Welcome to the Home Page of HLPpred-Fuse

HLPpred-Fuse could be established according to the following steps: (i) feature representation scheme was employed to generate 54 probabilistic features derived from 54 prediction models that utilized nine different types of peptide features, i.e. AAC, DPC, amino acid index (AAI), binary profile (BPF), composition-transition-distribution (CTD), conjoint triad (CTF), quasi-sequence order (QSO), grouped dipeptide composition (GDPC), and grouped tripeptide composition (GTPC), and six ML classifiers, i.e. SVM, RF, gradient boosting (GB), extremely randomized tree (ERT), k-nearest neighbor (KNN), and AdaBoost (AB); and (ii) those 54 probabilistic features were fused and inputted to ERT to develop a final predictor separately for both layers. For a given peptide sequence, HLPpred-Fuse predicts HLPs activity and probability values.

Paste or upload FASTA peptide sequence below to predict hemolytic peptide and its activity


Sample FASTA sequences


Click here only to predict activity


HLPpred-Fuse: improved and robust prediction of hemolytic peptide and its activity by fusing multiple feature representation (Submitted).  
[Please cite this paper if you find HLPpred-Fuse is useful in your research

Contact: bala@kias.re.kr