Biology subjects

Gevaert, O.

Publications and source records attributed to Gevaert, O..

8 recordsLinked to original sources

bioRxiv2018

Deep Recurrent Attention Models for Histopathological Image Analysis

Histopathology defines the gold standard in oncology. Automatic analysis of pathology images could thus have a significant impact on diagnoses, prognoses and treatment decisions for cancer patients. Recently, convolutional neural networks (CNNs) have shown strong performance in computational histopathology tasks. However, given it remains intractable to process pathology slides in their entirety, CNNs have traditionally performed inference on small individual patches extracted from the image. This often requires a significant amount of computation and can result in ignoring potentially relevant spatial and contextual information. Being able to process larger input patches and locating discriminatory regions more efficiently could help improve both computational and task specific performance. Inspired by the recent success of Deep Recurrent Attention Models (DRAMs) in image recognition tasks, we propose a novel attention-based architecture for classification in histopathology. Similar to CNNs, DRAMs have a degree of translation invariance built-in, but the amount of computation performed can be controlled independently from the input image size. The model is a deep recurrent neural network trained with reinforcement learning to attend to the most relevant areas of large input patches. We evaluate our model on histological and molecular subtype classification tasks for the glioma cohorts of The Cancer Genome Atlas (TCGA). Our results suggest that the DRAM has comparable performance to state-of-the-art CNNs despite only processing a select number of patches.

bioinformatics↗

bioRxiv2018

Dropout-Enabled Ensemble Learning for Multi-Scale Biomedical Data

Leveraging information from multiple scales is crucial to understanding complex diseases such as cancer where this could have a significant impact in improving diagnoses, patient management and treatment decisions. Recent advances in Convolutional Neural Networks (CNNs) have enabled major breakthroughs in biomedical image analysis, in particular for histopathology and radiology images. Our main contribution is a methodology to combine independent CNN models built for these two types of images in order to improve diagnostic accuracy. We train separate CNN models and combine them using a Dropout-Enabled meta-classifier. Our framework achieved second place in the MICCAI 2018 Computational Precision Medicine Challenge.

bioinformatics↗

bioRxiv2018

Proteogenomic view of cancer epigenetics: the impact of DNA methylation on the cancer proteome

Aberrant DNA methylation disrupts normal gene expression in cancer and broadly contributes to oncogenesis. We previously developed MethylMix, a model-based algorithmic approach to identify epigenetically regulated driver genes. MethylMix identifies genes where methylation likely executes a functional role by using transcriptomic data to select only methylation events that can be linked to changes in gene expression. However, given that proteins more closely link genotype to phenotype recent high-throughput proteomic data provides an opportunity to more accurately identify functionally relevant abnormal methylation events. Here we present ProteoMix, which refines nominations for epigenetic driver genes by leveraging quantitative high-throughput proteomic data to select only genes where DNA methylation is predictive of protein abundance. Applying our algorithm across three cancer cohorts we find that ProteoMix narrows candidate nominations, where the effect of DNA methylation is often buffered at the protein level. Next, we find that ProteoMix genes are enriched for biological processes involved in cancer including functions involved in epithelial and mesenchymal transition. ProteoMix results are also enriched for tumor markers which are predictive of clinical features like tumor stage and we find clustering on ProteoMix genes captures cancer subtypes.

bioinformatics↗

bioRxiv2018

Comparison of single gene and module-based methods for modeling gene regulatory networks

Gene regulatory networks describe the regulatory relationships among genes, and developing methods for reverse engineering these networks are an ongoing challenge in computational biology. The majority of the initially proposed methods for gene regulatory network discovery create a network of genes and then mine it in order to uncover previously unknown regulatory processes. More recent approaches have focused on inferring modules of co-regulated genes, linking these modules with regulator genes and then mining them to discover new molecular biology.\n\nIn this work we analyze module-based network approaches to build gene regulatory networks, and compare their performance to the well-established single gene network approaches. In particular, we focus on the problem of linking genes with known regulatory genes. First, modules are created iteratively using a regression approach that links co-expressed genes with few regulatory genes. After the modules are built, we create bipartite graphs to identify a set of target genes for each regulatory gene. We analyze several methods for uncovering these modules and show that a variational Bayes approach achieves significant improvement with respect to previously used methods for module creation on both simulated and real data. We also perform a topological and gene set enrichment analysis and compare several module-based approaches to single gene network approaches where a graph is built from the gene expression profiles without clustering genes in modules. We show that the module-based approach with variational Bayes outperforms all other methods and creates regulatory networks with a significantly higher rate of enriched molecular pathways.\n\nThe code is written in R and can be downloaded from https://github.com/mikelhernaez/linker.

