Shaidani Nikko-Ideen

No Thumbnail Available
Last Name
Shaidani
First Name
Nikko-Ideen
ORCID

Filters

2020 - 2021 2
2
2
Reset filters

Settings

Search Results

Now showing 1 - 2 of 2
  • Article
    Deep learning is widely applicable to phenotyping embryonic development and disease
    (The Company of Biologists, 2021-11-05) Naert, Thomas ; Çiçek, Özgün ; Ogar, Paulina ; Bürgi, Max ; Shaidani, Nikko-Ideen ; Kaminski, Michael M. ; Xu, Yuxiao ; Grand, Kelli ; Vujanovic, Marko ; Prata, Daniel ; Hildebrandt, Friedhelm ; Brox, Thomas ; Ronneberger, Olaf ; Voigt, Fabian F. ; Helmchen, Fritjof ; Loffing, Johannes ; Horb, Marko E. ; Rankin Willsey, Helen ; Lienkamp, Soeren S.
    Genome editing simplifies the generation of new animal models for congenital disorders. However, the detailed and unbiased phenotypic assessment of altered embryonic development remains a challenge. Here, we explore how deep learning (U-Net) can automate segmentation tasks in various imaging modalities, and we quantify phenotypes of altered renal, neural and craniofacial development in Xenopus embryos in comparison with normal variability. We demonstrate the utility of this approach in embryos with polycystic kidneys (pkd1 and pkd2) and craniofacial dysmorphia (six1). We highlight how in toto light-sheet microscopy facilitates accurate reconstruction of brain and craniofacial structures within X. tropicalis embryos upon dyrk1a and six1 loss of function or treatment with retinoic acid inhibitors. These tools increase the sensitivity and throughput of evaluating developmental malformations caused by chemical or genetic disruption. Furthermore, we provide a library of pre-trained networks and detailed instructions for applying deep learning to the reader's own datasets. We demonstrate the versatility, precision and scalability of deep neural network phenotyping on embryonic disease models. By combining light-sheet microscopy and deep learning, we provide a framework for higher-throughput characterization of embryonic model organisms.
  • Article
    Maximizing CRISPR/Cas9 phenotype penetrance applying predictive modeling of editing outcomes in Xenopus and zebrafish embryos
    (Nature Research, 2020-09-04) Naert, Thomas ; Tulkens, Dieter ; Edwards, Nicole A. ; Carron, Marjolein ; Shaidani, Nikko-Ideen ; Wlizla, Marcin ; Boel, Annekatrien ; Demuynck, Suzan ; Horb, Marko E. ; Coucke, Paul ; Willaert, Andy ; Zorn, Aaron M. ; Vleminckx, Kris
    CRISPR/Cas9 genome editing has revolutionized functional genomics in vertebrates. However, CRISPR/Cas9 edited F0 animals too often demonstrate variable phenotypic penetrance due to the mosaic nature of editing outcomes after double strand break (DSB) repair. Even with high efficiency levels of genome editing, phenotypes may be obscured by proportional presence of in-frame mutations that still produce functional protein. Recently, studies in cell culture systems have shown that the nature of CRISPR/Cas9-mediated mutations can be dependent on local sequence context and can be predicted by computational methods. Here, we demonstrate that similar approaches can be used to forecast CRISPR/Cas9 gene editing outcomes in Xenopus tropicalis, Xenopus laevis, and zebrafish. We show that a publicly available neural network previously trained in mouse embryonic stem cell cultures (InDelphi-mESC) is able to accurately predict CRISPR/Cas9 gene editing outcomes in early vertebrate embryos. Our observations can have direct implications for experiment design, allowing the selection of guide RNAs with predicted repair outcome signatures enriched towards frameshift mutations, allowing maximization of CRISPR/Cas9 phenotype penetrance in the F0 generation.