ArticleBMC genomics2025
Benchmarking foundation cell models for post-perturbation RNA-seq prediction.
Article in BMC genomics, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 23 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
23 citing papers in PubMed.
- Deep learning perturbation models can outperform baselines on calibrated metrics.Nature biotechnology · 2026Article
- Review
- A transcription factor regulatory atlas for activity inference and perturbation prediction.Nucleic acids research · 2026Article
- Benchmarking biomedical foundation models.Nature methods · 2026Review
- Evaluating the learnability of single-cell large language models on multiple tasks.BMC genomics · 2026Article
- Generalist biological artificial intelligence in modeling the language of life.Nature biotechnology · 2026Review
- Systema: a framework for evaluating genetic perturbation response prediction beyond systematic variation.Nature biotechnology · 2026Article
- TxPert: using multiple knowledge graphs for prediction of transcriptomic perturbation effects.Nature biotechnology · 2026Article
- A transcriptomics-native foundation model for universal cell representation and virtual cell synthesis.bioRxiv : the preprint server for biology · 2026Article
- Representation learning of single-cell RNA-seq data.RNA (New York, N.Y.) · 2026Review
- Counting cells can accurately predict small-molecule bioactivity benchmarks.Nature communications · 2026Article
- AI-guided ethnopharmacology for cardiovascular drug discovery: from biomedical data to experimental validation.Frontiers in pharmacology · 2026Review
- Predicting the unseen: A diffusion-based debiasing framework for transcriptional response prediction at single-cell resolution.Proceedings of the National Academy of Sciences of the United States of America · 2025Article
- A comparison of computational methods for expression forecasting.Genome biology · 2025Article
- Adaptive resampling for improved machine learning in imbalanced single-cell datasets.bioRxiv : the preprint server for biology · 2025Article
- Overcoming barriers to the wide adoption of single-cell large language models in biomedical research.Nature biotechnology · 2025Article
- The cell as a token: high-dimensional geometry in language models and cell embeddings.Bioinformatics (Oxford, England) · 2025Review
- Methods and applications of in vivo CRISPR screening.Nature reviews. Genetics · 2025Review
- Predicting the unseen: a diffusion-based debiasing framework for transcriptional response prediction at single-cell resolution.bioRxiv : the preprint server for biology · 2025Article
- Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear baselines.Nature methods · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Accurately predicting cellular responses to perturbations is essential for understanding cell behaviour in both healthy and diseased states. While perturbation data is ideal for building such predictive models, its availability is considerably lower than baseline (non-perturbed) cellular data. To address this limitation, several foundation cell models have been developed using large-scale single-cell gene expression data. These models are fine-tuned after pre-training for specific tasks, such as predicting post-perturbation gene expression profiles, and are considered state-of-the-art for these problems. However, proper benchmarking of these models remains an unsolved challenge. In this study, we benchmarked two recently published foundation models, scGPT and scFoundation, against baseline models. Surprisingly, we found that even the simplest baseline model-taking the mean of training examples-outperformed scGPT and scFoundation. Furthermore, basic machine learning models that incorporate biologically meaningful features outperformed scGPT by a large margin. Additionally, we identified that the current Perturb-Seq benchmark datasets exhibit low perturbation-specific variance, making them suboptimal for evaluating such models. Our results highlight important limitations in current benchmarking approaches and provide insights into more effectively evaluating post-perturbation gene expression prediction models.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.