Visual detection of seizures in mice using supervised machine learning.

Seizures are caused by abnormally synchronous brain activity that can result in changes in muscle tone, such as twitching, stiffness, limpness, or rhythmic jerking. These behavioral manifestations are clear on visual inspection and the most widely used seizure scoring systems in preclinical models, such as the Racine scale in rodents, use these behavioral patterns in semiquantitative seizure intensity scores. However, visual inspection is time-consuming, low-throughput, and partially subjective, and there is a need for rigorously quantitative approaches that are scalable. In this study, we used supervised machine learning approaches to develop automated classifiers to predict seizure severity directly from noninvasive video data. Using the PTZ-induced seizure model in mice, we trained video-only classifiers to predict ictal events, combined these events to predict an univariate seizure intensity for a recording session, as well as time-varying seizure intensity scores. Our results show, for the first time, that seizure events and overall intensity can be rigorously quantified directly from overhead video of mice in a standard open field using supervised approaches. These results enable high-throughput, noninvasive, and standardized seizure scoring for downstream applications such as neurogenetics and therapeutic discovery.

Inferring single-cell spatial gene expression with tissue morphology via explainable deep learning.

The spatial arrangement of cells is vital in developmental processes and organogenesis in multicellular life forms. Deep learning models trained with spatial omics data uncover complex patterns and relationships among cells, genes, and proteins in a high-dimensional space, providing new insights into biological processes and diseases. State-of-the-art in silico spatial multi-cell gene expression methods using histological images of tissue stained with hematoxylin and eosin (H&E) to characterize cellular heterogeneity. These computational techniques offer the advantage of analyzing vast amounts of spatial data in a scalable and automated manner, thereby accelerating scientific discovery and enabling more precise medical diagnostics and treatments. In this work, we developed a vision transformer (ViT) framework to map histological signatures to spatial single-cell transcriptomic signatures, named SPiRiT ( S patial Omics P rediction and R eproducibility integrated T ransformer). Our framework was enhanced by integrating cross validation with model interpretation during hyper-parameter tuning. SPiRiT predicts single-cell spatial gene expression using the matched histopathological image tiles of human breast cancer and whole mouse pup, evaluated by Xenium (10x Genomics) datasets. Furthermore, ViT model interpretation reveals the high-resolution, high attention area (HAR) that the ViT model uses to predict the gene expression, including marker genes for invasive cancer cells ( FASN ), stromal cells ( POSTN ), and lymphocytes ( IL7R ). In an apple-to-apple comparison with the ST-Net Convolutional Neural Network algorithm, SPiRiT improved predictive accuracy by 40% using human breast cancer Visium (10x Genomics) dataset. Cancer biomarker gene prediction and expression level are highly consistent with the tumor region annotation. In summary, our work highlights the feasibility to infer spatial single-cell gene expression using tissue morphology in multiple-species, i.e., human and mouse, and multi-organs, i.e., mouse whole body morphology. Importantly, incorporating model interpretation and vision transformer is expected to serve as a general-purpose framework for spatial transcriptomics.

Probing the basis of disease heterogeneity in multiple sclerosis using genetically diverse mice.

Multiple sclerosis (MS) is a complex disease with significant heterogeneity in disease course and progression. Genetic studies have identified numerous loci associated with MS risk, but the genetic basis of disease progression remains elusive. To address this, we leveraged the Collaborative Cross (CC), a genetically diverse mouse strain panel, and experimental autoimmune encephalomyelitis (EAE). The thirty-two CC strains studied captured a wide spectrum of EAE severity, trajectory, and presentation, including severe-progressive, monophasic, relapsing remitting, and axial rotary (AR)-EAE, accompanied by distinct immunopathology. Sex differences in EAE severity were observed in six strains. Quantitative trait locus analysis revealed distinct genetic linkage patterns for different EAE phenotypes, including EAE severity and incidence of AR-EAE. Machine learning-based approaches prioritized candidate genes for loci underlying EAE severity ( Abcc4 and Gpc6 ) and AR-EAE ( Yap1 and Dync2h1 ). This work expands the EAE phenotypic repertoire and identifies novel loci controlling unique EAE phenotypes, supporting the hypothesis that heterogeneity in MS disease course is driven by genetic variation. Summary: The genetic basis of disease heterogeneity in multiple sclerosis (MS) remains elusive. We leveraged the Collaborative Cross to expand the phenotypic repertoire of the experimental autoimmune encephalomyelitis (EAE) model of MS and identify loci controlling EAE severity, trajectory, and presentation.

