Interpretable Enzyme Function Prediction via Residue-Level Detection

TL;DR

This paper introduces ProtDETR, an attention-based model that predicts enzyme functions by detecting local residue regions, offering improved accuracy and interpretability over previous global representation methods.

Contribution

The novel ProtDETR framework casts enzyme function prediction as a detection task, utilizing residue-level features and functional queries for enhanced interpretability and performance.

Findings

ProtDETR significantly outperforms existing methods.

It provides interpretable detection of local residue regions.

The model offers a new perspective on enzyme function prediction.

Abstract

Predicting multiple functions labeled with Enzyme Commission (EC) numbers from the enzyme sequence is of great significance but remains a challenge due to its sparse multi-label classification nature, i.e., each enzyme is typically associated with only a few labels out of more than 6000 possible EC numbers. However, existing machine learning algorithms generally learn a fixed global representation for each enzyme to classify all functions, thereby they lack interpretability and the fine-grained information of some function-specific local residue fragments may be overwhelmed. Here we present an attention-based framework, namely ProtDETR (Protein Detection Transformer), by casting enzyme function prediction as a detection problem. It uses a set of learnable functional queries to adaptatively extract different local representations from the sequence of residue-level features for predicting different EC numbers. ProtDETR not only significantly outperforms existing deep learning-based enzyme function prediction methods, but also provides a new interpretable perspective on automatically detecting different local regions for identifying different functions through cross-attentions between queries and residue-level features. Code is available at https://github.com/yangzhao1230/ProtDETR.