Bayes-PD: Exploring a Sequence to Binding Bayesian Neural Network model trained on Phage Display data

2026-01-07

AI Summary

This work addresses the challenges of leveraging phage display data for deep learning–driven protein design, which are hindered by high experimental noise, complex preprocessing requirements, and limited interpretability of results. To overcome these limitations, the study introduces Bayesian neural networks to this domain for the first time, constructing a sequence-to-binding-affinity prediction model that explicitly simulates the phage display experimental process and its associated noise during training. By jointly modeling both experimental and epistemic uncertainties, the approach abandons conventional surrogate metrics and instead validates predictions directly against true binding affinities. This strategy substantially enhances the interpretability of model outputs and the reliability of affinity predictions, offering a more robust deep learning framework for phage display–based protein design.

Technology Category

• Machine Learning: Bayesian Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Phage display is a powerful laboratory technique used to study the interactions between proteins and other molecules, whether other proteins, peptides, DNA or RNA. The under-utilisation of this data in conjunction with deep learning models for protein design may be attributed to; high experimental noise levels; the complex nature of data pre-processing; and difficulty interpreting these experimental results. In this work, we propose a novel approach utilising a Bayesian Neural Network within a training loop, in order to simulate the phage display experiment and its associated noise. Our goal is to investigate how understanding the experimental noise and model uncertainty can enable the reliable application of such models to reliably interpret phage display experiments. We validate our approach using actual binding affinity measurements instead of relying solely on proxy values derived from'held-out'phage display rounds.

Problem

• phage display
• protein design
• experimental noise
• binding affinity
• deep learning

Innovation

• Bayesian Neural Network
• Phage Display
• Protein Design
• Model Uncertainty
• Binding Affinity