Systems genetics uncover new loci containing functional gene candidates in Mycobacterium tuberculosis-infected Diversity Outbred mice.

Mycobacterium tuberculosis infects two billion people across the globe, and results in 8-9 million new tuberculosis (TB) cases and 1-1.5 million deaths each year. Most patients have no known genetic basis that predisposes them to disease. Here, we investigate the complex genetic basis of pulmonary TB by modelling human genetic diversity with the Diversity Outbred mouse population. When infected with M. tuberculosis, one-third develop early onset, rapidly progressive, necrotizing granulomas and succumb within 60 days. The remaining develop non-necrotizing granulomas and survive longer than 60 days. Genetic mapping using immune and inflammatory mediators; and clinical, microbiological, and granuloma correlates of disease identified five new loci on mouse chromosomes 1, 2, 4, 16; and three known loci on chromosomes 3 and 17. Further, multiple positively correlated traits shared loci on chromosomes 1, 16, and 17 and had similar patterns of allele effects, suggesting these loci contain critical genetic regulators of inflammatory responses to M. tuberculosis. To narrow the list of candidate genes, we used a machine learning strategy that integrated gene expression signatures from lungs of M. tuberculosis-infected Diversity Outbred mice with gene interaction networks to generate scores representing functional relationships. The scores were used to rank candidates for each mapped trait, resulting in 11 candidate genes: Ncf2, Fam20b, S100a8, S100a9, Itgb5, Fstl1, Zbtb20, Ddr1, Ier3, Vegfa, and Zfp318. Although all candidates have roles in infection, inflammation, cell migration, extracellular matrix remodeling, or intracellular signaling, and all contain single nucleotide polymorphisms (SNPs), SNPs in only four genes (S100a8, Itgb5, Fstl1, Zfp318) are predicted to have deleterious effects on protein functions. We performed methodological and candidate validations to (i) assess biological relevance of predicted allele effects by showing that Diversity Outbred mice carrying PWK/PhJ alleles at the H-2 locus on chromosome 17 QTL have shorter survival; (ii) confirm accuracy of predicted allele effects by quantifying S100A8 protein in inbred founder strains; and (iii) infection of C57BL/6 mice deficient for the S100a8 gene. Overall, this body of work demonstrates that systems genetics using Diversity Outbred mice can identify new (and known) QTLs and functionally relevant gene candidates that may be major regulators of complex host-pathogens interactions contributing to granuloma necrosis and acute inflammation in pulmonary TB.

Causal network perturbation analysis identifies known and novel type-2 diabetes driver genes.

The molecular pathogenesis of diabetes is multifactorial, involving genetic predisposition and environmental factors that are not yet fully understood. However, pancreatic ß-cell failure remains among the primary reasons underlying the progression of type-2 diabetes (T2D) making targeting ß-cell dysfunction an attractive pathway for diabetes treatment. To identify genetic contributors to ß-cell dysfunction, we investigated single-cell gene expression changes in ß-cells from healthy (C57BL/6J) and diabetic (NZO/HlLtJ) mice fed with normal or high-fat, high-sugar diet (HFHS). Our study presents an innovative integration of the causal network perturbation assessment (ssNPA) framework with meta-cell transcriptome analysis to explore the genetic underpinnings of type-2 diabetes (T2D). By generating a reference causal network and in silico perturbation, we identified novel genes implicated in T2D and validated our candidates using the Knockout Mouse Phenotyping (KOMP) Project database.

Network-based analysis predicts interacting genetic modifiers from a meta-mapping study of spike-wave discharge in mice.

