PRIMRose: Insights into the Per-Residue Energy Metrics of Proteins with Double InDel Mutations using Deep Learning

2025-12-06

AI Summary

This study addresses the challenge of predicting the structural and functional impacts of double amino acid insertion/deletion (InDel) mutations. We propose the first residue-level local energy perturbation prediction method, leveraging Rosetta-computed multidimensional energy features. A convolutional neural network is trained and validated on a large-scale, multi-source dataset comprising nearly 300,000 double InDel variants. The model achieves high accuracy in predicting multiple energy-based metrics—including van der Waals, solvation, and hydrogen-bonding energies—and identifies solvent accessibility and secondary structure context as key determinants of mutational tolerance. Furthermore, it successfully pinpoints residue-level mutational hotspots with elevated tolerance. This work introduces the first interpretable, residue-resolution energy analysis tool for double InDels, enabling mechanistic insights into pathogenic variants and facilitating rational protein engineering design.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Adversarial Attacks & Robustness
• Natural Language Processing: Safety and Robustness

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Understanding how protein mutations affect protein structure is essential for advancements in computational biology and bioinformatics. We introduce PRIMRose, a novel approach that predicts energy values for each residue given a mutated protein sequence. Unlike previous models that assess global energy shifts, our method analyzes the localized energetic impact of double amino acid insertions or deletions (InDels) at the individual residue level, enabling residue-specific insights into structural and functional disruption. We implement a Convolutional Neural Network architecture to predict the energy changes of each residue in a protein mutation. We train our model on datasets constructed from nine proteins, grouped into three categories: one set with exhaustive double InDel mutations, another with approximately 145k randomly sampled double InDel mutations, and a third with approximately 80k randomly sampled double InDel mutations. Our model achieves high predictive accuracy across a range of energy metrics as calculated by the Rosetta molecular modeling suite and reveals localized patterns that influence model performance, such as solvent accessibility and secondary structure context. This per-residue analysis offers new insights into the mutational tolerance of specific regions within proteins and provides higher interpretable and biologically meaningful predictions of InDels' effects.

Problem

• Predicts per-residue energy changes from double InDel mutations
• Analyzes localized energetic impacts at individual amino acid level
• Provides interpretable insights into mutational tolerance and structural disruption

Innovation

• Deep learning predicts per-residue energy changes
• CNN analyzes double amino acid insertions or deletions
• Model trained on datasets with exhaustive and random mutations