Borzoi
A deep convolutional neural network that predicts RNA-seq coverage at 32bp resolution from DNA sequence.
What is Borzoi?
Borzoi is a deep convolutional neural network that predicts RNA-seq coverage from DNA sequence. It takes 524kb input sequences and outputs predictions at 32bp resolution, modeling gene expression, splicing, and polyadenylation. The tool solves the problem of interpreting how genetic variants affect RNA processing by providing in silico predictions without requiring new experiments.
Computational biologists and bioinformaticians working on variant interpretation, functional genomics, and gene expression modeling. Researchers needing to predict the effects of SNPs, indels, or structural variants on RNA-seq profiles.
Developers choose Borzoi for its high-resolution predictions, extensive training on diverse genomic assays, and ready-to-use models for human and mouse. Its open-source implementation and detailed tutorials for variant scoring make it a practical tool for in silico genomics experiments.
Overview
RNA-seq prediction with deep convolutional neural networks.
Use Cases
Best For
- Predicting the impact of genetic variants on RNA-seq coverage
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
