Complexity of cell-type composition has created much skepticism surrounding the interpretation of bulk tissue transcriptomic studies. Recent studies have shown that deconvolution algorithms can be applied to computationally estimate cell-type proportions from gene expression data of bulk blood samples, but their performance when applied to brain tissue is unclear. Here, we have generated an immunohistochemistry (IHC) dataset for five major cell-types from brain tissue of 70 individuals, who also have bulk cortical gene expression data. With the IHC data as the benchmark, this resource enables quantitative assessment of deconvolution algorithms for brain tissue. We apply existing deconvolution algorithms to brain tissue by using marker sets derived from human brain single cell and cell-sorted RNA-seq data. We show that these algorithms can indeed produce informative estimates of constituent cell-type proportions. In fact, neuronal subpopulations can also be estimated from bulk brain tissue samples. Further, we show that including the cell-type proportion estimates as confounding factors is important for reducing false associations between Alzheimer's disease phenotypes and gene expression. Lastly, we demonstrate that using more accurate marker sets can substantially improve statistical power in detecting cell-type specific expression quantitative trait loci (eQTLs).

There is a recent interest in using functional magnetic resonance imaging (fMRI) for decoding more naturalistic, cognitive states, in which subjects perform various tasks in a continuous, self-directed manner. In this setting, the set of brain volumes over the entire task duration is usually taken as a single sample with connectivity estimates, such as Pearson's correlation, employed as features. Since covariance matrices live on the positive semidefinite cone, their elements are inherently inter-related. The assumption of uncorrelated features implicit in most classifier learning algorithms is thus violated. Coupled with the usual small sample sizes, the generalizability of the learned classifiers is limited, and the identification of significant brain connections from the classifier weights is nontrivial. In this paper, we present a Riemannian approach for connectivity-based brain decoding. The core idea is to project the covariance estimates onto a common tangent space to reduce the statistical dependencies between their elements. For this, we propose a matrix whitening transport, and compare it against parallel transport implemented via the Schild's ladder algorithm. To validate our classification approach, we apply it to fMRI data acquired from twenty four subjects during four continuous, self-driven tasks. We show that our approach provides significantly higher classification accuracy than directly using Pearson's correlation and its regularized variants as features. To facilitate result interpretation, we further propose a non-parametric scheme that combines bootstrapping and permutation testing for identifying significantly discriminative brain connections from the classifier weights. Using this scheme, a number of neuro-anatomically meaningful connections are detected, whereas no significant connections are found with pure permutation testing.

A fundamental means for understanding the brain's organizational structure is to group its spatially disparate regions into functional subnetworks based on their interactions. Most community detection techniques are designed for generating partitions, but certain brain regions are known to interact with multiple subnetworks. Thus, the brain's underlying subnetworks necessarily overlap. In this paper, we propose a technique for identifying overlapping subnetworks from weighted graphs with statistical control over false node inclusion. Our technique improves upon the replicator dynamics formulation by incorporating a graph augmentation strategy to enable subnetwork overlaps, and a graph incrementation scheme for merging subnetworks that might be falsely split by replicator dynamics due to its stringent mutual similarity criterion in defining subnetworks. To statistically control for inclusion of false nodes into the detected subnetworks, we further present a procedure for integrating stability selection into our subnetwork identification technique. We refer to the resulting technique as stable overlapping replicator dynamics (SORD). Our experiments on synthetic data show significantly higher accuracy in subnetwork identification with SORD than several state-of-the-art techniques. We also demonstrate higher test-retest reliability in multiple network measures on the Human Connectome Project data. Further, we illustrate that SORD enables identification of neuroanatomically-meaningful subnetworks and network hubs.

Noise confounds present serious complications to functional magnetic resonance imaging (fMRI) analysis. The amount of discernible signals within a single dataset of a subject is often inadequate to obtain satisfactory intra-subject activation detection. To remedy this limitation, we propose a novel group Markov random field (GMRF) that extends each subject's neighborhood system to other subjects to enable information coalescing. A distinct advantage of GMRF over standard fMRI group analysis is that no stringent one-to-one voxel correspondence is required. Instead, intra- and inter-subject neighboring voxels are jointly regularized to encourage spatially proximal voxels to be assigned similar labels across subjects. Our proposed group-extended graph structure thus provides an effective means for handling inter-subject variability. Also, adopting a group-wise approach by integrating group information into intra-subject activation, as opposed to estimating a single average group map, permits inter-subject differences to be characterized and studied. GMRF can be elegantly implemented as a single MRF, thus enabling all subjects' activation maps to be simultaneously and collaboratively segmented with global optimality guaranteed in the case of binary labeling. We validate our technique on synthetic and real fMRI data and demonstrate GMRF's superior performance over standard fMRI analysis.

