Genetic and multi-omic risk assessment of Alzheimer's disease implicates core associated biological domains.

INTRODUCTION: Alzheimer's disease (AD) is the predominant dementia globally, with heterogeneous presentation and penetrance of clinical symptoms, variable presence of mixed pathologies, potential disease subtypes, and numerous associated endophenotypes. Beyond the difficulty of designing treatments that address the core pathological characteristics of the disease, therapeutic development is challenged by the uncertainty of which endophenotypic areas and specific targets implicated by those endophenotypes to prioritize for further translational research. However, publicly funded consortia driving large-scale open science efforts have produced multiple omic analyses that address both disease risk relevance and biological process involvement of genes across the genome. METHODS: Here we report the development of an informatic pipeline that draws from genetic association studies, predicted variant impact, and linkage with dementia associated phenotypes to create a genetic risk score. This is paired with a multi-omic risk score utilizing extensive sets of both transcriptomic and proteomic studies to identify system-level changes in expression associated with AD. These two elements combined constitute our target risk score that ranks AD risk genome-wide. The ranked genes are organized into endophenotypic space through the development of 19 biological domains associated with AD in the described genetics and genomics studies and accompanying literature. The biological domains are constructed from exhaustive Gene Ontology (GO) term compilations, allowing automated assignment of genes into objectively defined disease-associated biology. This rank-and-organize approach, performed genome-wide, allows the characterization of aggregations of AD risk across biological domains. RESULTS: The top AD-risk-associated biological domains are Synapse, Immune Response, Lipid Metabolism, Mitochondrial Metabolism, Structural Stabilization, and Proteostasis, with slightly lower levels of risk enrichment present within the other 13 biological domains. DISCUSSION: This provides an objective methodology to localize risk within specific biological endophenotypes and drill down into the most significantly associated sets of GO terms and annotated genes for potential therapeutic targets.

Human microglia show unique transcriptional changes in Alzheimer's disease.

Microglia, the innate immune cells of the brain, influence Alzheimer's disease (AD) progression and are potential therapeutic targets. However, microglia exhibit diverse functions, the regulation of which is not fully understood, complicating therapeutics development. To better define the transcriptomic phenotypes and gene regulatory networks associated with AD, we enriched for microglia nuclei from 12 AD and 10 control human dorsolateral prefrontal cortices (7 males and 15 females, all aged >60 years) before single-nucleus RNA sequencing. Here we describe both established and previously unrecognized microglial molecular phenotypes, the inferred gene networks driving observed transcriptomic change, and apply trajectory analysis to reveal the putative relationships between microglial phenotypes. We identify microglial phenotypes more prevalent in AD cases compared with controls. Further, we describe the heterogeneity in microglia subclusters expressing homeostatic markers. Our study demonstrates that deep profiling of microglia in human AD brain can provide insight into microglial transcriptional changes associated with AD.

Manifestations of Alzheimer's disease genetic risk in the blood are evident in a multiomic analysis in healthy adults aged 18 to 90.

Genetics play an important role in late-onset Alzheimer's Disease (AD) etiology and dozens of genetic variants have been implicated in AD risk through large-scale GWAS meta-analyses. However, the precise mechanistic effects of most of these variants have yet to be determined. Deeply phenotyped cohort data can reveal physiological changes associated with genetic risk for AD across an age spectrum that may provide clues to the biology of the disease. We utilized over 2000 high-quality quantitative measurements obtained from blood of 2831 cognitively normal adult clients of a consumer-based scientific wellness company, each with CLIA-certified whole-genome sequencing data. Measurements included: clinical laboratory blood tests, targeted chip-based proteomics, and metabolomics. We performed a phenome-wide association study utilizing this diverse blood marker data and 25 known AD genetic variants and an AD-specific polygenic risk score (PGRS), adjusting for sex, age, vendor (for clinical labs), and the first four genetic principal components; sex-SNP interactions were also assessed. We observed statistically significant SNP-analyte associations for five genetic variants after correction for multiple testing (for SNPs in or near NYAP1, ABCA7, INPP5D, and APOE), with effects detectable from early adulthood. The ABCA7 SNP and the APOE2 and APOE4 encoding alleles were associated with lipid variability, as seen in previous studies; in addition, six novel proteins were associated with the e2 allele. The most statistically significant finding was between the NYAP1 variant and PILRA and PILRB protein levels, supporting previous functional genomic studies in the identification of a putative causal variant within the PILRA gene. We did not observe associations between the PGRS and any analyte. Sex modified the effects of four genetic variants, with multiple interrelated immune-modulating effects associated with the PICALM variant. In post-hoc analysis, sex-stratified GWAS results from an independent AD case-control meta-analysis supported sex-specific disease effects of the PICALM variant, highlighting the importance of sex as a biological variable. Known AD genetic variation influenced lipid metabolism and immune response systems in a population of non-AD individuals, with associations observed from early adulthood onward. Further research is needed to determine whether and how these effects are implicated in early-stage biological pathways to AD. These analyses aim to complement ongoing work on the functional interpretation of AD-associated genetic variants.

