Biology subjects

Bigness, J.

Publications and source records attributed to Bigness, J..

3 recordsLinked to original sources

bioRxiv2023

scNODE: Generative Model for Temporal Single Cell Transcriptomic Data Prediction

AO_SCPLOWBSTRACTC_SCPLOWMeasurement of single-cell gene expression at different timepoints enables the study of cell development. However, due to the resource constraints and technical challenges associated with the single-cell experiments, researchers can only profile gene expression at discrete and sparsely-sampled timepoints. This missing timepoint information impedes downstream cell developmental analyses. We propose scNODE, an end-to-end deep learning model that can predict in silico single-cell gene expression at unobserved timepoints. scNODE integrates a variational autoencoder (VAE) with neural ordinary differential equations (ODEs) to predict gene expression using a continuous and non-linear latent space. Importantly, we incorporate a dynamic regularization term to learn a latent space that is robust against distribution shifts when predicting single-cell gene expression at unobserved timepoints. Our evaluations on three real-world scRNA-seq datasets show that scNODE achieves higher predictive performance than state-of-the-art methods. We further demonstrate that scNODEs predictions help cell trajectory inference under the missing timepoint paradigm and the learned latent space is useful for in silico perturbation analysis of relevant genes along a developmental cell path. The data and code are publicly available at https://github.com/rsinghlab/scNODE.

bioinformatics↗

bioRxiv2020

Integrating long-range regulatory interactions to predict gene expression using graph convolutional neural networks

Long-range spatial interactions among genomic regions are critical for regulating gene expression, and their disruption has been associated with a host of diseases. However, when modeling the effects of regulatory factors, most deep learning models either neglect long-range interactions or fail to capture the inherent 3D structure of the underlying genomic organization. To address these limitations, we present GC-MERGE, a Graph Convolutional Model for Epigenetic Regulation of Gene Expression. Using a graph-based framework, the model incorporates important information about long-range interactions via a natural encoding of spatial interactions into the graph representation. It integrates measurements of both the spatial genomic organization and local regulatory factors, specifically histone modifications, to not only predict the expression of a given gene of interest but also quantify the importance of its regulatory factors. We apply GC-MERGE to datasets for three cell lines - GM12878 (lymphoblastoid), K562 (myelogenous leukemia), and HUVEC (human umbilical vein endothelial) - and demonstrate its state-of-the-art predictive performance. Crucially, we show that our model is interpretable in terms of the observed biological regulatory factors, high-lighting both the histone modifications and the interacting genomic regions contributing to a genes predicted expression. We provide model explanations for multiple exemplar genes and validate them with evidence from the literature. Our model presents a novel setup for predicting gene expression by integrating multimodal datasets in a graph convolutional framework. More importantly, it enables interpretation of the biological mechanisms driving the models predictions. Available at: https://github.com/rsinghlab/GC-MERGE.

bioinformatics↗

bioRxiv2019

G1/S transcription factors assemble in discrete clusters that increase in number as cells grow

The spatio-temporal organization of transcription factor (TF)-promoter interactions is critical for the coordination of transcriptional programs. In budding yeast, the main G1/S transcription factors, SBF and MBF, are limiting with respect to target promoters in small G1 phase cells and accumulate as cells grow, raising the question of how SBF/MBF are dynamically distributed across the G1/S regulon. Super-resolution Photo-Activatable Localization Microscopy (PALM) mapping of the static positions of SBF/MBF subunits revealed that 85% were organized into discrete clusters containing [~]8 copies regardless of cell size, while the number of clusters increased with growth. Stochastic simulations with a mathematical model based on co-localization of promoters in clusters recapitulated observed cluster behavior. A prediction of the model that SBF/MBF should exhibit both fast and slow dynamics was confirmed in PALM experiments on live cells. This spatio-temporal organization of the TFs that activate the G1/S regulon may help coordinate commitment to division.

cell biology↗