skip to main content


Title: Network-based multi-task learning models for biomarker selection and cancer outcome prediction
Abstract Motivation Detecting cancer gene expression and transcriptome changes with mRNA-sequencing (RNA-Seq) or array-based data are important for understanding the molecular mechanisms underlying carcinogenesis and cellular events during cancer progression. In previous studies, the differentially expressed genes were detected across patients in one cancer type. These studies ignored the role of mRNA expression changes in driving tumorigenic mechanisms that are either universal or specific in different tumor types. To address the problem, we introduce two network-based multi-task learning frameworks, NetML and NetSML, to discover common differentially expressed genes shared across different cancer types as well as differentially expressed genes specific to each cancer type. The proposed frameworks consider the common latent gene co-expression modules and gene-sample biclusters underlying the multiple cancer datasets to learn the knowledge crossing different tumor types. Results Large-scale experiments on simulations and real cancer high-throughput datasets validate that the proposed network-based multi-task learning frameworks perform better sample classification compared with the models without the knowledge sharing across different cancer types. The common and cancer specific molecular signatures detected by multi-task learning frameworks on TCGA ovarian cancer, breast cancer, and prostate cancer datasets are correlated with the known marker genes and enriched in cancer relevant KEGG pathways and Gene Ontology terms. Availability and Implementation Source code is available at: https://github.com/compbiolabucf/NetML Supplementary information Supplementary data are available at Bioinformatics  more » « less
Award ID(s):
1755761 1908495 2003749
NSF-PAR ID:
10165122
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
Bioinformatics
ISSN:
1367-4803
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. 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
  2. Abstract Motivation

    The analysis of spatially resolved transcriptome enables the understanding of the spatial interactions between the cellular environment and transcriptional regulation. In particular, the characterization of the gene–gene co-expression at distinct spatial locations or cell types in the tissue enables delineation of spatial co-regulatory patterns as opposed to standard differential single gene analyses. To enhance the ability and potential of spatial transcriptomics technologies to drive biological discovery, we develop a statistical framework to detect gene co-expression patterns in a spatially structured tissue consisting of different clusters in the form of cell classes or tissue domains.

    Results

    We develop SpaceX (spatially dependent gene co-expression network), a Bayesian methodology to identify both shared and cluster-specific co-expression network across genes. SpaceX uses an over-dispersed spatial Poisson model coupled with a high-dimensional factor model which is based on a dimension reduction technique for computational efficiency. We show via simulations, accuracy gains in co-expression network estimation and structure by accounting for (increasing) spatial correlation and appropriate noise distributions. In-depth analysis of two spatial transcriptomics datasets in mouse hypothalamus and human breast cancer using SpaceX, detected multiple hub genes which are related to cognitive abilities for the hypothalamus data and multiple cancer genes (e.g. collagen family) from the tumor region for the breast cancer data.

    Availability and implementation

    The SpaceX R-package is available at github.com/bayesrx/SpaceX.

    Supplementary information

    Supplementary data are available at Bioinformatics online.

     
    more » « less
  3. Finding genes biologically directly or indirectly related to lung cancer has been drawing much attention, and many genes directly related to lung cancer have been reported. However, it has not been confirmed whether those published 'key' genes are truly critical to lung cancer formation, i.e., they may be with very limited useful information. As a result, finding essential genes remains a challenging lung cancer research problem. Using a recently developed competing linear factor analysis method in differentially expressed gene detection, we advance the study of lung cancer critical genes detection to a uniformly informative level. A set of common four genes and their functional effects are detected to be differentially expressed in tumor and non- tumor samples with 100% sensitivity and 100% specificity in one study of lung adenocarcinoma (LUAD) and one study of squamous cell lung cancers (LUSC) (two North American cohorts with 20429 genes, 576 and 552 samples respectively). Two additional analyses also gain accuracy of 97.8% sensitivity and 100% specificity in one study of non-small cell lung carcinomas (NSCLC, a European cohort with 20356 genes and 156 samples), and an accuracy of 100% sensitivity and 95% specificity (1 out of 20 non-tumor samples) in one study of ALK-positive and EGFR/KRAS/ALK-negative lung adenocarcinomas (LUAD, a Japanese cohort with 20356 genes and 224 samples). There are some common genes, but different functional effects, within each set of four genes among two North American cohorts and a European cohort and among North American cohorts and the Japanese cohort. These results show the four-gene-based classifiers are robust with different types of lung cancers and different race cohorts and accurate. The functional effects of four genes disclose significantly other mechanisms (mysteries) between LUAD and LUSC. These sets of four genes and their functional effects are considered to be essential for lung cancer studies and practice. These genes' functional effects naturally classify patients into different groups (more than seven subtypes). Subtype information is useful for personalized therapies. The new findings can motivate new lung cancer research in more focused and targeted directions to save lives, protect people, and reduce enormous economic costs in research and lung cancer treatments. 
    more » « less
  4. Abstract Motivation

