Biology subjects

Gevaert, O.

Publications and source records attributed to Gevaert, O..

At least 19 recordsLinked to original sources

bioRxiv2026

Digital pathological classification of peripheral neuroblastic tumors across multi-continent cohorts

Peripheral neuroblastic tumors (pNTs) are embryonal tumors of neural crest origin with highly variable clinical behaviors, ranging from spontaneous regression to aggressive and fatal disease. The International Neuroblastoma Pathology Classification (INPC) defines four diagnostic categories and stratifies tumors into Favorable Histology (FH) or Unfavorable Histology (UH) group based on age-linked assessment of tumor differentiation/maturation and the Mitosis-Karyorrhexis Index (MKI). Prognostic distinction according to INPC offers significant prediction of clinical outcomes, with patients harboring FH tumors demonstrating longer overall and event-free survival than those with UH tumor. Here, we assembled the largest multi-continental whole-slide histology imaging dataset of pNTs to date, comprising 2,030 tumors from the United States, Canada, Australia, New Zealand, Germany and Japan. Using this dataset, we developed NB-PathAssist, a computational pathology framework for automated INPC-based classification from digitized whole-slide images. NB-PathAssist integrates foundation-model-based feature extraction with an archetype-guided SummaryMixing architecture that compresses whole-slide morphology into representative histologic tokens for tumor-level classification. To automate MKI assessment, we manually annotated 14,049 nuclei, classifying them as mitotic-karyorrhectic (MK) tumor cells, non-MK tumor cells, or non-tumor cells. The resulting model was applied to phenotype cells in whole-slide images across 1,649 tissue sections. Across geographically and institutionally diverse cohorts, NB-PathAssist reproducibly assessed key diagnostic features and generated prognostic classifications concordant with reference INPC annotations. The average balanced accuracy for classifying tumor categories, grade of neuroblastic differentiation, MKI and prognostic groups achieved 0.84, 0.86, 0.89 and 0.96, respectively. We packaged the NB-PathAssist algorithms into an end-to-end online platform for scalable and standardized AI-assisted assessment of pNTs.

pathology↗

bioRxiv2025

Response to anti-angiogenic therapy is affected by AIMP protein family activity in glioblastoma and lower-grade gliomas

BackgroundGlioblastoma (GBM) is a highly vascularized, heterogeneous tumor, yet anti-angiogenic therapies have yielded limited survival benefits. The lack of validated predictive biomarkers for treatment response stratification remains a major challenge. Aminoacyl tRNA synthetase complex-interacting multicomplex proteins (AIMPs) 1/2/3 have been implicated in CNS diseases, but their roles in gliomas remain unexplored. We investigated their association with angiogenesis and their significance as predictive biomarkers for anti-angiogenic treatment response. MethodsIn this multi-cohort retrospective study we analyzed glioma samples from TCGA, CGGA, Rembrandt, Gravendeel, BELOB and REGOMA trials, and four single-cell transcriptomic datasets. Multi-omic analyses incorporated transcriptomic, epigenetic, and proteomic data. Kaplan-Meier and Cox proportional hazards models were used to assess the prognostic value of AIMPs in heterogeneous and homogeneous treatment-groups. Using single-cell transcriptomics, we explored spatial and cell-type-specific AIMP2 expression in GBM. ResultsAIMP1/2/3 expressions correlated significantly with angiogenesis across TCGA cancers. In gliomas, AIMPs were upregulated in tumor vs. normal tissues, higher- vs. lower-grade gliomas, and recurrent vs. primary tumors (p<0.05). Upon retrospective analysis of two clinical trials assessing different anti-angiogenic drugs, we found that high-AIMP2 subgroups had improved response to therapies in GBM (REGOMA: HR 4.75 [1.96-11.5], p<0.001; BELOB: HR 2.3 [1.17-4.49], p=0.015). AIMP2-cg04317940 methylation emerged as a clinically applicable stratification marker. Single-cell analysis revealed homogeneous AIMP2 expression in tumor tissues, particularly in AC-like cells, suggesting a mechanistic link to tumor angiogenesis. ConclusionsThese findings provide novel insights into the role of AIMPs in angiogenesis, offering improved patient stratification and therapeutic outcomes in recurrent GBM.