Functional magnetic resonance imaging (fMRI) is increasingly used for studying functional integration of the brain. However, large inter-subject variability in functional connectivity, particularly in disease populations, renders detection of representative group networks challenging. In this paper, we propose a novel technique, "group replicator dynamics" (GRD), for detecting sparse functional brain networks that are common across a group of subjects. We extend the replicator dynamics (RD) approach, which we show to be a solution of the nonnegative sparse principal component analysis problem, by integrating group information into each subject's RD process. Our proposed strategy effectively coaxes all subjects' networks to evolve towards the common network of the group. This results in sparse networks comprising the same brain regions across subjects yet with subject-specific weightings of the identified brain regions. Thus, in contrast to traditional averaging approaches, GRD enables inter-subject variability to be modeled, which facilitates statistical group inference. Quantitative validation of GRD on synthetic data demonstrated superior network detection performance over standard methods. When applied to real fMRI data, GRD detected task-specific networks that conform well to prior neuroscience knowledge.

The perplexing effects of noise and high feature dimensionality greatly complicate functional magnetic resonance imaging (fMRI) classification. In this paper, we present a novel formulation for constructing “Generalized Group Sparse Classifiers” (GSSC) to alleviate these problems. In particular, we propose an extension of group LASSO that permits associations between features within (predefined) groups to be modeled. Integrating this new penalty into classifier learning enables incorporation of additional prior information beyond group structure. In the context of fMRI, GGSC provides a flexible means for modeling how the brain is functionally organized into specialized modules (i.e. groups of voxels) with spatially proximal voxels often displaying similar level of brain activity (i.e. feature associations). Applying GSSC to real fMRI data improved predictive performance over standard classifiers, while providing more neurologically interpretable classifier weight patterns. Our results thus demonstrate the importance of incorporating prior knowledge into classification problems.

Noise confounds present serious complications to accurate data analysis in functional magnetic resonance imaging (fMRI). Simply relying on contextual image information often results in unsatisfactory segmentation of active brain regions. To remedy this, we propose a novel Group Markov Random Field (Group MRF) that extends the neighborhood system to other subjects to incorporate group information in modeling each subject's brain activation. Our approach has the distinct advantage of being able to regularize the states of both intra- and inter-subject neighbors without having to create a stringent one-to-one voxel correspondence as in standard fMRI group analysis. Also, our method can be efficiently implemented as a single MRF, hence enabling activation maps of a group of subjects to be simultaneously and collaboratively segmented. We validate on both synthetic and real fMRI data and demonstrate superior performance over standard analysis techniques.

A novel approach is proposed for quantitatively characterizing the spatial patterns of activation statistics in functional magnetic resonance imaging (fMRI) activation maps. Specifically, we propose using 3-D invariant moment descriptors, as opposed to the traditionally-employed magnitude-based features such as mean voxel statistics or percentage of activated voxels, to characterize the task-specific spatial distribution of activation statistics within a given region of interest (ROI). The proposed method is applied to real fMRI data collected from 21 healthy subjects performing previously-learned right-handed finger tapping sequences that are either externally guided (EG) by a cue or internally guided (IG)--tasks expected to incur subtle differences in motor-related cortical and subcortical ROIs. Voxel-based activation statistics contrasting EG versus rest and IG versus rest are examined in multiple manually-drawn ROIs on unwarped brain images. Analyzing the activation statistics within each ROI using the proposed 3-D invariant moment descriptors detected significant group differences between the two tasks, thus quantitatively demonstrating that the spatial distribution of activation statistics within an ROI represent an important task-related attribute of brain activation. In contrast, conventional methods that solely rely on activation statistic magnitudes and disregard spatial information showed reduced discriminability. Normally, incorporating spatial information would merely increase inter-subject variability partly due to differences in brain size and subject's orientation in the scanner. Yet, our results suggest that the proposed spatial features, which are invariant to similarity transformations, can effectively account for such inter-subject variability, while enhancing the sensitivity in detecting task-specific activation. Thus, we argue that this novel quantitative description of the "3-D texture" of activation maps provides new directions to explore for ROI-based fMRI analysis.