    High-throughput mRNA sequencing (RNA-Seq) is a powerful tool for quantifying gene expression. Identification of transcript isoforms that are differentially expressed in different conditions, such as in patients and healthy subjects, can provide insights into the molecular basis of diseases. Current transcript quantification approaches, however, do not take advantage of the shared information in the biological replicates, potentially decreasing sensitivity and accuracy.

    Results

    We present a novel hierarchical Bayesian model called Differentially Expressed Isoform detection from Multiple biological replicates (DEIsoM) for identifying differentially expressed (DE) isoforms from multiple biological replicates representing two conditions, e.g. multiple samples from healthy and diseased subjects. DEIsoM first estimates isoform expression within each condition by (1) capturing common patterns from sample replicates while allowing individual differences, and (2) modeling the uncertainty introduced by ambiguous read mapping in each replicate. Specifically, we introduce a Dirichlet prior distribution to capture the common expression pattern of replicates from the same condition, and treat the isoform expression of individual replicates as samples from this distribution. Ambiguous read mapping is modeled as a multinomial distribution, and ambiguous reads are assigned to the most probable isoform in each replicate. Additionally, DEIsoM couples an efficient variational inference and a post-analysis method to improve the accuracy and speed of identification of DE isoforms over alternative methods. Application of DEIsoM to an hepatocellular carcinoma (HCC) dataset identifies biologically relevant DE isoforms. The relevance of these genes/isoforms to HCC are supported by principal component analysis (PCA), read coverage visualization, and the biological literature.

    Availability and implementation

    The software is available at https://github.com/hao-peng/DEIsoM

    Supplementary information

    Supplementary data are available at Bioinformatics online.

     
    more » « less
  5. Abstract Background Transmissible cancers lie at the intersection of oncology and infectious disease, two traditionally divergent fields for which gene expression studies are particularly useful for identifying the molecular basis of phenotypic variation. In oncology, transcriptomics studies, which characterize the expression of thousands of genes, have identified processes leading to heterogeneity in cancer phenotypes and individual prognoses. More generally, transcriptomics studies of infectious diseases characterize interactions between host, pathogen, and environment to better predict population-level outcomes. Tasmanian devils have been impacted dramatically by a transmissible cancer (devil facial tumor disease; DFTD) that has led to widespread population declines. Despite initial predictions of extinction, populations have persisted at low levels, due in part to heterogeneity in host responses, particularly between sexes. However, the processes underlying this variation remain unknown. Results We sequenced transcriptomes from healthy and DFTD-infected devils, as well as DFTD tumors, to characterize host responses to DFTD infection, identify differing host-tumor molecular interactions between sexes, and investigate the extent to which tumor gene expression varies among host populations. We found minimal variation in gene expression of devil lip tissues, either with respect to DFTD infection status or sex. However, 4088 genes were differentially expressed in tumors among our sampling localities. Pathways that were up- or downregulated in DFTD tumors relative to normal tissues exhibited the same patterns of expression with greater intensity in tumors from localities that experienced DFTD for longer. No mRNA sequence variants were associated with expression variation. Conclusions Expression variation among localities may reflect morphological differences in tumors that alter ratios of normal-to-tumor cells within biopsies. Phenotypic variation in tumors may arise from environmental variation or differences in host immune response that were undetectable in lip biopsies, potentially reflecting variation in host-tumor coevolutionary relationships among sites that differ in the time since DFTD arrival. 
    more » « less