Transcriptome Architecture of Adult Mouse Brain Revealed by Sparse Coding of Genome-Wide In Situ Hybridization Images

Repairing the in situ hybridization missing data in the hippocampus region by using a 3D residual U-Net model

The hippocampus is a critical brain region. Transcriptome data provides valuable insights into the structure and function of the hippocampus at the gene level. However, transcriptome data is often incomplete. To address this issue, we use the convolutional neural network model to repair the missing voxels in the hippocampus region, based on Allen institute coronal slices in situ hybridization (ISH) dataset. Moreover, we analyze the gene expression correlation between coronal and sagittal dataset in the hippocampus region. The results demonstrated that the trend of gene expression correlation between the coronal and sagittal datasets remained consistent following the repair of missing data in the coronal ISH dataset. In the last, we use repaired ISH dataset to identify novel genes specific to hippocampal subregions. Our findings demonstrate the accuracy and effectiveness of using deep learning method to repair ISH missing data. After being repaired, ISH has the potential to improve our comprehension of the hippocampus's structure and function.

Sparse representation learning derives biological features with explicit gene weights from the Allen Mouse Brain Atlas

Unsupervised learning methods are commonly used to detect features within transcriptomic data and ultimately derive meaningful representations of biology. Contributions of individual genes to any feature however becomes convolved with each learning step, requiring follow up analysis and validation to understand what biology might be represented by a cluster on a low dimensional plot. We sought learning methods that could preserve the gene information of detected features, using the spatial transcriptomic data and anatomical labels of the Allen Mouse Brain Atlas as a test dataset with verifiable ground truth. We established metrics for accurate representation of molecular anatomy to find sparse learning approaches were uniquely capable of generating anatomical representations and gene weights in a single learning step. Fit to labeled anatomy was highly correlated with intrinsic properties of the data, offering a means to optimize parameters without established ground truth. Once representations were derived, complementary gene lists could be further compressed to generate a low complexity dataset, or to probe for individual features with >95% accuracy. We demonstrate the utility of sparse learning as a means to derive biologically meaningful representations from transcriptomic data and reduce the complexity of large datasets while preserving intelligible gene information throughout the analysis.

Multi-Resemblance Multi-Target Low-Rank Coding for Prediction of Cognitive Decline With Longitudinal Brain Images

An effective presymptomatic diagnosis and treatment of Alzheimer's disease (AD) would have enormous public health benefits. Sparse coding (SC) has shown strong potential for longitudinal brain image analysis in preclinical AD research. However, the traditional SC computation is time-consuming and does not explore the feature correlations that are consistent over the time. In addition, longitudinal brain image cohorts usually contain incomplete image data and clinical labels. To address these challenges, we propose a novel two-stage Multi-Resemblance Multi-Target Low-Rank Coding (MMLC) method, which encourages that sparse codes of neighboring longitudinal time points are resemblant to each other, favors sparse code low-rankness to reduce the computational cost and is resilient to both source and target data incompleteness. In stage one, we propose an online multi-resemblant low-rank SC method to utilize the common and task-specific dictionaries in different time points to immune to incomplete source data and capture the longitudinal correlation. In stage two, supported by a rigorous theoretical analysis, we develop a multi-target learning method to address the missing clinical label issue. To solve such a multi-task low-rank sparse optimization problem, we propose multi-task stochastic coordinate coding with a sequence of closed-form update steps which reduces the computational costs guaranteed by a theoretical convergence proof. We apply MMLC on a publicly available neuroimaging cohort to predict two clinical measures and compare it with six other methods. Our experimental results show our proposed method achieves superior results on both computational efficiency and predictive accuracy and has great potential to assist the AD prevention.

Characterization of Brain Iron Deposition Pattern and Its Association With Genetic Risk Factor in Alzheimer's Disease Using Susceptibility-Weighted Imaging

The presence of iron is an important factor for normal brain functions, whereas excessive deposition of iron may impair normal cognitive function in the brain and lead to Alzheimer’s disease (AD). MRI has been widely applied to characterize brain structural and functional changes caused by AD. However, the effectiveness of using susceptibility-weighted imaging (SWI) for the analysis of brain iron deposition is still unclear, especially within the context of early AD diagnosis. Thus, in this study, we aim to explore the relationship between brain iron deposition measured by SWI with the progression of AD using various feature selection and classification methods. The proposed model was evaluated on a 69-subject SWI imaging dataset consisting of 24 AD patients, 21 mild cognitive impairment patients, and 24 normal controls. The identified AD progression-related regions were then compared with the regions reported from previous genetic association studies, and we observed considerable overlap between these two. Further, we have identified a new potential AD-related gene (MEF2C) closely related to the interaction between iron deposition and AD progression in the brain.

