Injecting Hierarchical Biological Priors into Graph Neural Networks for Flow Cytometry Prediction

TL;DR

This paper introduces a hierarchical prior knowledge injection method into graph neural networks to improve cell classification accuracy in flow cytometry data by leveraging biological class hierarchies.

Contribution

It presents a novel hierarchical plug-in approach for GNNs that encodes biological class relationships, enhancing prediction performance on single-cell flow cytometry data.

Findings

Hierarchical priors significantly improve GNN performance.

The method outperforms baseline models across multiple metrics.

Structured biological constraints aid generalization in complex tasks.

Abstract

In the complex landscape of hematologic samples such as peripheral blood or bone marrow derived from flow cytometry (FC) data, cell-level prediction presents profound challenges. This work explores injecting hierarchical prior knowledge into graph neural networks (GNNs) for single-cell multi-class classification of tabular cellular data. By representing the data as graphs and encoding hierarchical relationships between classes, we propose our hierarchical plug-in method to be applied to several GNN models, namely, FCHC-GNN, and effectively designed to capture neighborhood information crucial for single-cell FC domain. Extensive experiments on our cohort of 19 distinct patients, demonstrate that incorporating hierarchical biological constraints boosts performance significantly across multiple metrics compared to baseline GNNs without such priors. The proposed approach highlights the importance of structured inductive biases for gaining improved generalization in complex biological prediction tasks.