Biology subjects

Hutson, D.

Publications and source records attributed to Hutson, D..

3 recordsLinked to original sources

bioRxiv2023

FocA: A deep learning tool for reliable, near-real-time imaging focus analysis in automated cell assay pipelines

The increasing use of automation in cellular assays and cell culture presents significant opportunities to enhance the scale and throughput of imaging assays, but to do so, reliable data quality and consistency are critical. Realizing the full potential of automation will thus require the design of robust analysis pipelines that span the entire workflow in question. Here we present FocA, a deep learning tool that, in near real-time, identifies in-focus and out-of-focus images generated on a fully automated cell biology research platform, the NYSCF Global Stem Cell Array(R). The tool is trained on small patches of downsampled images to maximize computational efficiency without compromising accuracy, and optimized to make sure no sub-quality images are stored and used in downstream analyses. The tool automatically generates balanced and maximally diverse training sets to avoid bias. The resulting model correctly identifies 100% of out-of-focus and 98% of in-focus images in under 4 seconds per 96-well plate, and achieves this result even in heavily downsampled data ([~]30 times smaller than native resolution). Integrating the tool into automated workflows minimizes the need for human verification as well as the collection and usage of low-quality data. FocA thus offers a solution to ensure reliable image data hygiene and improve the efficiency of automated imaging workflows using minimal computational resources.

bioinformatics↗

bioRxiv2020

Modular deep learning enables automated identification of monoclonal cell lines

Monoclonalization refers to the isolation and expansion of a single cell derived from a cultured population. This is a valuable step in cell culture so as to minimize a cell lines technical variability downstream of cell-altering events, such as reprogramming or gene editing, as well as for processes such as monoclonal antibody development. However, traditional methods for verifying clonality do not scale well, posing a critical obstacle to studies involving large cohorts. Without automated, standardized methods for assessing clonality post-hoc, methods involving monoclonalization cannot be reliably upscaled without exacerbating the technical variability of cell lines. We report the design of a deep learning workflow that automatically detects colony presence and identifies clonality from cellular imaging. The workflow, termed Monoqlo, integrates multiple convolutional neural networks and, critically, leverages the chronological directionality of the cell culturing process. Our algorithm design provides a fully scalable, highly interpretable framework, capable of analyzing industrial data volumes in under an hour using commodity hardware. In the present study, we focus on monoclonalization of human induced pluripotent stem cells (HiPSCs) as a case example. Monoqlo standardizes the monoclonalization process, enabling colony selection protocols to be infinitely upscaled while minimizing technical variability.

cell biology↗

bioRxiv2019

Pan-active imidazolopiperazine antimalarials target the Plasmodium falciparum intracellular secretory pathway

AO_SCPLOWBSTRACTC_SCPLOWOne of the most promising new compound classes in clinical development for the treatment of malaria is the imidazolopiperazines (IZPs) class. Human trials have demonstrated that members of the IZP series, which includes KAF156 (Ganaplacide) and GNF179, are potent and effective against Plasmodium symptomatic asexual blood-stage infections. Unlike other commonly used antimalarials, they also prevent transmission and block future infection in animal models. Despite the identification of several Plasmodium falciparum resistance mechanisms including mutations in ER-localized PfCARL (PfEMP65), Acetyl-coA transporter, and PfUGT transporter, IZPs mechanism of action remains unknown.\n\nTo investigate, we combined in vitro evolution and whole-genome analysis in the model organism Saccharomyces cerevisiae with molecular, metabolomic, and chemogenomic methods, in P. falciparum. S. cerevisiae clones that resist IZP activity carry multiple mutations in genes that encode endoplasmic reticulum(ER)-based lipid homeostasis and autophagy including elo2, elo3, sur2, atg15 and lcb4, as well as ER-based sec66. In Plasmodium, IZPs cause inhibition of protein trafficking, block the establishment of new permeation pathways and result in ER expansion. We also observe sensitization with other secretion inhibitors such as brefeldin A and golgicidin as well as synthetic lethality with PfSEC62. Our data show that IZPs target the secretory pathway and highlight a novel mechanism for blocking parasite growth and development that is distinct from those of standard compounds used to treat malaria. In addition, we provide physiological signatures and hallmarks for inhibitors that work through this mechanism of action and show that IZPs are tool compounds for studying ER-dependent protein processing in different species.

microbiology↗