bioinformatics↗

bioRxiv2025

JIND-Multi: Leveraging Multiple Labeled Datasets for Automated Annotation of Single-Cell RNA and ATAC Data

BackgroundThe creation of single-cell atlases is essential for understanding cellular diversity and heterogeneity. However, assembling these atlases is challenging due to batch effects and the need for accurate cell annotation. Current methods for single-cell RNA and ATAC sequencing, while effective for integration, are not optimized for cell annotation. Additionally, many annotation tools rely on external databases or reference scRNA-Seq datasets, which may limit their adaptability to specific study needs, especially for rare cell-types or scATAC-Seq data. ResultsWe introduce JIND-Multi, an extended version of the JIND framework, designed to transfer cell-type labels across multiple annotated datasets. JIND-Multi significantly reduces the proportion of unclassified cells in single-cell RNA sequencing (scRNA-Seq) data while maintaining the accuracy and performance of the original JIND model. Furthermore, JIND-Multi demonstrates robust and precise annotation results in its inaugural application to scATAC-Seq data, proving its versatility and effectiveness across different single-cell sequencing technologies. ConclusionsJIND-Multi represents an improvement in cell annotation, reducing unassigned cells and offering a reliable solution for both scRNA-Seq and scATAC-Seq data. Its ability to handle multiple labeled datasets enhances the precision of annotations, making it a valuable tool for the single-cell research community. JIND-Multi is publicly available at:https://github.com/ML4BM-Lab/JIND-Multi.git.

bioinformatics↗

bioRxiv2024

Towards Digital Quantification of Ploidy from Pan-Cancer Digital Pathology Slides using Deep Learning

Abnormal DNA ploidy, found in numerous cancers, is increasingly being recognized as a contributor in driving chromosomal instability, genome evolution, and the heterogeneity that fuels cancer cell progression. Furthermore, it has been linked with poor prognosis of cancer patients. While next-generation sequencing can be used to approximate tumor ploidy, it has a high error rate for near-euploid states, a high cost and is time consuming, motivating alternative rapid quantification methods. We introduce PloiViT, a transformer-based model for tumor ploidy quantification that outperforms traditional machine learning models, enabling rapid and cost-effective quantification directly from pathology slides. We trained PloiViT on a dataset of fifteen cancer types from The Cancer Genome Atlas and validated its performance in multiple independent cohorts. Additionally, we explored the impact of self-supervised feature extraction on performance. PloiViT, using self-supervised features, achieved the lowest prediction error in multiple independent cohorts, exhibiting better generalization capabilities. Our findings demonstrate that PloiViT predicts higher ploidy values in aggressive cancer groups and patients with specific mutations, validating PloiViT potential as complementary for ploidy assessment to next-generation sequencing data. To further promote its use, we release our models as a user-friendly inference application and a Python package for easy adoption and use.

bioinformatics↗

bioRxiv2024

Deep learning uncovers histological patterns of YAP1/TEAD activity related to disease aggressiveness in cancer patients.

Over the last decade, Hippo signaling has emerged as a major tumor-suppressing pathway. Its dysregulation is associated with abnormal expression of YAP1 and TEAD-family genes. Recent works have highlighted the role of YAP1/TEAD activity in several cancers and its potential therapeutic implications. Therefore, identifying patients with a dysregulated Hippo pathway is key to enhancing treatment impact. Although recent studies have derived RNAseq-based signatures, there remains a need for a reproducible and cost-effective method to measure the pathway activation. In recent years, deep learning applied to histology slides have emerged as an effective way to predict molecular information from a data modality available in clinical routine. Here, we trained models to predict YAP1/TEAD activity from H&E-stained histology slides in multiple cancers. The robustness of our approach was assessed in seven independent validation cohorts. Finally, we showed that histological markers of disease aggressiveness were associated with dysfunctional Hippo signaling.

