Antimicrobial Peptide Engineering With Machine-Learning-Guided Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in engineering antimicrobial peptides to achieve desired activity ranges and conditions for microbial growth inhibition, particularly in industrial and pharmaceutical applications.
Innovation Solution
A method involving in vitro translation and culture of candidate antimicrobial peptides under controlled conditions, followed by iterative testing and machine learning to optimize peptide variants for enhanced potency and broad-spectrum microbial inhibition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If naturally-occurring antimicrobial peptides are used, then the process is simple and reliable, but the potency and adaptability across different microbial strains and conditions are insufficient
Solution Approach 1:
The patent applies parameter changes by systematically modifying peptide sequences through iterative mutagenesis and selecting variants with improved antimicrobial activity. The method involves translating candidate nucleic acids to produce peptide variants, testing them against microbial organisms under controlled conditions, and using machine learning to guide further engineering based on performance data, thereby achieving both reliability and adaptability
Solution Approach 2:
The patent implements feedback mechanisms by detecting inhibition of microbial growth, indexing sequence information to performance data, and using machine learning algorithms to guide subsequent rounds of peptide engineering. This closed-loop feedback allows continuous improvement of peptide potency and adaptability across different microbial strains and culture conditions
2Adaptability or versatility
If iterative engineering with multiple variants is performed, then the potency and adaptability of the antimicrobial peptide are improved, but the time required for development increases
Solution Approach 1:
The patent uses copying by creating multiple variant nucleic acids through iterative mutagenesis and using machine learning to predict which variants are most likely to succeed, reducing the number of actual experimental iterations needed while maintaining high potency and adaptability
Solution Approach 2:
The patent applies parameter changes by using machine learning models to predict peptide performance and guide mutagenesis directions, allowing more efficient exploration of the sequence space and reducing the time required to achieve desired potency and adaptability compared to random screening approaches
3Reliability
If the antimicrobial peptide is engineered for high potency against specific microbes, then the effectiveness is improved, but the ability to function across a broad range of culture conditions and microbial strains decreases
Solution Approach 1:
The patent applies universality by designing and selecting peptide variants that demonstrate effective antimicrobial activity across multiple microbial strains and species while maintaining performance across different culture conditions. The iterative engineering process specifically targets peptides that can function broadly rather than optimizing for a single target, achieving multi-functionality in the antimicrobial peptide
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The method enables the development of engineered antimicrobial peptides with increased potency and adaptability across various microbial strains and conditions, surpassing the performance of naturally-occurring peptides.
Implementation Method 1
translating a candidate nucleic acid encoding a candidate antimicrobial peptide (e.g., bacteriocin) in vitro in a translation solution, so that the translation solution comprises the candidate antimicrobial peptide
Implementation Method 2
detecting inhibition of growth and/or reproduction, or a lack thereof, of the microbial organism in the solution environment
Data Source
AI summary
Embodiments herein relate to methods, systems and kits for engineering antimicrobial peptides such as bacteriocins, for example to have a desired range of activity in a desired range of culture conditions. The antimicrobial peptides may be engineered to have a particular activity for a particular culture, environmental conditions or a range of conditions. Some embodiments include screening an antimicrobial peptides or several candidate antimicrobial peptides for a desired activity. Some embodiments include an iterative process for engineering antimicrobial peptides such as bacteriocins. In some embodiments, the process is performed by automated machine learning.