Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Feb 2;21(3):986.
doi: 10.3390/ijms21030986.

Characterization and Identification of Natural Antimicrobial Peptides on Different Organisms

Chia-Ru Chung  1 , Jhih-Hua Jhong  2 , Zhuo Wang  2 , Siyu Chen  3 , Yu Wan  3 , Jorng-Tzong Horng  1   4 , Tzong-Yi Lee  2   3
Affiliations

Characterization and Identification of Natural Antimicrobial Peptides on Different Organisms

Chia-Ru Chung et al. Int J Mol Sci. .

Abstract

Because of the rapid development of multidrug resistance, conventional antibiotics cannot kill pathogenic bacteria efficiently. New antibiotic treatments such as antimicrobial peptides (AMPs) can provide a possible solution to the antibiotic-resistance crisis. However, the identification of AMPs using experimental methods is expensive and time-consuming. Meanwhile, few studies use amino acid compositions (AACs) and physicochemical properties with different sequence lengths against different organisms to predict AMPs. Therefore, the major purpose of this study is to identify AMPs on seven categories of organisms, including amphibians, humans, fish, insects, plants, bacteria, and mammals. According to the one-rule attribute evaluation, the selected features were used to construct the predictive models based on the random forest algorithm. Compared to the accuracies of iAMP-2L (a web-server for identifying AMPs and their functional types), ADAM (a database of AMP), and MLAMP (a multi-label AMP classifier), the proposed method yielded higher than 92% in predicting AMPs on each category. Additionally, the sensitivities of the proposed models in the prediction of AMPs of seven organisms were higher than that of all other tools. Furthermore, several physicochemical properties (charge, hydrophobicity, polarity, polarizability, secondary structure, normalized van der Waals volume, and solvent accessibility) of AMPs were investigated according to their sequence lengths. As a result, the proposed method is a practical means to complement the existing tools in the characterization and identification of AMPs in different organisms.

