相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Chemistry, Medicinal
Haiping Zhang et al.
Summary: Many bioactive peptides have therapeutic effects on complicated diseases, and deep learning can be used to generate potentially bioactive peptides, similar to the generation of de novo chemical compounds. Our work focuses on generating de novo peptides using the LSTM_Pep model and fine-tuning it for specific therapeutic benefits. We have utilized the Antimicrobial Peptide Database to generate various potential de novo peptides and developed the DeepPep model for rapid screening. Overall, this research demonstrates the potential of deep learning-based methods and pipelines to generate bioactive peptides and showcases the role of artificial intelligence in peptide discovery.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Biochemical Research Methods
Ke Yan et al.
Summary: In this study, a computational predictor called sAMPpred-GAT is proposed for the identification of antimicrobial peptides (AMPs). This predictor constructs graphs based on the predicted peptide structures, sequence information, and evolutionary information, and performs Graph Attention Network (GAT) to learn discriminative features. The full connection networks are then utilized as the output module to predict whether the peptides are AMP or not. Experimental results demonstrate that sAMPpred-GAT outperforms other state-of-the-art methods in terms of AUC and achieves comparable performance in other metrics, highlighting the importance of predicted peptide structure information for AMP prediction.
Article
Biotechnology & Applied Microbiology
Chenkai Li et al.
Summary: This study introduces a deep learning model called AMPlify for predicting antimicrobial peptides (AMPs) and demonstrates its effectiveness in lab experiments. The researchers found that four predicted AMPs showed activity against multiple bacterial species, including multi-drug resistant Escherichia coli.
Article
Engineering, Biomedical
Marcelo D. T. Torres et al.
Summary: By mining the human proteome, researchers identified 2,603 encrypted peptide antibiotics with antibacterial activity and low bacterial resistance, which target pathogenic bacteria by modulating their membranes and demonstrate anti-infective properties in mouse infection models. Additionally, peptides from the same geographical region show synergistic antimicrobial effects.
NATURE BIOMEDICAL ENGINEERING
(2022)
Article
Chemistry, Multidisciplinary
Ummu Gulsum Soylemez et al.
Summary: Antimicrobial peptides are potential alternatives to combat antibiotic resistance. In this study, computational prediction methods were used to identify and design the best candidate peptides based on their physico-chemical properties. The study successfully predicted the antimicrobial activity of the peptides using classification algorithms and could be valuable in evaluating the antibacterial potential of candidate peptide sequences.
APPLIED SCIENCES-BASEL
(2022)
Article
Biochemistry & Molecular Biology
Paola Ruiz Puentes et al.
Summary: Antibiotic resistance is a global public health problem, and large pharmaceutical industries have stopped searching for new antibiotics due to low profitability. On the other hand, antimicrobial peptides (AMPs) have emerged as potent molecules with a lower rate of resistance. This study proposes using an artificial intelligence algorithm to improve the efficiency of high-activity AMP discovery.
Article
Genetics & Heredity
Tong-Jie Sun et al.
Summary: Lactic acid bacteria antimicrobial peptides (LABAMPs) are active polypeptides produced by lactic acid bacteria that can inhibit or kill pathogenic or spoilage bacteria in food. It is urgent to develop a model to predict LABAMPs in a time-saving manner. In this study, a graph convolutional neural network was designed to identify LABAMPs by learning the weights of a heterogeneous graph. Experimental results showed that the accuracy of the model was higher than that of other machine learning and GNN algorithms.
FRONTIERS IN GENETICS
(2022)
Review
Infectious Diseases
Jielu Yan et al.
Summary: Antimicrobial resistance is a global health problem, and antimicrobial peptides (AMPs) show promise as next-generation antibiotics. This review discusses the use of deep learning methods in AMP prediction, including feature encoding techniques and novel peptide sequence design. The limitations and challenges of AMP prediction are also discussed.
Review
Biochemistry & Molecular Biology
Lei Wang et al.
Summary: Peptide drug development has achieved significant progress in the past decade, thanks to new production, modification, and analytic technologies. These advancements have addressed the inherent limitations of peptides and have resulted in achievements in various therapeutic areas.
SIGNAL TRANSDUCTION AND TARGETED THERAPY
(2022)
Review
Biology
Marcelo C. R. Melo et al.
