pipette
ESEspañol

AlphaGenome 2 predicts regulatory activity and variant effects across cell states

A. Gayoso, A. Mottram, A. Karollus, G. Novati, P. Drotar, J. Reid, L. Meng-Papaxanthos, A. Kosiorek, E. Arvaniti, V. Dutordoir, S. De, T. Ward, L. Hong Wong, M. Perino, K. Taylor, J. Cheng, N. Latysheva, J. Pan, D. Hariharan, C. Bycroft, L. Nicolaisen, D. Hassabis, P. Kohli, Z. Avsec

Preprint

In the authors' words

Most genetic variants associated with human traits and diseases lie in non-coding DNA, where they can alter gene regulation in specific cell types and states. Single-cell atlases chart these states across tissues and development, but rarely profile enough donors to associate variants with expression directly. Deep learning models could bridge this gap by predicting variant effects from DNA sequence, yet they poorly distinguish related cell states and require fine-tuning for new datasets. Here we present AlphaGenome 2 (AG2), which substantially advances cell-type-specific prediction of regulatory activity and variant effects for gene expression and chromatin accessibility. Trained on organism-wide human and mouse single-cell atlases and bulk functional genomics data, AG2 takes as input a 1-Mb DNA sequence and a condition specifying a target tissue, cell type, or cell state. Conditioning enables AG2 to impute unmeasured epigenomic tracks and predict multimodal variant effects across cell types. Inferring this condition directly from gene expression extends AG2 to unseen datasets and cell states without fine-tuning. AG2 outperforms fine-tuned AlphaGenome 1 and specialized models trained on target datasets, doubling recall of causal single-cell eQTLs at 90% precision. AG2 also achieves state-of-the-art enhancer-gene linking and can pinpoint causal variants at complex trait loci. Across hundreds of human cell types, we generated an atlas of enhancer-gene links and scores for 7 million common variants. As single-cell profiling expands across development, tissues, and disease cohorts, AG2 provides a blueprint for turning observational atlases into variant effect maps.

Main resultThe abstract does not state a limitation.

Appeared: Wednesday, November 18. bioRxiv. Preprint, not yet peer-reviewed.

DOI: 10.64898/2026.11.11.765857