Co-chairs: Lana Garmire (U Michigan) Smita Krishnaswamy (Yale), Jie Liu (U Michigan), Joshua Welch (U Michigan)

New: Workshop agenda is here.

News: Two best awards will be given! Thanks to the sponsorship from the Department of Computational Medicine & Bioinformatics of University of Michigan!

Keynote Speakers:

Panelists:

Dr. Rong Fan, Yale University

Dr Naftali Kaminski, Yale University

Dr. Kathryn Roeder, CMU

Dr. James Zou, Stanford

Dr. David Craig, USC

Program Committee:

Lana Garmire (U Michigan) Smita Krishnaswamy (Yale), Jie Liu (U Michigan), Joshua Welch (U Michigan), Ritambhara Singh (Brown University), Yang Lu (University of Washington)

The new revolution brought by single-cell genomics technologies to various biomedical fields is exciting in that it can offer unprecedented views of the inner workings of cells. However, this is accompanied with numerous challenges in single-cell analysis including, noise, sparsity, “curse” of high dimensionality, and lack of continuous-time measurements. Moreover, single-cell data have rapidly evolved from mostly transcriptomics data, to much more complex and heterogenous multi-omics data and multi-modal data types. A recent perspective laid out “Eleven Grand Challenges in Single-Cell Data Science” (Genome Biology, 2020); however, overcoming these grand challenges requires significant efforts in methodological innovation and benchmarking standardization. This workshop aims to be a platform to engage active discussions and participation on new machine-learning methodologies for single-cell analysis. Topics include but are not limited to:

-Benchmarking/standardization of single-cell analysis methods

-Alignment of single-cell studies across technology platforms, tissues and organisms

-Integration of multi-omics data at single-cell resolution

-Integration of single-cell with spatially informed omics studies

-Inference of disease (eg. tumor) progression through time and space

-Scaling up of single-cell based inference to higher resolutions, at tissue, organ, individual and population levels

-Learning dynamics and trajectories from single-cell snapshots