The newest DeepSEA model can be found at https://hb.flatironinstitute.org/deepsea/

What is DeepSEA?

DeepSEA is a deep learning-based algorithmic framework for predicting the chromatin effects of sequence alterations with single nucleotide sensitivity. DeepSEA can accurately predict the epigenetic state of a sequence, including transcription factors binding, DNase I sensitivities and histone marks in multiple cell types, and further utilize this capability to predict the chromatin effects of sequence variants and prioritize regulatory variants.

Please enter the information below to run a new DeepSEA Analysis.

To query variant effect predictions, upload a VCF file or paste below. To query DNA sequence feature predictions, upload a FASTA file (DNA sequence) or a BED file (chromatin regions - hg19 coordinates) or paste below.

Or paste a content of the file to the area below and specify the type:

Email address you want the results sent to. (Optional)
Click for format description:
FASTA format:
  • Each section starts with '>'.
  • The sequence has to have length of 1000bp.
  • Allowed nucleic acid codes: ATCGatcg (lowercases are treated the same of uppercases).
Example file: FASTA
BED format:
  • Each line has at least 3 tab separated fields.
  • The first column: Chromosome name (hg19). (check hg19 chromosome list)
  • The second column: Start Position (hg19). A non-negative integer within chromosome length. (check hg19 chromosome list)
  • The third column: End Position (hg19). A non-negative integer within chromosome length.
  • The difference in values between Start and End Position should be 1000 or less (We only use the center positions. See help page for details).
Example file: BED
VCF format:
  • Each line has at least 5 tab separated fields.
  • The first column: Chromosome name (hg19). (check hg19 chromosome list)
  • The second column: Position (hg19). A positive integer within chromosome length. (check hg19 chromosome list)
  • The third column: Variant name. This field can be left empty.
  • The fourth column: Reference allele. One or more upper case codes from ATCG. Maximum 100 characters.
  • The fifth column: Alternative allele. Empty or contain one or more upper case codes from ATCG. Maximum 100 characters.
Example file: VCF
Example files: