Astrocyte regional heterogeneity revealed through machine learning‐based glial neuroanatomical assays

Abstract

Evaluation of reactive astrogliosis by neuroanatomical assays represents a common experimental outcome for neuroanatomists. The literature demonstrates several conflicting results as to the accuracy of such measures. We posited that the diverging results within the neuroanatomy literature were due to suboptimal analytical workflows in addition to astrocyte regional heterogeneity. We therefore generated an automated segmentation workflow to extract features of glial fibrillary acidic protein (GFAP) and aldehyde dehydrogenase family 1, member L1 (ALDH1L1) labeled astrocytes with and without neuroinflammation. We achieved this by capturing multiplexed immunofluorescent confocal images of mouse brains treated with either vehicle or lipopolysaccharide (LPS) followed by implementation of our workflows. Using classical image analysis techniques focused on pixel intensity only, we were unable to identify differences between vehicle‐treated and LPS‐treated animals. However, when utilizing machine learning–based algorithms, we were able to (1) accurately predict which objects were derived from GFAP or ALDH1L1‐stained images indicating that GFAP and ALDH1L1 highlight distinct morphological aspects of astrocytes, (2) we could predict which neuroanatomical region the segmented GFAP or ALDH1L1 object had been derived from, indicating that morphological features of astrocytes change as a function of neuroanatomical location. (3) We discovered a statistically significant, albeit not highly accurate, prediction of which objects had come from LPS versus vehicle‐treated animals, indicating that although features exist capable of distinguishing LPS‐treated versus vehicle‐treated GFAP and ALDH1L1‐segmented objects, that significant overlap between morphologies exists. We further determined that for most classification scenarios, nonlinear models were required for improved treatment class designations. We propose that unbiased automated image analysis techniques coupled with well‐validated machine learning tools represent highly useful models capable of providing insights into neuroanatomical assays.

Progression of reactive gliosis and astroglial phenotypic changes following stab wound‐induced traumatic brain injury in mice

“…Emerging single-cell spatial transcriptomics offer spatial resolution but are relatively costly and not widely accessible. Therefore, cost-effective neuroanatomical evaluations with positional information as our present study are important to evaluate astroglial neuropathology (Blackburn et al, 2021).…”

“…The GFAP marker was used to follow reactive astrogliosis in spatiotemporal coordinates, taking advantage of its strong up‐regulation in reactive astrocytes in mice and keeping in mind that GFAP is a pan‐reactive astroglial gene expressed by reactive astrocytes regardless of their pro‐ or anti‐inflammatory characteristics (Escartin et al, 2021; Liddelow et al, 2017; Zamanian et al, 2012). Morphometrical studies have shown that GFAP is equivalent to ALDH1L1 in labeling, identifying, and characterizing reactive astrocytes (Blackburn et al, 2021). Single‐nuclei and single‐cell RNA‐seq have revealed multiple clusters or subpopulations of reactive astrocytes (Anderson et al, 2018; Liddelow et al, 2017; Zamanian et al, 2012), but these studies still lack detailed spatial information.…”

Assessing Astrocytes in Alzheimer's Disease

“…Other studies report sex-specific differences in astrocyte expression in different brain areas (Belonwu et al, 2022), or different astrocyte expression profiles across development, that are also sex-specific . Studies have also shown brain region-specific changes in astrocyte gene expression profile in response to inflammation (Blackburn et al, 2021;.…”