DeepVRegulome: DNABERT-based deep-learning framework for predicting the functional impact of short genomic variants on the human regulome

TL;DR

DeepVRegulome is a deep-learning framework that predicts the functional impact of non-coding genomic variants on the human regulome, aiding in understanding regulatory mutations in diseases like glioblastoma.

Contribution

It introduces a novel DNABERT-based deep-learning approach combining multiple models and interpretative tools for functional variant prediction in regulatory regions.

Findings

Identified thousands of mutations affecting regulatory regions in glioblastoma.

Linked mutations to patient survival outcomes and regulatory disruptions.

Provided publicly available code and models for community use.

Abstract

Whole-genome sequencing (WGS) has revealed numerous non-coding short variants whose functional impacts remain poorly understood. Despite recent advances in deep-learning genomic approaches, accurately predicting and prioritizing clinically relevant mutations in gene regulatory regions remains a major challenge. Here we introduce Deep VRegulome, a deep-learning method for prediction and interpretation of functionally disruptive variants in the human regulome, which combines 700 DNABERT fine-tuned models, trained on vast amounts of ENCODE gene regulatory regions, with variant scoring, motif analysis, attention-based visualization, and survival analysis. We showcase its application on TCGA glioblastoma WGS dataset in prioritizing survival-associated mutations and regulatory regions. The analysis identified 572 splice-disrupting and 9,837 transcription-factor binding site altering mutations occurring in greater than 10% of glioblastoma samples. Survival analysis linked 1352 mutations and 563 disrupted regulatory regions to patient outcomes, enabling stratification via non-coding mutation signatures. All the code, fine-tuned models, and an interactive data portal are publicly available.