systems biology↗

bioRxiv2018

Locoregional Radiogenomic Models Capture Gene Expression Heterogeneity in Glioblastoma

Radiogenomics mapping noninvasively determines important relationships between the molecular genotype and imaging phenotype of various tumors, allowing advances in both clinical care and cancer research. While early work has shown its technical feasibility, here we extend radiogenomic mapping to a locoregional level that can account for the molecular heterogeneity of tumors. To achieve this, our data processing pipeline relies on three main steps: 1) the use of multi-omics data fusion to generate a set of 100 interpretable gene modules, 2) the use of patch-based image analysis (specifically of contrast-enhanced T1-weighted weighted MR images) combined with Generalized Linear Models (GLM) to establish potential links between module expressions and local MR signal, and 3) the use of expression heatmaps based on GLMs decision values to explore visualization of tumor molecular heterogeneity. The performance of the proposed approach was evaluated using a leave-one-patient-out crossvalidation method as well as a separate validation data set. The top performing models were based on a small set of 20 features and yielded Area Under the receiver operating characteristic Curve (AUC) above 0.65 on the validation cohort for eight modules. Next, we demonstrate the clinical and biological interpretation of four modules using molecular expression heatmaps superimposed on clinical radiographic images, showing the potential for assessing tumor molecular heterogeneity and the utility of this method for precision treatment in clinical decision making and imaging surveillance.

bioinformatics↗

bioRxiv2018

Benchmark of lncRNA Quantification for RNA-Seq of Cancer Samples

Long non-coding RNAs (lncRNAs) emerge as important regulators of various biological processes. Many lncRNAs with tumor-suppressor or oncogenic functions in cancer have been discovered. While many studies have exploited public resources such as RNA-Seq data in The Cancer Genome Atlas (TCGA) to study lncRNAs in cancer, it is crucial to choose the optimal method for accurate expression quantification of lncRNAs. In this benchmarking study, we compared the performance of pseudoalignment methods Kallisto and Salmon, and alignment-based methods HTSeq, featureCounts, and RSEM, in lncRNA quantification, by applying them to a simulated RNA-Seq dataset and a pan-cancer RNA-Seq dataset from TCGA. We observed that full transcriptome annotation, including both protein coding and noncoding RNAs, greatly improves the specificity of lncRNA expression quantification. Pseudoalignment-based methods detect more lncRNAs than alignment-based methods and correlate highly with simulated ground truth. On the contrary, alignment-based methods tend to underestimate lncRNA expression or even fail to capture lncRNA signal in the ground truth. These underestimated genes include cancer-relevant lncRNAs such as TERC and ZEB2-AS1. Overall, 10-16% of lncRNAs can be detected in the samples, with antisense and lincRNAs the two most abundant categories. A higher proportion of antisense RNAs are detected than lincRNAs. Moreover, among the expressed lncRNAs, more antisense RNAs are discordant from ground truth than lincRNAs when measured by alignment-based methods, indicating that antisense RNAs are more susceptible to mis-quantification. In addition, the lncRNAs with fewer transcripts, less than three exons, and lower sequence uniqueness tend to be more discordant. In summary, pseudoalignment methods Kallisto or Salmon in combination with the full transcriptome annotation is our recommended strategy for RNA-Seq analysis for lncRNAs.\n\nAUTHOR SUMMARYLong non-coding RNAs (lncRNAs) emerge as important regulators of various biological processes. Our benchmarking work on both simulated RNA-Seq dataset and pan-cancer dataset provides timely and useful recommendations for wide research community who are studying lncRNAs, especially for those who are exploring public resources such as TCGA RNA-Seq data. We demonstrate that using full transcriptome annotation in RNA-Seq analysis is strongly recommended as it greatly improves the specificity of lncRNA quantification. Whats more, pseudoalignment methods Kallisto and Salmon outperform alignment-based methods in lncRNA quantification. It is worth noting that the default workflow for TCGA RNA-Seq data stored in Genomic Data Commons (GDC) data portal uses HTSeq, an alignment-based method. Thus, reanalyzing the data might be considered when checking gene expression in TCGA datasets. In summary, pseudoalignment methods Kallisto or Salmon in combination with full transcriptome annotation is our recommended strategy for RNA-Seq analysis for lncRNAs.