bioinformatics↗

bioRxiv2024

regionalpcs: improved discovery of DNA methylation associations with complex traits

We have developed the regional principal components (rPCs) method, a novel approach for summarizing gene-level methylation. rPCs address the challenge of deciphering complex epigenetic mechanisms in diseases like Alzheimers disease (AD). In contrast to traditional averaging, rPCs leverage principal components analysis to capture complex methylation patterns across gene regions. Our method demonstrated a 54% improvement in sensitivity over averaging in simulations, offering a robust framework for identifying subtle epigenetic variations. Applying rPCs to the AD brain methylation data in ROSMAP, combined with cell type deconvolution, we uncovered 838 differentially methylated genes associated with neuritic plaque burden--significantly outperforming conventional methods. Integrating methylation quantitative trait loci (meQTL) with genome-wide association studies (GWAS) identified 17 genes with potential causal roles in AD, including MS4A4A and PI-CALM. Our approach is available in the Bioconductor package regionalpcs, opening avenues for research and facilitating a deeper understanding of the epigenetic landscape in complex diseases.

genomics↗

bioRxiv2024

Revealing cancer driver genes through integrative transcriptomic and epigenomic analyses with Moonlight

Cancer involves dynamic changes caused by (epi)genetic alterations such as mutations or abnormal DNA methylation patterns which occur in cancer driver genes. These driver genes are divided into oncogenes and tumor suppressors depending on their function and mechanism of action. Discovering driver genes in different cancer (sub)types is important not only for increasing current understanding of carcinogenesis but also from prognostic and therapeutic perspectives. We have previously developed a framework called Moonlight which uses a systems biology multi-omics approach for prediction of driver genes. Here, we present an important development in Moonlight2 by incorporating a DNA methylation layer which provides epigenetic evidence for deregulated expression profiles of driver genes. To this end, we present a novel functionality called Gene Methylation Analysis (GMA) which investigates abnormal DNA methylation patterns to predict driver genes. This is achieved by integrating the tool EpiMix which is designed to detect such aberrant DNA methylation patterns in a cohort of patients and further couples these patterns with gene expression changes. To showcase GMA, we applied it to three cancer (sub)types (basal-like breast cancer, lung adenocarcinoma, and thyroid carcinoma) where we discovered 33, 190, and 263 epigenetically driven genes, respectively. A subset of these driver genes had prognostic effects with expression levels significantly affecting survival of the patients. Moreover, a subset of the driver genes demonstrated therapeutic potential as drug targets. This study provides a framework for exploring the driving forces behind cancer and provides novel insights into the landscape of three cancer sub(types) by integrating gene expression and methylation data. Moonlight2R is available on GitHub (https://github.com/ELELAB/Moonlight2R) and BioCondcutor (https://bioconduc-tor.org/packages/release/bioc/html/Moonlight2R.html). The associated case studies presented here are available on GitHub (https://github.com/ELELAB/Moon-light2_GMA_case_studies) and OSF (https://osf.io/j4n8q/). Author summaryCancer is a complex disease and a main cause of mortality worldwide. This heterogeneous disease arises due to accumulation of changes which occur in driver genes that drive cancer progression when they are altered. These driver genes are commonly divided into oncogenes, which promote cancer, and tumor suppressors, which prevent it. A major goal of cancer research is identifying these driver genes, crucial for increasing our current understanding of cancer biology and for developing novel treatment approaches. A large number of cancer driver genes have already been identified. However, the underlying mechanisms for the alterations in these genes is challenging to predict given their context-dependent behavior and the complexity of cancer. Such explanations are the focus of this study with the aim of providing evidence of why certain genes do not function normally in cancer. Within this context, we present new functionalities to our previously developed cancer driver predictive framework, Moonlight. These new functionalities integrate multiple data types to predict oncogenes and tumor suppressors in a systems-biology-oriented manner that is freely available as a R package for the community.

