PUFFIN: Protein Unit Discovery with Functional Supervision

TL;DR

PUFFIN is a novel graph neural network framework that discovers biologically meaningful protein units by integrating structural data and functional supervision, enhancing interpretability of structure-function relationships.

Contribution

It introduces a data-driven method that jointly learns structural partitioning and functional associations, improving understanding of protein units beyond existing residue-level or purely structural approaches.

Findings

Learned units are structurally coherent and functionally organized.

Units show meaningful correspondence with curated annotations.

PUFFIN provides an interpretable analysis framework for proteins.

Abstract

Proteins carry out biological functions through the coordinated action of groups of residues organized into structural arrangements. These arrangements, which we refer to as protein units, exist at an intermediate scale, being larger than individual residues yet smaller than entire proteins. A deeper understanding of protein function can be achieved by identifying these units and their associations with function. However, existing approaches either focus on residue-level signals, rely on curated annotations, or segment protein structures without incorporating functional information, thereby limiting interpretable analysis of structure-function relationships. We introduce PUFFIN, a data-driven framework for discovering protein units by jointly learning structural partitioning and functional supervision. PUFFIN represents proteins as residue-level structure graphs and applies a graph neural network with a structure-aware pooling mechanism that partitions each protein into multi-residue units, with functional supervision that shapes the partition. We show that the learned units are structurally coherent, exhibit organized associations with molecular function, and show meaningful correspondence with curated InterPro annotations. Together, these results demonstrate that PUFFIN provides an interpretable framework for analyzing structure-function relationships using learned protein units and their statistical function associations. We made our source code available at https://github.com/boun-tabi-lifelu/puffin.