A unified framework for joint-tissue transcriptome-wide association and Mendelian randomization analysis | Nature Genetics
Here, researchers present a joint-tissue imputation (JTI) approach and a Mendelian randomization framework for causal inference, MR-JTI. JTI borrows information across transcriptomes of different tissues, leveraging shared genetic regulation, to improve prediction performance in a tissue-dependent manner.
DeepCycle reconstructs a cyclic cell cycle trajectory from unsegmented cell images using convolutional neural networks | Molecular Systems Biology
DeepCycle is a deep neural network able to reconstruct a cyclic cell cycle trajectory from unsegmented cell images. The model is validated on cells undergoing a full cell cycle by comparing the progression of the inferred trajectory to real time.
Genome Complexity Browser: Visualization and quantification of genome variability | PLOS Computational Biology
Comparative genomics studies may be used to acquire new knowledge regarding genome architecture, which defines the rules for combining sets of genes in the genome of living organisms. Researchers developed the Genome Complexity Browser, a tool that allows the visualization of gene contexts, in a graph-based format, and the quantification of variability for different segments of a genome. The graph-based visualization allows the inspection of changes in gene contents and neighborhoods across hundreds of genomes, simultaneously, which may facilitate the identification of conserved and variable segments of operons or the estimation of the overall variability associated with a particular genome locus.