bioinformatics↗

bioRxiv2023

Digital profiling of cancer transcriptomes from histology images with grouped vision attention

Cancer is a heterogeneous disease that demands precise molecular profiling for better understanding and management. Recently, deep learning has demonstrated potentials for cost-efficient prediction of molecular alterations from histology images. While transformer-based deep learning architectures have enabled significant progress in non-medical domains, their application to histology images remains limited due to small dataset sizes coupled with the explosion of trainable parameters. Here, we develop SEQUOIA, a transformer model to predict cancer transcriptomes from whole-slide histology images. To enable the full potential of transformers, we first pre-train the model using data from 1,802 normal tissues. Then, we fine-tune and evaluate the model in 4,331 tumor samples across nine cancer types. The prediction performance is assessed at individual gene levels and pathway levels through Pearson correlation analysis and root mean square error. The generalization capacity is validated across two independent cohorts comprising 1,305 tumors. In predicting the expression levels of 25,749 genes, the highest performance is observed in cancers from breast, kidney and lung, where SEQUOIA accurately predicts the expression of 11,069, 10,086 and 8,759 genes, respectively. The accurately predicted genes are associated with the regulation of inflammatory response, cell cycles and metabolisms. While the model is trained at the tissue level, we showcase its potential in predicting spatial gene expression patterns using spatial transcriptomics datasets. Leveraging the prediction performance, we develop a digital gene expression signature that predicts the risk of recurrence in breast cancer. SEQUOIA deciphers clinically relevant gene expression patterns from histology images, opening avenues for improved cancer management and personalized therapies.

bioinformatics↗

bioRxiv2023

GeNNius: An ultrafast drug-target interaction inference method based on graph neural networks

Drug-target interaction (DTI) prediction is a relevant but challenging task in the drug repurposing field. In-silico approaches have drawn particular attention as they can reduce associated costs and time commitment of traditional methodologies. Yet, current state-of-the-art methods present several limitations: existing DTI prediction approaches are computationally expensive, thereby hindering the ability to use large networks and exploit available datasets and, the generalization to unseen datasets of DTI prediction methods remains unexplored, which could potentially improve the development processes of DTI inferring approaches in terms of accuracy and robustness. In this work, we introduce GO_SCPLOWEC_SCPLOWnnO_SCPLOWIUSC_SCPLOW (Graph Embedding Neural Network Interaction Uncovering System), a Graph Neural Network (GNN)-based method that outperforms state-of-the-art models in terms of both accuracy and time efficiency across a variety of datasets. We also demonstrated its prediction power to uncover new interactions by evaluating not previously known DTIs for each dataset. We further assessed the generalization capability of GO_SCPLOWEC_SCPLOWnnO_SCPLOWIUSC_SCPLOW by training and testing it on different datasets, showing that this framework can potentially improve the DTI prediction task by training on large datasets and testing on smaller ones. Finally, we investigated qualitatively the embeddings generated by GO_SCPLOWEC_SCPLOWnnO_SCPLOWIUSC_SCPLOW, revealing that the GNN encoder maintains biological information after the graph convolutions while diffusing this information through nodes, eventually distinguishing protein families in the node embedding space. Code Availabilityhttps://github.com/ubioinformat/GeNNius

