Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence
Antibiotic resistance is a worldwide public health problem due to the costs and mortality rates it generates. However, the large pharmaceutical industries have stopped searching for new antibiotics because of their low profitability, given the rapid replacement rates imposed by the increasingly obse...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Membranes |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0375/12/7/708 |
| _version_ | 1797417116172812288 |
|---|---|
| author | Paola Ruiz Puentes Maria C. Henao Javier Cifuentes Carolina Muñoz-Camargo Luis H. Reyes Juan C. Cruz Pablo Arbeláez |
| author_facet | Paola Ruiz Puentes Maria C. Henao Javier Cifuentes Carolina Muñoz-Camargo Luis H. Reyes Juan C. Cruz Pablo Arbeláez |
| author_sort | Paola Ruiz Puentes |
| collection | DOAJ |
| description | Antibiotic resistance is a worldwide public health problem due to the costs and mortality rates it generates. However, the large pharmaceutical industries have stopped searching for new antibiotics because of their low profitability, given the rapid replacement rates imposed by the increasingly observed resistance acquired by microorganisms. Alternatively, antimicrobial peptides (AMPs) have emerged as potent molecules with a much lower rate of resistance generation. The discovery of these peptides is carried out through extensive in vitro screenings of either rational or non-rational libraries. These processes are tedious and expensive and generate only a few AMP candidates, most of which fail to show the required activity and physicochemical properties for practical applications. This work proposes implementing an artificial intelligence algorithm to reduce the required experimentation and increase the efficiency of high-activity AMP discovery. Our deep learning (DL) model, called AMPs-Net, outperforms the state-of-the-art method by 8.8% in average precision. Furthermore, it is highly accurate to predict the antibacterial and antiviral capacity of a large number of AMPs. Our search led to identifying two unreported antimicrobial motifs and two novel antimicrobial peptides related to them. Moreover, by coupling DL with molecular dynamics (MD) simulations, we were able to find a multifunctional peptide with promising therapeutic effects. Our work validates our previously proposed pipeline for a more efficient rational discovery of novel AMPs. |
| first_indexed | 2024-03-09T06:14:10Z |
| format | Article |
| id | doaj.art-ec1bfeb581be44a5872ee869ff9ad17d |
| institution | Directory Open Access Journal |
| issn | 2077-0375 |
| language | English |
| last_indexed | 2024-03-09T06:14:10Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Membranes |
| spelling | doaj.art-ec1bfeb581be44a5872ee869ff9ad17d2023-12-03T11:55:36ZengMDPI AGMembranes2077-03752022-07-0112770810.3390/membranes12070708Rational Discovery of Antimicrobial Peptides by Means of Artificial IntelligencePaola Ruiz Puentes0Maria C. Henao1Javier Cifuentes2Carolina Muñoz-Camargo3Luis H. Reyes4Juan C. Cruz5Pablo Arbeláez6Center for Research and Formation in Artificial Intelligence, Universidad de los Andes, Bogota 111711, ColombiaGrupo de Diseño de Productos y Procesos (GDPP), Department of Chemical and Food Engineering, Universidad de los Andes, Bogota 111711, ColombiaDepartment of Biomedical Engineering, Universidad de los Andes, Bogota 111711, ColombiaDepartment of Biomedical Engineering, Universidad de los Andes, Bogota 111711, ColombiaGrupo de Diseño de Productos y Procesos (GDPP), Department of Chemical and Food Engineering, Universidad de los Andes, Bogota 111711, ColombiaDepartment of Biomedical Engineering, Universidad de los Andes, Bogota 111711, ColombiaCenter for Research and Formation in Artificial Intelligence, Universidad de los Andes, Bogota 111711, ColombiaAntibiotic resistance is a worldwide public health problem due to the costs and mortality rates it generates. However, the large pharmaceutical industries have stopped searching for new antibiotics because of their low profitability, given the rapid replacement rates imposed by the increasingly observed resistance acquired by microorganisms. Alternatively, antimicrobial peptides (AMPs) have emerged as potent molecules with a much lower rate of resistance generation. The discovery of these peptides is carried out through extensive in vitro screenings of either rational or non-rational libraries. These processes are tedious and expensive and generate only a few AMP candidates, most of which fail to show the required activity and physicochemical properties for practical applications. This work proposes implementing an artificial intelligence algorithm to reduce the required experimentation and increase the efficiency of high-activity AMP discovery. Our deep learning (DL) model, called AMPs-Net, outperforms the state-of-the-art method by 8.8% in average precision. Furthermore, it is highly accurate to predict the antibacterial and antiviral capacity of a large number of AMPs. Our search led to identifying two unreported antimicrobial motifs and two novel antimicrobial peptides related to them. Moreover, by coupling DL with molecular dynamics (MD) simulations, we were able to find a multifunctional peptide with promising therapeutic effects. Our work validates our previously proposed pipeline for a more efficient rational discovery of novel AMPs.https://www.mdpi.com/2077-0375/12/7/708antimicrobialpeptidesartificial intelligencegraphsmolecular dynamics |
| spellingShingle | Paola Ruiz Puentes Maria C. Henao Javier Cifuentes Carolina Muñoz-Camargo Luis H. Reyes Juan C. Cruz Pablo Arbeláez Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence Membranes antimicrobial peptides artificial intelligence graphs molecular dynamics |
| title | Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence |
| title_full | Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence |
| title_fullStr | Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence |
| title_full_unstemmed | Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence |
| title_short | Rational Discovery of Antimicrobial Peptides by Means of Artificial Intelligence |
| title_sort | rational discovery of antimicrobial peptides by means of artificial intelligence |
| topic | antimicrobial peptides artificial intelligence graphs molecular dynamics |
| url | https://www.mdpi.com/2077-0375/12/7/708 |
| work_keys_str_mv | AT paolaruizpuentes rationaldiscoveryofantimicrobialpeptidesbymeansofartificialintelligence AT mariachenao rationaldiscoveryofantimicrobialpeptidesbymeansofartificialintelligence AT javiercifuentes rationaldiscoveryofantimicrobialpeptidesbymeansofartificialintelligence AT carolinamunozcamargo rationaldiscoveryofantimicrobialpeptidesbymeansofartificialintelligence AT luishreyes rationaldiscoveryofantimicrobialpeptidesbymeansofartificialintelligence AT juanccruz rationaldiscoveryofantimicrobialpeptidesbymeansofartificialintelligence AT pabloarbelaez rationaldiscoveryofantimicrobialpeptidesbymeansofartificialintelligence |