Integrative clustering of multi-level 'omic data based on non-negative matrix factorization algorithm

Do we need a standardized 16S rRNA gene amplicon sequencing analysis protocol for poultry microbiota research?

Bacteria are the major component of poultry gastrointestinal tract (GIT) microbiota and play an important role in host health, nutrition, physiology regulation, intestinal development, and growth. Bacterial community profiling based on the 16S ribosomal RNA (rRNA) gene amplicon sequencing approach has become the most popular method to determine the taxonomic composition and diversity of the poultry microbiota. The 16S rRNA gene profiling involves numerous steps, including sample collection and storage, DNA isolation, 16S rRNA gene primer selection, Polymerase Chain Reaction (PCR), library preparation, sequencing, raw sequencing reads processing, taxonomic classification, α- and β-diversity calculations, and statistical analysis. However, there is currently no standardized protocol for 16S rRNA gene analysis profiling and data deposition for poultry microbiota studies. Variations in DNA storage and isolation, primer design, and library preparation are known to introduce biases, affecting community structure and microbial population analysis leading to over- or under-representation of individual bacteria within communities. Additionally, different sequencing platforms, bioinformatics pipeline, and taxonomic database selection can affect classification and determination of the microbial taxa. Moreover, detailed experimental design and DNA processing and sequencing methods are often inadequately reported in poultry 16S rRNA gene sequencing studies. Consequently, poultry microbiota results are often difficult to reproduce and compare across studies. This manuscript reviews current practices in profiling poultry microbiota using 16S rRNA gene amplicon sequencing and proposes the development of guidelines for protocol for 16S rRNA gene sequencing that spans from sample collection through data deposition to achieve more reliable data comparisons across studies and allow for comparisons and/or interpretations of poultry studies conducted worldwide.

EMitool: Explainable Multi-Omics Integration for Disease Subtyping

Disease subtyping is essential for personalized medicine, enabling tailored treatment strategies based on disease heterogeneity. Advances in high-throughput technologies have led to the rapid accumulation of multi-omics data, driving the development of integration methods for comprehensive disease subtyping. However, existing approaches often lack explainability and fail to establish clear links between subtypes and clinical outcomes. To address these challenges, we developed EMitool, an explainable multi-omics integration tool that leverages a network-based fusion strategy to achieve biologically and clinically relevant disease subtyping without requiring prior clinical information. Using data from 31 cancer types in The Cancer Genome Atlas (TCGA), EMitool demonstrated superior subtyping accuracy compared to eight state-of-the-art methods. It also provides contribution scores for different omics data types, enhancing interpretability. EMitool-derived subtypes exhibited significant associations with the overall survival, pathological stage, tumor mutational burden, immune microenvironment characteristics, and therapeutic responses. Specifically, in kidney renal clear cell carcinoma (KIRC), EMitool identified three distinct subtypes with varying prognoses, immune cell compositions, and drug sensitivities. These findings highlight its potential for biomarker discovery and precision oncology.

MVNMF: Multiview nonnegative matrix factorization for radio-multigenomic analysis in breast cancer prognosis

Radiogenomic research provides a deeper understanding of breast cancer biology by investigating the correlations between imaging phenotypes and genetic data. However, current radiogenomic research primarily focuses on the correlation between imaging phenotypes and single-genomic data (e.g., gene expression data), overlooking the potential of multi-genomics data to unveil more nuances in cancer characterization. To this end, we propose a multiview nonnegative matrix factorization (MVNMF) method for the radio-multigenomic analysis that identifies dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) features associated with multi-genomics data, including DNA copy number alterations, mutations, and mRNAs, each of which is independently predictive of cancer outcomes. MVNMF incorporates subspace learning and multiview regularization into a unified model to simultaneously select features and explore correlations. Subspace learning is utilized to identify representative radiomic features crucial for tumor analysis, while multiview regularization enables the learning of the correlation between the identified radiomic features and multi-genomics data. Experimental results showed that, for overall survival prediction in breast cancer, MVNMF classified patients into two distinct groups characterized by significant differences in survival (p = 0.0012). Furthermore, it achieved better performance with a C-index of 0.698 compared to the method without considering any genomics data (C-index = 0.528). MVNMF is an effective framework for identifying radiomic features linked to multi-genomics data, which improves its predictive power and provides a better understanding of the biological mechanisms underlying observed phenotypes. MVNMF offers a novel framework for prognostic prediction in breast cancer, with the potential to catalyze further radiogenomic/radio-multigenomic studies.

Multimodal fusion of radio-pathology and proteogenomics identify integrated glioma subtypes with prognostic and therapeutic opportunities

Integrating multimodal data can uncover causal features hidden in single-modality analyses, offering a comprehensive understanding of disease complexity. This study introduces a multimodal fusion subtyping (MOFS) framework that integrates radiological, pathological, genomic, transcriptomic, and proteomic data from 122 patients with IDH-wildtype adult glioma, identifying three subtypes: MOFS1 (proneural) with favorable prognosis, elevated neurodevelopmental activity, and abundant neurocyte infiltration; MOFS2 (proliferative) with the worst prognosis, superior proliferative activity, and genome instability; MOFS3 (TME-rich) with intermediate prognosis, abundant immune and stromal components, and sensitive to anti-PD-1 immunotherapy. STRAP emerges as a prognostic biomarker and potential therapeutic target for MOFS2, associated with its proliferative phenotype. Stromal infiltration in MOFS3 serves as a crucial prognostic indicator, allowing for further prognostic stratification. Additionally, we develop a deep neural network (DNN) classifier based on radiological features to further enhance the clinical translatability, providing a non-invasive tool for predicting MOFS subtypes. Overall, these findings highlight the potential of multimodal fusion in improving the classification, prognostic accuracy, and precision therapy of IDH-wildtype glioma, offering an avenue for personalized management.

MIDAA: deep archetypal analysis for interpretable multi-omic data integration based on biological principles

High-throughput multi-omic molecular profiling allows the probing of biological systems at unprecedented resolution. However, integrating and interpreting high-dimensional, sparse, and noisy multimodal datasets remains challenging. Deriving new biological insights with current methods is difficult because they are not rooted in biological principles but prioritise tasks like dimensionality reduction. Here, we introduce a framework that combines archetypal analysis, an approach grounded in biological principles, with deep learning. Using archetypes based on evolutionary trade-offs and Pareto optimality, MIDAA finds extreme data points that define the geometry of the latent space, preserving the complexity of biological interactions while retaining an interpretable output. We demonstrate that these extreme points represent cellular programmes reflecting the underlying biology. Moreover, we show that, compared to alternative methods, MIDAA can identify parsimonious, interpretable, and biologically relevant patterns from real and simulated multi-omics.

Benchmarking multi-omics integrative clustering methods for subtype identification in colorectal cancer

BACKGROUND AND OBJECTIVE

Colorectal cancer (CRC) represents a heterogeneous malignancy that has concerned global burden of incidence and mortality. The traditional tumor-node-metastasis staging system has exhibited certain limitations. With the advancement of omics technologies, researchers are directing their focus on developing a more precise multi-omics molecular classification. Therefore, the utilization of unsupervised multi-omics integrative clustering methods in CRC, advocating for the establishment of a comprehensive benchmark with practical guidelines.

METHODS

In this study, we obtained CRC multi-omics data, encompassing DNA methylation, gene expression, and protein expression from the cancer genome atlas (TCGA)database. We then generated interrelated CRC multi-omics data with various structures based on realistic multi-omics correlations, and performed a comprehensive evaluation of eight representative methods categorized as early integration, intermediate integration, and late integration using complementary benchmarks for subtype classification accuracy. Lastly, we employed these methods to integrate real-world CRC multi-omics data, survival and differential analysis were used to highlight differences among newly identified multi-omics subtypes.

RESULTS

Through in-depth comparisons, we observed that similarity network fusion (SNF) exhibited exceptional performance in integrating multi-omics data derived from simulations. Additionally, SNF effectively distinguished CRC patients into five subgroups with the highest classification accuracy. Moreover, we found significant survival differences and molecular distinctions among SNF subtypes.