Absence seizures are characterized by brief lapses in awareness accompanied by a hallmark spike-and-wave discharge (SWD) electroencephalographic pattern and are common to genetic generalized epilepsies (GGEs). While numerous genes have been associated with increased risk, including some Mendelian forms with a single causal allele, most cases of GGE are idiopathic and there are many unknown genetic modifiers of GGE influencing risk and severity. In a previous meta-mapping study, crosses between transgenic C57BL/6 and C3HeB/FeJ strains, each carrying one of three SWD-causing mutations (Gabrg2tm1Spet(R43Q) , Scn8a8j or Gria4spkw1 ), demonstrated an antagonistic epistatic interaction between loci on mouse chromosomes 2 and 7 influencing SWD. These results implicate universal modifiers in the B6 background that mitigate SWD severity through a common pathway, independent of the causal mutation. In this study, we prioritized candidate modifiers in these interacting loci. Our approach integrated human genome-wide association results with gene interaction networks and mouse brain gene expression to prioritize candidate genes and pathways driving variation in SWD outcomes. We considered candidate genes that are functionally associated with human GGE risk genes and genes with evidence for coding or non-coding allele effects between the B6 and C3H backgrounds. Our analyses output a summary ranking of gene pairs, one gene from each locus, as candidates for explaining the epistatic interaction. Our top-ranking gene pairs implicate microtubule function, cytoskeletal stability and cell cycle regulation as novel hypotheses about the source of SWD variation across strain backgrounds, which could clarify underlying mechanisms driving differences in GGE severity in humans.

A machine learning approach for quantifying age-related histological changes in the mouse kidney.

The ability to quantify aging-related changes in histological samples is important, as it allows for evaluation of interventions intended to effect health span. We used a machine learning architecture that can be trained to detect and quantify these changes in the mouse kidney. Using additional held out data, we show validation of our model, correlation with scores given by pathologists using the Geropathology Research Network aging grading scheme, and its application in providing reproducible and quantifiable age scores for histological samples. Aging quantification also provides the insights into possible changes in image appearance that are independent of specific geropathology-specified lesions. Furthermore, we provide trained classifiers for H&E-stained slides, as well as tutorials on how to use these and how to create additional classifiers for other histological stains and tissues using our architecture. This architecture and combined resources allow for the high throughput quantification of mouse aging studies in general and specifically applicable to kidney tissues.

A machine learning approach for quantifying age-related histological changes in the mouse kidney.

The ability to quantify aging-related changes in histological samples is important, as it allows for evaluation of interventions intended to effect health span. We used a machine learning architecture that can be trained to detect and quantify these changes in the mouse kidney. Using additional held out data, we show validation of our model, correlation with scores given by pathologists using the Geropathology Research Network aging grading scheme, and its application in providing reproducible and quantifiable age scores for histological samples. Aging quantification also provides the insights into possible changes in image appearance that are independent of specific geropathology-specified lesions. Furthermore, we provide trained classifiers for H&E-stained slides, as well as tutorials on how to use these and how to create additional classifiers for other histological stains and tissues using our architecture.This architecture and combined resources allow for the high throughput quantification of mouse aging studies in general and specifically applicable to kidney tissues.

Variation in histone configurations correlates with gene expression across nine inbred strains of mice.

The Diversity Outbred (DO) mice and their inbred founders are widely used models of human disease. However, although the genetic diversity of these mice has been well documented, their epigenetic diversity has not. Epigenetic modifications, such as histone modifications and DNA methylation, are important regulators of gene expression and, as such, are a critical mechanistic link between genotype and phenotype. Therefore, creating a map of epigenetic modifications in the DO mice and their founders is an important step toward understanding mechanisms of gene regulation and the link to disease in this widely used resource. To this end, we performed a strain survey of epigenetic modifications in hepatocytes of the DO founders. We surveyed four histone modifications (H3K4me1, H3K4me3, H3K27me3, and H3K27ac), as well as DNA methylation. We used ChromHMM to identify 14 chromatin states, each of which represents a distinct combination of the four histone modifications. We found that the epigenetic landscape is highly variable across the DO founders and is associated with variation in gene expression across strains. We found that epigenetic state imputed into a population of DO mice recapitulated the association with gene expression seen in the founders, suggesting that both histone modifications and DNA methylation are highly heritable mechanisms of gene expression regulation. We illustrate how DO gene expression can be aligned with inbred epigenetic states to identify putative cis-regulatory regions. Finally, we provide a data resource that documents strain-specific variation in the chromatin state and DNA methylation in hepatocytes across nine widely used strains of laboratory mice.

