In recent years, there has been significant interest in using machine learning for fast and accurate prediction of antibacterial peptides (ABPs) and for prediction of antimicrobial resistance (AMR) genes in numerous pathogens. Pharmaceutical companies are interested in discovering ABPs to use as broad-spectrum antibiotics, but conventional methods of discovery are time-consuming and expensive.
Machine Learning (ML) could be a much more cost-effective tool for predicting ABPs that can then be tested in the lab. Both sequence- and structural-based approaches can be used. In addition, ML can be used for antibacterial and antimicrobial drug design.
Sequencing technology has resulted in a vast number of completely sequenced bacterial genomes. While best-hit methods are good at identifying known and highly conserved AMR genes in these bacterial genomes, they are not good at identifying AMR genes with little sequence similarity to known AMR genes. ML is not limited by sequence similarity to predict AMR genes and can be used as an alternative approach to identifying AMR genes. In some instances, these predictions can be used in patient treatment.
At the turn of the twentieth century, infectious diseases were the primary cause of death. The discovery of the first antibiotic, i.e., penicillin, was only a temporary solution due to the development of penicillin-resistant bacteria. Since then, pharmaceutical companies have been fighting AMR which now extends to multiple antibiotics and is the cause of death worldwide.
This Research Topic focuses on ML applications to combat AMR (e.g., identifying ABPs that work as broad-spectrum antibiotics in a cost-effective manner, predicting AMR genes in bacterial genomes, and drug design). This knowledge could then be translated into clinics and used to treat infectious diseases.
All types of manuscripts will be considered, and topics of interest include, but are not limited to:
• Machine learning for predicting antibacterial/antimicrobial peptides using sequence-based approaches
• Machine learning for predicting antibacterial/antimicrobial peptides using structure-based approaches
• Machine learning techniques for antibacterial/antimicrobial drug design
• Machine learning techniques for predicting antimicrobial resistance genes in Gram-negative bacteria
• Machine learning techniques for predicting antimicrobial resistance genes in Gram-positive bacteria
• Machine learning techniques for predicting antimicrobial resistance genes for specific bacterial species
In recent years, there has been significant interest in using machine learning for fast and accurate prediction of antibacterial peptides (ABPs) and for prediction of antimicrobial resistance (AMR) genes in numerous pathogens. Pharmaceutical companies are interested in discovering ABPs to use as broad-spectrum antibiotics, but conventional methods of discovery are time-consuming and expensive.
Machine Learning (ML) could be a much more cost-effective tool for predicting ABPs that can then be tested in the lab. Both sequence- and structural-based approaches can be used. In addition, ML can be used for antibacterial and antimicrobial drug design.
Sequencing technology has resulted in a vast number of completely sequenced bacterial genomes. While best-hit methods are good at identifying known and highly conserved AMR genes in these bacterial genomes, they are not good at identifying AMR genes with little sequence similarity to known AMR genes. ML is not limited by sequence similarity to predict AMR genes and can be used as an alternative approach to identifying AMR genes. In some instances, these predictions can be used in patient treatment.
At the turn of the twentieth century, infectious diseases were the primary cause of death. The discovery of the first antibiotic, i.e., penicillin, was only a temporary solution due to the development of penicillin-resistant bacteria. Since then, pharmaceutical companies have been fighting AMR which now extends to multiple antibiotics and is the cause of death worldwide.
This Research Topic focuses on ML applications to combat AMR (e.g., identifying ABPs that work as broad-spectrum antibiotics in a cost-effective manner, predicting AMR genes in bacterial genomes, and drug design). This knowledge could then be translated into clinics and used to treat infectious diseases.
All types of manuscripts will be considered, and topics of interest include, but are not limited to:
• Machine learning for predicting antibacterial/antimicrobial peptides using sequence-based approaches
• Machine learning for predicting antibacterial/antimicrobial peptides using structure-based approaches
• Machine learning techniques for antibacterial/antimicrobial drug design
• Machine learning techniques for predicting antimicrobial resistance genes in Gram-negative bacteria
• Machine learning techniques for predicting antimicrobial resistance genes in Gram-positive bacteria
• Machine learning techniques for predicting antimicrobial resistance genes for specific bacterial species