bioinformatics↗

bioRxiv2023

RNA-to-image multi-cancer synthesis using cascaded diffusion models

Data scarcity presents a significant obstacle in the field of biomedicine, where acquiring diverse and sufficient datasets can be costly and challenging. Synthetic data generation offers a potential solution to this problem by expanding dataset sizes, thereby enabling the training of more robust and generalizable machine learning models. Although previous studies have explored synthetic data generation for cancer diagnosis, they have predominantly focused on single modality settings, such as whole-slide image tiles or RNA-Seq data. To bridge this gap, we propose a novel approach, RNA-Cascaded-Diffusion-Model or RNA-CDM, for performing RNA-to-image synthesis in a multi-cancer context, drawing inspiration from successful text-to-image synthesis models used in natural images. In our approach, we employ a variational auto-encoder to reduce the dimensionality of a patients gene expression profile, effectively distinguishing between different types of cancer. Subsequently, we employ a cascaded diffusion model to synthesize realistic whole-slide image tiles using the latent representation derived from the patients RNA-Seq data. Our results demonstrate that the generated tiles accurately preserve the distribution of cell types observed in real-world data, with state-of-the-art cell identification models successfully detecting important cell types in the synthetic samples. Furthermore, we illustrate that the synthetic tiles maintain the cell fraction observed in bulk RNA-Seq data and that modifications in gene expression affect the composition of cell types in the synthetic tiles. Next, we utilize the synthetic data generated by RNA-CDM to pretrain machine learning models and observe improved performance compared to training from scratch. Our study emphasizes the potential usefulness of synthetic data in developing machine learning models in sarce-data settings, while also highlighting the possibility of imputing missing data modalities by leveraging the available information. In conclusion, our proposed RNA-CDM approach for synthetic data generation in biomedicine, particularly in the context of cancer diagnosis, offers a novel and promising solution to address data scarcity. By generating synthetic data that aligns with real-world distributions and leveraging it to pretrain machine learning models, we contribute to the development of robust clinical decision support systems and potential advancements in precision medicine.

bioinformatics↗

bioRxiv2023

EpiMix: an integrative tool for epigenomic subtyping using DNA methylation

DNA methylation (DNAme) is a major epigenetic factor influencing gene expression with alterations leading to cancer, immunological, and cardiovascular diseases. Recent technological advances enable genome-wide quantification of DNAme in large human cohorts. So far, existing methods have not been evaluated to identify differential DNAme present in large and heterogeneous patient cohorts. We developed an end-to-end analytical framework named "EpiMix" for population-level analysis of DNAme and gene expression. Compared to existing methods, EpiMix showed higher sensitivity in detecting abnormal DNAme that was present in only small patient subsets. We extended the model-based analyses of EpiMix to cis-regulatory elements within protein-coding genes, distal enhancers, and genes encoding microRNAs and lncRNAs. Using cell-type specific data from two separate studies, we discovered novel epigenetic mechanisms underlying childhood food allergy and survival-associated, methylation-driven non-coding RNAs in non-small cell lung cancer.

bioinformatics↗

bioRxiv2022

Synthetic whole-slide image tile generation with gene expression profiles infused deep generative models

The acquisition of multi-modal biological data for the same sample, such as RNA sequencing and whole slide imaging (WSI), has increased in recent years, enabling studying human biology from multiple angles. However, despite these emerging multi-modal efforts, for the majority of studies only one modality is typically available, mostly due to financial or logistical constraints. Given these difficulties, multi-modal data imputation and multi-modal synthetic data generation are appealing as a solution for the multi-modal data scarcity problem. Currently, most studies focus on generating a single modality (e.g. WSI), without leveraging the information provided by additional data modalities (e.g. gene expression profiles). In this work, we propose an approach to generate WSI tiles by using deep generative models infused with matched gene expression profiles. First, we train a variational autoencoder (VAE) that learns a latent, lower dimensional representation of multi-tissue gene expression profiles. Then, we use this representation to infuse generative adversarial networks (GAN) that generate lung and brain cortex tissue tiles, resulting in a new model that we call RNA-GAN. Tiles generated by RNA-GAN were preferred by expert pathologists in comparison to tiles generated using traditional GANs and in addition, RNA-GAN needs fewer training epochs to generate high-quality tiles. Finally, RNA-GAN was able to generalize to gene expression profiles outside of the training set, showing imputation capabilities. A web-based quiz is available for users to play a game distinguishing real and synthetic tiles: https://rna-gan.stanford.edu/ and the code for RNA-GAN is available here: https://github.com/gevaertlab/RNA-GAN.

bioinformatics↗

bioRxiv2021

ImaGene: A web-based software platform for tumor radiogenomic evaluation and reporting