A genetic locus complements resistance to Bordetella pertussis-induced histamine sensitization.

Histamine plays pivotal role in normal physiology and dysregulated production of histamine or signaling through histamine receptors (HRH) can promote pathology. Previously, we showed that Bordetella pertussis or pertussis toxin can induce histamine sensitization in laboratory inbred mice and is genetically controlled by Hrh1/HRH1. HRH1 allotypes differ at three amino acid residues with P263-V313-L331 and L263-M313-S331, imparting sensitization and resistance respectively. Unexpectedly, we found several wild-derived inbred strains that carry the resistant HRH1 allotype (L263-M313-S331) but exhibit histamine sensitization. This suggests the existence of a locus modifying pertussis-dependent histamine sensitization. Congenic mapping identified the location of this modifier locus on mouse chromosome 6 within a functional linkage disequilibrium domain encoding multiple loci controlling sensitization to histamine. We utilized interval-specific single-nucleotide polymorphism (SNP) based association testing across laboratory and wild-derived inbred mouse strains and functional prioritization analyses to identify candidate genes for this modifier locus. Atg7, Plxnd1, Tmcc1, Mkrn2, Il17re, Pparg, Lhfpl4, Vgll4, Rho and Syn2 are candidate genes within this modifier locus, which we named Bphse, enhancer of Bordetella pertussis induced histamine sensitization. Taken together, these results identify, using the evolutionarily significant diversity of wild-derived inbred mice, additional genetic mechanisms controlling histamine sensitization.

Differential regulation of gene expression pathways with dexamethasone and ACTH after early life seizures.

Early-life seizures (ELS) are associated with persistent cognitive deficits such as ADHD and memory impairment. These co-morbidities have a dramatic negative impact on the quality of life of patients. Therapies that improve cognitive outcomes have enormous potential to improve patients' quality of life. Our previous work in a rat flurothyl-induction model showed that administration of adrenocorticotropic hormone (ACTH) at time of seizure induction led to improved learning and memory in the animals despite no effect on seizure latency or duration. Administration of dexamethasone (Dex), a corticosteroid, did not have the same positive effect on learning and memory and has even been shown to exacerbate injury in a rat model of temporal lobe epilepsy. We hypothesized that ACTH exerted positive effects on cognitive outcomes through beneficial changes to gene expression and proposed that administration of ACTH at seizure induction would return gene-expression in the brain towards the normal pattern of expression in the Control animals whereas Dex would not. Twenty-six Sprague-Dawley rats were randomized into vehicle- Control, and ACTH-, Dex-, and vehicle- ELS. Rat pups were subjected to 60 flurothyl seizures from P5 to P14. After seizure induction, brains were removed and the hippocampus and PFC were dissected, RNA was extracted and sequenced, and differential expression analysis was performed using generalized estimating equations. Differential expression analysis showed that ACTH pushes gene expression in the brain back to a more normal state of expression through enrichment of pathways involved in supporting homeostatic balance and down-regulating pathways that might contribute to excitotoxic cell-damage post-ELS.

Percolation of collagen stress in a random network model of the alveolar wall.

Fibrotic diseases are characterized by progressive and often irreversible scarring of connective tissue in various organs, leading to substantial changes in tissue mechanics largely as a result of alterations in collagen structure. This is particularly important in the lung because its bulk modulus is so critical to the volume changes that take place during breathing. Nevertheless, it remains unclear how fibrotic abnormalities in the mechanical properties of pulmonary connective tissue can be linked to the stiffening of its individual collagen fibers. To address this question, we developed a network model of randomly oriented collagen and elastin fibers to represent pulmonary alveolar wall tissue. We show that the stress-strain behavior of this model arises via the interactions of collagen and elastin fiber networks and is critically dependent on the relative fiber stiffnesses of the individual collagen and elastin fibers themselves. We also show that the progression from linear to nonlinear stress-strain behavior of the model is associated with the percolation of stress across the collagen fiber network, but that the location of the percolation threshold is influenced by the waviness of collagen fibers.

System-Level Analysis of Alzheimer's Disease Prioritizes Candidate Genes for Neurodegeneration.

Alzheimer's disease (AD) is a debilitating neurodegenerative disorder. Since the advent of the genome-wide association study (GWAS) we have come to understand much about the genes involved in AD heritability and pathophysiology. Large case-control meta-GWAS studies have increased our ability to prioritize weaker effect alleles, while the recent development of network-based functional prediction has provided a mechanism by which we can use machine learning to reprioritize GWAS hits in the functional context of relevant brain tissues like the hippocampus and amygdala. In parallel with these developments, groups like the Alzheimer's Disease Neuroimaging Initiative (ADNI) have compiled rich compendia of AD patient data including genotype and biomarker information, including derived volume measures for relevant structures like the hippocampus and the amygdala. In this study we wanted to identify genes involved in AD-related atrophy of these two structures, which are often critically impaired over the course of the disease. To do this we developed a combined score prioritization method which uses the cumulative distribution function of a gene's functional and positional score, to prioritize top genes that not only segregate with disease status, but also with hippocampal and amygdalar atrophy. Our method identified a mix of genes that had previously been identified in AD GWAS including APOE, TOMM40, and NECTIN2(PVRL2) and several others that have not been identified in AD genetic studies, but play integral roles in AD-effected functional pathways including IQSEC1, PFN1, and PAK2. Our findings support the viability of our novel combined score as a method for prioritizing region- and even cell-specific AD risk genes.

Effects of kinship correction on inflation of genetic interaction statistics in commonly used mouse populations.

It is well understood that variation in relatedness among individuals, or kinship, can lead to false genetic associations. Multiple methods have been developed to adjust for kinship while maintaining power to detect true associations. However, relatively unstudied are the effects of kinship on genetic interaction test statistics. Here, we performed a survey of kinship effects on studies of six commonly used mouse populations. We measured inflation of main effect test statistics, genetic interaction test statistics, and interaction test statistics reparametrized by the Combined Analysis of Pleiotropy and Epistasis (CAPE). We also performed linear mixed model (LMM) kinship corrections using two types of kinship matrix: an overall kinship matrix calculated from the full set of genotyped markers, and a reduced kinship matrix, which left out markers on the chromosome(s) being tested. We found that test statistic inflation varied across populations and was driven largely by linkage disequilibrium. In contrast, there was no observable inflation in the genetic interaction test statistics. CAPE statistics were inflated at a level in between that of the main effects and the interaction effects. The overall kinship matrix overcorrected the inflation of main effect statistics relative to the reduced kinship matrix. The two types of kinship matrices had similar effects on the interaction statistics and CAPE statistics, although the overall kinship matrix trended toward a more severe correction. In conclusion, we recommend using an LMM kinship correction for both main effects and genetic interactions and further recommend that the kinship matrix be calculated from a reduced set of markers in which the chromosomes being tested are omitted from the calculation. This is particularly important in populations with substantial population structure, such as recombinant inbred lines in which genomic replicates are used.

Fine Spike Timing in Hippocampal-Prefrontal Ensembles Predicts Poor Encoding and Underlies Behavioral Performance in Healthy and Malformed Brains.

Spatial working memory (SWM) is a central cognitive process during which the hippocampus and prefrontal cortex (PFC) encode and maintain spatial information for subsequent decision-making. This occurs in the context of ongoing computations relating to spatial position, recall of long-term memory, attention, among many others. To establish how intermittently presented information is integrated with ongoing computations we recorded single units, simultaneously in hippocampus and PFC, in control rats and those with a brain malformation during performance of an SWM task. Neurons that encode intermittent task parameters are also well modulated in time and incorporated into a functional network across regions. Neurons from animals with cortical malformation are poorly modulated in time, less likely to encode task parameters, and less likely to be integrated into a functional network. Our results implicate a model in which ongoing oscillatory coordination among neurons in the hippocampal-PFC network describes a functional network that is poised to receive sensory inputs that are then integrated and multiplexed as working memory. The background temporal modulation is systematically altered in disease, but the relationship between these dynamics and behaviorally relevant firing is maintained, thereby providing potential targets for stimulation-based therapies.

Identification of novel loci controlling inflammatory bowel disease susceptibility utilizing the genetic diversity of wild-derived mice.