CONCLUSIONS

The findings consistently demonstrate that SNF outperforms other methods in CRC multi-omics integrative clustering. The significant survival differences and molecular distinctions among SNF subtypes provide novel insights into the multi-omics perspective on CRC heterogeneity with potential clinical treatment.

Multi-omics clustering analysis carries out the molecular-specific subtypes of thyroid carcinoma: implicating for the precise treatment strategies

Thyroid cancer (TC) is the most prevalent endocrine malignancy worldwide. This study aimed to explore the molecular subtypes and improve the selection of targeted therapies. We used multi-omics data from 539 patients with DNA methylation, gene mutations, mRNA, lncRNA, and miRNA expressions. This study employed consensus clustering algorithms to identify molecular subtypes and used various bioinformatics tools to analyze genetic alterations, signaling pathways, immune infiltration, and responses to chemotherapy and immunotherapy. Two prognostically relevant TC subtypes, CS1 and CS2, were identified. CS2 was associated with a poorer prognosis of shorter progression-free survival times (P < 0.001). CS1 exhibited higher copy number alterations but a lower tumor mutation burden than CS2. CS2 exhibited activation in cell proliferation and immune-related pathways. Drug sensitivity analysis indicated CS2's higher sensitivity to cisplatin, doxorubicin, paclitaxel, and sunitinib, whereas CS1 was more sensitive to bicalutamide and FH535. The different activated pathways and sensitivity to drugs for the subtypes were further validated in an external cohort. Twenty-four paired tumors and adjacent normal tissues by immunohistochemical staining further demonstrated the prognostic value of CXCL17. In conclusion, we identified two distinct molecular subtypes of TC with significant implications for prognosis, genetic alterations, pathway activation, and treatment response.

Multimodal diagnostic models and subtype analysis for neoadjuvant therapy in breast cancer

Background

Breast cancer, a heterogeneous malignancy, comprises multiple subtypes and poses a substantial threat to women's health globally. Neoadjuvant therapy (NAT), administered prior to surgery, is integral to breast cancer treatment strategies. It aims to downsize tumors, optimize surgical outcomes, and evaluate tumor responsiveness to treatment. However, accurately predicting NAT efficacy remains challenging due to the disease's complexity and the diverse responses across different molecular subtypes.

Methods

In this study, we harnessed multimodal data, including proteomic, genomic, MRI imaging, and clinical information, sourced from multiple cohorts such as I-SPY2, TCGA-BRCA, GSE161529, and METABRIC. Post data preprocessing, Lasso regression was utilized for feature extraction and selection. Five machine learning algorithms were employed to construct diagnostic models, with pathological complete response (pCR) as the predictive endpoint.

Results

Our results revealed that the multi-omics Ridge regression model achieved the optimal performance in predicting pCR, with an AUC of 0.917. Through unsupervised clustering using the R package MOVICS and nine clustering algorithms, we identified four distinct multimodal breast cancer subtypes associated with NAT. These subtypes exhibited significant differences in proteomic profiles, hallmark cancer gene sets, pathway activities, tumor immune microenvironments, transcription factor activities, and clinical characteristics. For instance, CS1 subtype, predominantly ER-positive, had a low pCR rate and poor response to chemotherapy drugs, while CS4 subtype, characterized by high immune infiltration, showed a better response to immunotherapy. At the single-cell level, we detected significant heterogeneity in the tumor microenvironment among the four subtypes. Malignant cells in different subtypes displayed distinct copy number variations, differentiation levels, and evolutionary trajectories. Cell-cell communication analysis further highlighted differential interaction patterns among the subtypes, with implications for tumor progression and treatment response.

Conclusion

Our multimodal diagnostic model and subtype analysis provide novel insights into predicting NAT efficacy in breast cancer. These findings hold promise for guiding personalized treatment strategies. Future research should focus on experimental validation, in-depth exploration of the underlying mechanisms, and extension of these methods to other cancers and treatment modalities.

An Integrative Multi-Omics Random Forest Framework for Robust Biomarker Discovery

High-throughput technologies now produce a wide array of omics data, from genomic and transcriptomic profiles to epigenomic and proteomic measurements. Integrating these diverse data types can yield deeper insights into the biological mechanisms driving complex traits and diseases. Yet, extracting key shared biomarkers from multiple data layers remains a major challenge. We present a multivariate random forest (MRF)-based framework enhanced by a novel inverse minimal depth (IMD) metric for integrative variable selection. By assigning response variables to tree nodes and employing IMD to rank predictors, our approach efficiently identifies essential features across different omics types, even when confronted with high-dimensionality and noise. Through extensive simulations and analyses of multi-omics datasets from The Cancer Genome Atlas, we demonstrate that our method outperforms established integrative techniques in uncovering biologically meaningful biomarkers and pathways. Our findings show that selected biomarkers not only correlate with known regulatory and signaling networks but can also stratify patient subgroups with distinct clinical outcomes. The method's scalable, interpretable, and user-friendly implementation ensures broad applicability to a range of research questions. This MRF-based framework advances robust biomarker discovery and integrative multi-omics analyses, accelerating the translation of complex molecular data into tangible biological and clinical insights.

Nonlinear embedding and integration of omics data: a fast and tuning-free approach

The rapid progress of single-cell technology has facilitated cost-effective acquisition of diverse omics data, allowing biologists to unravel the complexities of cell populations, disease states, and more. Additionally, single-cell multi-omics technologies have opened new avenues for studying biological interactions. However, the high dimensionality and sparsity of omics data present significant analytical challenges. Dimension reduction (DR) techniques are hence essential for analyzing such complex data, yet many existing methods have inherent limitations. Linear methods like principal component analysis (PCA) struggle to capture intricate associations within data. In response, nonlinear techniques have emerged, but they may face scalability issues, be restricted to single-omics data, or prioritize visualization over generating informative embeddings. Here, we introduce dissimilarity based on conditional ordered list (DCOL) correlation, a novel measure for quantifying nonlinear relationships between variables. Based on this measure, we propose DCOL-PCA and DCOL-Canonical Correlation Analysis for dimension reduction and integration of single- and multi-omics data. In simulations, our methods outperformed nine DR methods and four joint dimension reduction methods, demonstrating stable performance across various settings. We also validated these methods on real datasets, with our method demonstrating its ability to detect intricate signals within and between omics data and generate lower dimensional embeddings that preserve the essential information and latent structures.

Heterogeneous Clustering of Multiomics Data for Breast Cancer Subgroup Classification and Detection

The rapid growth of diverse -omics datasets has made multiomics data integration crucial in cancer research. This study adapts the expectation-maximization routine for the joint latent variable modeling of multiomics patient profiles. By combining this approach with traditional biological feature selection methods, this study optimizes latent distribution, enabling efficient patient clustering from well-studied cancer types with reduced computational expense. The proposed optimization subroutines enhance survival analysis and improve runtime performance. This article presents a framework for distinguishing cancer subtypes and identifying potential biomarkers for breast cancer. Key insights into individual subtype expression and function were obtained through differentially expressed gene analysis and pathway enrichment for BRCA patients. The analysis compared 302 tumor samples to 113 normal samples across 60,660 genes. The highly upregulated gene COL10A1, promoting breast cancer progression and poor prognosis, and the consistently downregulated gene CDG300LG, linked to brain metastatic cancer, were identified. Pathway enrichment analysis revealed similarities in cellular matrix organization pathways across subtypes, with notable differences in functions like cell proliferation regulation and endocytosis by host cells. GO Semantic Similarity analysis quantified gene relationships in each subtype, identifying potential biomarkers like MATN2, similar to COL10A1. These insights suggest deeper relationships within clusters and highlight personalized treatment potential based on subtypes.

