# PersGNN: Applying Topological Data Analysis and Geometric Deep Learning to Structure-Based Protein Function Prediction

arXiv: https://arxiv.org/abs/2010.16027 · HTML: https://mlsanity.com/paper/2010.16027/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [Topological Graph Neural Networks](https://mlsanity.com/paper/2102.07835/) (2021)
- [GRIL: A 2-parameter Persistence Based Vectorization for Machine Learning](https://mlsanity.com/paper/2304.04970/) (2023)
- [Boosting Graph Pooling with Persistent Homology](https://mlsanity.com/paper/2402.16346/) (2024)
- [Encoding protein dynamic information in graph representation for functional residue identification](https://mlsanity.com/paper/2112.12033/) (2021)
- [A Pipeline for Data-Driven Learning of Topological Features with Applications to Protein Stability Prediction](https://mlsanity.com/paper/2408.04847/) (2024)
- [TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration](https://mlsanity.com/paper/2510.05102/) (2025)
- [Geometric Self-Supervised Pretraining on 3D Protein Structures using Subgraphs](https://mlsanity.com/paper/2406.14142/) (2024)

## Abstract (arXiv)

Understanding protein structure-function relationships is a key challenge in computational biology, with applications across the biotechnology and pharmaceutical industries. While it is known that protein structure directly impacts protein function, many functional prediction tasks use only protein sequence. In this work, we isolate protein structure to make functional annotations for proteins in the Protein Data Bank in order to study the expressiveness of different structure-based prediction schemes. We present PersGNN - an end-to-end trainable deep learning model that combines graph representation learning with topological data analysis to capture a complex set of both local and global structural features. While variations of these techniques have been successfully applied to proteins before, we demonstrate that our hybridized approach, PersGNN, outperforms either method on its own as well as a baseline neural network that learns from the same information. PersGNN achieves a 9.3% boost in area under the precision recall curve (AUPR) compared to the best individual model, as well as high F1 scores across different gene ontology categories, indicating the transferability of this approach.