Online

Predicts species-specific lysine acetylation sites based on support vector machine (SVM) classifier. KA-predictor was designed for four species, H. sapiens, M. musculus, E. coli, and S. typhimurium. It employs an efficient feature selection on each type to form the final optimal feature set for model learning. The results indicates that the predictor is highly competitive for the majority of species when compared with other existing methods.

User report

×
Vote up tools and offer feedback
Give value to tools and make your expertise visible

0 user reviews

0 user reviews

No review has been posted.

KA-predictor forum

×
Communicate with other users
Participate in the forum to get support for using tools. Ask questions about technical specifications.

No open topic.

KA-predictor versioning

×
Upload and version your source code
Get your DOI for better tool traceability. Archive your releases so the community can easily visualize progress on you work.

No versioning.

KA-predictor classification

  • Animals
    • Homo sapiens
    • Mus musculus
  • Eubacteria
    • Escherichia coli

KA-predictor specifications

Software type:
Package/Module
Restrictions to use:
None
Input format:
FASTA
Output format:
OUT
Programming languages:
Python
Computer skills:
Advanced
Requirements:
gfortran, numpy, tcsh
Maintained:
Yes
Interface:
Command line interface
Input data:
A protein sequence file
Output data:
Predicted lysine residue located in the sequence
Operating system:
Unix/Linux, Mac OS
License:
Academic Free License version 3.0
Stability:
Beta

KA-predictor support

Maintainer

  • Gang Hu <>

Credits

×
Promote your skills
Define all the tasks you managed and assign your profile the appropriate badges. Become an active member.

Publications

Institution(s)

School of Mathematical Sciences and LPMC, Nankai University, Tianjin, China; Department of Mathematics, School of Science, Hebei University of Engineering, Handan, China; State Key Laboratory of Medicinal Chemical Biology, Nankai University, Tianjin, China

Funding source(s)

This work was supported by NSFC (grant number 11101226) and the Ph.D. Candidate Research Innovation Fund of Nankai University (no. 68150003).

By using OMICtools you acknowledge that you have read and accepted the terms of the end user license agreement.