Limits...
Prediction of antimicrobial peptides based on sequence alignment and support vector machine-pairwise algorithm utilizing LZ-complexity.

Ng XY, Rosdi BA, Shahrudin S - Biomed Res Int (2015)

Bottom Line: Recently, researchers are interested in designing alternative drugs based on AMPs because they have found that a large number of bacterial strains have become resistant to available antibiotics.However, researchers have encountered obstacles in the AMPs designing process as experiments to extract AMPs from protein sequences are costly and require a long set-up time.Therefore, a computational tool for AMPs prediction is needed to resolve this problem.

View Article: PubMed Central - PubMed

Affiliation: School of Electrical & Electronic Engineering, Universiti Sains Malaysia, 14300 Nibong Tebal, Seberang Perai Selatan, Pulau Pinang, Malaysia.

ABSTRACT
This study concerns an attempt to establish a new method for predicting antimicrobial peptides (AMPs) which are important to the immune system. Recently, researchers are interested in designing alternative drugs based on AMPs because they have found that a large number of bacterial strains have become resistant to available antibiotics. However, researchers have encountered obstacles in the AMPs designing process as experiments to extract AMPs from protein sequences are costly and require a long set-up time. Therefore, a computational tool for AMPs prediction is needed to resolve this problem. In this study, an integrated algorithm is newly introduced to predict AMPs by integrating sequence alignment and support vector machine- (SVM-) LZ complexity pairwise algorithm. It was observed that, when all sequences in the training set are used, the sensitivity of the proposed algorithm is 95.28% in jackknife test and 87.59% in independent test, while the sensitivity obtained for jackknife test and independent test is 88.74% and 78.70%, respectively, when only the sequences that has less than 70% similarity are used. Applying the proposed algorithm may allow researchers to effectively predict AMPs from unknown protein peptide sequences with higher sensitivity.

Show MeSH
The flowchart of the SVM training model generation.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4352747&req=5

fig4: The flowchart of the SVM training model generation.

Mentions: Before performing prediction on test sequences, a SVM training model is generated. Figure 4 shows the steps of generation of SVM training model for this study. In order to generate a training model for AMPs prediction, a “General Training Set” has to be prepared. All sequences in the General Training Set are formed by the training sequences that cannot be predicted by the sequence alignment method. This training set consists of an equal number of positive training and negative training sequences. Equation (9) shows the relationship between the size of “General Training Set,” SGT, and the number of the remaining positive sequences, SRP:(9)SGT=2×SRP−1.


Prediction of antimicrobial peptides based on sequence alignment and support vector machine-pairwise algorithm utilizing LZ-complexity.

Ng XY, Rosdi BA, Shahrudin S - Biomed Res Int (2015)

The flowchart of the SVM training model generation.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4352747&req=5

fig4: The flowchart of the SVM training model generation.
Mentions: Before performing prediction on test sequences, a SVM training model is generated. Figure 4 shows the steps of generation of SVM training model for this study. In order to generate a training model for AMPs prediction, a “General Training Set” has to be prepared. All sequences in the General Training Set are formed by the training sequences that cannot be predicted by the sequence alignment method. This training set consists of an equal number of positive training and negative training sequences. Equation (9) shows the relationship between the size of “General Training Set,” SGT, and the number of the remaining positive sequences, SRP:(9)SGT=2×SRP−1.

Bottom Line: Recently, researchers are interested in designing alternative drugs based on AMPs because they have found that a large number of bacterial strains have become resistant to available antibiotics.However, researchers have encountered obstacles in the AMPs designing process as experiments to extract AMPs from protein sequences are costly and require a long set-up time.Therefore, a computational tool for AMPs prediction is needed to resolve this problem.

View Article: PubMed Central - PubMed

Affiliation: School of Electrical & Electronic Engineering, Universiti Sains Malaysia, 14300 Nibong Tebal, Seberang Perai Selatan, Pulau Pinang, Malaysia.

ABSTRACT
This study concerns an attempt to establish a new method for predicting antimicrobial peptides (AMPs) which are important to the immune system. Recently, researchers are interested in designing alternative drugs based on AMPs because they have found that a large number of bacterial strains have become resistant to available antibiotics. However, researchers have encountered obstacles in the AMPs designing process as experiments to extract AMPs from protein sequences are costly and require a long set-up time. Therefore, a computational tool for AMPs prediction is needed to resolve this problem. In this study, an integrated algorithm is newly introduced to predict AMPs by integrating sequence alignment and support vector machine- (SVM-) LZ complexity pairwise algorithm. It was observed that, when all sequences in the training set are used, the sensitivity of the proposed algorithm is 95.28% in jackknife test and 87.59% in independent test, while the sensitivity obtained for jackknife test and independent test is 88.74% and 78.70%, respectively, when only the sequences that has less than 70% similarity are used. Applying the proposed algorithm may allow researchers to effectively predict AMPs from unknown protein peptide sequences with higher sensitivity.

Show MeSH