Biology subjects

Wahlby, C.

Publications and source records attributed to Wahlby, C..

3 recordsLinked to original sources

bioRxiv2020

Spage2vec: Unsupervised detection of spatial gene expression constellations

Investigation of spatial cellular composition of tissue architectures revealed by multiplexed in situ RNA detection often rely on inaccurate cell segmentation or prior biological knowledge from complementary single cell sequencing experiments. Here we present spage2vec, an unsupervised segmentation free approach for decrypting the spatial transcriptomic heterogeneity of complex tissues at subcellular resolution. Spage2vec represents the spatial transcriptomic landscape of tissue samples as a spatial functional network and leverages a powerful machine learning graph representation technique to create a lower dimensional representation of local spatial gene expression. We apply spage2vec to mouse brain data from three different in situ transcriptomic assays, showing that learned representations encode meaningful biological spatial information of re-occuring gene constellations involved in cellular and subcellular processes.

bioinformatics↗

bioRxiv2019

Weakly-Supervised Prediction of Cell Migration Modes in Confocal Microscopy Images Using Bayesian Deep Learning

Cell migration is pivotal for their development, physiology and disease treatment. A single cell on a 2D surface can utilize continuous or discontinuous migration modes. To comprehend the cell migration, an adequate quantification for single cell-based analysis is crucial. An automatized approach could alleviate tedious manual analysis, facilitating large-scale drug screening. Supervised deep learning has shown promising outcomes in computerized microscopy image analysis. However, their implication is limited due to the scarcity of carefully annotated data and uncertain deterministic outputs. We compare three deep learning models to study the problem of learning discriminative morphological representations using weakly annotated data for predicting the cell migration modes. We also estimate Bayesian uncertainty to describe the confidence of the probabilistic predictions. Amongst three compared models, DenseNet yielded the best results with a sensitivity of 87.91% {+/-} 13.22 at a false negative rate of 1.26% {+/-} 4.18.

systems biology↗

bioRxiv2018

Zebrafish larvae as a model system for systematic characterization of drugs and genes in dyslipidemia and atherosclerosis

BackgroundHundreds of loci have been robustly associated with circulating lipids, atherosclerosis and coronary artery disease; but for most loci the causal genes and mechanisms remain uncharacterized.\n\nMethodsWe developed a semi-automated experimental pipeline for systematic, quantitative, large-scale characterization of mechanisms, drugs and genes associated with dyslipidemia and atherosclerosis in a zebrafish model system. We validated our pipeline using a dietary (n>2000), drug treatment (n>1000), and genetic intervention (n=384), and used it to characterize three candidate genes in a GWAS-identified pleiotropic locus on chr 19p13.11 (n>500).\n\nResultsOur results show that five days of overfeeding and cholesterol supplementation had independent pro-atherogenic effects, which could be diminished by concomitant treatment with atorvastatin and ezetimibe. CRISPR-Cas9-induced mutations in orthologues of proof-of-concept genes resulted in higher LDL cholesterol levels (apoea), and more early stage atherosclerosis (apobb.1). Finally, our pipeline helped identify putative causal genes for circulating lipids and early-stage atherosclerosis (LPAR2 and GATAD2A).\n\nConclusionsIn summary, our pipeline facilitates systematic, in vivo characterization of drugs and candidate genes to increase our understanding of disease etiology, and can likely help identify novel targets for therapeutic intervention.

genomics↗