For a paper appearing in Genome Biology, a Technical University of Munich-led team evaluates a suite of sequence-based transcription regulation models, setting in silico results against assay data for a range of tissue and developmental stages and results from CRISPR-based enhancer knockdown experiments and several other perturbation assays. While available models often unearthed authentic regulatory variants falling in promoter regions, the investigators saw poorer performance by these sequence-based models when it came to gauging the gene expression effects of mid- to long-range enhancer elements. "Our results suggest that sequence-based models have advanced to the point that in silico study of promoter regions and promoter variants can provide meaningful insights and we provide practical guidance on how to use them," the authors suggest. "Moreover, we foresee that it will require significantly more and particularly new kinds of data to train models accurately accounting for distal elements."
Study Considers Gene Regulatory Features Available by Sequence-Based Modeling
Mar 29, 2023