Viswanathan, L. | bioRxiv Science

bioRxiv2021

NiftyTorch: A Deep Learning framework for NeuroImaging

We present NiftyTorch a Deep Learning Framework for NeuroImaging. The motivation behind the development of such a library is that there are scant amount of centralized tool for deploying 3D deep learning for NeuroImaging. In addition, most of the existing tools require expert technical knowledge in Deep Learning or programming, creating a barrier for entry. The goal is to provide a one stop package using which the users can perform classification tasks, Segmentation tasks and Image Transformation tasks. The intended audience are the members of NeuroImaging who would like to explore deep learning but have no background in coding. In this article we explore the capabilities of the framework, the performance of the framework and the future work for the framework.

neuroscience↗

bioRxiv2018

CRISPR/Cas9 Targeted Capture Of Mammalian Genomic Regions For Characterization By NGS

The robust detection of structural variants in mammalian genomes remains a challenge. It is particularly difficult in the case of genetically unstable Chinese hamster ovary (CHO) cell lines with only draft genome assemblies available. We explore the potential of the CRISPR/Cas9 system for the targeted capture of genomic loci containing integrated vectors in CHO-K1-based cell lines, and compare it to popular target-enrichment methods and to whole genome sequencing (WGS). The CRISPR/Cas9-based techniques allow for amplification-free capture of genomic regions, which reduces the possibility of sequencing artifacts. Other advantages of these methods are the ease of bioinformatics analysis, potential for multiplexing, and the production of longer sequencing templates for real-time sequencing. The utility of these protocols has been proven by identification of transgene integration sites and flanking sequences in a number of CHO cell lines. However, data produced by these and other targeted capture methods are not always sufficient to analyze complex genomic rearrangements (CGRs) or unexpected sequences introduced into genome by vector integration events. In contrast, WGS provides complete information about vector integration sites, vector copy number, CGRs, and foreign DNA-but despite these benefits, WGS is not easily implemented due to the cost and complexity of the analysis.

genomics↗