Integrated multi-omics analysis identifies a machine learning-derived signature for predicting prognosis and therapeutic vulnerability in clear cell renal cell carcinoma

AIMS

Clear cell renal cell carcinoma (ccRCC) shows considerable variation within and between tumors, presents varying treatment responses among patients, possibly due to molecular distinctions. This study utilized a multi-center and multi-omics analysis to establish and validate a prognosis and treatment vulnerability signature (PTVS) capable of effectively predicting patient prognosis and drug responsiveness.

MATERIALS AND METHODS

To address this complexity, we constructed an integrative multi-omics analysis using 10 clustering algorithms on ccRCC patient data. Afterwards, we applied bootstrapping in univariate Cox regression and the Boruta algorithm to pinpoint clinically relevant genes. Based on this, we developed a robust PTVS using seven machine learning algorithms.

KEY FINDINGS

Our analysis revealed two distinct ccRCC subtypes with differential prognostic implications, notably identifying subtype 2 with poorer outcomes. Patients in the low PTVS group exhibited superior prognosis statistics and an augmented sensitivity to immunotherapy, features consistent with a 'hot tumor' phenotype. Conversely, individuals within the high PTVS group exhibited diminished prognosis statistic and restricted advantages from immunotherapy. Importantly, the PTVS holds future potential as a notable biomarker for guiding personalized treatment strategies, with four prospective targets (CTSK, XDH, PKMYT1, and EGLN2) indicating therapeutic promise in patients scoring high on PTVS.

SIGNIFICANCE

The integrative analysis of multi-omics data profoundly enhances the molecular stratification of ccRCC, underscoring far-reaching impact of such comprehensive profiling on its therapeutic strategies.

Multiple machine learning-based integrations of multi-omics data to identify molecular subtypes and construct a prognostic model for HNSCC

BACKGROUND

Immunotherapy has introduced new breakthroughs in improving the survival of head and neck squamous cell carcinoma (HNSCC) patients, yet drug resistance remains a critical challenge. Developing personalized treatment strategies based on the molecular heterogeneity of HNSCC is essential to enhance therapeutic efficacy and prognosis.

METHODS

We integrated four HNSCC datasets (TCGA-HNSCC, GSE27020, GSE41613, and GSE65858) from TCGA and GEO databases. Using 10 multi-omics consensus clustering algorithms via the MOVICS package, we identified two molecular subtypes (CS1 and CS2) and validated their stability. A machine learning-driven prognostic signature was constructed by combining 101 algorithms, ultimately selecting 30 prognosis-related genes (PRGs) with the Elastic Net model. This signature was further linked to immune infiltration, functional pathways, and therapeutic sensitivity.

RESULTS

CS1 exhibited superior survival outcomes in both TCGA and META-HNSCC cohorts. The PRG-based signature stratified patients into low- and high-risk groups, with the low-risk group showing prolonged survival, enhanced immune cell infiltration (B cells, T cells, monocytes), and activated immune functions (cytolytic activity, T cell co-stimulation). High-risk patients were more sensitive to radiotherapy and chemotherapy (e.g., Cisplatin, 5-Fluorouracil), while low-risk patients responded better to immunotherapy and targeted therapies.

CONCLUSION

Our study delineates two molecular subtypes of HNSCC and establishes a robust prognostic model using multi-omics data and machine learning. These findings provide a framework for personalized treatment selection, offering clinical insights to optimize therapeutic strategies for HNSCC patients.

NMFProfiler: a multi-omics integration method for samples stratified in groups

MOTIVATION

The development of high-throughput sequencing enabled the massive production of "omics" data for various applications in biology. By analyzing simultaneously paired datasets collected on the same samples, integrative statistical approaches allow researchers to get a global picture of such systems and to highlight existing relationships between various molecular types and levels. Here, we introduce NMFProfiler, an integrative supervised NMF that accounts for the stratification of samples into groups of biological interest.

RESULTS

NMFProfiler was shown to successfully extract signatures characterizing groups with performances comparable to or better than state-of-the-art approaches. In particular, NMFProfiler was used in a clinical study on atopic dermatitis (AD) and to analyze a multi-omic cancer dataset. In the first case, it successfully identified signatures combining known AD protein biomarkers and novel transcriptomic biomarkers. In addition, it was also able to extract signatures significantly associated to cancer survival.

AVAILABILITY AND IMPLEMENTATION

NMFProfiler is released as a Python package, NMFProfiler (v0.3.0), available on PyPI.

Comprehensive Evaluation of Multi-Omics Clustering Algorithms for Cancer Molecular Subtyping

As a highly heterogeneous and complex disease, the identification of cancer's molecular subtypes is crucial for accurate diagnosis and personalized treatment. The integration of multi-omics data enables a comprehensive interpretation of the molecular characteristics of cancer at various biological levels. In recent years, an increasing number of multi-omics clustering algorithms for cancer molecular subtyping have been proposed. However, the absence of a definitive gold standard makes it challenging to evaluate and compare these methods effectively. In this study, we developed a general framework for the comprehensive evaluation of multi-omics clustering algorithms and introduced an innovative metric, the accuracy-weighted average index, which simultaneously considers both clustering performance and clinical relevance. Using this framework, we performed a thorough evaluation and comparison of 11 state-of-the-art multi-omics clustering algorithms, including deep learning-based methods. By integrating the accuracy-weighted average index with computational efficiency, our analysis reveals that PIntMF demonstrates the best overall performance, making it a promising tool for molecular subtyping across a wide range of cancers.

Integrative multi-omic and machine learning approach for prognostic stratification and therapeutic targeting in lung squamous cell carcinoma

The proliferation, metastasis, and drug resistance of cancer cells pose significant challenges to the treatment of lung squamous cell carcinoma (LUSC). However, there is a lack of optimal predictive models that can accurately forecast patient prognosis and guide the selection of targeted therapies. The extensive multi-omic data obtained from multi-level molecular biology provides a unique perspective for understanding the underlying biological characteristics of cancer, offering potential prognostic indicators and drug sensitivity biomarkers for LUSC patients. We integrated diverse datasets encompassing gene expression, DNA methylation, genomic mutations, and clinical data from LUSC patients to achieve consensus clustering using a suite of 10 multi-omics integration algorithms. Subsequently, we employed 10 commonly used machine learning algorithms, combining them into 101 unique configurations to design an optimal performing model. We then explored the characteristics of high- and low-risk LUSC patient groups in terms of the tumor microenvironment and response to immunotherapy, ultimately validating the functional roles of the model genes through in vitro experiments. Through the application of 10 clustering algorithms, we identified two prognostically relevant subtypes, with CS1 exhibiting a more favorable prognosis. We then constructed a subtype-specific machine learning model, LUSC multi-omics signature (LMS) based on seven key hub genes. Compared to previously published LUSC biomarkers, our LMS score demonstrated superior predictive performance. Patients with lower LMS scores had higher overall survival rates and better responses to immunotherapy. Notably, the high LMS group was more inclined toward "cold" tumors, characterized by immune suppression and exclusion, but drugs like dasatinib may represent promising therapeutic options for these patients. Notably, we also validated the model gene SERPINB13 through cell experiments, confirming its role as a potential oncogene influencing the progression of LUSC and as a promising therapeutic target. Our research provides new insights into refining the molecular classification of LUSC and further optimizing immunotherapy strategies.

Multi-modality MRI radiomics phenotypes in intermediate-high risk endometrial cancer: correlations with histopathology and prognosis

OBJECTIVES

This study aimed to identify the magnetic resonance imaging (MRI)-based radiomics phenotypes of intermediate-to-high-risk endometrial cancers (ECs), explore their association with histopathologic features, and compare their prognostic ability with the International Federation of Gynecology and Obstetrics (FIGO) stage.

METHODS

This study retrospectively recruited 355 patients with pathologically confirmed EC from 01/2016 to 06/2023. 166(46.8%) were classified as intermediate-to-high-risk ECs according to the European Society for Medical Oncology guidelines. Radiomics clustering analysis was performed on preoperative MRI to identify the radiomics phenotype of intermediate-to-high-risk ECs. The association between the radiomics phenotypes and the clinicopathologic information was explored, and the added value in predicting the recurrence was also evaluated using concordance index (C-index).

