Multi-omics Datasets Research Articles

Isoform-resolved transcriptome of the human preimplantation embryo

Human preimplantation development involves extensive remodeling of RNA expression and splicing. However, its transcriptome has been compiled using short-read sequencing data, which fails to capture most full-length mRNAs. Here, we generate an isoform-resolved transcriptome of early human development by performing long- and short-read RNA sequencing on 73 embryos spanning the zygote to blastocyst stages. We identify 110,212 unannotated isoforms transcribed from known genes, including highly conserved protein-coding loci and key developmental regulators. We further identify 17,964 isoforms from 5,239 unannotated genes, which are largely non-coding, primate-specific, and highly associated with transposable elements. These isoforms are widely supported by the integration of published multi-omics datasets, including single-cell 8CLC and blastoid studies. Alternative splicing and gene co-expression network analyses further reveal that embryonic genome activation is associated with splicing disruption and transient upregulation of gene modules. Together, these findings show that the human embryo transcriptome is far more complex than currently known, and will act as a valuable resource to empower future studies exploring development.

MICA: a multi-omics method to predict gene regulatory networks in early human embryos.

Recent advances in single-cell omics have transformed characterisation of cell types in challenging-to-study biological contexts. In contexts with limited single-cell samples, such as the early human embryo inference of transcription factor-gene regulatory network (GRN) interactions is especially difficult. Here, we assessed application of different linear or non-linear GRN predictions to single-cell simulated and human embryo transcriptome datasets. We also compared how expression normalisation impacts on GRN predictions, finding that transcripts per million reads outperformed alternative methods. GRN inferences were more reproducible using a non-linear method based on mutual information (MI) applied to single-cell transcriptome datasets refined with chromatin accessibility (CA) (called MICA), compared with alternative network prediction methods tested. MICA captures complex non-monotonic dependencies and feedback loops. Using MICA, we generated the first GRN inferences in early human development. MICA predicted co-localisation of the AP-1 transcription factor subunit proto-oncogene JUND and the TFAP2C transcription factor AP-2γ in early human embryos. Overall, our comparative analysis of GRN prediction methods defines a pipeline that can be applied to single-cell multi-omics datasets in especially challenging contexts to infer interactions between transcription factor expression and target gene regulation.

Identification of the methotrexate resistance-related diagnostic markers in osteosarcoma via adaptive total variation netNMF and multi-omics datasets.

Osteosarcoma is one of the most common malignant bone tumors with high chemoresistance and poor prognosis, exhibiting abnormal gene regulation and epigenetic events. Methotrexate (MTX) is often used as a primary agent in neoadjuvant chemotherapy for osteosarcoma; However, the high dosage of methotrexate and strong drug resistance limit its therapeutic efficacy and application prospects. Studies have shown that abnormal expression and dysfunction of some coding or non-coding RNAs (e.g., DNA methylation and microRNA) affect key features of osteosarcoma progression, such as proliferation, migration, invasion, and drug resistance. Comprehensive multi-omics analysis is critical to understand its chemoresistant and pathogenic mechanisms. Currently, the network analysis-based non-negative matrix factorization (netNMF) method is widely used for multi-omics data fusion analysis. However, the effects of data noise and inflexible settings of regularization parameters affect its performance, while integrating and processing different types of genetic data is also a challenge. In this study, we introduced a novel adaptive total variation netNMF (ATV-netNMF) method to identify feature modules and characteristic genes by integrating methylation and gene expression data, which can adaptively choose an anisotropic smoothing scheme to denoise or preserve feature details based on the gradient information of the data by introducing an adaptive total variation constraint in netNMF. By comparing with other similar methods, the results showed that the proposed method could extract multi-omics fusion features more effectively. Furthermore, by combining the mRNA and miRNA data of methotrexate (MTX) resistance with the extracted feature genes, four genes, Carboxypeptidase E (CPE), LIM, SH3 protein 1 (LASP1), Pyruvate Dehydrogenase Kinase 1 (PDK1) and Serine beta-lactamase-like protein (LACTB) were finally identified. The results showed that the gene signature could reliably predict the prognostic status and immune status of osteosarcoma patients.

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.