bioinformatics↗

bioRxiv2017

Module analysis captures pancancer (epi)genetically deregulated cancer driver genes for smoking and antiviral response

The availability of increasing volumes of multi-omics profiles across many cancers promises to improve our understanding of the regulatory mechanisms underlying cancer. The main challenge is to integrate these multiple levels of omics profiles and especially to analyze them across many cancers. Here we present AMARETTO, an algorithm that addresses both challenges in three steps. First, AMARETTO identifies potential cancer driver genes through integration of copy number, DNA methylation and gene expression data. Then AMARETTO connects these driver genes with co-expressed target genes that they control, defined as regulatory modules. Thirdly, we connect AMARETTO modules identified from different cancer sites into a pancancer network to identify cancer driver genes. Here we applied AMARETTO in a pancancer study comprising eleven cancer sites and confirmed that AMARETTO captures hallmarks of cancer. We also demonstrated that AMARETTO enables the identification of novel pancancer driver genes. In particular, our analysis led to the identification of pancancer driver genes of smoking-induced cancers and antiviral interferon-modulated innate immune response.\n\nSoftware availabilityAMARETTO is available as an R package at https://bitbucket.org/gevaertlab/pancanceramaretto\n\nHighlightsO_LIWe present an algorithm for pancancer identification of cancer driver genes based on multiomics data fusion\nC_LIO_LIGPX2 is a novel driver gene in smoking induced cancers and validated using knockdown of GPX2 in the A549 cell line.\nC_LIO_LIOAS2 is a novel driver gene defining cancers with an antiviral signature supported by increased infiltration of tumor-associated macrophages.\nC_LI\n\nResearch in contextWe present an algorithm that combines multiple sources of molecular data to identify novel genes that are involved in cancer development. We applied this algorithm on multiple cancers in a combined fashion and identified a network of pancancer driver genes. We highlighted two genes in detail GPX2 and OAS2. We showed that GPX2 is an important cancer gene in smoking induced cancers, and validated our predictions using experimental data where GPX2 was inactivated in a lung cancer cell line. Similarly we showed that OAS2 is an important cancer driver gene in cancers that show an antiviral signature.

bioinformatics↗

bioRxiv2017

NSD1 inactivation defines an immune cold, DNA hypomethylated subtype in squamous cell carcinoma

Chromatin modifying enzymes are frequently mutated in cancer, resulting in a cascade of epigenetic deregulation. Recent reports indicate that inactivating mutations in the histone methyltransferase NSD1 define an intrinsic subtype of head and neck squamous cell carcinoma (HNSC) that features widespread DNA hypomethylation. Here, we describe a similar DNA hypomethylated subtype of lung squamous cell carcinoma (LUSC) that is enriched for both inactivating mutations and deletions in NSD1. The NSD1 subtype of HNSC and LUSC are highly correlated at the DNA methylation and gene expression levels, with concordant DNA hypomethylation and overexpression of a strongly overlapping set of genes, a subset of which are also hypomethylated in Sotos syndrome, a congenital growth disorder caused by germline NSD1 mutations. Further, the NSD1 subtype of HNSC displays an immune cold phenotype characterized by low infiltration of tumor-associated leukocytes, particularly macrophages and CD8+ T cells, as well as low expression of genes encoding the immunotherapy target PD-1 immune checkpoint receptor and its ligands PD-L1 and PD-L2. Using an in vivo model, we demonstrate that NSD1 inactivation results in a reduction in the degree of T cell infiltration into the tumor microenvironment, implicating NSD1 as a tumor cell-intrinsic driver of an immune cold phenotype. These data have important implications for immunotherapy and reveal a general role of NSD1 in maintaining epigenetic repression.

cancer biology↗