Scholarlink

<p>Sequence-to-function models have been very successful in predicting gene expression, chromatin accessibility, and epigenetic marks from DNA sequences alone. However, current state-of-the-art&#xa0;models have a fundamental limitation: they cannot extrapolate beyond the cell types and conditions included in their training dataset. Here, we introduce Corgi, a context-aware sequence-to-function model that overcomes this limitation by integrating DNA sequence and <i>trans</i>-regulator expression to predict chromatin accessibility, histone modifications, and gene expression coverage, even in held-out cell types. Trained on a diverse set of bulk and single-cell sequencing&#xa0;datasets, Corgi achieves top performance in joint cross-sequence and cross-cell-type epigenetic track prediction. Additionally, we present an advanced model version, Corgi+, which is state-of-the-art in imputation of epigenetic tracks using only RNA-seq data. We further show that Corgi learns key cell type-specific <i>trans</i>-regulators in a zero-shot manner, and it can predict genomic variant effects in held-out cell types.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Context-aware sequence-to-function model of human gene regulation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月14日

查看全文
  • Ekin Deniz Aksu,
  • Martin Vingron

摘要

Sequence-to-function models have been very successful in predicting gene expression, chromatin accessibility, and epigenetic marks from DNA sequences alone. However, current state-of-the-art models have a fundamental limitation: they cannot extrapolate beyond the cell types and conditions included in their training dataset. Here, we introduce Corgi, a context-aware sequence-to-function model that overcomes this limitation by integrating DNA sequence and trans-regulator expression to predict chromatin accessibility, histone modifications, and gene expression coverage, even in held-out cell types. Trained on a diverse set of bulk and single-cell sequencing datasets, Corgi achieves top performance in joint cross-sequence and cross-cell-type epigenetic track prediction. Additionally, we present an advanced model version, Corgi+, which is state-of-the-art in imputation of epigenetic tracks using only RNA-seq data. We further show that Corgi learns key cell type-specific trans-regulators in a zero-shot manner, and it can predict genomic variant effects in held-out cell types.