTION-NTR cohort. In order to validate the results, we project data of the ACTION-Curium-LUMC cohort onto the latent dimensions and determine if correlations between omics and phenotype data can be reproduced. Integration of data across cohorts and across data types, requires interoperability. We applied different practices to make the data FAIR, including conversion of files to community-standard formats, and capturing experimental metadata using the ISA (Investigation, Study, Assay) metadata framework (Johnson 2021) and ontology-based annotations. All data analysis steps including pre-processing of different omics data types were implemented in either R or Python and combined in a modular Nextflow (Di Tommaso 2017) workflow, where the environment for each step is provided as a Singularity (Kurtzer 2017) container. The analysis workflow is packaged in a Research Object Crate (RO-Crate) (Soiland-Reyes 2022). The RO-Crate is a FAIR digital object that contains the Nextflow workflow including ontology-based annotations of each analysis step. Since omics data is considered to be potentially personally identifiable, the packaged workflow contains a minimal synthetic data set resembling the original data structure. Finally, the code is made available on GitHub and the workflow is registered at Workflowhub (Goble 2021). Since our Nextflow workflow is set up in a modular manner, the individual analysis steps can be reused in other workflows. We demonstrate this replicability by applying different sub-workflows to data from two different cohorts.

O-02: RADIOMICS AND ARTIFICIAL INTELLIGENCE FOR IDENTIFICATION AND MONITORING OF SILENT CEREBRAL INFARCTS IN SICKLE CELL DISEASE: FIRST ANALYSIS FROM THE GENOMED4ALL EUROPEAN PROJECT

Purpose: The use of Artificial Intelligence (AI) for personalized medicine has recently guided dramatic improvements in the diagnostic pathway of several diseases. The European Project GENOMED4ALL, aims at using European level data of patients affected by Multiple Myeloma, Myelodysplastic Syndromes and Sickle Cell Disease (SCD) to find correlation between genomics – and other omics data – with phenotypic manifestations and seize the opportunity of improving diagnostics through AI. Silent Cerebral Infarcts (SCIs) are a significant determinant of morbidity since childhood in SCD. One of the aims of the SCD clinical case in GENOMED4ALL is the use of radiomics – quantitative method for the evaluation and interpretation of medical images- and AI firstly to develop an automatic and uniform identification and characterization of SCI through the analysis of cerebral MRI, secondly, to correlate imaging data with other types of omics data in order to predict risk of recurrence. Materials and methods: The MRI protocol included 3D-T1, FLAIR and DWI sequences. Neuroradiological reports were cross checked for consistency. A stepwise segmentation (identification of lesion volume), pre-processing and extraction of MRIs was performed utilizing different open-source software: Lesion Segmentation Tools and UNet for segmentation, Freesurfer for brain extraction. To optimize SCI identification, we have selected the best software for segmentation; freesurfer was substituted with a faster approach. Results: Six European SCD centers participated in this first phase of the Radiomics project with 501 MRIs: 225 were classified as abnormal by the local neuroradiologists due to presence of SCI, 275 were normal; 70% were pediatric MRIs. Different instruments were used in the 6 centers: Philips 1.5 T (n.2), Siemens 1.5 T and 3 T (n.2), GE 3T (n.2). A stepwise procedure allowed the optimization of SCI identification, with distinction between SCI and background non clinically significant noise (i.e periventricular areas) or other white matter hyperintensities (i.e transient glial maturation). As shown in Figure 1, to segment SCI in FLAIR MRI, we have used a pre-trained UNet [Li H, 2018]. Firstly, we have extracted the brain registering the MNI152 on the T1 image. Then we have applied the brain mask and a threshold taking only the largest component. The UNet performs the segmentation of hyperintensities. We have removed the regions surrounded by less than the 90% of White Matter or near the brain ventricles to remove non-SCI region. In the end, we have enlarged the remaining ones. To date, segmentation on 303 exams from different centers showed very few false positive and false negatives highlighting the need to take into account different technical characteristics due to the various equipment used in the different centers. Conclusion: SCD is a systemic disorder with extreme phenotypic variability. Radiomics and AI offer the opportunity to seize the potential of big datasets analysis to optimize diagnostic in SCD. SCI can be detected automatically from different datasets. Four more European Centers will add their MRI in the second phase of the project, to increase variability and allow correlation of in detailed Radiomics data (lesion volume, lesion site, etc) with clinical-hematological characteristics and other omics data.Figure 1. Stepwise Segmentation (identification and selection of lesion volume) workflow for automatic selection of all SCI. From left to right: Axial slices of the input scan, Slice after skull stripping to highlight only the brain parenchyma, Segmentatio The authors do not declare any conflict of interest

