Compact autoencoder improves heart disease and cell type classification from gene data
scHFBiMamba: a bidirectional Mamba autoencoder for cardiac disease-state classification from single-nucleus RNA-seq data
Machine LearningArtificial Intelligence
Summary
Classifying heart disease conditions and cell types using gene data is challenging because of the large amount of information and complexity involved. The authors created a new compact tool called scHFBiMamba that makes this classification more accurate and requires far fewer parameters than previous methods. Their approach also helps identify important genes related to heart failure, making it easier to understand the biology behind the disease. This method was tested on thousands of heart cell gene samples and showed improved performance over similar tools.
What this means in practice
- •For bioinformatics teams: Classify heart tissue samples by disease state and cell type more accurately and efficiently using compact gene expression models.
- •For pharmaceutical data analysts: Identify disease-related genes from compact models to assist in hypothesis generation for drug target discovery in cardiac conditions.
Authors
Ugo Lomoio, Pietro Hiram Guzzi, Pierangelo Veltri
Abstract
To evaluate whether a compact bidirectional state-space autoencoder improves joint classification of species, cell type, and disease state from single-nucleus RNA-sequencing profiles in heart failure (HF), while yielding interpretable gene attributions. Building on the dense denoising autoencoder (DAE) and MLP framework of Ruz Jurado et al., we developed scHFBiMamba, combining a bidirectional Mamba autoencoder (BiMambaAE) with an MLP head. BiMambaAE maps 16,545-gene profiles to 350-dimensional latent representations using 13.2M parameters, about 14.6-fold fewer than the dense DAE (192.9M). We compared six encoder-classifier configurations on 38,275 held-out cardiac nuclei using McNemar tests with Benjamini-Hochberg correction, and assessed nine classifiers on frozen representations. Biological relevance was evaluated by comparing SHAP-derived differentially explained genes with differentially expressed genes against curated HF-related Gene Ontology keywords. BiMambaAE+MLP achieved the highest aggregate F1: pooled macro-F1 across 13 outputs was 0.966 versus 0.957 for DAE+MLP, and the mean category macro-F1 was 0.977 versus 0.970. It significantly improved cell-type and disease-state accuracy (adjusted p=7.1e-3 and p=4.8e-6, respectively), with species F1 of 1.000. SHAP-derived differentially explained genes achieved a pathway-enrichment benchmark F1 of 0.105 versus 0.053 for differentially expressed genes. Compact bidirectional state-space autoencoders can outperform substantially larger dense autoencoders for joint cardiac transcriptomic classification while reducing parameters. scHFBiMamba enables accurate multi-task prediction and hypothesis-generating gene-level interpretation. Code: https://github.com/UgoLomoio/scHFBiMamba.