Global and cross-modal feature aggregation for multi-omics data classification and application on drug response prediction

With rapid development of single-cell multi-modal sequencing technologies, more and more multi-omics data come into being and provide a unique opportunity for the identification of distinct cell types at the single-cell level. Therefore, it is important to integrate different modalities which are with high-dimensional features for boosting final multi-omics data classification performance. However, existing multi-omics data classification methods mainly focus on exploiting the complementary information of different modalities, while ignoring the learning confidence and cross-modal sample relationship during information fusion. In this paper, we propose a multi-omics data classification network via global and cross-modal feature aggregation, referred to as GCFANet. On one hand, considering that a large number of feature dimensions in different modalities could not contribute to final classification performance but disturb the discriminability of different samples, we propose a feature confidence learning mechanism to suppress some redundant features, as well as enhancing the expression of discriminative feature dimensions in each modality. On the other hand, in order to capture the inherent sample structure information implied in each modality, we design a graph convolutional network branch to learn the corresponding structure preserved feature representation. Then the modal-specific feature representations are concatenated and input to a transformer induced global and cross-modal feature aggregation module for learning consensus feature representation from different modalities. In addition, the consensus feature representation used for final classification is enhanced via a view-specific consistency preserved contrastive learning strategy. Extensive experiments on four multi-omics datasets are conducted to demonstrate the efficacy of the proposed GCFANet.

Comprehensive characterization of patient-derived xenograft models of pediatric leukemia

Patient-derived xenografts (PDX) remain valuable models for understanding the biology and for developing novel therapeutics. To expand current PDX models of childhood leukemia, we have developed new PDX models from Hispanic patients, a subgroup with a poorer overall outcome. Of 117 primary leukemia samples obtained, successful engraftment and serial passage in mice were achieved in 82 samples (70%). Hispanic patient samples engrafted at a rate (51/73, 70%) that was similar to non-Hispanic patient samples (31/45, 70%). With a new algorithm to remove mouse contamination in multi-omics datasets including methylation data, we found PDX models faithfully reflected somatic mutations, copy-number alterations, RNA expression, gene fusions, whole-genome methylation patterns, and immunophenotypes found in primary tumor (PT) samples in the first 50 reported here. This cohort of characterized PDX childhood leukemias represents a valuable resource in that germline DNA sequencing has allowed the unambiguous determination of somatic mutations in both PT and PDX.

SoyMD: a platform combining multi-omics data with various tools for soybean research and breeding.

Advanced multi-omics technologies offer much information that can uncover the regulatory mechanisms from genotype to phenotype. In soybean, numerous multi-omics databases have been published. Although they cover multiple omics, there are still limitations when it comes to the types and scales of omics datasets and analysis methods utilized. This study aims to address these limitations by collecting and integrating a comprehensive set of multi-omics datasets. This includes 38 genomes, transcriptomes from 435 tissue samples, 125 phenotypes from 6686 accessions, epigenome data involving histone modification, transcription factor binding, chromosomal accessibilityand chromosomal interaction, as well as genetic variation data from 24501 soybean accessions. Then, common analysis pipelines and statistical methods were applied to mine information from these multi-omics datasets, resulting in the successful establishment of a user-friendly multi-omics database called SoyMD (https://yanglab.hzau.edu.cn/SoyMD/#/). SoyMD provides researchers with efficient query options and analysis tools, allowing them to swiftly access relevant omics information and conduct comprehensive multi-omics data analyses. Another notable feature of SoyMD is its capability to facilitate the analysis of candidate genes, as demonstrated in the case study on seed oil content. This highlights the immense potential of SoyMD in soybean genetic breeding and functional genomics research.

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.

OR01-06 Single Nucleus Multi-omics Analysis Identifies Cellular Trajectories And Dynamic Changes In Gene Expression And Chromatin Accessibility In The Pituitary During The Mouse Estrous Cycle