RESULTS

Of the included 166 patients (average age 56.83 ± 9.25 years), 23 were recurrent patients. The corresponding tumors in various clusters were assigned to phenotypes 1 and 2. Larger tumor diameter (P < .01), cervical mucosa invasion [30(36.15%) vs 15(18.07%), P = .01], deep myometrial infiltration [51(61.45%) vs 31(37.35%), P = .00], and histologic subtype [17(20.48%) vs 5(6.02%), P = .01] were associated with subtype 1. The risk of recurrence (P = .01) was higher in phenotype 1, and the FIGO stage could further differentiate higher recurrence risk in phenotype 1 (P < .01). The C-index was 0.66 for the radiomics phenotype model, 0.69 for the FIGO stage model, and 0.72 for the combined model.

CONCLUSIONS

MRI-based radiomics consensus clustering enabled the identification of associations between radiomics features and histopathologic features in intermediate-to-high-risk EC. The FIGO stage could further elevate the prediction ability of recurrence risk.

Integrating immune multi-omics and machine learning to improve prognosis, immune landscape, and sensitivity to first- and second-line treatments for head and neck squamous cell carcinoma

In recent years, immune checkpoint inhibitors (ICIs) has emerged as a fundamental component of the standard treatment regimen for patients with head and neck squamous cell carcinoma (HNSCC). However, accurately predicting the treatment effectiveness of ICIs for patients at the same TNM stage remains a challenge. In this study, we first combined multi-omics data (mRNA, lncRNA, miRNA, DNA methylation, and somatic mutations) and 10 clustering algorithms, successfully identifying two distinct cancer subtypes (CSs) (CS1 and CS2). Subsequently, immune-regulated genes (IRGs) and machine learning algorithms were utilized to construct a consensus machine learning-driven prediction immunotherapy signature (CMPIS). Further, the prognostic model was validated and compared across multiple datasets, including clinical characteristics, external datasets, and previously published models. Ultimately, the response of different CMPIS patients to immunotherapy, targeted therapy, radiotherapy and chemotherapy was also explored. First, Two distinct molecular subtypes were successfully identified by integrating immunomics data with machine learning techniques, and it was discovered that the CS1 subtype tended to be classified as "cold tumors" or "immunosuppressive tumors", whereas the CS2 subtype was more likely to represent "hot tumors" or "immune-activated tumors". Second, 303 different algorithms were employed to construct prognostic models and the average C-index value for each model was calculated across various cohorts. Ultimately, the StepCox [forward] + Ridge algorithm, which had the highest average C-index value of 0.666, was selected and this algorithm was used to construct the CMPIS predictive model comprising 16 key genes. Third, this predictive model was compared with patients' clinical features, such as age, gender, TNM stage, and grade stage. The findings indicated that this prognostic model exhibited the best performance in terms of C-index and AUC values. Additionally, it was compared with previously published models and it was found that the C-index of CMPIS ranked in the top 5 among 94 models across the TCGA, GSE27020, GSE41613, GSE42743, GSE65858, and META datasets. Lastly, the study revealed that patients with lower CMPIS were more sensitive to immunotherapy and chemotherapy, while those with higher CMPIS were more responsive to radiation therapy and EGFR-targeted treatments. In summary, our study identified two CSs (CS1 and CS2) of HNSCC using multi-omics data and predicted patient prognosis and treatment response by constructing the CMPIS model with IRGs and 303 machine learning algorithms, which underscores the importance of immunotherapy biomarkers in providing more targeted, precise, and personalized immunotherapy plans for HNSCC patients, significantly contributing to the optimization of clinical treatment outcomes.

Multiomics integration and machine learning reveal prognostic programmed cell death signatures in gastric cancer

Gastric cancer (GC) is characterized by notable heterogeneity and the impact of molecular subtypes on treatment and prognosis. The role of programmed cell death (PCD) in cellular processes is critical, yet its specific function in GC is underexplored. This study applied multiomics approaches, integrating transcriptomic, epigenetic, and somatic mutation data, with consensus clustering algorithms to classify GC molecular subtypes and assess their biological and immunological features. A machine learning model was developed to create the Gastric Cancer Multi-Omics Programmed Cell Death Signature (GMPS), targeting PCD-related genes. We verified the expression of the GMPS hub genes using the RT-qPCR method. The prognostic influence of GMPS on GC was then evaluated. Single-cell analysis was performed to examine the heterogeneity of PCD characteristics in GC. Findings indicate that GMPS notably correlates with patient survival rates, tumor mutational burden (TMB), and copy number variations (CNV), demonstrating substantial prognostic predictive power. Moreover, GMPS is closely associated with the tumor microenvironment (TME) and immune therapy response. This research elucidates the molecular subtypes of GC, highlighting PCD's critical role in prognosis assessment. The relationship between GMPS and immune therapy response, alongside gastric cancer's microenvironmental features, provides insights for personalized treatment.

SiRCle (Signature Regulatory Clustering) model integration reveals mechanisms of phenotype regulation in renal cancer

BACKGROUND

Clear cell renal cell carcinoma (ccRCC) tumours develop and progress via complex remodelling of the kidney epigenome, transcriptome, proteome and metabolome. Given the subsequent tumour and inter-patient heterogeneity, drug-based treatments report limited success, calling for multi-omics studies to extract regulatory relationships, and ultimately, to develop targeted therapies. Yet, methods for multi-omics integration to reveal mechanisms of phenotype regulation are lacking.

METHODS

Here, we present SiRCle (Signature Regulatory Clustering), a method to integrate DNA methylation, RNA-seq and proteomics data at the gene level by following central dogma of biology, i.e. genetic information proceeds from DNA, to RNA, to protein. To identify regulatory clusters across the different omics layers, we group genes based on the layer where the gene's dysregulation first occurred. We combine the SiRCle clusters with a variational autoencoder (VAE) to reveal key features from omics' data for each SiRCle cluster and compare patient subpopulations in a ccRCC and a PanCan cohort.

RESULTS

Applying SiRCle to a ccRCC cohort, we showed that glycolysis is upregulated by DNA hypomethylation, whilst mitochondrial enzymes and respiratory chain complexes are translationally suppressed. Additionally, we identify metabolic enzymes associated with survival along with the possible molecular driver behind the gene's perturbations. By using the VAE to integrate omics' data followed by statistical comparisons between tumour stages on the integrated space, we found a stage-dependent downregulation of proximal renal tubule genes, hinting at a loss of cellular identity in cancer cells. We also identified the regulatory layers responsible for their suppression. Lastly, we applied SiRCle to a PanCan cohort and found common signatures across ccRCC and PanCan in addition to the regulatory layer that defines tissue identity.

CONCLUSIONS

Our results highlight SiRCle's ability to reveal mechanisms of phenotype regulation in cancer, both specifically in ccRCC and broadly in a PanCan context. SiRCle ranks genes according to biological features. https://github.com/ArianeMora/SiRCle_multiomics_integration .

Multi-omics characterization and machine learning of lung adenocarcinoma molecular subtypes to guide precise chemotherapy and immunotherapy

Background

Lung adenocarcinoma (LUAD) is a heterogeneous tumor characterized by diverse genetic and molecular alterations. Developing a multi-omics-based classification system for LUAD is urgently needed to advance biological understanding.

Methods

Data on clinical and pathological characteristics, genetic alterations, DNA methylation patterns, and the expression of mRNA, lncRNA, and microRNA, along with somatic mutations in LUAD patients, were gathered from the TCGA and GEO datasets. A computational workflow was utilized to merge multi-omics data from LUAD patients through 10 clustering techniques, which were paired with 10 machine learning methods to pinpoint detailed molecular subgroups and refine a prognostic risk model. The disparities in somatic mutations, copy number alterations, and immune cell infiltration between high- and low-risk groups were assessed. The effectiveness of immunotherapy in patients was evaluated through the TIDE and SubMap algorithms, supplemented by data from various immunotherapy groups. Furthermore, the Cancer Therapeutics Response Portal (CTRP) and the PRISM Repurposing dataset (PRISM) were employed to investigate new drug treatment approaches for LUAD. In the end, the role of SLC2A1 in tumor dynamics was examined using RT-PCR, immunohistochemistry, CCK-8, wound healing, and transwell tests.

