Empirical Evaluation of Single-Cell Foundation Models for Predicting Cancer Outcomes
Elmarakeby, H.; Roman, A.; Johri, S.; Van Allen, E.
Show abstract
AbstractFoundation models pretrained on large-scale single-cell RNA sequencing data present a promising opportunity to advance translational cancer research. However, their utility in clinically relevant, patient-level applications of single-cell analysis remains underexplored. Here, we systematically evaluated nine emerging single-cell foundation models (scFMs) and three alternative baseline approaches across six cancer-specific tasks, ranging from subtype classification to treatment response prediction. We assessed model performance under zero- shot, continual training, and fine-tuning conditions, conducting 1,170 supervised and 130 unsupervised experiments. Our findings revealed that while current scFMs excel in certain analysis tasks, such as tumor microenvironment cell annotation, they had limited advantages in predicting clinical and biological outcomes of cancer patients compared to simpler baseline models. These insights highlight the critical role of evaluation on biologically and clinically relevant tasks in the responsible and impactful application of scFMs in precision oncology. They also emphasize the necessity of further methodological innovation and expanded cancer single-cell cohorts for the future development of scFMs.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Generalizing AI-driven Assessment of Immunohistochemistry across Immunostains and Cancer Types: A Universal Immunohistochemistry Analyzer 95%
- Deep learning inference of cell type-specific gene expression from breast tumor histopathology 94%
- Predicting the Tumor Microenvironment Composition and Immunotherapy Response in Non-Small Cell Lung Cancer from Digital Histopathology Images 94%
Similar papers in this journal
- Deep transfer learning for reducing health care disparities arising from biomedical data inequality 95%
- Features fusion or not: harnessing multiple pathological foundation models using Meta-Encoder for downstream tasks fine-tuning 95%
- Learning tissue representation by identification of persistent local patterns in spatial omics data 95%
Similar papers in this journal
- STPath: A Generative Foundation Model for Integrating Spatial Transcriptomics and Whole Slide Images 95%
- Biologically-informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post-treatment glioblastoma 94%
- High-Sensitivity Pan-Cancer AI Assessment of Lymph Node Metastasis via Uncertainty Quantification 94%
Similar papers in this journal
- Obtaining Spatially Resolved Tumor Purity Maps Using Deep Multiple Instance Learning In A Pan-cancer Study 95%
- Bi-level Graph Learning Unveils Prognosis-Relevant Tumor Microenvironment Patterns in Breast Multiplexed Digital Pathology 94%
- Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference 93%
Similar papers in this journal
- An in-depth comparison of linear and non-linear joint embedding methods for bulk and single-cell multi-omics 96%
- SHEST: Single-cell-level artificial intelligence from haematoxylin and eosin morphology for cell type prediction and spatial transcriptomics reconstruction 96%
- Benchmarking computational methods for multi-omics biomarker discovery in cancer 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.