Co-varying neighborhood analysis identifies cell populations associated with phenotypes of interest from single-cell transcriptomics | Nature Biotechnology
As single-cell datasets grow in sample size, there is a critical need to characterize cell states that vary across samples and associate with sample attributes, such as clinical phenotypes. Current statistical approaches typically map cells to clusters and then assess differences in cluster abundance. Here researchers present co-varying neighborhood analysis (CNA), an unbiased method to identify associated cell populations with greater flexibility than cluster-based approaches.
Panache: a web browser-based viewer for linearized pangenomes | Bioinformatics
Pangenomics evolved since its first applications on bacteria, extending from the study of genes for a given population to the study of all of its sequences available. Researchers introduce Panache, a tool for the visualization and exploration of linear representations of gene-based and sequence-based pangenomes. It uses a layout similar to genome browsers to display presence absence variations and additional tracks along a linear axis with a pangenomics perspective.
Deep learning improves macromolecule identification in 3D cellular cryo-electron tomograms | Nature Methods
Cryogenic electron tomography (cryo-ET) visualizes the 3D spatial distribution of macromolecules at nanometer resolution inside native cells. Here, researchers present DeepFinder, a computational procedure that uses artificial neural networks to simultaneously localize multiple classes of macromolecules. Once trained, the inference stage of DeepFinder is faster than template matching and performs better than other competitive deep learning methods at identifying macromolecules of various sizes in both synthetic and experimental datasets.