AlphaGenome Atlas: in silico mutagenesis of the entire human genome improves prioritization and interpretation of non-coding variants
- 1Google DeepMind
Abstract
A major challenge in genomics is deciphering the functional consequences of non-coding genetic variation. Here we present AlphaGenome Atlas, a comprehensive resource that enables the joint interpretation and prioritization of variant effects across the entire human genome. Using AlphaGenome, we predicted the regulatory effects across thousands of molecular phenotypes for every possible human single nucleotide variant and many observed indels. These predictions were then used to derive a unified and interpretable AlphaGenome Variant Impact (AVI) score and to map cis-regulatory motifs across the genome. AVI achieved state-of-the-art performance across diverse benchmarks with improved prioritization of deleterious non-coding variants. Application of the combined Atlas resource helped solve an epileptic encephalopathy rare disease case, increased the statistical power to detect rare non-coding variants driving population-level phenotypes, and enhanced the mechanistic interpretation of these variants. Thus, AlphaGenome Atlas improves the prioritization and molecular interpretation of non-coding variants with genetic and clinical significance.
Related
- Utilizing a Variant Prioritization Approach to Explore Genetic Variants in Cervical Cancer Cases among Malawian Women
- Hyperbolic heterogeneous graph learning for adverse drug reaction prediction, candidate prioritization, and pathway-based interpretation in pharmacovigilance
- Mapping intronic mutational hotspots by in silico mutagenesis enables single antisense oligonucleotide correction of multiple variants
- A population-based resource for the prioritization of rare variants of unknown significance in clinical genomics
- Genetic and structural interpretation of NLRP1 FIIND domain variants in glioma in an Indian cohort: a pilot study
BibTeX
@misc{cheng2026alphagenome,
title = {{AlphaGenome Atlas: in silico mutagenesis of the entire human genome improves prioritization and interpretation of non-coding variants}},
author = {J. Cheng and K. R. Taylor and L. Nicolaisen and J. Pan and C. Bycroft and M. Perino and T. Ward and G. Hawkes and L. E. Covill and M. Weilert and R. W. Thomas and N. Latysheva and M. J. Hirschmann and X. D. Chen and R. N. Beaumont and V. K. Chundru and M. N. Weedon and S. Bourdareau and H. Chu and D. Hariharan and T. Kagohara and L. Tenorio and Y. Ushigome and C. A. Shearer and B. Ikica and A. Fang and M. Naciri and V. Johnston and R. Green and L. H. Wong and V. Dutordoir and A. Mottram and A. Gayoso and E. Arvaniti and G. Novati and H. L. Rehm and F. Chen and C. A. Lareau and C. F. Wright and A. O'Donnell-Luria and J. Zeitlinger and P. Kohli and Z. Avsec},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.16.26363192},
url = {https://www.medrxiv.org/content/10.64898/2026.09.16.26363192v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - AlphaGenome Atlas: in silico mutagenesis of the entire human genome improves prioritization and interpretation of non-coding variants
AU - J. Cheng
AU - K. R. Taylor
AU - L. Nicolaisen
AU - J. Pan
AU - C. Bycroft
AU - M. Perino
AU - T. Ward
AU - G. Hawkes
AU - L. E. Covill
AU - M. Weilert
AU - R. W. Thomas
AU - N. Latysheva
AU - M. J. Hirschmann
AU - X. D. Chen
AU - R. N. Beaumont
AU - V. K. Chundru
AU - M. N. Weedon
AU - S. Bourdareau
AU - H. Chu
AU - D. Hariharan
AU - T. Kagohara
AU - L. Tenorio
AU - Y. Ushigome
AU - C. A. Shearer
AU - B. Ikica
AU - A. Fang
AU - M. Naciri
AU - V. Johnston
AU - R. Green
AU - L. H. Wong
AU - V. Dutordoir
AU - A. Mottram
AU - A. Gayoso
AU - E. Arvaniti
AU - G. Novati
AU - H. L. Rehm
AU - F. Chen
AU - C. A. Lareau
AU - C. F. Wright
AU - A. O'Donnell-Luria
AU - J. Zeitlinger
AU - P. Kohli
AU - Z. Avsec
PY - 2026
DA - 2026/09/16
PB - medRxiv
DO - 10.64898/2026.09.16.26363192
UR - https://www.medrxiv.org/content/10.64898/2026.09.16.26363192v1
AB - A major challenge in genomics is deciphering the functional consequences of non-coding genetic variation. Here we present AlphaGenome Atlas, a comprehensive resource that enables the joint interpretation and prioritization of variant effects across the entire human genome. Using AlphaGenome, we predicted the regulatory effects across thousands of molecular phenotypes for every possible human single nucleotide variant and many observed indels. These predictions were then used to derive a unified and interpretable AlphaGenome Variant Impact (AVI) score and to map cis-regulatory motifs across the genome. AVI achieved state-of-the-art performance across diverse benchmarks with improved prioritization of deleterious non-coding variants. Application of the combined Atlas resource helped solve an epileptic encephalopathy rare disease case, increased the statistical power to detect rare non-coding variants driving population-level phenotypes, and enhanced the mechanistic interpretation of these variants. Thus, AlphaGenome Atlas improves the prioritization and molecular interpretation of non-coding variants with genetic and clinical significance.
ER -