Goberdhan, S. | bioRxiv Science

bioRxiv2023

Cell-type-specific regulation of APOE levels in human neurons by the Alzheimer's disease risk gene SORL1

SORL1 is strongly implicated in the pathogenesis of Alzheimers disease (AD) through human genetic studies that point to an association of reduced SORL1 levels with higher risk for AD. To interrogate the role(s) of SORL1 in human brain cells, SORL1 null iPSCs were generated, followed by differentiation to neuron, astrocyte, microglia, and endothelial cell fates. Loss of SORL1 led to alterations in both overlapping and distinct pathways across cell types, with the greatest effects in neurons and astrocytes. Intriguingly, SORL1 loss led to a dramatic neuron-specific reduction in APOE levels. Further, analyses of iPSCs derived from a human aging cohort revealed a neuron-specific linear correlation between SORL1 and APOE RNA and protein levels, a finding validated in human post-mortem brain. Pathway analysis implicated intracellular transport pathways and TGF- {beta}/SMAD signaling in the function of SORL1 in neurons. In accord, enhancement of retromer-mediated trafficking and autophagy rescued elevated phospho-tau observed in SORL1 null neurons but did not rescue APOE levels, suggesting that these phenotypes are separable. Stimulation and inhibition of SMAD signaling modulated APOE RNA levels in a SORL1-dependent manner. These studies provide a mechanistic link between two of the strongest genetic risk factors for AD.

neuroscience↗

bioRxiv2022

Generative Adversarial Networks Can Create High Quality Artificial Prostate Cancer Magnetic Resonance Images

PurposeRecent integration of open-source data to machine learning models, especially in the medical field, has opened new doors to study disease progression and/or regression. However, the limitation of using medical data for machine learning approaches is the specificity of data to a particular medical condition. In this context, most recent technologies like generative adversarial networks (GAN) could be used to generate high quality synthetic data that preserves the clinical variability. Materials and MethodsIn this study, we used 139 T2-weighted prostate magnetic resonant images (MRI) from various sources as training data for Single Natural Image GAN (SinGAN), to make a generative model. A deep learning semantic segmentation pipeline trained the model to segment the prostate boundary on 2D MRI slices. Synthetic images with a high-level segmentation boundary of the prostate were filtered and used in the quality control assessment by participating scientists with varying degree of experience (more than 10 years, 1 year, or no experience) to work with MRI images. ResultsThe most experienced participating group correctly identified conventional vs synthetic images with 67% accuracy, the group with 1 year of experience correctly identified the images with 58% accuracy, and group with no prior experience reached 50% accuracy. Nearly half (47%) of the synthetic images were mistakenly evaluated as conventional images. Interestingly, a blinded quality assessment by a board-certified radiologist to differentiate conventional and synthetic images was not significantly different in context of the mean quality of synthetic and conventional images. ConclusionsThis study shows promise that high quality synthetic images from MRI can be generated using GAN. Such an AI model may contribute significantly to various clinical applications which involves supervised machine learning approaches.

bioinformatics↗