Predicting future cognitive decline with hyperbolic stochastic coding

Hyperbolic geometry has been successfully applied in modeling brain cortical and subcortical surfaces with general topological structures. However, such approaches, similar to other surface-based brain morphology analysis methods, usually generate high dimensional features. It limits their statistical power in cognitive decline prediction research, especially in datasets with limited subject numbers. To address the above limitation, we propose a novel framework termed as hyperbolic stochastic coding (HSC). We first compute diffeomorphic maps between general topological surfaces by mapping them to a canonical hyperbolic parameter space with consistent boundary conditions and extracts critical shape features. Secondly, in the hyperbolic parameter space, we introduce a farthest point sampling with breadth-first search method to obtain ring-shaped patches. Thirdly, stochastic coordinate coding and max-pooling algorithms are adopted for feature dimension reduction. We further validate the proposed system by comparing its classification accuracy with some other methods on two brain imaging datasets for Alzheimer's disease (AD) progression studies. Our preliminary experimental results show that our algorithm achieves superior results on various classification tasks. Our work may enrich surface-based brain imaging research tools and potentially result in a diagnostic and prognostic indicator to be useful in individualized treatment strategies.

Marmoset Brain ISH Data Revealed Molecular Difference Between Cortical Folding Patterns

Literature studies have demonstrated the structural, connectional, and functional differences between cortical folding patterns in mammalian brains, such as convex and concave patterns. However, the molecular underpinning of such convex/concave differences remains largely unknown. Thanks to public access to a recently released set of marmoset whole-brain in situ hybridization data by RIKEN, Japan; this data's accessibility empowers us to improve our understanding of the organization, regulation, and function of genes and their relation to macroscale metrics of brains. In this work, magnetic resonance imaging and diffusion tensor imaging macroscale neuroimaging data in this dataset were used to delineate convex/concave patterns in marmoset and to examine their structural features. Machine learning and visualization tools were employed to investigate the possible transcriptome difference between cortical convex and concave patterns. Experimental results demonstrated that a collection of genes is differentially expressed in convex and concave patterns, and their expression profiles can robustly characterize and differentiate the two folding patterns. More importantly, neuroscientific interpretations of these differentially expressed genes, as well as axonal guidance pathway analysis and gene enrichment analysis, offer novel understanding of structural and functional differences between cortical folding patterns in different regions from a molecular perspective.

Deep Neural Networks for In Situ Hybridization Grid Completion and Clustering

Transcriptome in brain plays a crucial role in understanding the cortical organization and the development of brain structure and function. Two challenges, incomplete data and high dimensionality of transcriptome, remain unsolved. Here, we present a novel training scheme that successfully adapts the U-net architecture to the problem of volume recovery. By analogy to denoising autoencoder, we hide a portion of each training sample so that the network can learn to recover missing voxels from context. Then on the completed volumes, we show that Restricted Boltzmann Machines (RBMs) can be used to infer co-occurrences among voxels, providing foundations for dividing the cortex into discrete subregions. As we stack multiple RBMs to form a deep belief network (DBN), we progressively map the high-dimensional raw input into abstract representations and create a hierarchy of transcriptome architecture. A coarse to fine organization emerges from the network layers. This organization incidentally corresponds to the anatomical structures, suggesting a close link between structures and the genetic underpinnings. Thus, we demonstrate a new way of learning transcriptome-based hierarchical organization using RBM and DBN.

ZEBrA: Zebra finch Expression Brain Atlas-A resource for comparative molecular neuroanatomy and brain evolution studies

An in-depth understanding of the genetics and evolution of brain function and behavior requires a detailed mapping of gene expression in functional brain circuits across major vertebrate clades. Here we present the Zebra finch Expression Brain Atlas (ZEBrA; www.zebrafinchatlas.org, RRID: SCR_012988), a web-based resource that maps the expression of genes linked to a broad range of functions onto the brain of zebra finches. ZEBrA is a first of its kind gene expression brain atlas for a bird species and a first for any sauropsid. ZEBrA's >3,200 high-resolution digital images of in situ hybridized sections for ~650 genes (as of June 2019) are presented in alignment with an annotated histological atlas and can be browsed down to cellular resolution. An extensive relational database connects expression patterns to information about gene function, mouse expression patterns and phenotypes, and gene involvement in human diseases and communication disorders. By enabling brain-wide gene expression assessments in a bird, ZEBrA provides important substrates for comparative neuroanatomy and molecular brain evolution studies. ZEBrA also provides unique opportunities for linking genetic pathways to vocal learning and motor control circuits, as well as for novel insights into the molecular basis of sex steroids actions, brain dimorphisms, reproductive and social behaviors, sleep function, and adult neurogenesis, among many fundamental themes.