An official website of the United States government
Accurate cancer subtype prediction is crucial for personalized medicine. Integrating multi-omics data represents a viable approach to comprehending the intricate pathophysiology of complex diseases like cancer. Conventional machine learning techniques are not ideal for analyzing the complex interrelationships among different categories of omics data. Numerous models have been suggested using graph-based learning to uncover veiled representations and network formations unique to distinct types of omics data to heighten predictions regarding cancers and characterize patients’ profiles, amongst other applications aimed at improving disease management in medical research. The existing graph-based state-of-the-art multi-omics integration approaches for cancer subtype prediction, MOGONET, and SUPREME, use a graph convolutional network (GCN), which fails to consider the level of importance of neighboring nodes on a particular node. To address this gap, we hypothesize that paying attention to each neighbor or providing appropriate weights to neighbors based on their importance might improve the cancer subtype prediction. The natural choice to determine the importance of each neighbor of a node in a graph is to explore the graph attention network (GAT). Here, we propose MOGAT, a novel multi-omics integration approach, leveraging GAT models that incorporate graph-based learning with an attention mechanism. MOGAT utilizes a multi-head attention mechanism to extract appropriate information for a specific sample by assigning unique attention coefficients to neighboring samples. Based on our knowledge, our group is the first to explore GAT in multi-omics integration for cancer subtype prediction. To evaluate the performance of MOGAT in predicting cancer subtypes, we explored two sets of breast cancer data from TCGA and METABRIC. Our proposed approach, MOGAT, outperforms MOGONET by 32% to 46% and SUPREME by 2% to 16% in cancer subtype prediction in different scenarios, supporting our hypothesis. Our results also showed that GAT embeddings provide a better prognosis in differentiating the high-risk group from the low-risk group than raw features.
more »
« less
A multimodal graph neural network framework for cancer molecular subtype classification
Abstract BackgroundThe recent development of high-throughput sequencing has created a large collection of multi-omics data, which enables researchers to better investigate cancer molecular profiles and cancer taxonomy based on molecular subtypes. Integrating multi-omics data has been proven to be effective for building more precise classification models. Most current multi-omics integrative models use either an early fusion in the form of concatenation or late fusion with a separate feature extractor for each omic, which are mainly based on deep neural networks. Due to the nature of biological systems, graphs are a better structural representation of bio-medical data. Although few graph neural network (GNN) based multi-omics integrative methods have been proposed, they suffer from three common disadvantages. One is most of them use only one type of connection, either inter-omics or intra-omic connection; second, they only consider one kind of GNN layer, either graph convolution network (GCN) or graph attention network (GAT); and third, most of these methods have not been tested on a more complex classification task, such as cancer molecular subtypes. ResultsIn this study, we propose a novel end-to-end multi-omics GNN framework for accurate and robust cancer subtype classification. The proposed model utilizes multi-omics data in the form of heterogeneous multi-layer graphs, which combine both inter-omics and intra-omic connections from established biological knowledge. The proposed model incorporates learned graph features and global genome features for accurate classification. We tested the proposed model on the Cancer Genome Atlas (TCGA) Pan-cancer dataset and TCGA breast invasive carcinoma (BRCA) dataset for molecular subtype and cancer subtype classification, respectively. The proposed model shows superior performance compared to four current state-of-the-art baseline models in terms of accuracy, F1 score, precision, and recall. The comparative analysis of GAT-based models and GCN-based models reveals that GAT-based models are preferred for smaller graphs with less information and GCN-based models are preferred for larger graphs with extra information.
more »
« less
- Award ID(s):
- 1942303
- PAR ID:
- 10485978
- Publisher / Repository:
- Springer Science + Business Media
- Date Published:
- Journal Name:
- BMC Bioinformatics
- Volume:
- 25
- Issue:
- 1
- ISSN:
- 1471-2105
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Uveal melanoma (UM) is a comparatively rare cancer but requires serious consideration since patients with developing metastatic UM survive only for about 6–12 months. Fortunately, increasingly large multi-omics databases allow us to further understand cancer initiation and development. Moreover, previous studies have observed that associations between copy number aberrations (CNA) or methylation (MET) versus messenger RNA (mRNA) expression have affected these processes. From that, we decide to explore the effect of these associations on a case study of UM. Also, the current subtypes of UM display its weak association with biological phenotypes and its lack of therapy suggestions. Therefore, the re-identification of molecular subtypes is a pressing need. In this study, we recruit three omics profiles, including CNA, MET, and mRNA, in a UM cohort from The Cancer Genome Atlas (TCGA). Firstly, we identify two sets of genes, CNAexp and METexp, whose CNA and MET significantly correlated with their corresponding mRNA, respectively. Then, single and integrative analyses of the three data types are performed using the PINSPlus tool. As a result, we discover two novel integrative subgroups, IntSub1 and IntSub2, which could be a useful alternative classification for UM patients in the future. To further explore molecular events behind each subgroup, we identify their subgroup-specific genes computationally. Accordingly, the highest expressed genes among IntSub1-specific genes are mostly enriched with immune-related processes. On the other hand, IntSub2-specific genes are highly associated with cellular cation homeostasis, which responds effectively to chemotherapy using ion channel inhibitor drugs. In addition, we detect that the two integrative subgroups show different age-related risks and survival rates. These discoveries can influence the frequency of metastatic surveillance and support medical practitioners to choose an appropriate treatment regime.more » « less
