# Multi-level Interaction Modeling for Protein Mutational Effect Prediction

arXiv: https://arxiv.org/abs/2405.17802 · HTML: https://mlsanity.com/paper/2405.17802/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 69 references that are in the map.
- First posted on arXiv 28 May 2024.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Neural Spline Flows](https://mlsanity.com/paper/1906.04032/) (2019)
- [Normalizing Flows on Tori and Spheres](https://mlsanity.com/paper/2002.02428/) (2020)
- [Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking](https://mlsanity.com/paper/2111.07786/) (2021)
- [End-to-End Learning on 3D Protein Structure for Interface Prediction](https://mlsanity.com/paper/1807.01297/) (2018)
- [Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Prediction](https://mlsanity.com/paper/2105.06709/) (2021)
- [DiffDock-PP: Rigid Protein-Protein Docking with Diffusion Models](https://mlsanity.com/paper/2304.03889/) (2023)
- [DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing](https://mlsanity.com/paper/2306.01794/) (2023)
- [MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding](https://mlsanity.com/paper/2402.14391/) (2024)
- [Pre-training of Graph Neural Network for Modeling Effects of Mutations on Protein-Protein Binding Affinity](https://mlsanity.com/paper/2008.12473/) (2020)
- [Learning to design protein-protein interactions with enhanced generalization](https://mlsanity.com/paper/2310.18515/) (2023)
- [SemiGNN-PPI: Self-Ensembling Multi-Graph Neural Network for Efficient and Generalizable Protein-Protein Interaction Prediction](https://mlsanity.com/paper/2305.08316/) (2023)
- [ProFSA: Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment](https://mlsanity.com/paper/2310.07229/) (2023)
- [Predicting mutational effects on protein-protein binding via a side-chain diffusion probabilistic model](https://mlsanity.com/paper/2310.19849/) (2023)
- [Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Prediction](https://mlsanity.com/paper/2401.08986/) (2024)

## Built on by (most cited first, 5 of 5)

- [Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions](https://mlsanity.com/paper/2410.09543/) (2024)
- [Predicting mutational effects on protein binding from folding energy](https://mlsanity.com/paper/2507.05502/) (2025)
- [EnerBridge-DPO: Energy-Guided Protein Inverse Folding with Markov Bridges and Direct Preference Optimization](https://mlsanity.com/paper/2506.09496/) (2025)
- [A Simple yet Effective DDG Predictor is An Unsupervised Antibody Optimizer and Explainer](https://mlsanity.com/paper/2502.06913/) (2025)
- [Energy-Based Models for Predicting Mutational Effects on Proteins](https://mlsanity.com/paper/2508.10629/) (2025)

## Abstract (arXiv)

Protein-protein interactions are central mediators in many biological processes. Accurately predicting the effects of mutations on interactions is crucial for guiding the modulation of these interactions, thereby playing a significant role in therapeutic development and drug discovery. Mutations generally affect interactions hierarchically across three levels: mutated residues exhibit different sidechain conformations, which lead to changes in the backbone conformation, eventually affecting the binding affinity between proteins. However, existing methods typically focus only on sidechain-level interaction modeling, resulting in suboptimal predictions. In this work, we propose a self-supervised multi-level pre-training framework, ProMIM, to fully capture all three levels of interactions with well-designed pretraining objectives. Experiments show ProMIM outperforms all the baselines on the standard benchmark, especially on mutations where significant changes in backbone conformations may occur. In addition, leading results from zero-shot evaluations for SARS-CoV-2 mutational effect prediction and antibody optimization underscore the potential of ProMIM as a powerful next-generation tool for developing novel therapeutic approaches and new drugs.