Summary: Antibiotics insert themselves into the ancient struggle of host-pathogen evolution, driving urgent interest in computational methods for candidate discovery. Advances in artificial intelligence have been applied to antibiotic discovery, emphasizing antimicrobial activity prediction, drug-likeness traits, resistance, and de novo molecular design. Best practices such as open science and reproducibility are crucial in accelerating preclinical research in the face of antimicrobial resistance crisis.
COMMUNICATIONS BIOLOGY
(2021)
Review
Biochemistry & Molecular Biology
Ying Luo et al.
Summary: Antimicrobial peptides (AMPs) are considered a new generation of antibiotics with not only antimicrobial activity but also antibiofilm, immune-regulatory, and other activities. Research on the mechanism of action of AMPs can aid in their modification and development, with many studies focusing on this area. AMPs exhibit a dual mechanism of action and possess antifibroblast and anti-inflammatory properties, making them a promising therapeutic prospect.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2021)
Review
Chemistry, Multidisciplinary
Marcelo D. T. Torres et al.
Summary: Antibiotic resistance poses a significant global health challenge, with the need for innovative strategies becoming more urgent. Antimicrobial peptides (AMPs) offer a natural template for the discovery, design, and production of antibiotics, potentially leading the way for future advancements in peptide drug discovery through computational and synthetic biology approaches.
Review
Immunology
Nicholas Palmer et al.
Summary: Antimicrobial resistance is a growing concern, with only two new classes of antibiotics approved for human use since the 1960s. Molecular dynamics simulation is a valuable tool for understanding antibiotic mechanisms and can lay the groundwork for new antibiotic discovery. Antimicrobial peptides show promise in combating resistance due to their lower tendency to induce resistance compared to small-molecule antibiotics.
INFECTION AND IMMUNITY
(2021)
Review
Biochemical Research Methods
Jing Xu et al.
Summary: Antimicrobial peptides (AMPs) are a diverse group of molecules playing crucial roles in biological processes and cellular functions. With the emerging global concern of antimicrobial resistance, research on AMPs has gained popularity. Various computational methods have been developed for accurate prediction of AMPs, with differences in data sets and algorithms affecting predictive performance.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biochemistry & Molecular Biology
Rohan Gupta et al.
Summary: Drug designing and development faces challenges in terms of low efficacy, high cost, and complexity of data. However, artificial intelligence and machine learning technologies play a crucial role in overcoming these challenges and advancing the field.
MOLECULAR DIVERSITY
(2021)
Article
Biochemistry & Molecular Biology
Christina Wang et al.
Summary: Antimicrobial resistance is a growing concern in healthcare, and antimicrobial peptides offer a promising route for developing new antibiotics, which can be designed successfully using deep learning techniques.
Article
Biochemistry & Molecular Biology
Faiza Hanif Waghu et al.
Article
Biochemistry & Molecular Biology
Chia-Ru Chung et al.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2020)
Article
Biochemical Research Methods
P. Gainza et al.
Review
Multidisciplinary Sciences
Brian P. Lazzaro et al.
Article
Medicine, Research & Experimental
Jielu Yan et al.
MOLECULAR THERAPY-NUCLEIC ACIDS
(2020)
Review
Infectious Diseases
Maria Magana et al.
LANCET INFECTIOUS DISEASES
(2020)
Review
Biochemistry & Molecular Biology
Markus Huemer et al.
Article
Computer Science, Information Systems
Bing Rao et al.
Review
Computer Science, Artificial Intelligence
Jose Jimenez-Luna et al.
NATURE MACHINE INTELLIGENCE
(2020)
Article
Microbiology
Cesar De la Fuente-Nunez
Article
Engineering, Electrical & Electronic
Ron Levie et al.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2019)
Article
Multidisciplinary Sciences
William F. Porto et al.
NATURE COMMUNICATIONS
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Hongyang Gao et al.
KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Federico Monti et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Biochemistry & Molecular Biology
Sandeep Singh et al.
NUCLEIC ACIDS RESEARCH
(2016)
Review
Biochemistry & Molecular Biology
Cesar de la Fuente-Nunez et al.
BIOCHIMICA ET BIOPHYSICA ACTA-BIOMEMBRANES
(2016)
Article
Multidisciplinary Sciences
O. N. Silva et al.
SCIENTIFIC REPORTS
(2016)
Article
Computer Science, Artificial Intelligence
Franco Scarselli et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS
(2009)