paper✓ VerifiedVC0144

Simple controls exceed best deep learning algorithms and reveal foundation model effectiveness for predicting genetic perturbations.

Wong, Hill, Moccia (Bioinformatics 2025): a 'CRISPR-informed mean' (training-set perturbed-cell mean, with the target gene set by prior knowledge of CRISPRi/CRISPRa) is reported to beat fine-tuned scGPT, GEARS and simple neural baselines on Adamson, Norman and Replogle K562 Essential; also provides a corrected Adamson dataset.

Authors / organisation: Wong DR, Hill AS, Moccia R.
Venue: Bioinformatics
Date: 2025-06-01
Type: paper
Year: 2025
DOI: 10.1093/bioinformatics/btaf317
PMID: 40407144
Verification: Europe PMC (metadata, abstract) + Europe PMC full-text XML read 2026-10-16 (PMC12202205)

Benchmark & validation Critique Perturbation

Cited by GlioState topics

Linear baselines and systematic variation in perturbation prediction: what 'a strong baseline' means, and where the papers disagree (Validation)

Entities mentioned

Open in the searchable library → · JSON

Simple controls exceed best deep learning algorithms and reveal foundation model effectiveness for predicting genetic perturbations.

Cited by GlioState topics

Entities mentioned

Related papers (shared tags)

A comparison of computational methods for expression forecasting.

Deep learning perturbation models can outperform baselines on calibrated metrics.

Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear baselines.

Benchmarking foundation cell models for post-perturbation RNA-seq prediction.

Zero-shot evaluation reveals limitations of single-cell foundation models.

Biological domain shift and statistical nesting concerns in generative AI-based spatial tumor growth prediction for pediatric diffuse midline glioma.