Corrigendum: Uncovering Disease Mechanisms in a Novel Mouse Model Expressing Humanized APOEε4 and Trem2*R47H.

[This corrects the article DOI: 10.3389/fnagi.2021.735524.].

Atlas of RNA editing events affecting protein expression in aged and Alzheimer's disease human brain tissue.

RNA editing is a feature of RNA maturation resulting in the formation of transcripts whose sequence differs from the genome template. Brain RNA editing may be altered in Alzheimer's disease (AD). Here, we analyzed data from 1,865 brain samples covering 9 brain regions from 1,074 unrelated subjects on a transcriptome-wide scale to identify inter-regional differences in RNA editing. We expand the list of known brain editing events by identifying 58,761 previously unreported events. We note that only a small proportion of these editing events are found at the protein level in our proteome-wide validation effort. We also identified the occurrence of editing events associated with AD dementia, neuropathological measures and longitudinal cognitive decline in: SYT11, MCUR1, SOD2, ORAI2, HSDL2, PFKP, and GPRC5B. Thus, we present an extended reference set of brain RNA editing events, identify a subset that are found to be expressed at the protein level, and extend the narrative of transcriptomic perturbation in AD to RNA editing.

Uncovering Disease Mechanisms in a Novel Mouse Model Expressing Humanized APOEε4 and Trem2*R47H.

Late-onset Alzheimer's disease (AD; LOAD) is the most common human neurodegenerative disease, however, the availability and efficacy of disease-modifying interventions is severely lacking. Despite exceptional efforts to understand disease progression via legacy amyloidogenic transgene mouse models, focus on disease translation with innovative mouse strains that better model the complexity of human AD is required to accelerate the development of future treatment modalities. LOAD within the human population is a polygenic and environmentally influenced disease with many risk factors acting in concert to produce disease processes parallel to those often muted by the early and aggressive aggregate formation in popular mouse strains. In addition to extracellular deposits of amyloid plaques and inclusions of the microtubule-associated protein tau, AD is also defined by synaptic/neuronal loss, vascular deficits, and neuroinflammation. These underlying processes need to be better defined, how the disease progresses with age, and compared to human-relevant outcomes. To create more translatable mouse models, MODEL-AD (Model Organism Development and Evaluation for Late-onset AD) groups are identifying and integrating disease-relevant, humanized gene sequences from public databases beginning with APOEε4 and Trem2*R47H, two of the most powerful risk factors present in human LOAD populations. Mice expressing endogenous, humanized APOEε4 and Trem2*R47H gene sequences were extensively aged and assayed using a multi-disciplined phenotyping approach associated with and relative to human AD pathology. Robust analytical pipelines measured behavioral, transcriptomic, metabolic, and neuropathological phenotypes in cross-sectional cohorts for progression of disease hallmarks at all life stages. In vivo PET/MRI neuroimaging revealed regional alterations in glycolytic metabolism and vascular perfusion. Transcriptional profiling by RNA-Seq of brain hemispheres identified sex and age as the main sources of variation between genotypes including age-specific enrichment of AD-related processes. Similarly, age was the strongest determinant of behavioral change. In the absence of mouse amyloid plaque formation, many of the hallmarks of AD were not observed in this strain. However, as a sensitized baseline model with many additional alleles and environmental modifications already appended, the dataset from this initial MODEL-AD strain serves an important role in establishing the individual effects and interaction between two strong genetic risk factors for LOAD in a mouse host.

Comprehensive Evaluation of the 5XFAD Mouse Model for Preclinical Testing Applications: A MODEL-AD Study.

