MethylQUEEN: A Methylation Encoded DNA Foundation Model
Li, M.; Gu, R.; Fan, S.; Fan, Y.; He, B.; Yang, J.; Chen, Y.; Xin, M.; Wen, H.; Yi, C.
Show abstract
DNA 5-methylcytosine (5mC) modification plays a pivotal role in many biological processes, yet 5mC information and pattern hidden behind remains to be explored. Here, we develop Methylation Language Model based on Quintuple Bidirectional Transformer (MethylQUEEN), a novel pre-trained DNA methylation foundation model capable of sensing methylation states and covering the genome-wide methylation landscape. Through tailored methylation-prone pre-training, MethylQUEEN effectively captured epigenetics information hidden within the DNA sequences: it accurately traces DNAs tissue-of-origin, and successfully recovers the expression profile through methylation states. Integrative analysis on MethylQUEENs attention scores also enables us to reveal the unique methylation status of a tissue for precise disease detection, and identifying key regulatory 5mC sites for disease intervention. As a result, MethylQUEEN signifies a new paradigm in methylation analysis for various biological problems. Besides, our study demonstrates the effectiveness of directly integrating methylation information into pre-training, offering new perspectives and methodologies for a range of methylation-related biological processes. It serves as an initial exploration for the development of more comprehensive epigenomic models.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- PACS allows comprehensive dissection of multiple factors governing chromatin accessibility from snATAC-seq data 96%
- Atlas of imprinted and allele-specific DNA methylation in the human body 96%
- Genome-wide Detection of Cytosine Methylations in Plant from Nanopore sequencing data using Deep Learning 96%
Similar papers in this journal
- Evaluating the representational power of pre-trained DNA language models for regulatory genomics 96%
- Deep-learning prediction of gene expression from personal genomes 96%
- DEMINERS enables clinical metagenomics and comparative transcriptomic analysis by increasing throughput and accuracy of nanopore direct RNA sequencing 95%
Similar papers in this journal
- Multi-omics integration and regulatory inference for unpaired single-cell data with a graph-linked unified embedding framework 96%
- Quantitative single cell 5hmC sequencing reveals non-canonical gene regulation by non-CG hydroxymethylation 96%
- DeepMosaic: Control-independent mosaic single nucleotide variant detection using deep convolutional neural networks 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.