Try Boost
Accelerate your research with up to 20 hours of computing
Contact Us
Google DeepMind |

Enformer

13
13
Omics
    More
Step 1: Upload your data

Upload VCF File

Drag your file(s) or upload
  • Your file can be in the following formats:vcf.gz, vcf
    • VCF stands for Variant Call Format. It is a text file format that is used to represent SNP, indel, and structural variation calls. If REF or ALT columns contain <.> in the VCF file, program will automatically skip these variant lines.
or
Don’t have a file?
Use our demo data to run
Use Demo Data

Select Targets

No targets selected

There is a significant unsolved problem about how non-coding DNA regulates gene expression in many cell types, and important downstream applications in human genetics rely on improved solutions. Enformer is a deep learning architecture that can incorporate data from long-distance interactions (up to 100 kb apart) in the genome. Predicting the impact of genetic variations on cell-type-specific gene expression is a key objective of this app.

Example use case: Variant effect prediction

Technology: Neural Network, Transformers

Limitation: Pretrained models created based on human and mouse genomes only.

Metrics: Some metrics related to research can be found here.

Note: "Select Targets" section below is optional!

Citation:
Avsec, Ž., Agarwal, V., Visentin, D. et al. Effective gene expression prediction from sequence by integrating long-range interactions. Nat Methods 18, 1196–1203 (2021). https://doi.org/10.1038/s41592-021-01252-x
Released:
Aug-08-2022
Results
Parameters