Reinforcement learning for the design of targeted antimicrobial peptides against resistant pathogens
- Abstract
- Antimicrobial peptides (AMPs) are considered the most promising alternative to traditional antibiotics, addressing the issue of antibiotic resistance through diverse mechanisms that differ from conventional antibiotics. However, failures in clinical trials of AMPs highlight the importance of balancing low toxicity with high activity.
This study proposes a novel AMP generation model that integrates reinforcement learning, Generative Pretrained Transformer (GPT), and Low-Rank Adaptation (LoRA) to design peptides that account for both activity and non-hemolytic properties for each strain. The goal of this thesis is to contribute to the development of potential AMPs by ensuring activity and simultaneously generating non-hemolytic peptides tailored to individual strain.
To validate the strain-aware generation, the embeddings of peptides generated for each strain were visualized using t-SNE plots. Furthermore, the model demonstrated the ability to generate peptides satisfying both activity and non-hemolytic conditions for unseen strains, highlighting its potential to design AMPs for emerging pathogens.
- Issued Date
- 2025
- Type
- Thesis
- Alternative Author(s)
- Park Juntae
- Department
- 대학원 AI대학원
- Advisor
- Nam, Hojung
- Table Of Contents
- Abstract i
Contents ii
List of tables iv
List of figures v
I. Introduction 1
1. 1. Antibiotic resistance 1
1. 2. Antimicrobial peptides (AMPs) 2
1. 3. Existing methods for AMP generation 3
1. 4. Research Objectives 5
II. Materials and Methods 7
2. 1. Datasets and feature extraction 7
2. 2. MIC regression model 9
2. 3. Hemolysis prediction model 10
2. 4. Causal language modeling for pretraining 11
2. 5. Reinforcement learning 12
2. 6. Hyper-parameter tuning 14
2. 7. Evaluation metrics and prediction tools 15
III. Results and Discussion 16
3. 1. Pretraining performance 16
3. 2. Diversity, uniqueness, novelty 18
3. 3. Hemolysis prediction performance 19
3. 4. MIC regression performance 21
3. 5. MIC & Hemolysis performance 22
3. 6. T-SNE plot of generated peptides 23
3. 7. Amino acid composition 24
3. 8. Top 3 structure predictions 25
3. 9. Unseen strain generation performance 26
IV. Conclusion 28
Summary 29
References 30
Acknowledgement 34
Curriculum Vitae 35
- Degree
- Master
- Appears in Collections:
- Department of AI Convergence > 3. Theses(Master)
- 파일 목록
-
-
관련 파일이 존재하지 않습니다.
-
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.