Abstract Disclosure: F.M. Ruf-Zamojski: None. W. Cheng: None. Z. Zhang: None. M. Zamojski: None. G.R. Smith: None. X. Chen: None. N. Mendelev: None. G. Strupinsky: None. C.A. Alonso: None. L. Ongaro Gambino: None. X. Zhou: None. E. Brule: None. M.S. Amper: None. P. Hanna: None. V.D. Nair: None. C.L. Andoniadou: None. J.L. Turgeon: None. O. Troyanskaya: None. E. Zaslavsky: None. D.J. Bernard: None. S.C. Sealfon: None. Single cell multi-omics datasets provide an unparalleled power to resolve gene regulatory circuits underlying cellular function in complex tissues such as the pituitary gland [1, 2]. To better understand cellular plasticity and dynamics in the mouse pituitary during the estrous cycle in vivo, we performed same-cell single nucleus (sn) multi-omics for gene expression and chromatin accessibility on individual pituitaries collected from mice at 9am on each day of the cycle, as well as at 6pm and 11pm on proestrus and at 2am on estrus to capture surge events. Cycle stage was determined by vaginal cytology and post-mortem measurement of serum LH and FSH levels. In total, 102,069 cells passed rigorous quality control (QC, [2]), with over 5,000 cells analyzed per sample, ∼2,000 genes/cell, ∼15,000 ATAC median high-quality fragments, and Transcription Start Site (TSS) enrichment scores above 9 for all samples. We identified 13 well-separated clusters in the snRNAseq and 10 in the snATACseq datasets representing the pituitary cell types that were followed over time. We integrated the gene expression and chromatin accessibility datasets and analyzed changes in cell type proportions, gene expression, and chromatin accessibility through time. We detected major differential gene expression changes in the gonadotropes and lactotropes, which we further investigated using pseudotime trajectory analyses. Several upstream Fshb loci showed dynamic changes during the estrous cycle. Additionally, we uncovered regulatory components of major pituitary genes over time using linkage data analysis.To our knowledge, this is the first study to present detailed and comprehensive data on gene expression and chromatin structure changes at sn resolution in all pituitary cell types during a dynamic physiological process. Thus, it provides critical new resources to the field of endocrinology.

200 RESPIRE: Searchable, downloadable multi-omic data sets for lung disease research

200 RESPIRE: Searchable, downloadable multi-omic data sets for lung disease research

Multi-channel Partial Graph Integration Learning of Partial Multi-omics Data for Cancer Subtyping

Background: The appearance of cancer subtypes with different clinical significance fully reflects the high heterogeneity of cancer. At present, the method of multi-omics integration has become more and more mature. However, in the practical application of the method, the omics of some samples are missing. Objective: The purpose of this study is to establish a depth model that can effectively integrate and express partial multi-omics data to accurately identify cancer subtypes. Methods: We proposed a novel partial multi-omics learning model for cancer subtypes, MPGIL (Multichannel Partial Graph Integration Learning). MPGIL has two main components. Firstly, it obtains more lateral adjacency information between samples within the omics through the multi-channel graph autoencoders based on high-order proximity. To reduce the negative impact of missing samples, the weighted fusion layer is introduced to replace the concatenate layer to learn the consensus representation across multi-omics. Secondly, a classifier is introduced to ensure that the consensus representation is representative of clustering. Finally, subtypes were identified by K-means. Results: This study compared MPGIL with other multi-omics integration methods on 16 datasets. The clinical and survival results show that MPGIL can effectively identify subtypes. Three ablation experiments are designed to highlight the importance of each component in MPGIL. A case study of AML was conducted. The differentially expressed gene profiles among its subtypes fully reveal the high heterogeneity of cancer. Conclusion: MPGIL can effectively learn the consistent expression of partial multi-omics datasets and discover subtypes, and shows more significant performance than the state-of-the-art methods.

Causal inference on microbiome-metabolome relations in observational host-microbiome data via in silico in vivo association pattern analyses

Understanding the effects of the microbiome on the host's metabolism is core to enlightening the role of the microbiome in health and disease. Herein, we develop the paradigm of in silico invivo association pattern analyses, combining microbiome metabolome association studies with in silico constraint-based community modeling. Via theoretical dissection of confounding and causal paths, we show that in silico invivo association pattern analyses allow for causal inference on microbiome-metabolome relations in observational data. We justify the corresponding theoretical criterion by structural equation modeling of host-microbiome systems, integrating deterministic microbiome community modeling into population statistics approaches. We show the feasibility of our approach on a published multi-omics dataset (n= 347), demonstrating causal microbiome-metabolite relations for 26 out of 54 fecal metabolites. In summary, we generate a promising approach for causal inference in metabolic host-microbiome interactions by integrating hypothesis-free screening association studies with knowledge-based in silico modeling.

Genetically Engineered Mouse Models of CIC-DUX4 Sarcoma Reveal an Unexpected Sensitivity to Histone Deacetylase (HDAC) Inhibition

