BrainGENIE: The Brain Gene Expression and Network Imputation Engine
Hess, J. L.; Chen, S.; Quinn, T. P.; Neuropsychiatric Consortium for Analysis and Sharing of Transcriptomes, ; Kong, S. W.; Cairns, M.; Tsuang, M.; Faraone, S. V.; Glatt, S. J.
Show abstract
In vivo experimental analysis of human brain tissue poses substantial challenges and ethical concerns. We developed a novel method called the Brain Gene Expression and Network Imputation Engine (BrainGENIE) that uses peripheral-blood transcriptomes to predict brain-tissue-specific gene-expression levels. BrainGENIE reliably predicted brain-tissue-specific expression levels for 1,733 - 11,569 genes (false-discovery rate-adjusted p<0.05), including many transcripts that cannot be predicted reliably by a transcriptome imputation method such as PrediXcan. We tested the generalizability of BrainGENIE in external within-individual data from ex vivo peripheral blood and postmortem brain samples from the Religious Orders Study and Memory and Aging Project, wherein we validated 39% of predicted gene expression levels as concordant with observed expression levels in dorsolateral prefrontal cortex and 23% in caudate. BrainGENIE recapitulated diagnosis-related gene expression changes in brain better than direct correlations from blood and predictions from PrediXcan. BrainGENIE complements and, in some ways, outperforms existing transcriptome-imputation tools, providing biologically meaningful predictions and opening new research avenues.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Comprehensive analyses of RNA-seq and genome-wide data point to enrichment of neuronal cell type subsets in neuropsychiatric disorders 96%
- Immunological Drivers and Potential Novel Drug Targets for Major Psychiatric, Neurodevelopmental, and Neurodegenerative Conditions 96%
- Genetic architecture of brain age and its casual relations with brain and mental disorders 95%
Similar papers in this journal
- Human-lineage-specific genomic elements: relevance to neurodegenerative disease and APOE transcript usage 97%
- Identifying cell type specific driver genes in autism-associated copy number loci from cerebral organoids 95%
- Molecular Signatures of Resilience to Alzheimer's Disease in Neocortical Layer 4 Neurons 95%
Similar papers in this journal
- A mesocorticolimbic dopamine gene network moderates the effect of early adversity on the risk for psychiatric and cardio-metabolic comorbidities 94%
- Modeling of mitochondrial genetic polymorphisms reveals induction of heteroplasmy by pleiotropic disease locus MT:10398A>G 94%
- Identifying cellular markers of focal cortical dysplasia type II with cell-type deconvolution and single-cell signatures 93%
Similar papers in this journal
- Whole genome sequence-based association analysis of African American individuals with bipolar disorder and schizophrenia 94%
- Scalable Bayesian functional GWAS method accounting for multivariate quantitative functional annotations with applications to studying Alzheimer’s disease 94%
- Accurate DNA Methylation Predictor for C9orf72 Repeat Expansion Alleles in the Pathogenic Range 94%
Similar papers in this journal
- Knockout of the longevity gene Klotho perturbs aging- and Alzheimer's disease-linked brain microRNAs and tRNA fragments 94%
- Sex-specific single cell-level transcriptomic signatures of Rett syndrome disease progression 94%
- Cerebrospinal fluid metabolomics identifies 19 brain-related phenotype associations 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.