About DMRU...

Epigenetic regulation of gene expression is a complex and multifaceted process that plays a crucial role in plant development and adaptation. DNA methylation at cytosines has been shown to influence gene expression by regulating chromatin structure and accessibility. Some approaches have been developed to identify DNA methylation but none of them are capable to tell the condition specific DNA methylation, making them hardly of any use. Here, we report a first of its kind an explainable Deep Encoders-Decoders generative system, DMRU, which learns the relationship between transcritpome status and DNA methylation states at any given time. It was also found that instead of looking for homology to relate condition specificity of DNA methylation marks across species, GC similarity is more relevant to the specificity of DNA methylation patterns. The developed approach, DMRU, is capable to discover the methylated cytosines in total independence from data volume and species specific models, and works with same performance across different species in universal manner. In a comprehensive benchmarking study across a huge volume of experimental data covering different conditions and species, it has consistently achieved >90% accuracy. With this all, DMRU brings a completely new chapter in methylated cytosine discovery through generative AI, giving a strong alternative to costly bisulfite sequencing experiments, saving enormous amount of time and money. DMRU may have significant impact on the development of novel strategies for crop improvement and biotechnology applications, while accelerating the research in the field of epigenomics and gene regulation.