AssayBench is a new gene-ranking benchmark for phenotypic CRISPR screens that shows zero-shot generalist LLMs outperform both biology-specific LLMs and trainable baselines on adjusted nDCG.
Perturbench: Benchmarking machine learning models for cellular perturbation analysis.arXiv preprint arXiv:2408.10609
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
years
2026 7roles
other 1polarities
unclear 1representative citing papers
CellxPert uses inference-time MCMC steering on a multi-omics single-cell foundation model to predict genome-wide transcriptomic responses to gene perturbations and outperforms baselines on cell-type annotation, perturbation prediction, and multi-omic integration benchmarks.
Chem2Gen-Bench is a new benchmark and evaluation framework for measuring alignment between chemical and genetic perturbation responses in matched cell-target contexts using retrieval, similarity, and embedding comparisons.
Analogical reasoning increases LLM solution diversity by 90-173% and novelty rate to over 50%, delivering up to 13-fold gains on biomedical tasks including perturbation prediction and cell communication.
A new benchmarking framework shows virtual cell models overestimate performance on standard tests, drop sharply on unseen contexts and perturbations, and produce inconsistent rankings across metrics.
AblateCell reproduces baselines in three single-cell perturbation repositories with 88.9% success and recovers ground-truth critical components with 93.3% accuracy via closed-loop ablation.
PRiMeFlow applies flow matching in gene expression space with a U-Net velocity field and pretraining-finetuning to model perturbation-induced heterogeneity, showing strong benchmark performance on PerturBench and the ARC Virtual Cell Challenge.
citing papers explorer
-
AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
AssayBench is a new gene-ranking benchmark for phenotypic CRISPR screens that shows zero-shot generalist LLMs outperform both biology-specific LLMs and trainable baselines on adjusted nDCG.
-
CellxPert: Inference-Time MCMC Steering of a Multi-Omics Single-Cell Foundation Model for In-Silico Perturbation
CellxPert uses inference-time MCMC steering on a multi-omics single-cell foundation model to predict genome-wide transcriptomic responses to gene perturbations and outperforms baselines on cell-type annotation, perturbation prediction, and multi-omic integration benchmarks.
-
Chem2Gen-Bench: Benchmarking Chemical-to-Genetic Translation in Perturbation Response Space
Chem2Gen-Bench is a new benchmark and evaluation framework for measuring alignment between chemical and genetic perturbation responses in matched cell-target contexts using retrieval, similarity, and embedding comparisons.
-
Unlocking LLM Creativity in Science through Analogical Reasoning
Analogical reasoning increases LLM solution diversity by 90-173% and novelty rate to over 50%, delivering up to 13-fold gains on biomedical tasks including perturbation prediction and cell communication.
-
Benchmarking virtual cell models for in-the-wild perturbation response
A new benchmarking framework shows virtual cell models overestimate performance on standard tests, drop sharply on unseen contexts and perturbations, and produce inconsistent rankings across metrics.
-
AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories
AblateCell reproduces baselines in three single-cell perturbation repositories with 88.9% success and recovers ground-truth critical components with 93.3% accuracy via closed-loop ablation.
-
PRiMeFlow: Capturing Complex Expression Heterogeneity in Perturbation Response Modelling
PRiMeFlow applies flow matching in gene expression space with a U-Net velocity field and pretraining-finetuning to model perturbation-induced heterogeneity, showing strong benchmark performance on PerturBench and the ARC Virtual Cell Challenge.