Deep Learning Approaches for Blood Disease Diagnosis Across Hematopoietic Lineages

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bo, Gabriel, Gu, Justin, Sun, Christopher
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916662759915520
author Bo, Gabriel
Gu, Justin
Sun, Christopher
author_facet Bo, Gabriel
Gu, Justin
Sun, Christopher
contents We present a foundation modeling framework that leverages deep learning to uncover latent genetic signatures across the hematopoietic hierarchy. Our approach trains a fully connected autoencoder on multipotent progenitor cells, reducing over 20,000 gene features to a 256-dimensional latent space that captures predictive information for both progenitor and downstream differentiated cells such as monocytes and lymphocytes. We validate the quality of these embeddings by training feed-forward, transformer, and graph convolutional architectures for blood disease diagnosis tasks. We also explore zero-shot prediction using a progenitor disease state classification model to classify downstream cell conditions. Our models achieve greater than 95% accuracy for multi-class classification, and in the zero-shot setting, we achieve greater than 0.7 F1-score on the binary classification task. Future work should improve embeddings further to increase robustness on lymphocyte classification specifically.
format Preprint
id arxiv_https___arxiv_org_abs_2503_20049
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Learning Approaches for Blood Disease Diagnosis Across Hematopoietic Lineages
Bo, Gabriel
Gu, Justin
Sun, Christopher
Machine Learning
Quantitative Methods
We present a foundation modeling framework that leverages deep learning to uncover latent genetic signatures across the hematopoietic hierarchy. Our approach trains a fully connected autoencoder on multipotent progenitor cells, reducing over 20,000 gene features to a 256-dimensional latent space that captures predictive information for both progenitor and downstream differentiated cells such as monocytes and lymphocytes. We validate the quality of these embeddings by training feed-forward, transformer, and graph convolutional architectures for blood disease diagnosis tasks. We also explore zero-shot prediction using a progenitor disease state classification model to classify downstream cell conditions. Our models achieve greater than 95% accuracy for multi-class classification, and in the zero-shot setting, we achieve greater than 0.7 F1-score on the binary classification task. Future work should improve embeddings further to increase robustness on lymphocyte classification specifically.
title Deep Learning Approaches for Blood Disease Diagnosis Across Hematopoietic Lineages
topic Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2503.20049