DeepSF specifications

Information


Unique identifier OMICS_24998
Name DeepSF
Interface Web user interface
Restrictions to use None
Input data Some protein sequences.
Input format FASTA
Computer skills Basic
Stability Stable
Maintained Yes

Documentation


Maintainers


  • person_outline Jianlin Cheng
  • person_outline Jie Hou

Additional information


https://youtu.be/rvHk83BgaTE https://youtu.be/zqf7foz2q_I

Publication for DeepSF

DeepSF citation

library_books

DeepSF: deep convolutional neural network for mapping protein sequences to folds

2017
Bioinformatics
PMCID: 5905591
PMID: 29228193
DOI: 10.1093/bioinformatics/btx780

[…] r than PSI-BLAST for hard cases when sequence identity is very low. On the validation datasets whose redundancy is reduced to at most 95, 70, 40 and 25% sequence similarity with the training dataset, DeepSF achieves the accuracy of 80.4% (or 93.7%) for top 1 (or top 5) predictions at the 95% similarity level. The average accuracy on all the four validation datasets (95%/70%/40%/25%) is 75.3% (or 9 […]

DeepSF institution(s)
Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, USA; Department of Mathematics and Computer Science, University of Missouri-St. Louis, St. Louis, MO, USA; Informatics Institute, University of Missouri, Columbia, MO, USA
DeepSF funding source(s)
Supported by an NIH R01 grant (R01GM093123).

DeepSF reviews

star_border star_border star_border star_border star_border
star star star star star

Be the first to review DeepSF