The ability to investigate therapeutic interventions in animal models of neurodegenerative diseases depends on extensive characterization of the model(s) being used. There are numerous models that have been generated to study Alzheimer's disease (AD) and the underlying pathogenesis of the disease. While transgenic models have been instrumental in understanding AD mechanisms and risk factors, they are limited in the degree of characteristics displayed in comparison with AD in humans, and the full spectrum of AD effects has yet to be recapitulated in a single mouse model. The Model Organism Development and Evaluation for Late-Onset Alzheimer's Disease (MODEL-AD) consortium was assembled by the National Institute on Aging (NIA) to develop more robust animal models of AD with increased relevance to human disease, standardize the characterization of AD mouse models, improve preclinical testing in animals, and establish clinically relevant AD biomarkers, among other aims toward enhancing the translational value of AD models in clinical drug design and treatment development. Here we have conducted a detailed characterization of the 5XFAD mouse, including transcriptomics, electroencephalogram, in vivo imaging, biochemical characterization, and behavioral assessments. The data from this study is publicly available through the AD Knowledge Portal.

Transfer learning-trained convolutional neural networks identify novel MRI biomarkers of Alzheimer's disease progression.

INTRODUCTION: Genome-wide association studies (GWAS) for late onset Alzheimer's disease (AD) may miss genetic variants relevant for delineating disease stages when using clinically defined case/control as a phenotype due to its loose definition and heterogeneity. METHODS: We use a transfer learning technique to train three-dimensional convolutional neural network (CNN) models based on structural magnetic resonance imaging (MRI) from the screening stage in the Alzheimer's Disease Neuroimaging Initiative consortium to derive image features that reflect AD progression. RESULTS: CNN-derived image phenotypes are significantly associated with fasting metabolites related to early lipid metabolic changes as well as insulin resistance and with genetic variants mapped to candidate genes enriched for amyloid beta degradation, tau phosphorylation, calcium ion binding-dependent synaptic loss, APP-regulated inflammation response, and insulin resistance. DISCUSSION: This is the first attempt to show that non-invasive MRI biomarkers are linked to AD progression characteristics, reinforcing their use in early AD diagnosis and monitoring.

Multi-tissue neocortical transcriptome-wide association study implicates 8 genes across 6 genomic loci in Alzheimer's disease.

BACKGROUND: Alzheimer's disease (AD) is an incurable neurodegenerative disease currently affecting 1.75% of the US population, with projected growth to 3.46% by 2050. Identifying common genetic variants driving differences in transcript expression that confer AD risk is necessary to elucidate AD mechanism and develop therapeutic interventions. We modify the FUSION transcriptome-wide association study (TWAS) pipeline to ingest gene expression values from multiple neocortical regions. METHODS: A combined dataset of 2003 genotypes clustered to 1000 Genomes individuals from Utah with Northern and Western European ancestry (CEU) was used to construct a training set of 790 genotypes paired to 888 RNASeq profiles from temporal cortex (TCX = 248), prefrontal cortex (FP = 50), inferior frontal gyrus (IFG = 41), superior temporal gyrus (STG = 34), parahippocampal cortex (PHG = 34), and dorsolateral prefrontal cortex (DLPFC = 461). Following within-tissue normalization and covariate adjustment, predictive weights to impute expression components based on a gene's surrounding cis-variants were trained. The FUSION pipeline was modified to support input of pre-scaled expression values and support cross validation with a repeated measure design arising from the presence of multiple transcriptome samples from the same individual across different tissues. RESULTS: Cis-variant architecture alone was informative to train weights and impute expression for 6780 (49.67%) autosomal genes, the majority of which significantly correlated with gene expression; FDR < 5%: N = 6775 (99.92%), Bonferroni: N = 6716 (99.06%). Validation of weights in 515 matched genotype to RNASeq profiles from the CommonMind Consortium (CMC) was (72.14%) in DLPFC profiles. Association of imputed expression components from all 2003 genotype profiles yielded 8 genes significantly associated with AD (FDR < 0.05): APOC1, EED, CD2AP, CEACAM19, CLPTM1, MTCH2, TREM2, and KNOP1. CONCLUSIONS: We provide evidence of cis-genetic variation conferring AD risk through 8 genes across six distinct genomic loci. Moreover, we provide expression weights for 6780 genes as a valuable resource to the community, which can be abstracted across the neocortex and a wide range of neuronal phenotypes.