Keywords: antimicrobial peptides; feature selection; machine learning; organisms; sequence analysis.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure A1
Figure A1
Comparisons of charge distributions between AMPs and non-AMPs.
Figure A2
Figure A2
Comparisons of physicochemical properties between AMPs and non-AMPs for (A) polarizability, (B) normalized van der Waals volume, (C) secondary structure, and (D) solvent accessibility.
Figure A3
Figure A3
Comparisons of physicochemical properties between AMPs and non-AMPs at different positions (quantiles of sequence length) for (A) polarity, (B) polarizability, (C) normalized van der Waals volume, (D) secondary structure, and (E) solvent accessibility.
Figure A3
Figure A3
Comparisons of physicochemical properties between AMPs and non-AMPs at different positions (quantiles of sequence length) for (A) polarity, (B) polarizability, (C) normalized van der Waals volume, (D) secondary structure, and (E) solvent accessibility.
Figure A3
Figure A3
Comparisons of physicochemical properties between AMPs and non-AMPs at different positions (quantiles of sequence length) for (A) polarity, (B) polarizability, (C) normalized van der Waals volume, (D) secondary structure, and (E) solvent accessibility.
Figure A4
Figure A4
Comparisons of AMP charges (A) for different categories of organisms and (B) at different positions of sequence (percentiles of sequence length) in each category of organism.
Figure A5
Figure A5
Charge distribution of AMPs from different organisms.
Figure A6
Figure A6
Performance with different numbers of features using forward selection method for (A) amphibians, (B) bacteria, (C) fish, (D) humans, (E) insects, (F) mammals, and (G) plants. Note that the red point means the number of features associated with the accuracy for the optimal model.
Figure A7
Figure A7
Top 100 features for (A) Amphibians, (B) bacteria, (C) fish, (D) humans, (E) insects, (F) mammals, and (G) plants. The rank column with blue background color indicates that the feature was selected from the feature-selection method. The features marked red in (A) are related to charge property which is the majority member among the top 100 features for Amphibians. The features marked yellow in (B) are associated with the hydrophobicity which is the majority member among the top 100 features for bacteria. The features marked orange in (D) are related to AAPC which is the majority member among the top 100 features for human.
Figure A7
Figure A7
Top 100 features for (A) Amphibians, (B) bacteria, (C) fish, (D) humans, (E) insects, (F) mammals, and (G) plants. The rank column with blue background color indicates that the feature was selected from the feature-selection method. The features marked red in (A) are related to charge property which is the majority member among the top 100 features for Amphibians. The features marked yellow in (B) are associated with the hydrophobicity which is the majority member among the top 100 features for bacteria. The features marked orange in (D) are related to AAPC which is the majority member among the top 100 features for human.
Figure A7
Figure A7
Top 100 features for (A) Amphibians, (B) bacteria, (C) fish, (D) humans, (E) insects, (F) mammals, and (G) plants. The rank column with blue background color indicates that the feature was selected from the feature-selection method. The features marked red in (A) are related to charge property which is the majority member among the top 100 features for Amphibians. The features marked yellow in (B) are associated with the hydrophobicity which is the majority member among the top 100 features for bacteria. The features marked orange in (D) are related to AAPC which is the majority member among the top 100 features for human.
Figure A7
Figure A7
Top 100 features for (A) Amphibians, (B) bacteria, (C) fish, (D) humans, (E) insects, (F) mammals, and (G) plants. The rank column with blue background color indicates that the feature was selected from the feature-selection method. The features marked red in (A) are related to charge property which is the majority member among the top 100 features for Amphibians. The features marked yellow in (B) are associated with the hydrophobicity which is the majority member among the top 100 features for bacteria. The features marked orange in (D) are related to AAPC which is the majority member among the top 100 features for human.
Figure A7
Figure A7
Top 100 features for (A) Amphibians, (B) bacteria, (C) fish, (D) humans, (E) insects, (F) mammals, and (G) plants. The rank column with blue background color indicates that the feature was selected from the feature-selection method. The features marked red in (A) are related to charge property which is the majority member among the top 100 features for Amphibians. The features marked yellow in (B) are associated with the hydrophobicity which is the majority member among the top 100 features for bacteria. The features marked orange in (D) are related to AAPC which is the majority member among the top 100 features for human.
Figure A7
Figure A7
Top 100 features for (A) Amphibians, (B) bacteria, (C) fish, (D) humans, (E) insects, (F) mammals, and (G) plants. The rank column with blue background color indicates that the feature was selected from the feature-selection method. The features marked red in (A) are related to charge property which is the majority member among the top 100 features for Amphibians. The features marked yellow in (B) are associated with the hydrophobicity which is the majority member among the top 100 features for bacteria. The features marked orange in (D) are related to AAPC which is the majority member among the top 100 features for human.
Figure A7
Figure A7
Top 100 features for (A) Amphibians, (B) bacteria, (C) fish, (D) humans, (E) insects, (F) mammals, and (G) plants. The rank column with blue background color indicates that the feature was selected from the feature-selection method. The features marked red in (A) are related to charge property which is the majority member among the top 100 features for Amphibians. The features marked yellow in (B) are associated with the hydrophobicity which is the majority member among the top 100 features for bacteria. The features marked orange in (D) are related to AAPC which is the majority member among the top 100 features for human.
Figure A8
Figure A8
AAPC heatmaps for (A) human, (B) amphibians, (C) bacteria, (D) fish, (E) insects, (F) mammals, and (G) plants.
Figure 1
Figure 1
Average AACs of (A) AMPs and non-AMPs, and (B) AMPs with respect to the seven categories of organisms.
Figure 2
Figure 2
Comparisons of physicochemical properties between AMPs and non-AMPs for (A) hydrophobicity, (B) polarity, and (C) charge.
Figure 3
Figure 3
Comparisons of (A) charge on different positions of sequence between AMPs and non-AMPs, and (B) hydrophobicity at different positions of sequence between AMPs and non-AMPs.
Figure 4
Figure 4
Comparisons of AMP hydrophobicity (A) in different categories of organisms and (B) at different positions of sequence (percentiles of sequence length) in each category of organism.
Figure 5
Figure 5
Distribution of features (top 100). Shows the performance of AAC and amino acid pair composition (AAPC), as well as physicochemical composition in different organisms.
Figure 6
Figure 6
Comparison of ROC curves between our method and other prediction tools in the identification of AMPs on (A) Amphibians, (B) bacteria, (C) fish, (D) humans, (E) insects, (F) mammals, and (G) plants.
Figure 7
Figure 7
Conceptual framework. This study was divided into three parts: data collection and preprocessing, feature investigation, and model training and evaluation.
See this image and copyright information in PMC

References

    1. Huang K.Y., Chang T.H., Jhong J.H., Chi Y.H., Li W.C., Chan C.L., Robert Lai K., Lee T.Y. Identification of natural antimicrobial peptides from bacteria through metagenomic and metatranscriptomic analysis of high-throughput transcriptome data of Taiwanese oolong teas. BMC Syst. Biol. 2017;11:131. doi: 10.1186/s12918-017-0503-4. - DOI - PMC - PubMed
    1. Waghu F.H., Barai R.S., Gurung P., Idicula-Thomas S. CAMPR3: A database on sequences, structures and signatures of antimicrobial peptides. Nucleic Acids Res. 2016;44:D1094–D1097. doi: 10.1093/nar/gkv1051. - DOI - PMC - PubMed
    1. Yeaman M.R., Yount N.Y. Mechanisms of antimicrobial peptide action and resistance. Pharmacol. Rev. 2003;55:27–55. doi: 10.1124/pr.55.1.2. - DOI - PubMed
    1. Gabere M.N., Noble W.S. Empirical comparison of web-based antimicrobial peptide prediction tools. Bioinformatics. 2017;33:1921–1929. doi: 10.1093/bioinformatics/btx081. - DOI - PMC - PubMed
    1. Lata S., Sharma B.K., Raghava G.P. Analysis and prediction of antibacterial peptides. BMC Bioinform. 2007;8:263. doi: 10.1186/1471-2105-8-263. - DOI - PMC - PubMed

MeSH terms

Substances

LinkOut - more resources