Inflammatory bowel disease (IBD) is a complex disorder that imposes a growing health burden. Multiple genetic associations have been identified in IBD, but the mechanisms underlying many of these associations are poorly understood. Animal models are needed to bridge this gap, but conventional laboratory mouse strains lack the genetic diversity of human populations. To more accurately model human genetic diversity, we utilized a panel of chromosome (Chr) substitution strains, carrying chromosomes from the wild-derived and genetically divergent PWD/PhJ (PWD) strain on the commonly used C57BL/6J (B6) background, as well as their parental B6 and PWD strains. Two models of IBD were used, TNBS- and DSS-induced colitis. Compared with B6 mice, PWD mice were highly susceptible to TNBS-induced colitis, but resistant to DSS-induced colitis. Using consomic mice, we identified several PWD-derived loci that exhibited profound effects on IBD susceptibility. The most pronounced of these were loci on Chr1 and Chr2, which yielded high susceptibility in both IBD models, each acting at distinct phases of the disease. Leveraging transcriptomic data from B6 and PWD immune cells, together with a machine learning approach incorporating human IBD genetic associations, we identified lead candidate genes, including Itga4, Pip4k2a, Lcn10, Lgmn, and Gpr65.

Coordination of hippocampal theta and gamma oscillations relative to spatial active avoidance reflects cognitive outcome after febrile status epilepticus.

Cognitive deficits may arise from a variety of genetic alterations and neurological insults that impair neural coding mechanisms and the routing of neural information underpinning learning and memory. Slow and medium gamma oscillations underpin memory recall and sensorimotor processing and represent dynamic inputs at CA1 synapses. Febrile status epilepticus (FSE) can lead to increased risk for temporal lobe epilepsy and enduring cognitive impairments. In a rodent model, we assessed how FSE alters hippocampal CA1 signals relative to spatial task performance and serve as a readout of synaptic input efficacy. The power of theta (5-12 Hz), slow gamma (30-50 Hz), and medium gamma (70-90 Hz) differentially interact with respect to cognitive demands during active avoidance behavior on a rotating arena. Successful avoidance was characterized by slow gamma that was largest several seconds before or after peak acceleration. Peak acceleration coincides with peak theta oscillations, followed within approximately 1 s by peak medium gamma. FSE animals showing impairment in the task maintained the profiles of theta and medium gamma associated with increased sensorimotor processing following peak acceleration but did not exhibit the same slow gamma profile associated with epochs of memory retrieval. While CA1 synapses from entorhinal cortex were functionally unaffected by FSE, communication via synapses from CA3 may have been impaired, leading to both temporal discoordination and poor memory retrieval. These findings demonstrate theta/gamma profiles can serve as both physiological biomarkers for memory retrieval or encoding deficits and synapse level treatment targets that could attenuate cognitive comorbidities associated with early life seizures. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

High-throughput quantitative histology in systemic sclerosis skin disease using computer vision.

BACKGROUND: Skin fibrosis is the clinical hallmark of systemic sclerosis (SSc), where collagen deposition and remodeling of the dermis occur over time. The most widely used outcome measure in SSc clinical trials is the modified Rodnan skin score (mRSS), which is a semi-quantitative assessment of skin stiffness at seventeen body sites. However, the mRSS is confounded by obesity, edema, and high inter-rater variability. In order to develop a new histopathological outcome measure for SSc, we applied a computer vision technology called a deep neural network (DNN) to stained sections of SSc skin. We tested the hypotheses that DNN analysis could reliably assess mRSS and discriminate SSc from normal skin. METHODS: We analyzed biopsies from two independent (primary and secondary) cohorts. One investigator performed mRSS assessments and forearm biopsies, and trichrome-stained biopsy sections were photomicrographed. We used the AlexNet DNN to generate a numerical signature of 4096 quantitative image features (QIFs) for 100 randomly selected dermal image patches/biopsy. In the primary cohort, we used principal components analysis (PCA) to summarize the QIFs into a Biopsy Score for comparison with mRSS. In the secondary cohort, using QIF signatures as the input, we fit a logistic regression model to discriminate between SSc vs. control biopsy, and a linear regression model to estimate mRSS, yielding Diagnostic Scores and Fibrosis Scores, respectively. We determined the correlation between Fibrosis Scores and the published Scleroderma Skin Severity Score (4S) and between Fibrosis Scores and longitudinal changes in mRSS on a per patient basis. RESULTS: In the primary cohort (n = 6, 26 SSc biopsies), Biopsy Scores significantly correlated with mRSS (R = 0.55, p = 0.01). In the secondary cohort (n = 60 SSc and 16 controls, 164 biopsies; divided into 70% training and 30% test sets), the Diagnostic Score was significantly associated with SSc-status (misclassification rate = 1.9% [training], 6.6% [test]), and the Fibrosis Score significantly correlated with mRSS (R = 0.70 [training], 0.55 [test]). The DNN-derived Fibrosis Score significantly correlated with 4S (R = 0.69, p = 3 × 10- 17). CONCLUSIONS: DNN analysis of SSc biopsies is an unbiased, quantitative, and reproducible outcome that is associated with validated SSc outcomes.

