# Multiscale Graph Neural Networks for Protein Residue Contact Map Prediction

arXiv: https://arxiv.org/abs/2212.02251 · HTML: https://mlsanity.com/paper/2212.02251/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 24 references that are in the map.
- First posted on arXiv 2 Dec 2022.

## Builds on (most cited first, 7 of 7)

- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)
- [Horovod: fast and easy distributed deep learning in TensorFlow](https://mlsanity.com/paper/1802.05799/) (2018)
- [Learning protein sequence embeddings using information from structure](https://mlsanity.com/paper/1902.08661/) (2019)
- [ProteinNet: a standardized data set for machine learning of protein structure](https://mlsanity.com/paper/1902.00249/) (2019)
- [Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model](https://mlsanity.com/paper/1609.00680/) (2016)
- [A Spatial Mapping Algorithm with Applications in Deep Learning-Based Structure Classification](https://mlsanity.com/paper/1802.02532/) (2018)
- [Balsam: Automated Scheduling and Execution of Dynamic, Data-Intensive HPC Workflows](https://mlsanity.com/paper/1909.08704/) (2019)

## Built on by (most cited first, 1 of 1)

- [Graph Representation Learning for Interactive Biomolecule Systems](https://mlsanity.com/paper/2304.02656/) (2023)

## Abstract (arXiv)

Machine learning (ML) is revolutionizing protein structural analysis, including an important subproblem of predicting protein residue contact maps, i.e., which amino-acid residues are in close spatial proximity given the amino-acid sequence of a protein. Despite recent progresses in ML-based protein contact prediction, predicting contacts with a wide range of distances (commonly classified into short-, medium- and long-range contacts) remains a challenge. Here, we propose a multiscale graph neural network (GNN) based approach taking a cue from multiscale physics simulations, in which a standard pipeline involving a recurrent neural network (RNN) is augmented with three GNNs to refine predictive capability for short-, medium- and long-range residue contacts, respectively. Test results on the ProteinNet dataset show improved accuracy for contacts of all ranges using the proposed multiscale RNN+GNN approach over the conventional approach, including the most challenging case of long-range contact prediction.