Biology subjects

Filipovic, D.

Publications and source records attributed to Filipovic, D..

3 recordsLinked to original sources

bioRxiv2022

Generative Modeling of Single Cell Gene Expression for Dose-Dependent Chemical Perturbations

Single cell sequencing provides a new opportunity to study the heterogeneity of chemical perturbation within tissues. However, exploring the combinatorial space of all cell type-chemical combinations is experimentally and financially unfeasible. This space is significantly expanded by the dose axis of chemical perturbation. Thus, computational tools are needed to predict responses not only across tissues, but also across doses while capturing the nuances of cell type specific gene expression. Variational autoencoders simplify the single cell expression space allowing cross cell type predictions using simple vector arithmetic. However, differing sensitivities and non-linearities make cell type specific gene expression predictions following treatment at higher doses challenging. Here we introduce single cell Variational Inference of Dose-Response (scVIDR) which achieves high dose and cell type specific predictions better than other state of the art algorithms. scVIDR predicts in vivo and in vitro dose-dependent gene expression across cell types in mouse liver, peripheral blood mononuclear cells, and cancer cell lines. We use regression to interpret the outputs of scVIDR. Additionally, we use scVIDR to order individual cells based on their sensitivities to a particular chemical by assigning a pseudo-dose value to each cell. Taken together, we show that scVIDR can effectively predict the dose and cell state dependent changes associated with chemical perturbations.

bioinformatics↗

bioRxiv2022

Prediction of mammalian tissue-specific CLOCK-BMAL1 binding to E-box motifs

The mammalian circadian clock is based on a core intracellular gene regulatory network, coordinated by communication between the central nervous system and peripheral tissues like the liver. Transcriptional and translational feedback loops underlie the molecular mechanism of circadian oscillation and generate its 24 h periodicity. The Brain and muscle Arnt-like protein-1 (Bmal1) forms a heterodimer with Circadian Locomotor Output Cycles Kaput (Clock) that binds to E-box gene regulatory elements, activating transcription of clock genes. In this work we aimed to develop a predictive model of genome-wide CLOCK-BMAL1 binding to E-box motifs. We found over-representation of the canonical E-box motif CACGTG in BMAL1-bound regions in accessible chromatin of the mouse liver, heart and kidney. We developed three different tissue-specific machine learning models based on DNA sequence, DNA sequence plus DNA shape, and DNA sequence and shape plus histone modifications. Combining DNA sequence with DNA shape and histone modification features yielded improved transcription factor binding site prediction. Further, we identified the genomic and epigenomic features that best correlate to the binding of BMAL1 to DNA. The DNA shape features Electrostatic Potential, Minor Groove Width and Propeller Twist together with the histone modifications H3K27ac, H3K4me1, H3K36me3, and H3K4me3 were the features most highly predictive of DNA binding by BMAL1 across all three tissues.

bioinformatics↗

bioRxiv2022

Predictive Models of Genome-wide Aryl Hydrocarbon Receptor DNA Binding Reveal Tissue Specific Binding Determinants

BackgroundThe Aryl Hydrocarbon Receptor (AhR) is an inducible transcription factor (TF) whose ligands include the environmental contaminant 2,3,7,8-tetrachlorodibenzo-p-dioxin (TCDD). TCDD-mediated toxicity occurs through activation of AhR and its subsequent binding to the Dioxin Response Element (DRE), comprising the DNA motif 5-GCGTG-3. However, AhR binding in human tissues is highly dynamic and tissue specific. Approximately 50% of all experimentally verified AhR binding sites do not contain a DRE. Additionally, most accessible DREs are not bound by AhR. Identification of tissue specific AhR binding determinants is crucial for understanding downstream gene regulation and potential adverse outcomes of AhR activation. ResultsWe applied XGBoost, a supervised machine learning architecture, to predict the genome wide AhR binding status of DREs in open chromatin as a function of DNA sequence flanking the DRE, chromatin accessibility, histone modifications (HM), TF binding, and proximity of the DRE to gene promoters. We trained and validated our models using 5-fold cross validation to predict the binding status of DREs in AhR-activated MCF-7 breast cancer cells, primary human hepatocytes, and lymphoblastoid GM17212 cells, as well as AhR non-activated HepG2 hepatocellular carcinoma cells. Our results demonstrate highly accurate and robust models of AhR binding; and identify patterns of transcription factor binding and histone modifications predictive of AhR binding. These patterns are consistent within tissues but highly variable across tissues, which is suggestive of tissue-specific mechanisms of AhR binding. ConclusionsAhR binding is driven by a complex interplay of tissue-agnostic DNA sequence flanking its binding motif and tissue-specific local chromatin context.

genomics↗