Genetic Interactions Affect Lung Function in Patients with Systemic Sclerosis.

Scleroderma, or systemic sclerosis (SSc), is an autoimmune disease characterized by progressive fibrosis of the skin and internal organs. The most common cause of death in people with SSc is lung disease, but the pathogenesis of lung disease in SSc is insufficiently understood to devise specific treatment strategies. Developing targeted treatments requires not only the identification of molecular processes involved in SSc-associated lung disease, but also understanding of how these processes interact to drive pathology. One potentially powerful approach is to identify alleles that interact genetically to influence lung outcomes in patients with SSc. Analysis of interactions, rather than individual allele effects, has the potential to delineate molecular interactions that are important in SSc-related lung pathology. However, detecting genetic interactions, or epistasis, in human cohorts is challenging. Large numbers of variants with low minor allele frequencies, paired with heterogeneous disease presentation, reduce power to detect epistasis. Here we present an analysis that increases power to detect epistasis in human genome-wide association studies (GWAS). We tested for genetic interactions influencing lung function and autoantibody status in a cohort of 416 SSc patients. Using Matrix Epistasis to filter SNPs followed by the Combined Analysis of Pleiotropy and Epistasis (CAPE), we identified a network of interacting alleles influencing lung function in patients with SSc. In particular, we identified a three-gene network comprising WNT5A, RBMS3, and MSI2, which in combination influenced multiple pulmonary pathology measures. The associations of these genes with lung outcomes in SSc are novel and high-confidence. Furthermore, gene coexpression analysis suggested that the interactions we identified are tissue-specific, thus differentiating SSc-related pathogenic processes in lung from those in skin.

Network-Based Functional Prediction Augments Genetic Association To Predict Candidate Genes for Histamine Hypersensitivity in Mice.

Genetic mapping is a primary tool of genetics in model organisms; however, many quantitative trait loci (QTL) contain tens or hundreds of positional candidate genes. Prioritizing these genes for validation is often ad hoc and biased by previous findings. Here we present a technique for prioritizing positional candidates based on computationally inferred gene function. Our method uses machine learning with functional genomic networks, whose links encode functional associations among genes, to identify network-based signatures of functional association to a trait of interest. We demonstrate the method by functionally ranking positional candidates in a large locus on mouse Chr 6 (45.9 Mb to 127.8 Mb) associated with histamine hypersensitivity (Histh). Histh is characterized by systemic vascular leakage and edema in response to histamine challenge, which can lead to multiple organ failure and death. Although Histh risk is strongly influenced by genetics, little is known about its underlying molecular or genetic causes, due to genetic and physiological complexity of the trait. To dissect this complexity, we ranked genes in the Histh locus by predicting functional association with multiple Histh-related processes. We integrated these predictions with new single nucleotide polymorphism (SNP) association data derived from a survey of 23 inbred mouse strains and congenic mapping data. The top-ranked genes included Cxcl12, Ret, Cacna1c, and Cntn3, all of which had strong functional associations and were proximal to SNPs segregating with Histh. These results demonstrate the power of network-based computational methods to nominate highly plausible quantitative trait genes even in challenging cases involving large QTL and extreme trait complexity.