Biology subjects

Schuster, V.

Publications and source records attributed to Schuster, V..

4 recordsLinked to original sources

bioRxiv2026

miDGD: a multi-modal deep generative model predicts miRNA expression from bulk or single-cell mRNA expression

MicroRNAs (miRNAs) are key post-transcriptional regulators, yet standard bulk and single-cell RNA-seq do not capture them, leaving this regulatory layer invisible in most transcriptomic data. We present miDGD, a deep generative decoder that jointly models paired mRNA and miRNA profiles through a shared latent representation, enabling miRNA expression to be predicted from mRNA alone. Trained on tumors (TCGA), healthy tissues (GTEx), and human cell lines, miDGD recovers hundreds of miRNAs in held-out tumors (mean Spearman {rho} = 0.56), captures both tissue-specific and ubiquitous miRNAs, and preserves known miRNA--target repression and host-gene co-expression. Without label supervision, its latent space separates 32 cancer types (80% accuracy). Predictions remain stable at single-cell-like sparsity and transfer across datasets--from tumors to healthy tissues and from bulk to single cells--where miDGD outperforms existing supervised and activity-inference methods. miDGD thus unlocks miRNA regulation in the vast body of existing mRNA-only data, including single-cell datasets.

bioinformatics↗

bioRxiv2023

multiDGD: A versatile deep generative model for multi-omics data

Recent technological advancements in single-cell genomics have enabled joint profiling of gene expression and alternative modalities at unprecedented scale. Consequently, the complexity of multi-omics data sets is increasing massively. Existing models for multi-modal data are typically limited in functionality or scalability, making data integration and downstream analysis cumbersome. We present multiDGD, a scalable deep generative model providing a probabilistic framework to learn shared representations of transcriptome and chromatin accessibility. It shows outstanding performance on data reconstruction without feature selection. We demonstrate on several data sets from human and mouse that multiDGD learns well-clustered joint representations. We further find that probabilistic modelling of sample covatiates enables post-hoc data integration without the need for fine-tuning. Additionally, we show that multiDGD can detect statistical associations between genes and regulatory regions conditioned on the learned representations. multiDGD is available as an scverse-compatible package (https://github.com/Center-for-Health-Data-Science/multiDGD).

bioinformatics↗

bioRxiv2023

N-of-one differential gene expression without control samples using a deep generative model

Differential gene expression analysis of bulk RNA sequencing data plays a major role in the diagnosis, prognosis, and understanding of disease. Such analyses are often challenging due to a lack of good controls and the heterogeneous nature of the samples. Here, we present a deep generative model that can replace control samples. The model is trained on RNA-seq data from healthy tissues and learns a low-dimensional representation that clusters tissues very well without supervision. When applied to cancer samples, the model accurately identifies representations close to the tissue of origin. We interpret these inferred representations as the closest normal to the disease samples and use the resulting count distributions to perform differential expression analysis of single cancer samples without control samples. In a detailed analysis of breast cancer, we demonstrate how our approach finds subtype-specific cancer driver and marker genes with high specificity and greatly outperforms the state-of-the-art method in detecting differentially expressed genes, DESeq2. We further show that the significant genes found using the model are highly enriched within cancer-specific driver genes across different cancer types. Our results show that the in silico closest normal provides a more favorable comparison than control samples.

bioinformatics↗

bioRxiv2019

LAB-QA2GO: A free, easy-to-use toolbox for the quality assessment of magnetic resonance imaging data

Image characteristics of magnetic resonance imaging (MRI) data (e.g. signal-to-noise ratio, SNR) may change over the course of a study. To monitor these changes a quality assurance (QA) protocol is necessary. QA can be realized both by performing regular phantom measurements and by controlling the human MRI datasets (e.g. noise detection in structural or movement parameters in functional datasets). Several QA tools for the assessment of MRI data quality have been developed. Many of them are freely available. This allows in principle the flexible set-up of a QA protocol specifically adapted to the aims of ones own study. However, setup and maintenance of these tools bind time, in particular since the installation and operation often require a fair amount of technical knowledge. In this article we present a light-weighted virtual machine, named LAB-QA2GO, which provides scripts for fully automated QA analyses of phantom and human datasets. This virtual machine is ready for analysis by starting it the first time. With minimal configuration in the guided web-interface the first analysis can start within 10 minutes, while adapting to local phantoms and needs is easily possible. The usability and scope of LAB-QA2GO is illustrated using a data set from the QA protocol of our lab. With LAB-QA2GO we hope to provide an easy-to-use toolbox that is able to calculate QA statistics without high effort.

neuroscience↗