Undifferentiated small round cell sarcomas constitute a highly aggressive subtype of soft tissue sarcoma that affects adolescents and young adults. Frequently, these cancers are caused by a gene fusion between the DNA binding domain of capicua (CIC), a canonical tumor suppressor that normally acts as a transcriptional repressor, with the transcriptional activation domain of double homeobox 4 (DUX4). Given the rare nature of CIC-DUX4 sarcoma (CDS), obtaining patient tissues to study the mechanisms of disease is very challenging. Moreover, conducting clinical trials to identify radiosensitizers or other novel treatments is not possible underscoring the need for a primary animal model. Here, we report the development and characterization of the first genetically engineered mouse model of CDS and the use of this model to investigate novel therapies. Using Cre-loxP technology, three genetically engineered mouse models of CDS were developed. The resulting tumors were characterized by hematoxylin and eosin (H&E) staining, immunohistochemistry (IHC), and RNA-sequencing. Cell lines from multiple primary and metastatic tumors were derived and used for Chromatin Immunoprecipitation (ChiP) sequencing, Rapid Immunoprecipitation mass spectrometry of Endogenous proteins (RIME), and targeted drug screening. In all three models, spontaneous (Cre-independent) recombination occurred in chimeric animals resulting in the formation of soft tissue tumors, widespread metastasis to the lungs, liver, and brain, and 100% lethality within 4-8 weeks of life. The tumors histologically resembled human CDS and stained positive for an HA (hemagglutinin) epitope tag confirming transgene expression. Of 108 chimeric pups (generation 0, G0), only one male bred before succumbing to metastatic disease. G2 progeny now exhibit resistance to spontaneous recombination and tumor development enabling reliable propagation of one of the models for experimentation. Using tumor derived cell lines for integrative analyses of multi-omics datasets, we find evidence for a model where CIC-DUX4 functions as a neomorphic and oncogenic transcriptional activator, which cooperates with ETS family transcription factors to drive the CDS transcriptional program. Lastly, small molecule epigenetic drug screens in mouse and human CDS cell lines point to an unexpected sensitivity to HDAC inhibitors, which we hypothesize may be attributable to ETS factor hyperactivity. Genetically engineered mouse models of CIC-DUX4 sarcoma form tumors that recapitulate the human disease. Using mouse tumors and tumor-derived cell lines, we identify a mechanistic role and potential therapeutic vulnerability that converges on the ETS family transcription factors.

ScBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integration

Single-cell multi-omics data integration aims to reduce the omics difference while keeping the cell type difference. However, it is daunting to model and distinguish the two differences due to cell heterogeneity. Namely, even cells of the same omics and type would have various features, making the two differences less significant. In this work, we reveal that instead of being an interference, cell heterogeneity could be exploited to improve data integration. Specifically, we observe that the omics difference varies in cells, and cells with smaller omics differences are easier to be integrated. Hence, unlike most existing works that homogeneously treat and integrate all cells, we propose a multi-omics data integration method (dubbed scBridge) that integrates cells in a heterogeneous manner. In brief, scBridge iterates between i) identifying reliable scATAC-seq cells that have smaller omics differences, and ii) integrating reliable scATAC-seq cells with scRNA-seq data to narrow the omics gap, thus benefiting the integration for the rest cells. Extensive experiments on seven multi-omics datasets demonstrate the superiority of scBridge compared with six representative baselines.

IMOVNN: incomplete multi-omics data integration variational neural networks for gut microbiome disease prediction and biomarker identification

Abstract The gut microbiome has been regarded as one of the fundamental determinants regulating human health, and multi-omics data profiling has been increasingly utilized to bolster the deep understanding of this complex system. However, stemming from cost or other constraints, the integration of multi-omics often suffers from incomplete views, which poses a great challenge for the comprehensive analysis. In this work, a novel deep model named Incomplete Multi-Omics Variational Neural Networks (IMOVNN) is proposed for incomplete data integration, disease prediction application and biomarker identification. Benefiting from the information bottleneck and the marginal-to-joint distribution integration mechanism, the IMOVNN can learn the marginal latent representation of each individual omics and the joint latent representation for better disease prediction. Moreover, owing to the feature-selective layer predicated upon the concrete distribution, the model is interpretable and can identify the most relevant features. Experiments on inflammatory bowel disease multi-omics datasets demonstrate that our method outperforms several state-of-the-art methods for disease prediction. In addition, IMOVNN has identified significant biomarkers from multi-omics data sources.

Context-dependent perturbations in chromatin folding and the transcriptome by cohesin and related factors

Cohesin regulates gene expression through context-specific chromatin folding mechanisms such as enhancer–promoter looping and topologically associating domain (TAD) formation by cooperating with factors such as cohesin loaders and the insulation factor CTCF. We developed a computational workflow to explore how three-dimensional (3D) structure and gene expression are regulated collectively or individually by cohesin and related factors. The main component is CustardPy, by which multi-omics datasets are compared systematically. To validate our methodology, we generated 3D genome, transcriptome, and epigenome data before and after depletion of cohesin and related factors and compared the effects of depletion. We observed diverse effects on the 3D genome and transcriptome, and gene expression changes were correlated with the splitting of TADs caused by cohesin loss. We also observed variations in long-range interactions across TADs, which correlated with their epigenomic states. These computational tools and datasets will be valuable for 3D genome and epigenome studies.

