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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mojarrad, Fatemeh Nassajian, Bini, Lorenzo, Matthes, Thomas, Marchand-Maillet, Stéphane
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910544441638912
author Mojarrad, Fatemeh Nassajian
Bini, Lorenzo
Matthes, Thomas
Marchand-Maillet, Stéphane
author_facet Mojarrad, Fatemeh Nassajian
Bini, Lorenzo
Matthes, Thomas
Marchand-Maillet, Stéphane
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18507
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Injecting Hierarchical Biological Priors into Graph Neural Networks for Flow Cytometry Prediction
Mojarrad, Fatemeh Nassajian
Bini, Lorenzo
Matthes, Thomas
Marchand-Maillet, Stéphane
Machine Learning
Artificial Intelligence
Quantitative Methods
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.
title Injecting Hierarchical Biological Priors into Graph Neural Networks for Flow Cytometry Prediction
topic Machine Learning
Artificial Intelligence
Quantitative Methods
url https://arxiv.org/abs/2405.18507