# Master of Metals2: a graph neural network based architecture for the prediction of zinc binding sites in protein structures

## TL;DR

This paper introduces MoM2, a new tool that uses graph neural networks to accurately predict where zinc ions bind in protein structures.

## Contribution

The novelty lies in using a graph neural network trained solely on spatial coordinates to predict zinc-binding sites without relying on sequence-based methods.

## Key findings

- MoM2 outperformed existing methods with an F1-score of 55.7% and a false discovery rate of 44.1%.
- It successfully identified 18 out of 20 predicted zinc sites in SARS-CoV-2 proteins.
- The tool processes entire proteomes within hours and is accessible via a web interface.

## Abstract

Zinc ions play essential structural and catalytic roles in a wide range of proteins. Accurate prediction of their binding sites is crucial for structural and functional annotation. We present MoM2, a web-accessible tool for predicting zinc-binding sites in protein 3D structures. MoM2 employs a graph neural network trained exclusively on spatial features specifically, Cα and Cβ coordinates eliminating the need for templates or sequence-based heuristics. The tool efficiently processes entire proteomes within hours and demonstrates strong predictive performance. In a benchmark of 412 experimentally determined apo-structures, MoM2 outperformed existing methods, achieving the highest F1-score (55.7%) and the lowest false discovery rate (44.1%). The web interface supports input via structure files, PDB or UniProt IDs, and allows batch processing with customizable thresholds. As an independent validation, MoM2 correctly identified 18 out of 20 predicted zinc sites in SARS-CoV-2 proteins. The tool is freely available at https://mom2.cerm.unifi.it.