Predicting cell-type-specific non-coding RNA transcription from genome sequence
Koido, M.; Terao, C.
Show abstract
Transcription is regulated through complex mechanisms involving non-coding RNAs (ncRNAs). However, because transcription of ncRNAs, especially enhancer RNAs, is often low and cell type-specific, its dependency on genotype remains largely unexplored. Here, we developed mutation effect prediction on ncRNA transcription (MENTR), a quantitative machine learning framework reliably connecting genetic associations with expression of ncRNAs, resolved to the level of cell type. MENTR-predicted mutation effects on ncRNA transcription were concordant with estimates from previous genetic studies in a cell type-dependent manner. We inferred reliable causal variants from 41,223 GWAS variants, and proposed 7,775 enhancers and 3,548 long-ncRNAs as complex trait-associated ncRNAs in 348 major human primary cells and tissues, including plausible enhancer-mediated functional alterations in single-variant resolution in Crohns disease. In summary, we present new resources for discovering causal variants, the biological mechanisms driving complex traits, and the sequence-dependency of ncRNA regulation in relevant cell types.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Promoter sequence and architecture determine expression variability and confer robustness to genetic variants 97%
- Alternative polyadenylation mediates genetic regulation of gene expression 97%
- Systematic analysis of naturally occurring insertions and deletions that alter transcription factor spacing identifies tolerant and sensitive transcription factor pairs 96%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- A catalog of transcription start sites across 115 human tissue and cell types 96%
- Dissecting the regulatory activity and sequence content of loci with exceptional numbers of transcription factor associations 96%
- Identifying transcription factor-bound gene activators and silencers in the chromatin accessible human genome using ATAC-STARR-seq 96%
"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.