In the rapidly evolving field of drug discovery, peptides play essential roles in human physiology and can be used to mimic protein functions in the body. Peptide-based drugs are being developed in many therapeutic areas, including cancer, cardiovascular diseases, and more. However, their translations to the clinic are hampered by their metabolic instability, poor oral bioavailability, lability during storage, and unwanted toxicity. Improving the biological activities (e.g., target specificity, binding affinity) while mitigating undesirable side effects (e.g., aggregation, immunogenicity) is a pivotal challenge in peptide drug design campaigns. The process of discovering and designing peptide-based drugs is complex and time-consuming.

This Research Topic explores how artificial intelligence (AI) can streamline the discovery and design of peptide-based drugs. AI offers promising avenues to overcome historical obstacles in drug discovery by learning complex patterns from extensive datasets; this includes predicting biological activities (e.g., target binding affinity, hemotoxicity, etc.) and generating novel peptide sequences or structures. The combined use of predictive and generative models helps design peptides with the desired characteristics (e.g., increased thermostability, solubility, binding affinity), which are crucial for their effectiveness as drugs.

There are also limitations to using AI in discovering and designing peptide-based drugs. Limitations in peptide predictive and generative modelling lie in the diversity of peptide sequences and biological information. Biases and imbalances in harnessing chemical and biological information impact the performance of machine learning models. Understanding the boundaries and biases of our existing AI-powered applications to peptide-based drug discovery is necessary for their applicability to the real world.

In this Research Topic, we welcome submissions of Original Research, Review, Mini Review, Opinion, and Perspective articles, on the following, but not limited to, topics:

- The effects of peptide embeddings on predictive and generative models
- Machine learning models for peptides with non-natural amino acids and chemical modifications.
- Machine learning models applied to multi-objectivity and promiscuous functionality
- Novel approaches to detect peptides “within-distribution” (inliers) and “out-of-distribution” (outliers)
- Novel methods to mitigate data imbalance and algorithmic bias
- Predictive modelling of peptide properties
- AI-driven generative design for novel peptide sequences
- Optimization of peptide-protein interactions through AI
- Case studies of AI applications in real-world peptide drug development
- Comparative analyses of AI models versus traditional methods in peptide research

Submit your idea

Impact

Frontiers in Drug Discovery

Submit your idea

Impact