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

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

Breast cancer survival prognosis using the graph convolutional network with Choquet fuzzy integral

Breast cancer is the most prevalent kind of cancer among women and there is a need for a reliable algorithm to predict its prognosis. Previous studies focused on using gene expression data to build predictive models. However, recent advancements have made multi-omics cancer data sets (gene expression, copy number alteration, etc.) accessible. This has acted as the motivation for the creation of a novel model that utilizes a graph convolutional network (GCN) and Choquet fuzzy ensemble, incorporating multi-omics and clinical data retrieved from the publicly available METABRIC Database. In this study, graphs have been used to extract structural information, and a Choquet Fuzzy Ensemble with Logistic Regression, Random Forest, and Support Vector Machine as base classifiers has been employed to classify breast cancer patients as short-term or long-term survivors. The model has been run using all possible combinations of gene expression, copy number alteration, and clinical modality, and the results have been reported. Furthermore, a comparison has been made between the obtained results and different baseline models and state-of-the-art to demonstrate the efficacy of the proposed model in terms of different metrics. The results of this model based on Accuracy, Matthews correlation coefficient, Precision, Sensitivity, Specificity, Balanced Accuracy, and F1-Measure are 0.820, 0.528, 0.630, 0.666, 0.871, 0.769, and 0.647, respectively.

Multiomics Data Reveal the Important Role of ANXA2R in T Cell-mediated Rejection After Renal Transplantation.

T cell-mediated rejection (TCMR) is a severe issue after renal transplantation, but research on its T cell-receptor (TCR) repertoire is lacking. This study intended to elucidate the TCR repertoire landscape in TCMR and hence identify novel potential targets. A total of 12 multiomics data sets were collected. The TRUST4 algorithm was used to construct and analyze the TCR repertoire in renal allografts with TCMR and stable renal function. Then, novel TCR-related key genes were identified through various criteria and literature research. In bulk transcriptome, cell line, single-cell transcriptome data sets, multiple immune cell infiltration algorithms, and gene set enrichment analysis were used to analyze potential mechanisms of the identified key gene. Twenty-three pathological sections were collected for immunofluorescence staining in the clinical cohort. Finally, the diagnostic and prognostic values of ANXA2R were evaluated in multiple renal transplant data sets. Allografts with TCMR showed significantly increased clonotype and specific clonal expansion. ANXA2R was found to be a novel key gene for TCMR and showed strong positive connections with the TCR complex and lymphocyte cells, especially CD8 + T cells. Immunofluorescence staining confirmed the existence of ANXA2R + CD8 + T cells, with their percentage significantly elevated in TCMR compared with stable renal function. Finally, both mRNA and protein levels of ANXA2R showed promising diagnostic and prognostic value for renal transplant recipients. ANXA2R , identified as a novel TCR-related gene, had critical roles in clinicopathology, diagnosis, and prognosis in renal transplantation, which offered promising potential therapeutic targets.

Spatial transformation of multi-omics data unlocks novel insights into cancer biology.

The application of next-generation sequencing (NGS) has transformed cancer research. As costs have decreased, NGS has increasingly been applied to generate multiple layers of molecular data from the same samples, covering genomics, transcriptomics, and methylomics. Integrating these types of multi-omics data in a combined analysis is now becoming a common issue with no obvious solution, often handled on an ad hoc basis, with multi-omics data arriving in a tabular format and analyzed using computationally intensive statistical methods. These methods particularly ignore the spatial orientation of the genome and often apply stringent p-value corrections that likely result in the loss of true positive associations. Here, we present GENIUS (GEnome traNsformatIon and spatial representation of mUltiomicS data), a framework for integrating multi-omics data using deep learning models developed for advanced image analysis. The GENIUS framework is able to transform multi-omics data into images with genes displayed as spatially connected pixels and successfully extract relevant information with respect to the desired output. We demonstrate the utility of GENIUS by applying the framework to multi-omics datasets from the Cancer Genome Atlas. Our results are focused on predicting the development of metastatic cancer from primary tumors, and demonstrate how through model inference, we are able to extract the genes which are driving the model prediction and are likely associated with metastatic disease progression. We anticipate our framework to be a starting point and strong proof of concept for multi-omics data transformation and analysis without the need for statistical correction.