Systema: a framework for evaluating genetic perturbation response prediction beyond systematic variation
Nonparametric baselines We design two nonparametric baselines that we refer to as perturbed mean and matching mean. Perturbed…
CRISPR-GPT for agentic automation of gene-editing experiments
Building AI co-pilot harnessing LLM’s reasoning ability CRISPR-GPT supports four major gene-editing modalities and 22 gene-editing experiment tasks…
Morphological map of under- and overexpression of genes in human cells
Mattiazzi Usaj, M. et al. High-content screening for quantitative cell biology. Trends Cell Biol. 26, 598–611 (2016). CAS …
The Platinum Pedigree: a long-read benchmark for genetic variants
Gonzaga-Jauregui, C., Lupski, J. R. & Gibbs, R. A. Human genome sequencing in health and disease. Annu. Rev.…
Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear baselines
The success of large language models in knowledge representation has spawned efforts to apply the foundation model concept…
GeneAgent: self-verification language agent for gene-set analysis using domain databases
Model setting and data collection In this work, we utilized GPT-4 (version 20230613) as the backend model via…