Brain proteome-wide association study implicates novel proteins in depression pathogenesis.

Depression is a common condition, but current treatments are only effective in a subset of individuals. To identify new treatment targets, we integrated depression genome-wide association study (GWAS) results (N = 500,199) with human brain proteomes (N = 376) to perform a proteome-wide association study of depression followed by Mendelian randomization. We identified 19 genes that were consistent with being causal in depression, acting via their respective cis-regulated brain protein abundance. We replicated nine of these genes using an independent depression GWAS (N = 307,353) and another human brain proteomic dataset (N = 152). Eleven of the 19 genes also had cis-regulated mRNA levels that were associated with depression, based on integration of the depression GWAS with human brain transcriptomes (N = 888). Meta-analysis of the discovery and replication proteome-wide association study analyses identified 25 brain proteins consistent with being causal in depression, 20 of which were not previously implicated in depression by GWAS. Together, these findings provide promising brain protein targets for further mechanistic and therapeutic studies.

Integrating human brain proteomes with genome-wide association data implicates new proteins in Alzheimer's disease pathogenesis.

Genome-wide association studies (GWAS) have identified many risk loci for Alzheimer's disease (AD)1,2, but how these loci confer AD risk is unclear. Here, we aimed to identify loci that confer AD risk through their effects on brain protein abundance to provide new insights into AD pathogenesis. To that end, we integrated AD GWAS results with human brain proteomes to perform a proteome-wide association study (PWAS) of AD, followed by Mendelian randomization and colocalization analysis. We identified 11 genes that are consistent with being causal in AD, acting via their cis-regulated brain protein abundance. Nine replicated in a confirmation PWAS and eight represent new AD risk genes not identified before by AD GWAS. Furthermore, we demonstrated that our results were independent of APOE e4. Together, our findings provide new insights into AD pathogenesis and promising targets for further mechanistic and therapeutic studies.

Author Correction: Molecular estimation of neurodegeneration pseudotime in older brains.

A Correction to this paper has been published: https://doi.org/10.1038/s41467-020-20261-6.

Model organism development and evaluation for late-onset Alzheimer's disease: MODEL-AD.

Alzheimer's disease (AD) is a major cause of dementia, disability, and death in the elderly. Despite recent advances in our understanding of the basic biological mechanisms underlying AD, we do not know how to prevent it, nor do we have an approved disease-modifying intervention. Both are essential to slow or stop the growth in dementia prevalence. While our current animal models of AD have provided novel insights into AD disease mechanisms, thus far, they have not been successfully used to predict the effectiveness of therapies that have moved into AD clinical trials. The Model Organism Development and Evaluation for Late-onset Alzheimer's Disease (MODEL-AD; www.model-ad.org) Consortium was established to maximize human datasets to identify putative variants, genes, and biomarkers for AD; to generate, characterize, and validate the next generation of mouse models of AD; and to develop a preclinical testing pipeline. MODEL-AD is a collaboration among Indiana University (IU); The Jackson Laboratory (JAX); University of Pittsburgh School of Medicine (Pitt); Sage BioNetworks (Sage); and the University of California, Irvine (UCI) that will generate new AD modeling processes and pipelines, data resources, research results, standardized protocols, and models that will be shared through JAX's and Sage's proven dissemination pipelines with the National Institute on Aging-supported AD Centers, academic and medical research centers, research institutions, and the pharmaceutical industry worldwide.

Molecular estimation of neurodegeneration pseudotime in older brains.

The temporal molecular changes that lead to disease onset and progression in Alzheimer's disease (AD) are still unknown. Here we develop a temporal model for these unobserved molecular changes with a manifold learning method applied to RNA-Seq data collected from human postmortem brain samples collected within the ROS/MAP and Mayo Clinic RNA-Seq studies. We define an ordering across samples based on their similarity in gene expression and use this ordering to estimate the molecular disease stage-or disease pseudotime-for each sample. Disease pseudotime is strongly concordant with the burden of tau (Braak score, P = 1.0 × 10-5), Aß (CERAD score, P = 1.8 × 10-5), and cognitive diagnosis (P = 3.5 × 10-7) of late-onset (LO) AD. Early stage disease pseudotime samples are enriched for controls and show changes in basic cellular functions. Late stage disease pseudotime samples are enriched for late stage AD cases and show changes in neuroinflammation and amyloid pathologic processes. We also identify a set of late stage pseudotime samples that are controls and show changes in genes enriched for protein trafficking, splicing, regulation of apoptosis, and prevention of amyloid cleavage pathways. In summary, we present a method for ordering patients along a trajectory of LOAD disease progression from brain transcriptomic data.