Connecting omics signatures and revealing biological mechanisms with iLINCS

There are only a few platforms that integrate multiple omics data types, bioinformatics tools, and interfaces for integrative analyses and visualization that do not require programming skills. Here we present iLINCS (http://ilincs.org), an integrative web-based platform for analysis of omics data and signatures of cellular perturbations. The platform facilitates mining and re-analysis of the large collection of omics datasets (>34,000), pre-computed signatures (>200,000), and their connections, as well as the analysis of user-submitted omics signatures of diseases and cellular perturbations. iLINCS analysis workflows integrate vast omics data resources and a range of analytics and interactive visualization tools into a comprehensive platform for analysis of omics signatures. iLINCS user-friendly interfaces enable execution of sophisticated analyses of omics signatures, mechanism of action analysis, and signature-driven drug repositioning. We illustrate the utility of iLINCS with three use cases involving analysis of cancer proteogenomic signatures, COVID 19 transcriptomic signatures and mTOR signaling.

Uncertainty-aware dynamic integration for multi-omics classification of tumors.

Omics data are crucial for medical diagnosis as it contains intrinsic biomedical information. Multi-omics integrated analysis has become a new direction for scientists to explore life mechanisms. Nevertheless, the quality of complex omics data often varies greatly due to different samples or even different omics types, it is challenging to dynamically capture the uncertainty for different kinds of omics data. This paper proposes a uncertainty-aware dynamic integration framework for multi-omics classification. The framework consists of three modules: deep embedding, confidence prediction, and downstream tasks. The deep embedding module extract key information from multi-omics data to obtain a low-dimensional feature representation which is used to train downstream tasks. Combined with the deep embedding module, the confidence prediction module is used to dynamically capture the uncertainty of the data. We introduce "confidNet" to assign a confidence value for each type of omics data, which is used for dynamic integration between multi-omics. Compared with other integration methods, the proposed method can contain more crucial biomedical information in the obtained low-dimensional representation. Our framework realizes reliable integration among multiple omics, and it can still achieve high accuracy on small sample data sets. We have verified the effectiveness of the model in a large number of experiments. Our framework can be widely applied to high-dimensional omics data and has great potential to facilitate medical decision-making and biological analysis.

Metabolomic predictors of phenotypic traits can replace and complement measured clinical variables in population-scale expression profiling studies

Population-scale expression profiling studies can provide valuable insights into biological and disease-underlying mechanisms. The availability of phenotypic traits is essential for studying clinical effects. Therefore, missing, incomplete, or inaccurate phenotypic information can make analyses challenging and prevent RNA-seq or other omics data to be reused. A possible solution are predictors that infer clinical or behavioral phenotypic traits from molecular data. While such predictors have been developed based on different omics data types and are being applied in various studies, metabolomics-based surrogates are less commonly used than predictors based on DNA methylation profiles.In this study, we inferred 17 traits, including diabetes status and exposure to lipid medication, using previously trained metabolomic predictors. We evaluated whether these metabolomic surrogates can be used as an alternative to reported information for studying the respective phenotypes using expression profiling data of four population cohorts. For the majority of the 17 traits, the metabolomic surrogates performed similarly to the reported phenotypes in terms of effect sizes, number of significant associations, replication rates, and significantly enriched pathways.The application of metabolomics-derived surrogate outcomes opens new possibilities for reuse of multi-omics data sets. In studies where availability of clinical metadata is limited, missing or incomplete information can be complemented by these surrogates, thereby increasing the size of available data sets. Additionally, the availability of such surrogates could be used to correct for potential biological confounding. In the future, it would be interesting to further investigate the use of molecular predictors across different omics types and cohorts.

