Human Lysine Acetylation Predictor


BRABSB-PHKA is an in silico online tool for Prediction of potential Human Lysine(K) Acetylation(PHKA) sites from protein sequences. The computational methodology is based on Bi-Relative Binomial Score Bayes (BRBSB) combined with support vector machines (SVMs). BRBSB-PHKA yields, on average, a sensitivity of 83.91%, a specificity of 87.25% and an accuracy of 85.58% in the case of 5-fold cross validation, together with the results on independent test data sets, suggesting that BRBSB-PHKA presented here can facilitate the identification of human lysine acetylation sites and more confident annotation.

BRBSB-PHKA supports two input forms for query sequence(s), directly PASTE a single sequence or several sequences in FASTA format into the input frame or UPLOAD a file in FASTA format from local disk (protein sequences here are all represented in single-letter code amino acids). The sequence part allows any character, figure or space except ˇ°>ˇ±.

The prediction results of BRBSB-PHKA are shown in output table.

Sequence name---denotes the name of each query sequence in FASTA format. If no names are provided for query sequences in FASTA format, the system will give them names of ˇ°default sequence 1ˇ±, ˇ°default sequence2ˇ±, ˇ­ˇ­.

Position---stands for the absolute position of potentially acetyllysine sites in proteins.

Acetylated residue ---refers to corresponding acetylated amino acid.

Score ---refers to the predictive probability of acetylation at the corresponding site.

Flanking residues---represents the flanking sequence centering on acetylated residue (the length is 15 for BRABSB-PHKA).


Human Lysine Acetylation Predictor


Jianlin Shao,Dong Xu,Landian Hu,Yiu-Wa Kwan,Yifei Wang,Xiangyin Kong,Sai-Ming Ngai. (2012)Systematic analysis of human lysine acetylation proteins and accurate prediction of human lysine acetylation through bi-relative adapted binomial score Bayes feature representation. Molecular Biosystems. 8(11):2964-2973.