A novel systems biology approach to evaluate mouse models of late-onset Alzheimer's disease.

BACKGROUND: Late-onset Alzheimer's disease (LOAD) is the most common form of dementia worldwide. To date, animal models of Alzheimer's have focused on rare familial mutations, due to a lack of frank neuropathology from models based on common disease genes. Recent multi-cohort studies of postmortem human brain transcriptomes have identified a set of 30 gene co-expression modules associated with LOAD, providing a molecular catalog of relevant endophenotypes. RESULTS: This resource enables precise gene-based alignment between new animal models and human molecular signatures of disease. Here, we describe a new resource to efficiently screen mouse models for LOAD relevance. A new NanoString nCounter® Mouse AD panel was designed to correlate key human disease processes and pathways with mRNA from mouse brains. Analysis of the 5xFAD mouse, a widely used amyloid pathology model, and three mouse models based on LOAD genetics carrying APOE4 and TREM2*R47H alleles demonstrated overlaps with distinct human AD modules that, in turn, were functionally enriched in key disease-associated pathways. Comprehensive comparison with full transcriptome data from same-sample RNA-Seq showed strong correlation between gene expression changes independent of experimental platform. CONCLUSIONS: Taken together, we show that the nCounter Mouse AD panel offers a rapid, cost-effective and highly reproducible approach to assess disease relevance of potential LOAD mouse models.

The AD Knowledge Portal: A Repository for Multi-Omic Data on Alzheimer's Disease and Aging.

The AD Knowledge Portal (adknowledgeportal.org) is a public data repository that shares data and other resources generated by multiple collaborative research programs focused on aging, dementia, and Alzheimer's disease (AD). In this article, we highlight how to use the Portal to discover and download genomic variant and transcriptomic data from the same individuals. First, we show how to use the web interface to browse and search for data of interest using relevant file annotations. We demonstrate how to learn more about the context surrounding the data, including diagnostic criteria and methodological details about sample preparation and data analysis. We present two primary ways to download data-using a web interface, and using a programmatic method that provides access using the command line. Finally, we show how to merge separate sources of metadata into a comprehensive file that contains factors and covariates necessary in downstream analyses. © 2020 The Authors. Basic Protocol 1: Find and download files associated with a selected study Basic Protocol 2: Download files in bulk using the command line client Basic Protocol 3: Working with file annotations and metadata.

Large eQTL meta-analysis reveals differing patterns between cerebral cortical and cerebellar brain regions.

The availability of high-quality RNA-sequencing and genotyping data of post-mortem brain collections from consortia such as CommonMind Consortium (CMC) and the Accelerating Medicines Partnership for Alzheimer's Disease (AMP-AD) Consortium enable the generation of a large-scale brain cis-eQTL meta-analysis. Here we generate cerebral cortical eQTL from 1433 samples available from four cohorts (identifying >4.1 million significant eQTL for >18,000 genes), as well as cerebellar eQTL from 261 samples (identifying 874,836 significant eQTL for >10,000 genes). We find substantially improved power in the meta-analysis over individual cohort analyses, particularly in comparison to the Genotype-Tissue Expression (GTEx) Project eQTL. Additionally, we observed differences in eQTL patterns between cerebral and cerebellar brain regions. We provide these brain eQTL as a resource for use by the research community. As a proof of principle for their utility, we apply a colocalization analysis to identify genes underlying the GWAS association peaks for schizophrenia and identify a potentially novel gene colocalization with lncRNA RP11-677M14.2 (posterior probability of colocalization 0.975).

Transcriptomic stratification of late-onset Alzheimer's cases reveals novel genetic modifiers of disease pathology.

