Genome BiolJClub
Comparing machine learning methods predicting transcriptome from epigenome with applications to association studies.
Genome Biology · · Comparative Study · Open access
Behjati Ardakani, Ashrafiyan + more
Abstract ↗AI summary
The abstract is read at the publisher; the summary is JClub's.
Using the IHEC EpiATLAS dataset, models trained on epigenomic data predict transcriptome variation across over 28,000 human genes, yielding a regulatory catalog.
- Why it matters: Regulatory regions are cell type-specific and vary in location, size, and distance to targets, making epigenome-to-transcriptome association discovery difficult.
- What they did: The study benchmarks optimized linear and nonlinear machine learning approaches per gene, then evaluates performance with CRISPRi and eQTL validation data.
- The result: Model-based histone-acetylation association studies identify genes and regulatory regions linked to B-cell leukemia in patient data, supporting disease-relevant interpretation.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.
- Open access