Omnireg-gpt: a high-efficiency foundation model for comprehensive genomic sequence understanding.
Aowen Wang1, Jiaqi Li2,3, Hongyu Dong1,4,5
1College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China.
Nature Communications
|November 19, 2025
Summary
OmniReg-GPT is a new foundation model for analyzing long genomic sequences. It efficiently decodes cis-regulatory elements across various scales, enabling diverse genomic research applications.
Area of Science:
- Genomics
- Computational Biology
- Bioinformatics
Background:
- The human genome has complex regulatory elements crucial for gene activity.
- Processing long genomic sequences for foundation models is challenging.
- Decoding cis-regulatory elements requires efficient computational tools.
Purpose of the Study:
- Introduce OmniReg-GPT, a generative foundation model for low-resource pretraining of long genomic sequences.
- Optimize attention mechanisms for efficient processing of genomic data.
- Capture the complete distribution of regulatory elements across diverse genomic scales.
Main Methods:
- Developed OmniReg-GPT, a generative foundation model.
- Utilized an optimized attention mechanism for efficient pretraining.
- Pretrained on long genomic sequences, capturing regulatory element distributions.
Main Results:
- OmniReg-GPT demonstrates efficient training speed and memory usage.
- Achieved exceptional performance in identifying cis-regulatory elements.
- Showcased effectiveness in gene expression prediction, chromatin accessibility analysis, and 3D chromatin contact modeling.
- Demonstrated potential for generating cell-type-specific enhancers via prompt engineering.
Conclusions:
- OmniReg-GPT advances foundation models in genomics.
- Provides a valuable pretraining resource for extensive genomic research.
- Extends the capabilities for analyzing complex regulatory landscapes.
Related Concept Videos
03:00Next-generation Sequencing
97.6K
The first human genome sequencing project cost $2.7 billion and was declared complete in 2003, after 15 years of international cooperation and collaboration between several research teams and funding agencies. Today, with the advent of next-generation sequencing technologies, the cost and time of sequencing a human genome have dropped over 100 fold.
Next-Generation Sequencing Methods
Although all next-generation methods use different technologies, they all share a set of standard features....
Next-Generation Sequencing Methods
Although all next-generation methods use different technologies, they all share a set of standard features....
97.6K
02:54Evolutionary Relationships through Genome Comparisons
6.8K
Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...
6.8K
03:36Genome Annotation and Assembly
20.5K
The genome refers to all of the genetic material in an organism. It can range from a few million base pairs in microbial cells to several billion base pairs in many eukaryotic organisms. Genome assembly refers to the process of taking the DNA sequencing data and putting it all back together in a correct order to create a close representation of the original genome. This is followed by the identification of functional elements on the newly assembled genome, a process called genome annotation.
20.5K