Results

By employing multi-omics clustering, we discovered two unique cancer subtypes (CSs) linked to prognosis, with CS2 demonstrating a better outcome. A strong model made up of 17 genes was created using a random survival forest (RSF) method, which turned out to be an independent predictor of overall survival and showed reliable and impressive performance. The low-risk group not only had a better prognosis but also was more likely to display the "cold tumor" phenotype. On the other hand, individuals in the high-risk group showed a worse outlook and were more likely to respond positively to immunotherapy and six particular chemotherapy medications. Laboratory cell tests demonstrated that SLC2A1 is abundantly present in LUAD tissues and cells, greatly enhancing the proliferation and movement of LUAD cells.

Conclusions

Thorough examination of multi-omics data offers vital understanding and improves the molecular categorization of LUAD. Utilizing a powerful machine learning system, we highlight the immense potential of the riskscore in providing individualized risk evaluations and customized treatment suggestions for LUAD patients.

Multi-view multi-level contrastive graph convolutional network for cancer subtyping on multi-omics data

Cancer is a highly diverse group of diseases, and each type of cancer can be further divided into various subtypes according to specific characteristics, cellular origins, and molecular markers. Subtyping helps in tailoring treatment and prognosis accuracy. However, the existing studies are more concerned with integrating different omics data to discover potential connections, but ignoring the relationships between consensus information and individual information within each omics level during the integration process. To this end, we propose a novel fusion-free method called multi-view multi-level contrastive graph convolutional network (M$^{2}$CGCN) for cancer subtyping. M$^{2}$CGCN learns multi-level features, i.e. high-level and low-level features, respectively. The low-level features from each view capture the intrinsic information in each omics by reconstruction of node attribute and graph structures. The high-level features achieve cancer subtyping via contrastive learning. Comprehensive experiments were performed on 34 multi-omics cancer datasets. The findings indicate that M$^{2}$CGCN achieves results comparable to or surpassing many state-of-the-art methods.

Multi-Omics Integration in Nephrology: Advances, Challenges, and Future Directions

Omics technologies have transformed nephrology, providing deep insights into molecular mechanisms of kidney disease and enabling more precise diagnostic tools, therapeutic strategies, and prognostic markers. Multi-omics data integration, spanning bulk, single-cell, and spatial omics, offers a comprehensive view of kidney biology in health and disease. In this review, we explore methods and challenges for integrating transcriptomic, epigenomic, and spatial data. By combining omics layers, researchers can uncover novel molecular interactions and spatial tissue organization, advancing our understanding of diseases like diabetic kidney disease and autosomal polycystic kidney disease. This integrated approach is reshaping diagnostic and therapeutic strategies in nephrology and is critical for optimizing insights available from spatial and multi-omics analysis.

Interpretable multi-omics integration with UMAP embeddings and density-based clustering

Integrating high-dimensional cellular multi-omics data is crucial for understanding various layers of biological control. Single 'omic methods provide important insights, but often fall short in handling the complex relationships between genes, proteins, metabolites and beyond. Here, we present a novel, non-linear, and unsupervised method called GAUDI (Group Aggregation via UMAP Data Integration) that leverages independent UMAP embeddings for the concurrent analysis of multiple data types. GAUDI uncovers non-linear relationships among different omics data better than several state-of-the-art methods. This approach not only clusters samples by their multi-omic profiles but also identifies latent factors across each omics dataset, thereby enabling interpretation of the underlying features contributing to each cluster. Consequently, GAUDI facilitates more intuitive, interpretable visualizations to identify novel insights and potential biomarkers from a wide range of experimental designs.

A metagene based similarity network fusion approach for multi-omics data integration identified novel subtypes in renal cell carcinoma

Renal cell carcinoma (RCC) ranks among the most prevalent cancers worldwide, with both incidence and mortality rates increasing annually. The heterogeneity among RCC patients presents considerable challenges for developing universally effective treatment strategies, emphasizing the necessity of in-depth research into RCC's molecular mechanisms, understanding the variations among RCC patients and further identifying distinct molecular subtypes for precise treatment. We proposed a metagene-based similarity network fusion (Meta-SNF) method for RCC subtype identification with multi-omics data, using a non-negative matrix factorization technique to capture alternative structures inherent in the dataset as metagenes. These latent metagenes were then integrated to construct a fused network under the Similarity Network Fusion (SNF) framework for more precise subtyping. We conducted simulation studies and analyzed real-world data from two RCC datasets, namely kidney renal clear cell carcinoma (KIRC) and kidney renal papillary cell carcinoma (KIRP) to demonstrate the utility of Meta-SNF. The simulation studies indicated that Meta-SNF achieved higher accuracy in subtype identification compared with the original SNF and other state-of-the-art methods. In analyses of real data, Meta-SNF produced more distinct and well-separated clusters, classifying both KIRC and KIRP into four subtypes with significant differences in survival outcomes. Subsequently, we performed comprehensive bioinformatics analyses focused on subtypes with poor prognoses in KIRC and KIRP and identified several potential biomarkers. Meta-SNF offers a novel strategy for subtype identification using multi-omics data, and its application to RCC datasets has yielded diverse biological insights which are highly valuable for informing clinical decision-making processes in the treatment of RCC.

Molecular precision medicine: Multi-omics-based stratification model for acute myeloid leukemia

Acute myeloid leukemia (AML), as the most common malignancy of the hematopoietic system, poses challenges in treatment efficacy, relapse, and drug resistance. In this study, we have utilized 151 RNA sequencing datasets, 194 DNA methylation datasets, and 200 somatic mutation datasets from the AML cohort in the TCGA database to develop a multi-omics stratification model. This model enables comparison of prognosis, clinical features, gene mutations, immune microenvironment and drug sensitivity across subgroups. External validation datasets have been sourced from the GEO database, which includes 562 mRNA datasets and 136 miRNA datasets from 984 adult AML patients. Through multi-omics-based stratification model, we classified 126 AML patients into 4 clusters (CS). CS4 had the best prognosis, with the youngest age, highest M3 subtype proportion, fewest copy number alterations, and common mutations in WT1, FLT3, and KIT genes. It showed sensitivity to HDAC inhibitors and BCL-2 inhibitors. Both the M3 subtype and CS4 were identified as independent protective factors for survival. Conversely, CS3 had the worst prognosis due to older age, high copy number alterations, and frequent mutations in RUNX1, DNMT3A, and TP53 genes. Additionally, it showed higher proportions of cytotoxic cells and Tregs, suggesting potential sensitivity to mTOR inhibitors. CS1 had a better prognosis than CS2, with more copy number alterations, while CS2 had higher monocyte proportions. CS1 showed good sensitivity to cytarabine, while CS2 was sensitive to RXR agonists. Both CS1 and CS2, which predominantly featured mutations in FLT3, NPM1, and DNMT3A genes, benefited from FLT3 inhibitors. Using the Kappa test, our stratification model underwent robust validation in the miRNA and mRNA external validation datasets. With advancements in sequencing technology and machine learning algorithms, AML is poised to transition towards multi-omics precision medicine in the future. We aspire for our study to offer new perspectives on multi-drug combination clinical trials and multi-targeted precision medicine for AML.

