AMP-EBiLSTM: employing novel deep learning strategies for the accurate prediction of antimicrobial peptides
Antimicrobial peptides are present ubiquitously in intra- and extra-biological environments and display considerable antibacterial and antifungal activities. Clinically, it has shown good antibacterial effect in the treatment of diabetic foot and its complications. However, the discovery and screeni...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-07-01
|
Series: | Frontiers in Genetics |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fgene.2023.1232117/full |
_version_ | 1797773465493700608 |
---|---|
author | Yuanda Wang Liyang Wang Chengquan Li Yilin Pei Xiaoxiao Liu Yu Tian |
author_facet | Yuanda Wang Liyang Wang Chengquan Li Yilin Pei Xiaoxiao Liu Yu Tian |
author_sort | Yuanda Wang |
collection | DOAJ |
description | Antimicrobial peptides are present ubiquitously in intra- and extra-biological environments and display considerable antibacterial and antifungal activities. Clinically, it has shown good antibacterial effect in the treatment of diabetic foot and its complications. However, the discovery and screening of antimicrobial peptides primarily rely on wet lab experiments, which are inefficient. This study endeavors to create a precise and efficient method of predicting antimicrobial peptides by incorporating novel machine learning technologies. We proposed a deep learning strategy named AMP-EBiLSTM to accurately predict them, and compared its performance with ensemble learning and baseline models. We utilized Binary Profile Feature (BPF) and Pseudo Amino Acid Composition (PSEAAC) for effective local sequence capture and amino acid information extraction, respectively, in deep learning and ensemble learning. Each model was cross-validated and externally tested independently. The results demonstrate that the Enhanced Bi-directional Long Short-Term Memory (EBiLSTM) deep learning model outperformed others with an accuracy of 92.39% and AUC value of 0.9771 on the test set. On the other hand, the ensemble learning models demonstrated cost-effectiveness in terms of training time on a T4 server equipped with 16 GB of GPU memory and 8 vCPUs, with training durations varying from 0 to 30 s. Therefore, the strategy we propose is expected to predict antimicrobial peptides more accurately in the future. |
first_indexed | 2024-03-12T22:05:56Z |
format | Article |
id | doaj.art-3e9ab40b21c548e097e5399f4feae926 |
institution | Directory Open Access Journal |
issn | 1664-8021 |
language | English |
last_indexed | 2024-03-12T22:05:56Z |
publishDate | 2023-07-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Genetics |
spelling | doaj.art-3e9ab40b21c548e097e5399f4feae9262023-07-24T11:58:14ZengFrontiers Media S.A.Frontiers in Genetics1664-80212023-07-011410.3389/fgene.2023.12321171232117AMP-EBiLSTM: employing novel deep learning strategies for the accurate prediction of antimicrobial peptidesYuanda Wang0Liyang Wang1Chengquan Li2Yilin Pei3Xiaoxiao Liu4Yu Tian5School of Modern Post (School of Automation), Beijing University of Posts and Telecommunications, Beijing, ChinaSchool of Clinical Medicine, Tsinghua University, Beijing, ChinaSchool of Clinical Medicine, Tsinghua University, Beijing, ChinaSchool of Clinical Medicine, Tsinghua University, Beijing, ChinaLaboratory Medicine, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, ChinaVascular Surgery Department, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi Hospital, Third Hospital of Shanxi Medical University, Taiyuan, ChinaAntimicrobial peptides are present ubiquitously in intra- and extra-biological environments and display considerable antibacterial and antifungal activities. Clinically, it has shown good antibacterial effect in the treatment of diabetic foot and its complications. However, the discovery and screening of antimicrobial peptides primarily rely on wet lab experiments, which are inefficient. This study endeavors to create a precise and efficient method of predicting antimicrobial peptides by incorporating novel machine learning technologies. We proposed a deep learning strategy named AMP-EBiLSTM to accurately predict them, and compared its performance with ensemble learning and baseline models. We utilized Binary Profile Feature (BPF) and Pseudo Amino Acid Composition (PSEAAC) for effective local sequence capture and amino acid information extraction, respectively, in deep learning and ensemble learning. Each model was cross-validated and externally tested independently. The results demonstrate that the Enhanced Bi-directional Long Short-Term Memory (EBiLSTM) deep learning model outperformed others with an accuracy of 92.39% and AUC value of 0.9771 on the test set. On the other hand, the ensemble learning models demonstrated cost-effectiveness in terms of training time on a T4 server equipped with 16 GB of GPU memory and 8 vCPUs, with training durations varying from 0 to 30 s. Therefore, the strategy we propose is expected to predict antimicrobial peptides more accurately in the future.https://www.frontiersin.org/articles/10.3389/fgene.2023.1232117/fullantimicrobial peptidesdiabetic footdeep learningensemble learningaccurate screening |
spellingShingle | Yuanda Wang Liyang Wang Chengquan Li Yilin Pei Xiaoxiao Liu Yu Tian AMP-EBiLSTM: employing novel deep learning strategies for the accurate prediction of antimicrobial peptides Frontiers in Genetics antimicrobial peptides diabetic foot deep learning ensemble learning accurate screening |
title | AMP-EBiLSTM: employing novel deep learning strategies for the accurate prediction of antimicrobial peptides |
title_full | AMP-EBiLSTM: employing novel deep learning strategies for the accurate prediction of antimicrobial peptides |
title_fullStr | AMP-EBiLSTM: employing novel deep learning strategies for the accurate prediction of antimicrobial peptides |
title_full_unstemmed | AMP-EBiLSTM: employing novel deep learning strategies for the accurate prediction of antimicrobial peptides |
title_short | AMP-EBiLSTM: employing novel deep learning strategies for the accurate prediction of antimicrobial peptides |
title_sort | amp ebilstm employing novel deep learning strategies for the accurate prediction of antimicrobial peptides |
topic | antimicrobial peptides diabetic foot deep learning ensemble learning accurate screening |
url | https://www.frontiersin.org/articles/10.3389/fgene.2023.1232117/full |
work_keys_str_mv | AT yuandawang ampebilstmemployingnoveldeeplearningstrategiesfortheaccuratepredictionofantimicrobialpeptides AT liyangwang ampebilstmemployingnoveldeeplearningstrategiesfortheaccuratepredictionofantimicrobialpeptides AT chengquanli ampebilstmemployingnoveldeeplearningstrategiesfortheaccuratepredictionofantimicrobialpeptides AT yilinpei ampebilstmemployingnoveldeeplearningstrategiesfortheaccuratepredictionofantimicrobialpeptides AT xiaoxiaoliu ampebilstmemployingnoveldeeplearningstrategiesfortheaccuratepredictionofantimicrobialpeptides AT yutian ampebilstmemployingnoveldeeplearningstrategiesfortheaccuratepredictionofantimicrobialpeptides |