The field of radiomics has undergone several advancements in approaches to uncovering hidden quantitative features from tumor imaging data for use in guiding clinical decision-making for cancer patients. Radiographic imaging techniques provide insight into the imaging features of tumor regions of interest (ROIs), while immunohistochemistry and sequencing techniques performed on biopsy samples yield omics data. Potential associations between tumor genotype and phenotype can be identified from imaging and omics data via traditional correlation analysis, as well as through artificial intelligence (AI) models. However, at present the radiogenomics community lacks a unified software platform for which to conduct such analyses in a reproducible manner. To address this gap, we propose ImaGene, a web-based platform that takes tumor omics and imaging data sets as input, performs correlation analysis between them, and constructs AI models (optionally using only those features found to exhibit statistically significant correlation with some element of the opposing dataset). ImaGene has several modifiable configuration parameters, providing users complete control over their analysis. For each run, ImaGene produces a comprehensive report displaying a number of intuitive model diagnostics. To demonstrate the utility of ImaGene, exploratory studies surrounding Invasive Breast Carcinoma (IBC) and Head and Neck Squamous Cell Carcinoma (HNSCC) on datasets acquired from public databases are conducted. Potential associations are identified between several imaging features and 6 genes: CRABP1, SMTNL2, FABP1, HAS1, FAM163A and DSG1 for IBC, and 4 genes: CEACAM6, NANOG, ACSM2B, and UPK2 for HNSCC. In summary, the software provides researchers with a transparent tool for which to begin radiogenomic analysis and explore possible further directions in their research. We anticipate that ImaGene will become the standard platform for tumor analyses in the field of radiogenomics due to its ease of use, flexibility, and reproducibility, and that it can serve as an enabling centrepoint for an emerging radiogenomic knowledge base.

bioinformatics↗

bioRxiv2020

A meta-learning approach for genomic survival analysis

RNA sequencing has emerged as a promising approach in cancer prognosis as sequencing data becomes more easily and affordably accessible. However, it remains challenging to build good predictive models especially when the sample size is limited and the number of features is high, which is a common situation in biomedical settings. To address these limitations, we propose a meta-learning framework based on neural networks for survival analysis and evaluate it in a genomic cancer research setting. We demonstrate that, compared to regular transfer-learning, meta-learning is a significantly more effective paradigm to leverage high-dimensional data that is relevant but not directly related to the problem of interest. Specifically, meta-learning explicitly constructs a model, from abundant data of relevant tasks, to learn a new task with few samples effectively. For the application of predicting cancer survival outcome, we also show that the meta-learning framework with a few samples is able to achieve competitive performance with learning from scratch with a significantly larger number of samples. Finally, we demonstrate that the meta-learning model implicitly prioritizes genes based on their contribution to survival prediction and allows us to identify important pathways in cancer.

bioinformatics↗

bioRxiv2019

Deep Learning with Multimodal Representation for Pancancer Prognosis Prediction

Estimating the future course of cancer is invaluable to physicians; however, current clinical methods fail to effectively use the vast amount of multimodal data that is available for cancer patients.\n\nTo tackle this problem, we constructed a deep neural network based model to predict the survival of patients for 20 different cancer types using gene expressions, microRNA data, clinical data and histopathology whole slide images (WSIs). We developed an unsupervised encoder to compress these four data modalities into a single feature vector for each patient, handling missing data through a resilient, multimodal dropout method. Encoding methods were tailored to each data type - using deep highway networks to extract features from genomic and clinical data, and convolutional neural networks extract features from pathology images. We then used these feature encodings trained on pancancer data to predict pancancer and single cancer survival data, achieving a C-index of 0.784 overall.\n\nThis work shows that it is possible to build a pancancer model for prognosis that also predicts prognosis in single cancer sites. Furthermore, our model handles multiple data modalities, efficiently analyzes WSIs, and summarizes patient details flexibly into an unsupervised, informative profile. We thus present a powerful automated tool to accurately determine prognosis, a key step towards personalized treatment for cancer patients.

bioinformatics↗

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↗