Integrative analysis of multi-omics data reveals importance of collagen and the PI3K AKT signalling pathway in CAKUT

Congenital Anomalies of the Kidney and Urinary Tract (CAKUT) is the leading cause of childhood chronic kidney failure and a significant cause of chronic kidney disease in adults. Genetic and environmental factors are known to influence CAKUT development, but the currently known disease mechanism remains incomplete. Our goal is to identify affected pathways and networks in CAKUT, and thereby aid in getting a better understanding of its pathophysiology. With this goal, the miRNome, peptidome, and proteome of over 30 amniotic fluid samples of patients with non-severe CAKUT was compared to patients with severe CAKUT. These omics data sets were made findable, accessible, interoperable, and reusable (FAIR) to facilitate their integration with external data resources. Furthermore, we analysed and integrated the omics data sets using three different bioinformatics strategies: integrative analysis with mixOmics, joint dimensionality reduction and pathway analysis. The three bioinformatics analyses provided complementary features, but all pointed towards an important role for collagen in CAKUT development and the PI3K-AKT signalling pathway. Additionally, several key genes (CSF1, IGF2, ITGB1, and RAC1) and microRNAs were identified. We published the three analysis strategies as containerized workflows. These workflows can be applied to other FAIR data sets and help gaining knowledge on other rare diseases.

Artificial intelligence in ovarian cancer drug resistance advanced 3PM approach: subtype classification and prognostic modeling

Background

Ovarian cancer patients' resistance to first-line treatment posed a significant challenge, with approximately 70% experiencing recurrence and developing strong resistance to first-line chemotherapies like paclitaxel.

Objectives

Within the framework of predictive, preventive, and personalized medicine (3PM), this study aimed to use artificial intelligence to find drug resistance characteristics at the single cell, and further construct the classification strategy and deep learning prognostic models based on these resistance traits, which can better facilitate and perform 3PM.

Methods

This study employed "Beyondcell," an algorithm capable of predicting cellular drug responses, to calculate the similarity between the expression patterns of 21,937 cells from ovarian cancer samples and the signatures of 5201 drugs to identify drug-resistance cells. Drug resistance features were used to perform 10 multi-omics clustering on the TCGA training set to identify patient subgroups with differential drug responses. Concurrently, a deep learning prognostic model with KAN architecture which had a flexible activation function to better fit the model was constructed for this training set. The constructed patient subtype classifier and prognostic model were evaluated using three external validation sets from GEO: GSE17260, GSE26712, and GSE51088.

Results

This study identified that endothelial cells are resistant to paclitaxel, doxorubicin, and docetaxel, suggesting their potential as targets for cellular therapy in ovarian cancer patients. Based on drug resistance features, 10 multi-omics clustering identified four patient subtypes with differential responses to four chemotherapy drugs, in which subtype CS2 showed the highest drug sensitivity to all four drugs. The other subtypes also showed enrichment in different biological pathways and immune infiltration, allowing for targeted treatment based on their characteristics. Besides, this study applied the latest KAN architecture in artificial intelligence to replace the MLP structure in the DeepSurv prognostic model, finally demonstrating robust performance on patients' prognosis prediction.

Conclusions

This study, by classifying patients and constructing prognostic models based on resistance characteristics to first-line drugs, has effectively applied multi-omics data into the realm of 3PM.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13167-024-00374-4.

Singular Value Decomposition-Driven Non-negative Matrix Factorization with Application to Identify the Association Patterns of Sarcoma Recurrence

Sarcomas are malignant tumors from mesenchymal tissue and are characterized by their complexity and diversity. The high recurrence rate making it important to understand the mechanisms behind their recurrence and to develop personalized treatments and drugs. However, previous studies on the association patterns of multi-modal data on sarcoma recurrence have overlooked the fact that genes do not act independently, but rather function within signaling pathways. Therefore, this study collected 290 whole solid images, 869 gene and 1387 pathway data of over 260 sarcoma samples from UCSC and TCGA to identify the association patterns of gene-pathway-cell related to sarcoma recurrences. Meanwhile, considering that most multi-modal data fusion methods based on the joint non-negative matrix factorization (NMF) model led to poor experimental repeatability due to random initialization of factorization parameters, the study proposed the singular value decomposition (SVD)-driven joint NMF model by applying the SVD method to calculate initialized weight and coefficient matrices to achieve the reproducibility of the results. The results of the experimental comparison indicated that the SVD algorithm enhances the performance of the joint NMF algorithm. Furthermore, the representative module indicated a significant relationship between genes in pathways and image features. Multi-level analysis provided valuable insights into the connections between biological processes, cellular features, and sarcoma recurrence. In addition, potential biomarkers were uncovered, while various mechanisms of sarcoma recurrence were identified from an imaging genetic perspective. Overall, the SVD-NMF model affords a novel perspective on combining multi-omics data to explore the association related to sarcoma recurrence.

Integrating host and microbiome biology using holo-omics

Holo-omics is the use of omics data to study a host and its inherent microbiomes - a biological system known as a "holobiont". A microbiome that exists in such a space often encounters habitat stability and in return provides metabolic capacities that can benefit their host. Here we present an overview of beneficial host-microbiome systems and propose and discuss several methodological frameworks that can be used to investigate the intricacies of the many as yet undefined host-microbiome interactions that influence holobiont homeostasis. While this is an emerging field, we anticipate that ongoing methodological advancements will enhance the biological resolution that is necessary to improve our understanding of host-microbiome interplay to make meaningful interpretations and biotechnological applications.

Bootstrap Evaluation of Association Matrices (BEAM) for Integrating Multiple Omics Profiles with Multiple Outcomes

Motivation

Large datasets containing multiple clinical and omics measurements for each subject motivate the development of new statistical methods to integrate these data to advance scientific discovery.

Model

We propose bootstrap evaluation of association matrices (BEAM), which integrates multiple omics profiles with multiple clinical endpoints. BEAM associates a set omic features with clinical endpoints via regression models and then uses bootstrap resampling to determine statistical significance of the set. Unlike existing methods, BEAM uniquely accommodates an arbitrary number of omic profiles and endpoints.

Results

In simulations, BEAM performed similarly to the theoretically best simple test and outperformed other integrated analysis methods. In an example pediatric leukemia application, BEAM identified several genes with biological relevance established by a CRISPR assay that had been missed by univariate screens and other integrated analysis methods. Thus, BEAM is a powerful, flexible, and robust tool to identify genes for further laboratory and/or clinical research evaluation.

Availability

Source code, documentation, and a vignette for BEAM are available on GitHub at: https://github.com/annaSeffernick/BEAMR. The R package is available from CRAN at: https://cran.r-project.org/package=BEAMR.

Contact

Stanley.Pounds@stjude.org.

Supplementary Information

Supplementary data are available at the journal's website.

Deep self-reconstruction driven joint nonnegative matrix factorization model for identifying multiple genomic imaging associations in complex diseases

OBJECTIVE

Comprehensive analysis of histopathology images and transcriptomics data enables the identification of candidate biomarkers and multimodal association patterns. Most existing multimodal data association studies are derived from extensions of the joint nonnegative matrix factorization model for identifying complex data associations, which can make full use of clinical prior information. However, the raw data were usually taken as the input without considering the underlying complex multi-subspace structure, influencing the subsequent integration analysis results.

METHODS

This study proposed a deep-self reconstructed joint nonnegative matrix factorization (DSRJNMF) model to use self-expressive properties to reconstruct the raw data to characterize the similarity structure associated with clinical labels. Then, the sparsity, orthogonality, and regularization constraints constructed from prior information are added to the DSRJNMF model to determine the sparse set of biologically relevant features across modalities.

RESULTS

The algorithm has been applied to identify the imaging genetic association of triple negative breast cancer (TNBC). Multilevel experimental results demonstrate that the proposed algorithm better estimates potential associations between pathological image features and miRNA-gene and identifies consistent multimodal imaging genetic biomarkers to guide the interpretation of TNBC.

CONCLUSION

The propose method provides a novel idea of data association analysis oriented to complex diseases.

