Monthly Archives: April 2018


Alignment of single-cell trajectories to compare cellular expression dynamics

Our next meeting will be at 2pm on April 23rd, in room 4160 of the Discovery building. Our Selected paper is Alignment of single-cell trajectories to compare cellular expression dynamics.
The abstract is as follows.

Single-cell RNA sequencing and high-dimensional cytometry can be used to generate detailed trajectories of dynamic biological processes such as differentiation or development. Here we present cellAlign, a quantitative framework for comparing expression dynamics within and between single-cell trajectories. By applying cellAlign to mouse and human embryonic developmental trajectories, we systematically delineate differences in the temporal regulation of gene expression programs that would otherwise be masked.

We welcome all who can join us for this discussion. Feel free to begin that discussion in the comments section below.


Using deep learning to model the hierarchical structure and function of a cell

Our next meeting will be at 2pm on April 9th, in room 4160 of the Discovery building. Our Selected paper is Using deep learning to model the hierarchical structure and function of a cell.
The abstract is as follows.

Although artificial neural networks are powerful classifiers, their internal structures are hard to interpret. In the life sciences, extensive knowledge of cell biology provides an opportunity to design visible neural networks (VNNs) that couple the model’s inner workings to those of real systems. Here we develop DCell, a VNN embedded in the hierarchical structure of 2,526 subsystems comprising a eukaryotic cell (http://d-cell.ucsd.edu/). Trained on several million genotypes, DCell simulates cellular growth nearly as accurately as laboratory observations. During simulation, genotypes induce patterns of subsystem activities, enabling in silico investigations of the molecular mechanisms underlying genotype–phenotype associations. These mechanisms can be validated, and many are unexpected; some are governed by Boolean logic. Cumulatively, 80% of the importance for growth prediction is captured by 484 subsystems (21%), reflecting the emergence of a complex phenotype. DCell provides a foundation for decoding the genetics of disease, drug resistance and synthetic life.

We welcome all who can join us for this discussion. Feel free to begin that discussion in the comments section below.