J
Joshua D. Welch
Researcher at University of Michigan
Publications - 62
Citations - 3819
Joshua D. Welch is an academic researcher from University of Michigan. The author has contributed to research in topics: Biology & Gene. The author has an hindex of 20, co-authored 50 publications receiving 2081 citations. Previous affiliations of Joshua D. Welch include Broad Institute & University of North Carolina at Chapel Hill.
Papers
More filters
Journal ArticleDOI
MichiGAN: sampling from disentangled representations of single-cell data using generative adversarial networks
Hengshi Yu,Joshua D. Welch +1 more
TL;DR: MichiGAN as discussed by the authors combines the strengths of variational autoencoders and GANs to sample from disentangled representations without sacrificing data generation quality, allowing to manipulate semantically distinct aspects of cellular identity and predict single-cell gene expression response to drug treatment.
Journal ArticleDOI
Intercellular Interactions of an Adipogenic CXCL12 ‐Expressing Stromal Cell Subset in Murine Bone Marrow
TL;DR: In this article, the authors highlight CXCL12-dependent physical coupling with hematopoietic cells as a potential mechanism regulating the adipogenic potential of C-X-C motif chemokine ligand 12+ stromal cells.
Posted ContentDOI
Manifold Alignment Reveals Correspondence Between Single Cell Transcriptome and Epigenome Dynamics
TL;DR: It is shown that it is possible to construct cell trajectories, reflecting the changes that occur in a sequential biological process, from single cell ATAC-seq, bisulfite sequencing, and ChIP-seq data and an approach called MATCHER, which accurately predicts true single cell correlations between DNA methylation and gene expression without using known cell correspondence information.
Book ChapterDOI
Iterative Refinement of Cellular Identity from Single-Cell Data Using Online Learning
Chao Gao,Joshua D. Welch +1 more
TL;DR: An alternating nonnegative least squares (ANLS) algorithm is developed to solve the iNMF optimization problem and help solve the single-cell measurement of gene expression, chromatin accessibility and DNA methylation.
Proceedings ArticleDOI
Variational Mixtures of ODEs for Inferring Cellular Gene Expression Dynamics
TL;DR: This work developed an approach called variational mixtures of ordinary differential equations, which can simultaneously infer the latent time and latent state of each cell and predict its future gene expression state and dramatically improves data, latent time inference, and future cell state estimation of single-cell gene expression data compared to previous approaches.