COPS: A novel platform for multi-omic disease subtype discovery via robust multi-objective evaluation of clustering algorithms

Recent research on multi-view clustering algorithms for complex disease subtyping often overlooks aspects like clustering stability and critical assessment of prognostic relevance. Furthermore, current frameworks do not allow for a comparison between data-driven and pathway-driven clustering, highlighting a significant gap in the methodology. We present the COPS R-package, tailored for robust evaluation of single and multi-omics clustering results. COPS features advanced methods, including similarity networks, kernel-based approaches, dimensionality reduction, and pathway knowledge integration. Some of these methods are not accessible through R, and some correspond to new approaches proposed with COPS. Our framework was rigorously applied to multi-omics data across seven cancer types, including breast, prostate, and lung, utilizing mRNA, CNV, miRNA, and DNA methylation data. Unlike previous studies, our approach contrasts data- and knowledge-driven multi-view clustering methods and incorporates cross-fold validation for robustness. Clustering outcomes were assessed using the ARI score, survival analysis via Cox regression models including relevant covariates, and the stability of the results. While survival analysis and gold-standard agreement are standard metrics, they vary considerably across methods and datasets. Therefore, it is essential to assess multi-view clustering methods using multiple criteria, from cluster stability to prognostic relevance, and to provide ways of comparing these metrics simultaneously to select the optimal approach for disease subtype discovery in novel datasets. Emphasizing multi-objective evaluation, we applied the Pareto efficiency concept to gauge the equilibrium of evaluation metrics in each cancer case-study. Affinity Network Fusion, Integrative Non-negative Matrix Factorization, and Multiple Kernel K-Means with linear or Pathway Induced Kernels were the most stable and effective in discerning groups with significantly different survival outcomes in several case studies.

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

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

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

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

Joint multi-omics discriminant analysis with consistent representation learning using PANDA

Integrative multi-omics analysis provides deeper insight and enables better and more realistic modeling of the underlying biology and causes of diseases than does single omics analysis. Although several integrative multi-omics analysis methods have been proposed and demonstrated promising results in integrating distinct omics datasets, inconsistent distribution of the different omics data, which is caused by technology variations, poses a challenge for paired integrative multi-omics methods. In addition, the existing discriminant analysis-based integrative methods do not effectively exploit correlation and consistent discriminant structures, necessitating a compromise between correlation and discrimination in using these methods. Herein we present PAN-omics Discriminant Analysis (PANDA), a joint discriminant analysis method that seeks omics-specific discriminant common spaces by jointly learning consistent discriminant latent representations for each omics. PANDA jointly maximizes between-class and minimizes within-class omics variations in a common space and simultaneously models the relationships among omics at the consistency representation and cross-omics correlation levels, overcoming the need for compromise between discrimination and correlation as with the existing integrative multi-omics methods. Because of the consistency representation learning incorporated into the objective function of PANDA, this method seeks a common discriminant space to minimize the differences in distributions among omics, can lead to a more robust latent representations than other methods, and is against the inconsistency of the different omics. We compared PANDA to 10 other state-of-the-art multi-omics data integration methods using both simulated and real-world multi-omics datasets and found that PANDA consistently outperformed them while providing meaningful discriminant latent representations. PANDA is implemented using both R and MATLAB, with codes available at https://github.com/WuLabMDA/PANDA.

Exploring the mystery of colon cancer from the perspective of molecular subtypes and treatment

The molecular categorization of colon cancer patients remains elusive. Gene set enrichment analysis (GSEA), which investigates the dysregulated genes among tumor and normal samples, has revealed the pivotal role of epithelial-to-mesenchymal transition (EMT) in colon cancer pathogenesis. In this study, we employed multi-clustering method for grouping data, resulting in the identification of two clusters characterized by varying prognostic outcomes. These two subgroups not only displayed disparities in overall survival (OS) but also manifested variations in clinical variables, genetic mutation, and gene expression profiles. Using the nearest template prediction (NTP) method, we were able to replicate the molecular classification effectively within the original dataset and validated it across multiple independent datasets, underscoring its robust repeatability. Furthermore, we constructed two prognostic signatures tailored to each of these subgroups. Our molecular classification, centered on EMT, hold promise in offering fresh insights into the therapy strategies and prognosis assessment for colon cancer.

iCluF: an unsupervised iterative cluster-fusion method for patient stratification using multiomics data

Motivation

Patient stratification is crucial for the effective treatment or management of heterogeneous diseases, including cancers. Multiomic technologies facilitate molecular characterization of human diseases; however, the complexity of data warrants the need for the development of robust data integration tools for patient stratification using machine-learning approaches.

Results

iCluF iteratively integrates three types of multiomic data (mRNA, miRNA, and DNA methylation) using pairwise patient similarity matrices built from each omic data. The intermediate omic-specific neighborhood matrices implement iterative matrix fusion and message passing among the similarity matrices to derive a final integrated matrix representing all the omics profiles of a patient, which is used to further cluster patients into subtypes. iCluF outperforms other methods with significant differences in the survival profiles of 8581 patients belonging to 30 different cancers in TCGA. iCluF also predicted the four intrinsic subtypes of Breast Invasive Carcinomas with adjusted rand index and Fowlkes-Mallows scores of 0.72 and 0.83, respectively. The Gini importance score showed that methylation features were the primary decisive players, followed by mRNA and miRNA to identify disease subtypes. iCluF can be applied to stratify patients with any disease containing multiomic datasets.

Availability and implementation

Source code and datasets are available at https://github.com/GudaLab/iCluF_core.

Mononuclear phagocyte system-related multi-omics features yield head and neck squamous cell carcinoma subtypes with distinct overall survival, drug, and immunotherapy responses

BACKGROUND

Recent research reported that mononuclear phagocyte system (MPS) can contribute to immune defense but the classification of head and neck squamous cell carcinoma (HNSCC) patients based on MPS-related multi-omics features using machine learning lacked.

METHODS

In this study, we obtain marker genes for MPS through differential analysis at the single-cell level and utilize "similarity network fusion" and "MoCluster" algorithms to cluster patients' multi-omics features. Subsequently, based on the corresponding clinical information, we investigate the prognosis, drugs, immunotherapy, and biological differences between the subtypes. A total of 848 patients have been included in this study, and the results obtained from the training set can be verified by two independent validation sets using "the nearest template prediction".

RESULTS

We identified two subtypes of HNSCC based on MPS-related multi-omics features, with CS2 exhibiting better predictive prognosis and drug response. CS2 represented better xenobiotic metabolism and higher levels of T and B cell infiltration, while the biological functions of CS1 were mainly enriched in coagulation function, extracellular matrix, and the JAK-STAT signaling pathway. Furthermore, we established a novel and stable classifier called "getMPsub" to classify HNSCC patients, demonstrating good consistency in the same training set. External validation sets classified by "getMPsub" also illustrated similar differences between the two subtypes.

CONCLUSIONS

Our study identified two HNSCC subtypes by machine learning and explored their biological difference. Notably, we constructed a robust classifier that presented an excellent classifying prediction, providing new insight into the precision medicine of HNSCC.

Accurate integration of single-cell DNA and RNA for analyzing intratumor heterogeneity using MaCroDNA

Cancers develop and progress as mutations accumulate, and with the advent of single-cell DNA and RNA sequencing, researchers can observe these mutations and their transcriptomic effects and predict proteomic changes with remarkable temporal and spatial precision. However, to connect genomic mutations with their transcriptomic and proteomic consequences, cells with either only DNA data or only RNA data must be mapped to a common domain. For this purpose, we present MaCroDNA, a method that uses maximum weighted bipartite matching of per-gene read counts from single-cell DNA and RNA-seq data. Using ground truth information from colorectal cancer data, we demonstrate the advantage of MaCroDNA over existing methods in accuracy and speed. Exemplifying the utility of single-cell data integration in cancer research, we suggest, based on results derived using MaCroDNA, that genomic mutations of large effect size increasingly contribute to differential expression between cells as Barrett's esophagus progresses to esophageal cancer, reaffirming the findings of the previous studies.

Paired single-cell multi-omics data integration with Mowgli

The profiling of multiple molecular layers from the same set of cells has recently become possible. There is thus a growing need for multi-view learning methods able to jointly analyze these data. We here present Multi-Omics Wasserstein inteGrative anaLysIs (Mowgli), a novel method for the integration of paired multi-omics data with any type and number of omics. Of note, Mowgli combines integrative Nonnegative Matrix Factorization and Optimal Transport, enhancing at the same time the clustering performance and interpretability of integrative Nonnegative Matrix Factorization. We apply Mowgli to multiple paired single-cell multi-omics data profiled with 10X Multiome, CITE-seq, and TEA-seq. Our in-depth benchmark demonstrates that Mowgli's performance is competitive with the state-of-the-art in cell clustering and superior to the state-of-the-art once considering biological interpretability. Mowgli is implemented as a Python package seamlessly integrated within the scverse ecosystem and it is available at http://github.com/cantinilab/mowgli .