-
Cancer is an umbrella term that includes a range of disorders, from those that are fast-growing and lethal to indolent lesions with low or delayed potential for progression to death. The treatment options, as well as treatment success, are highly dependent on the correct subtyping of individual patients. With the advancement of high-throughput platforms, we have the opportunity to differentiate among cancer subtypes from a holistic perspective that takes into consideration phenomena at different molecular levels (mRNA, methylation, etc.). This demands powerful integrative methods to leverage large multi-omics datasets for a better subtyping. Here we introduce Subtyping Multi-omics using a Randomized Transformation (SMRT), a new method for multi-omics integration and cancer subtyping. SMRT offers the following advantages over existing approaches: (i) the scalable analysis pipeline allows researchers to integrate multi-omics data and analyze hundreds of thousands of samples in minutes, (ii) the ability to integrate data types with different numbers of patients, (iii) the ability to analyze un-matched data of different types, and (iv) the ability to offer users a convenient data analysis pipeline through a web application. We also improve the efficiency of our ensemble-based, perturbation clustering to support analysis on machines with memory constraints. In an extensive analysis, we compare SMRT with eight state-of-the-art subtyping methods using 37 TCGA and two METABRIC datasets comprising a total of almost 12,000 patient samples from 28 different types of cancer. We also performed a number of simulation studies. We demonstrate that SMRT outperforms other methods in identifying subtypes with significantly different survival profiles. In addition, SMRT is extremely fast, being able to analyze hundreds of thousands of samples in minutes. The web application is available at http://SMRT.tinnguyen-lab.com . The R package will be deposited to CRAN as part of our PINSPlus software suite.more » « less
-
Advanced genomic and molecular profiling technologies accelerated the enlightenment of the regulatory mechanisms behind cancer development and progression, and the targeted therapies in patients. Along this line, intense studies with immense amounts of biological information have boosted the discovery of molecular biomarkers. Cancer is one of the leading causes of death around the world in recent years. Elucidation of genomic and epigenetic factors in Breast Cancer (BRCA) can provide a roadmap to uncover the disease mechanisms. Accordingly, unraveling the possible systematic connections between-omics data types and their contribution to BRCA tumor progression is crucial. In this study, we have developed a novel machine learning (ML) based integrative approach for multi-omics data analysis. This integrative approach combines information from gene expression (mRNA), microRNA (miRNA) and methylation data. Due to the complexity of cancer, this integrated data is expected to improve the prediction, diagnosis and treatment of disease through patterns only available from the 3-way interactions between these 3-omics datasets. In addition, the proposed method bridges the interpretation gap between the disease mechanisms that drive onset and progression. Our fundamental contribution is the 3 Multi-omics integrative tool (3Mint). This tool aims to perform grouping and scoring of groups using biological knowledge. Another major goal is improved gene selection via detection of novel groups of cross-omics biomarkers. Performance of 3Mint is assessed using different metrics. Our computational performance evaluations showed that the 3Mint classifies the BRCA molecular subtypes with lower number of genes when compared to the miRcorrNet tool which uses miRNA and mRNA gene expression profiles in terms of similar performance metrics (95% Accuracy). The incorporation of methylation data in 3Mint yields a much more focused analysis. The 3Mint tool and all other supplementary files are available at https://github.com/malikyousef/3Mint/ .more » « less
-
Normalization is a critical step in quantitative analyses of biological processes. Recent works show that cross-platform integration and normalization enable machine learning (ML) training on RNA microarray and RNA-seq data, but no independent datasets were used in their studies. Therefore, it is unclear how to improve ML modelling performance on independent RNA array and RNA-seq based datasets. Inspired by the house-keeping genes that are commonly used in experimental biology, this study tests the hypothesis that non-differentially expressed genes (NDEG) may improve normalization of transcriptomic data and subsequently cross-platform modelling performance of ML models. Microarray and RNA-seq datasets of the TCGA breast cancer were used as independent training and test datasets, respectively, to classify the molecular subtypes of breast cancer. NDEG (p>0.85) and differentially expressed genes (DEG, p<0.05) were selected based on the p values of ANOVA analysis and used for subsequent data normalization and classification, respectively. Models trained based on data from one platform were used for testing on the other platform. Our data show that NDEG and DEG gene selection could effectively improve the model classification performance. Normalization methods based on parametric statistical analysis were inferior to those based on nonparametric statistics. In this study, the LOG_QN and LOG_QNZ normalization methods combined with the neural network classification model seem to achieve better performance. Therefore, NDEG-based normalization appears useful for cross-platform testing on completely independent datasets. However, more studies are required to examine whether NDEG-based normalization can improve ML classification performance in other datasets and other omic data types.more » « less
