---
title: "Equivariant Graph Neural Networks for Protein Interaction Modeling and Structure-Aware Molecular Design"
authors:
  - "Animesh Animesh"
doi: "10.24963/ijcai.2026/938"
url: "https://ijcai.org/proceedings/2026/938"
pdf: "https://ijcai.org/proceedings/2026/0938.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "8319-8320"
track: "Doctoral Consortium"
keywords:
  - "Machine Learning: Attention models"
  - "Multidisciplinary Topics and Applications: Life sciences"
  - "Machine Learning: Geometric learning"
---

# Equivariant Graph Neural Networks for Protein Interaction Modeling and Structure-Aware Molecular Design

Animesh Animesh

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 8319-8320. DOI: [10.24963/ijcai.2026/938](https://doi.org/10.24963/ijcai.2026/938)

## Abstract

Equivariant graph neural networks (EGNNs) have revolutionized molecular property prediction by encoding 3D structures while preserving physical symmetry. However, existing EGNNs struggle to capture fine-grained geometric features needed for tasks like understanding protein interactions, and designing molecules that modulate them are central challenges in computational drug discovery.
This thesis develops a progressive framework based on equivariant graph neural networks (EqGNNs) that respects the geometric symmetries of molecular structures.
Our contributions progress along two axes: from discriminative to generative and from basic representations to physics-informed, language-conditioned generation. In this study, we propose novel methods for both discriminative (E(Q)AGNN-PPIS, GDEGAN) and generative tasks (PhysFlow). Together, these advance symmetry-aware geometric deep learning for drug discovery.