Exploiting Gene Expression Profiles for the Automated Prediction of Connectivity between Brain Regions

Abstract

The brain comprises a complex system of neurons interconnected by an intricate network of anatomical links. While recent studies demonstrated the correlation between anatomical connectivity patterns and gene expression of neurons, using transcriptomic information to automatically predict such patterns is still an open challenge. In this work, we present a completely data-driven approach relying on machine learning (i.e., neural networks) to learn the anatomical connection directly from a training set of gene expression data. To do so, we combined gene expression and connectivity data from the Allen Mouse Brain Atlas to generate thousands of gene expression profile pairs from different brain regions. To each pair, we assigned a label describing the physical connection between the corresponding brain regions. Then, we exploited these data to train neural networks, designed to predict brain area connectivity. We assessed our solution on two prediction problems (with three and two connectivity class categories) involving cortical and cerebellum regions. As demonstrated by our results, we distinguish between connected and unconnected regions with 85% prediction accuracy and good balance of precision and recall. In our future work we may extend the analysis to more complex brain structures and consider RNA-Seq data as additional input to our model.

Identification of genetic markers for cortical areas using a Random Forest classification routine and the Allen Mouse Brain Atlas

“…Examples include cytochrome oxidase histochemistry and antibodies against m2 muscarinic receptors [3]. Numerous differences in expression across cortical areas have been observed, including abrupt changes in expression at area borders, more graded changes between areas, gradients in expression across an area, and changes in cell-specific expression [4–11].…”

Where the genome meets the connectome: understanding how genes shape human brain connectivity

“…In mice and rats, gene-expression profiles can predict inter-regional connectivity, with genes related to axon guidance, neuronal communication, and development being among the most informative French & Pavlidis, 2011;Ji et al, 2014;Roberti et al, 2019). A model that incorporates CGE, structural connectivity, and the physical distance between pairs of brain regions has been shown to account for 62% of in inter-regional functional coupling in the mouse brain (Mills et al, 2018), indicating that geometry and regional gene-expression similarity are also informative of resting-state functional connectivity.…”

Buffer-MIL: Robust Multi-instance Learning with a Buffer-Based Approach

“…The histopathological image analysis is a research area with a wide interest as it helps pathologists to carry out accurate diagnosis [12], especially when combined with genomic features [7,14,19]. The most common way to acquire glass slides is by employing Whole-Slide Image (WSI) scanners, which can produce digital high-resolution images [18].…”