Inferring protein from transcript abundances using convolutional neural networks.

Background: Although transcript abundance is often used as a proxy for protein abundance, it is an unreliable predictor. As proteins execute biological functions and their expression levels influence phenotypic outcomes, we developed a convolutional neural network (CNN) to predict protein abundances from mRNA abundances, protein sequence, and mRNA sequence in Homo sapiens (H. sapiens) and the reference plant Arabidopsis thaliana (A.

Optimized CRISPR-Cas9-based Strategy for Complex Gene Targeting in Murine Embryonic Stem Cells for Germline Transmission.

Although CRISPR-Cas9 genome editing can be performed directly in single-cell mouse zygotes, the targeting efficiency for more complex modifications such as the insertion of two loxP sites, multiple mutations in cis, or the precise insertion or deletion of longer DNA sequences often remains low (Cohen, 2016). Thus, targeting and validation of correct genomic modification in murine embryonic stem cells (ESCs) with subsequent injection into early-stage mouse embryos may still be preferable, allowing for large-scale screening before transfer of thoroughly characterized and genetically defined ESC clones into the germline. This procedure can result in a reduction of animal numbers with cost effectiveness and compliance with the 3R principle of animal welfare regulations.