Multi-agent Feature Selection for Integrative Multi-omics Analysis.

Multiomics data integration is key for cancer prediction as it captures different aspects of molecular mechanisms. Nevertheless, the high-dimensionality of multi-omics data with a relatively small number of patients presents a challenge for the cancer prediction tasks. While feature selection techniques have been widely used to tackle the curse of dimensionality of multi-omics data, most existing methods have been applied to each type of omics data separately. In this paper, we propose a multi-agent architecture for feature selection, called MAgentOmics, to consider all omics data together. MAgentOmics extends the ant colony optimization algorithm to multi-omics data, which iteratively builds candidate solutions and evaluates them. Moreover, a new fitness function is introduced to assess the candidate feature subsets without using prediction target such as survival time of patients. Therefore, it can be considered as an unsupervised method. We evaluate the performance of MAgentOmics on the TCGA ovarian cancer multi-omics data from 176 patients using a 5-fold cross-validation. The results demonstrate that the integration power of MAgentOmics is relatively better than the state-of-the-art supervised multi-view method. The code is publicly available at https://github.com/SinaTabakhi/MAgentOmics. Clinical relevance- Discovering knowledge in existing multi-omics datasets through better feature selection enhances the clinical understanding of cancers and speeds-up decision-making in the clinic.

Abstract 5858: A multi-omics signature for patients’ risk classification in prostate cancer

Abstract Background: Effective biomarkers are urgently needed in the clinical settings. However, most biomarkers are currently developed from single type of omics data. The goal of this study is to identify prognostic prostate cancer signatures using transcriptomics and metabolomics profiles jointly aiming to capture wider spectrum of biological information. Methods: In this study, we included 94 tumor and 48 adjacency normal samples with both transcriptomics and metabolomics profiles from Dana-Farber/Harvard Cancer Center SPORE Prostate Cancer Cohort. There were 85 patients being followed up with median length of 2.02 years including 3 lethal and 8 progression cases. We first constructed a multi-omics covering network that contained minimal set of variable pairs but sufficiently rich to account for observed inter-patient variations. The network was built on known gene-metabolite interaction pairs from Pathway Commons as prior knowledge. Next, we used a diffusion process with each of connected gene-metabolite pairs as seeds to identify candidate signatures in the network. Signature sizes were controlled under 5 by adjusting the tree height during pruning. Hierarchical clustering and survival analyses were then performed to stratify patients into two risk groups for disease-free survival probability. Only the prognostic signatures with power higher than 0.9 from bootstrapping were kept for external validation and functional analyses. Since to our best knowledge, there is no publicly available dataset with both transcriptomics and metabolomics to validate the multi-omics signature we identified. We thus trained a rank-based kTSP classifier using gene expression data in SPORE cohort as a surrogate signature and validated it in TCGA prostate cancer cohort independently. Results: Constructed covering network consisted of 12 metabolites and 54 genes with inter-patient heterogeneities being captured efficiently. We identified one high-powered multi-omics signature (Gene: EGLN3; Metabolites: succinate, trans-4-hydroxyproline) that exhibited good prognostic value where high-risk patients had significant less time of disease-free survival (log rank test: p=0.019, power: 0.974). In addition, genomic variations were observed in different percentages of patients in high and low risk groups including NCOR1(SNV, 70.6% vs 96.3% p=0.025), NKX3.1(CNV, 29.6% vs 64.7% p=0.031) and TNFRSF10C (CNV, 29.6% vs 64.7%, p=0.031). No evidence indicated the patient grouping by the signature depend on Gleason scores (p=0.44). The surrogated gene signature contained 6 pairs of genes that can effectively classify TCGA patients into two prognostic groups (log rank test: p=0.048). Still, no evidence indicated the surrogate gene signature is associated with Gleason score (p=0.23) in TCGA dataset. Conclusions: We identified a prognostic multi-omics signature (EGLN3, succinate, trans-4-hydroxyproline) with high statistical power. Citation Format: Zhuoran Xu, Elisa Benedetti, Ryan Carelli, Jacob Rosenthal, Hubert Pakula, Mohamed Omar, Renato Umeton, David Brundage, Jan Krumsiek, Massimo Loda, Luigi Marchionni. A multi-omics signature for patients’ risk classification in prostate cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 5858.