Late-Onset Alzheimer's disease (LOAD) is a common, complex genetic disorder well-known for its heterogeneous pathology. The genetic heterogeneity underlying common, complex diseases poses a major challenge for targeted therapies and the identification of novel disease-associated variants. Case-control approaches are often limited to examining a specific outcome in a group of heterogenous patients with different clinical characteristics. Here, we developed a novel approach to define relevant transcriptomic endophenotypes and stratify decedents based on molecular profiles in three independent human LOAD cohorts. By integrating post-mortem brain gene co-expression data from 2114 human samples with LOAD, we developed a novel quantitative, composite phenotype that can better account for the heterogeneity in genetic architecture underlying the disease. We used iterative weighted gene co-expression network analysis (WGCNA) to reduce data dimensionality and to isolate gene sets that are highly co-expressed within disease subtypes and represent specific molecular pathways. We then performed single variant association testing using whole genome-sequencing data for the novel composite phenotype in order to identify genetic loci that contribute to disease heterogeneity. Distinct LOAD subtypes were identified for all three study cohorts (two in ROSMAP, three in Mayo Clinic, and two in Mount Sinai Brain Bank). Single variant association analysis identified a genome-wide significant variant in TMEM106B (p-value < 5×10-8, rs1990620G) in the ROSMAP cohort that confers protection from the inflammatory LOAD subtype. Taken together, our novel approach can be used to stratify LOAD into distinct molecular subtypes based on affected disease pathways.

Brain microRNAs associated with late-life depressive symptoms are also associated with cognitive trajectory and dementia.

Late-life depression is associated with an increased risk for dementia but we have limited knowledge of the molecular mechanisms underlying this association. Here we investigated whether brain microRNAs, important posttranscriptional regulators of gene expression, contribute to this association. Late-life depressive symptoms were assessed annually in 300 participants of the Religious Orders Study and Rush Memory and Aging Project for a mean of 7 years. Participants underwent annual cognitive testing, clinical assessment of cognitive status, and uniform neuropathologic examination after death. microRNAs were profiled from the prefrontal cortex using NanoString platform in the discovery cohort and small RNA sequencing in the replication cohort. A global microRNA association study of late-life depressive symptoms was performed using linear mixed model adjusting for the potential confounding factors. Four brain microRNAs were associated with late-life depressive symptoms at adjusted p < 0.05: miR-484, miR-26b-5p, miR-30d-5p, and miR-197-3p. Lower expression levels of these miRNAs were associated having greater depressive symptoms. Furthermore, lower levels of miR-484 and miR-197-3p were associated with faster decline of cognition over time. Moreover, lower miR-484 level was associated with higher probability of having Alzheimer's dementia. Importantly, the associations between miR-484 and depressive symptoms and Alzheimer's dementia, respectively, were replicated in an independent cohort. Lastly, the predicted targets of miR-484 were enriched in a brain protein co-expression module involving synaptic transmission and regulation of synaptic plasticity. This study identified four brain microRNAs associated with late-life depressive symptoms assessed longitudinally. In addition, we found a molecular connection between late-life depression and dementia through miR-484.

Identifying and ranking potential driver genes of Alzheimer's disease using multiview evidence aggregation.

MOTIVATION: Late onset Alzheimer's disease is currently a disease with no known effective treatment options. To better understand disease, new multi-omic data-sets have recently been generated with the goal of identifying molecular causes of disease. However, most analytic studies using these datasets focus on uni-modal analysis of the data. Here, we propose a data driven approach to integrate multiple data types and analytic outcomes to aggregate evidences to support the hypothesis that a gene is a genetic driver of the disease. The main algorithmic contributions of our article are: (i) a general machine learning framework to learn the key characteristics of a few known driver genes from multiple feature sets and identifying other potential driver genes which have similar feature representations, and (ii) A flexible ranking scheme with the ability to integrate external validation in the form of Genome Wide Association Study summary statistics. While we currently focus on demonstrating the effectiveness of the approach using different analytic outcomes from RNA-Seq studies, this method is easily generalizable to other data modalities and analysis types. RESULTS: We demonstrate the utility of our machine learning algorithm on two benchmark multiview datasets by significantly outperforming the baseline approaches in predicting missing labels. We then use the algorithm to predict and rank potential drivers of Alzheimer's. We show that our ranked genes show a significant enrichment for single nucleotide polymorphisms associated with Alzheimer's and are enriched in pathways that have been previously associated with the disease. AVAILABILITY AND IMPLEMENTATION: Source code and link to all feature sets is available at https://github.com/Sage-Bionetworks/EvidenceAggregatedDriverRanking.