Multiomics characterization and verification of clear cell renal cell carcinoma molecular subtypes to guide precise chemotherapy and immunotherapy

Clear cell renal cell carcinoma (ccRCC) is a heterogeneous tumor with different genetic and molecular alterations. Schemes for ccRCC classification system based on multiomics are urgent, to promote further biological insights. Two hundred and fifty-five ccRCC patients with paired data of clinical information, transcriptome expression profiles, copy number alterations, DNA methylation, and somatic mutations were collected for identification. Bioinformatic analyses were performed based on our team's recently developed R package "MOVICS." With 10 state-of-the-art algorithms, we identified the multiomics subtypes (MoSs) for ccRCC patients. MoS1 is an immune exhausted subtype, presented the poorest prognosis, and might be caused by an exhausted immune microenvironment, activated hypoxia features, but can benefit from PI3K/AKT inhibitors. MoS2 is an immune "cold" subtype, which represented more mutation of VHL and PBRM1, favorable prognosis, and is more suitable for sunitinib therapy. MoS3 is the immune "hot" subtype, and can benefit from the anti-PD-1 immunotherapy. We successfully verified the different molecular features of the three MoSs in external cohorts GSE22541, GSE40435, and GSE53573. Patients that received Nivolumab therapy helped us to confirm that MoS3 is suitable for anti-PD-1 therapy. E-MTAB-3267 cohort also supported the fact that MoS2 patients can respond more to sunitinib treatment. We also confirm that SETD2 is a tumor suppressor in ccRCC, along with the decreased SETD2 protein level in advanced tumor stage, and knock-down of SETD2 leads to the promotion of cell proliferation, migration, and invasion. In summary, we provide novel insights into ccRCC molecular subtypes based on robust clustering algorithms via multiomics data, and encourage future precise treatment of ccRCC patients.

Integrated multiomics analysis and machine learning refine molecular subtypes and prognosis for muscle-invasive urothelial cancer

Muscle-invasive urothelial cancer (MUC), characterized by high aggressiveness and significant heterogeneity, is currently lacking highly precise individualized treatment options. We used a computational pipeline to synthesize multiomics data from MUC patients using 10 clustering algorithms, which were then combined with 10 machine learning algorithms to identify molecular subgroups of high resolution and develop a robust consensus machine learning-driven signature (CMLS). Through multiomics clustering, we identified three cancer subtypes (CSs) that are related to prognosis, with CS2 exhibiting the most favorable prognostic outcome. Subsequent screening enabled identification of 12 hub genes that constitute a CMLS with robust predictive power for prognosis. The low-CMLS group exhibited a more favorable prognosis and greater responsiveness to immunotherapy and was more likely to exhibit the "hot tumor" phenotype. The high-CMLS group had a poor prognosis and lower likelihood of benefitting from immunotherapy, but dasatinib and romidepsin may serve as promising treatments for them. Comprehensive analysis of multiomics data can offer important insights and further refine the molecular classification of MUC. Identification of CMLS represents a valuable tool for early prediction of patient prognosis and for screening potential candidates likely to benefit from immunotherapy, with broad implications for clinical practice.

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

BACKGROUND

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

RESULTS

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

CONCLUSIONS

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

Single-Cell Multiomics

Single-cell RNA sequencing methods have led to improved understanding of the heterogeneity and transcriptomic states present in complex biological systems. Recently, the development of novel single-cell technologies for assaying additional modalities, specifically genomic, epigenomic, proteomic, and spatial data, allows for unprecedented insight into cellular biology. While certain technologies collect multiple measurements from the same cells simultaneously, even when modalities are separately assayed in different cells, we can apply novel computational methods to integrate these data. The application of computational integration methods to multimodal paired and unpaired data results in rich information about the identities of the cells present and the interactions between different levels of biology, such as between genetic variation and transcription. In this review, we both discuss the single-cell technologies for measuring these modalities and describe and characterize a variety of computational integration methods for combining the resulting data to leverage multimodal information toward greater biological insight.

Predictive overfitting in immunological applications: Pitfalls and solutions

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

Phenomics and Robust Multiomics Data for Cardiovascular Disease Subtyping

The complex landscape of cardiovascular diseases encompasses a wide range of related pathologies arising from diverse molecular mechanisms and exhibiting heterogeneous phenotypes. This variety of manifestations poses significant challenges in the development of treatment strategies. The increasing availability of precise phenotypic and multiomics data of cardiovascular disease patient populations has spurred the development of a variety of computational disease subtyping techniques to identify distinct subgroups with unique underlying pathogeneses. In this review, we outline the essential components of computational approaches to select, integrate, and cluster omics and clinical data in the context of cardiovascular disease research. We delve into the challenges faced during different stages of the analysis, including feature selection and extraction, data integration, and clustering algorithms. Next, we highlight representative applications of subtyping pipelines in heart failure and coronary artery disease. Finally, we discuss the current challenges and future directions in the development of robust subtyping approaches that can be implemented in clinical workflows, ultimately contributing to the ongoing evolution of precision medicine in health care.

Clustering single-cell multimodal omics data with jrSiCKLSNMF

Introduction: The development of multimodal single-cell omics methods has enabled the collection of data across different omics modalities from the same set of single cells. Each omics modality provides unique information about cell type and function, so the ability to integrate data from different modalities can provide deeper insights into cellular functions. Often, single-cell omics data can prove challenging to model because of high dimensionality, sparsity, and technical noise. Methods: We propose a novel multimodal data analysis method called joint graph-regularized Single-Cell Kullback-Leibler Sparse Non-negative Matrix Factorization (jrSiCKLSNMF, pronounced "junior sickles NMF") that extracts latent factors shared across omics modalities within the same set of single cells. Results: We compare our clustering algorithm to several existing methods on four sets of data simulated from third party software. We also apply our algorithm to a real set of cell line data. Discussion: We show overwhelmingly better clustering performance than several existing methods on the simulated data. On a real multimodal omics dataset, we also find our method to produce scientifically accurate clustering results.

Integrative analysis of multi-omics and imaging data with incorporation of biological information via structural Bayesian factor analysis

MOTIVATION

With the rapid development of modern technologies, massive data are available for the systematic study of Alzheimer's disease (AD). Though many existing AD studies mainly focus on single-modality omics data, multi-omics datasets can provide a more comprehensive understanding of AD. To bridge this gap, we proposed a novel structural Bayesian factor analysis framework (SBFA) to extract the information shared by multi-omics data through the aggregation of genotyping data, gene expression data, neuroimaging phenotypes and prior biological network knowledge. Our approach can extract common information shared by different modalities and encourage biologically related features to be selected, guiding future AD research in a biologically meaningful way.

METHOD

Our SBFA model decomposes the mean parameters of the data into a sparse factor loading matrix and a factor matrix, where the factor matrix represents the common information extracted from multi-omics and imaging data. Our framework is designed to incorporate prior biological network information. Our simulation study demonstrated that our proposed SBFA framework could achieve the best performance compared with the other state-of-the-art factor-analysis-based integrative analysis methods.

RESULTS

We apply our proposed SBFA model together with several state-of-the-art factor analysis models to extract the latent common information from genotyping, gene expression and brain imaging data simultaneously from the ADNI biobank database. The latent information is then used to predict the functional activities questionnaire score, an important measurement for diagnosis of AD quantifying subjects' abilities in daily life. Our SBFA model shows the best prediction performance compared with the other factor analysis models.

AVAILABILITY

Code are publicly available at https://github.com/JingxuanBao/SBFA.

CONTACT

qlong@upenn.edu.

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

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