Integration of Multi-Omics Data to Identify Cancer Biomarkers

A novel method for integrating multi-omics data, including gene expression, copy number variation, DNA methylation, and miRNA data, is proposed to identify biomarkers of cancer prognosis. First, survival analysis was performed for these four types of omics data to obtain survival-related genes. Next, survival-related genes detected in at least two types of omics data were selected as candidate genes. The four types of omics data only composed of candidate genes were subjected to dimension reduction using an autoencoder to obtain a one-dimensional data representation. The mRMR algorithm was used to screen for key genes. This method was applied to lung squamous cell carcinoma and 20 cancer-related genes were identified. Gene function analysis revealed that the genes were related to cancer. Using survival analysis, the genes were verified to distinguish between high- and low-risk groups. These results indicate that the genes can be used as biomarkers for cancer.

Multi-Omics Integrative Analysis of Lung Adenocarcinoma: An in silico Profiling for Precise Medicine.

Lung adenocarcinoma (LUAD) is one of the most common histological subtypes of lung cancer. The aim of this study was to construct consensus clusters based on multi-omics data and multiple algorithms. In order to identify specific molecular characteristics and facilitate the use of precision medicine on patients we used gene expression, DNA methylation, gene mutations, copy number variation data, and clinical data of LUAD patients for clustering. Consensus clusters were obtained using a consensus ensemble of five multi-omics integrative algorithms. Four molecular subtypes were identified. The CS1 and CS2 subtypes had better prognosis. Based on the immune and drug sensitivity predictions, we inferred that CS1 may be less responsive to immunotherapy and less sensitive to chemotherapeutic drugs. The high immune infiltration of CS2 cells may respond well to immunotherapy. Additionally, the CS2 subtype may also respond to EGFR molecular targeted therapy. The CS3 and CS4 subtypes were associated with poor prognosis. These two subtypes had more mutations, especially TP53 ones, as well as higher sensitivity to chemotherapeutics for lung cancer. However, CS3 was enriched in immune-related pathways and may respond to anti-PD1 immunotherapy. In addition, CS1 and CS4 were less sensitive to ferroptosis inhibitors. We performed a comprehensive analysis of the five types of omics data using five clustering algorithms to reveal the molecular characteristics of LUAD patients. These findings provide new insights into LUAD subtypes and potential clinical treatment strategies to guide personalized management and treatment.

Transforming OMIC features for classification using siamese convolutional networks.

Modern biotechnologies have generated huge amount of OMIC data, among which transcriptomes and methylomes are two major OMIC types. Transcriptomes measure the expression levels of all the transcripts while methylomes depict the cytosine methylation levels across a genome. Both OMIC data types could be generated by array or sequencing. And some studies deliver many more features (the number of features is denoted as [Formula: see text]) for a sample than the number [Formula: see text] of samples in a cohort, which induce the "large [Formula: see text] small [Formula: see text]" paradigm. This study focused on the classification problem about OMIC with "large [Formula: see text] small [Formula: see text]" paradigm. A Siamese convolutional network was utilized to transform the OMIC features into a new space with minimized intra-class distances and maximized inter-class distances between the samples. The proposed feature engineering algorithm SiaCo was comprehensively evaluated using both transcriptome and methylome datasets. The experimental data showed that SiaCo generated SiaCo features with improved classification accuracies for binary classification problems, and achieved improvements on the independent test dataset. The individual SiaCo features did not show better inter-class discrimination powers than the original OMIC features. This may be due to that the Siamese convolutional network optimized the collective performances of the SiaCo features, instead of the individual feature's discrimination power. The inherent transformation nature of the Siamese twin network also makes the SiaCo features lack of interpretability. The source code of SiaCo is freely available at http://www.healthinformaticslab.org/supp/resources.php.