eSPred: Explainable scRNA-seq Prediction via Customized Foundation Models and Pathway-Aware Fine-tuning
Sun, L.; Yang, Q.; Zhang, J.; Guo, W.; Lin, L.
Show abstract
Single-cell RNA sequencing (scRNA-seq) has been widely used for studying cellular heterogeneity, but its use for subject-level prediction and clinical applications is still limited. We introduce eSPred, a customized foundation model designed for predictive analysis of scRNA-seq. It integrates cell-type information through a grouping strategy during pre-training and leverages pathway information to guide network flow during fine-tuning. Across multiple datasets, eSPred improves prediction accuracy and highlights pathways linked to disease mechanisms. These results suggest that eSPred can help bridge the gap between single-cell data and subject-level clinical insights, supporting more precise diagnosis and better-informed treatment decisions.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Non-linear Archetypal Analysis of Single-cell RNA-seq Data by Deep Autoencoders 96%
- Highly Accurate Cancer Phenotype Prediction with AKLIMATE, a Stacked Kernel Learner Integrating Multimodal Genomic Data and Pathway Knowledge 96%
- Building, Benchmarking, and Exploring Perturbative Maps of Transcriptional and Morphological Data 95%
Similar papers in this journal
- CellFM: a large-scale foundation model pre-trained on transcriptomics of 100 million human cells 97%
- FastCCC: A permutation-free framework for scalable, robust, and reference-based cell-cell communication analysis in single cell transcriptomics studies 97%
- scSemiProfiler: Advancing Large-scale Single-cell Studiesthrough Semi-profiling with Deep Generative Models andActive Learning 96%
Similar papers in this journal
- SHEST: Single-cell-level artificial intelligence from haematoxylin and eosin morphology for cell type prediction and spatial transcriptomics reconstruction 96%
- Graph Contrastive Learning of Subcellular-resolution Spatial Transcriptomics Improves Cell Type Annotation and Reveals Critical Molecular Pathways 95%
- scValue: value-based subsampling of large-scale single-cell transcriptomic data for machine and deep learning tasks 95%
Similar papers in this journal
- Enhancement of network architecture alignment in comparative single-cell studies 97%
- Integrating temporal single-cell gene expression modalities for trajectory inference and disease prediction 97%
- Knowledge-primed neural networks enable biologically interpretable deep learning on single-cell sequencing data 96%
Similar papers in this journal
- scELMo: Embeddings from Language Models are Good Learners for Single-cell Data Analysis 96%
- Bi-level Graph Learning Unveils Prognosis-Relevant Tumor Microenvironment Patterns in Breast Multiplexed Digital Pathology 96%
- scTenifoldNet: a machine learning workflow for constructing and comparing transcriptome-wide gene regulatory networks from single-cell data 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.