Predicting expression-altering promoter mutations with deep learning
Only a minority of patients with rare genetic diseases are presently diagnosed by exome sequencing, suggesting that additional unrecognized pathogenic variants may reside in noncoding sequence. In this work, we describe PromoterAI, a deep neural network that accurately identifies noncoding promoter variants that dysregulate gene expression. We show that promoter variants with predicted expression-altering consequences produce outlier expression at both the RNA and protein levels in thousands of individuals and that these variants experience strong negative selection in human populations. We observed that clinically relevant genes in patients with rare diseases are enriched for such variants and validated their functional impact through reporter assays. Our estimates suggest that promoter variation accounts for 6% of the genetic burden associated with rare diseases.
Authors
- Evin M. Padhi (ORCID: https://orcid.org/0000-0003-2578-2435)
- Gherman Novakovsky (ORCID: https://orcid.org/0000-0002-7089-5941)
- Damian Smedley (ORCID: https://orcid.org/0000-0002-5836-9850)
- Nicole M. Ferraro (ORCID: https://orcid.org/0000-0003-4291-193X)
- Sofia Kyriazopoulou Panagiotopoulou
- Heidi L. Rehm (ORCID: https://orcid.org/0000-0002-6025-0015)
- Johann S. Hawe (ORCID: https://orcid.org/0000-0003-3890-303X)
- Kyle Kai‐How Farh (ORCID: https://orcid.org/0000-0001-6947-8537)
- Heather Cavanagh (ORCID: https://orcid.org/0000-0001-5587-1397)
- Grace Png (ORCID: https://orcid.org/0000-0003-3962-7436)
- Irfahan Kassam (ORCID: https://orcid.org/0000-0002-6150-5614)
- Fan Cao (ORCID: https://orcid.org/0000-0003-2355-7277)
- Stephen B. Montgomery (ORCID: https://orcid.org/0000-0002-5200-3903)
- Pierrick Wainschtein
- Laksshman Sundaram (ORCID: https://orcid.org/0000-0002-8953-3940)
- Abhimanyu Banerjee (ORCID: https://orcid.org/0000-0003-3047-6803)
- Jeremy Schwartzentruber (ORCID: https://orcid.org/0000-0002-6183-2092)
- Terena James
- Kishore Jaganathan (ORCID: https://orcid.org/0000-0002-7829-4892)
- Stephan Sanders (ORCID: https://orcid.org/0000-0001-9112-5148)
- Jeremy F. McRae (ORCID: https://orcid.org/0000-0003-3411-9248)
- Jacob C. Ulirsch (ORCID: https://orcid.org/0000-0002-7947-0827)
- Ashley J. W. Lim (ORCID: https://orcid.org/0000-0002-5641-075X)
- Delasa Aghamirzaie
- Mark J. Caulfield (ORCID: https://orcid.org/0000-0001-9295-3594)
- François Aguet (ORCID: https://orcid.org/0000-0001-9414-300X)
- Shan Dong (ORCID: https://orcid.org/0000-0001-9130-0225)
- Anshul Kundaje (ORCID: https://orcid.org/0000-0003-3084-2287)
- Petko P. Fiziev (ORCID: https://orcid.org/0000-0002-1572-4621)
- Anne O’Donnell‐Luria (ORCID: https://orcid.org/0000-0001-6418-9592)
- Yan Zhang (ORCID: https://orcid.org/0000-0002-2267-8408)
- Yuchuan Wang (ORCID: https://orcid.org/0000-0001-7082-2884)
- Arvind Kumar (ORCID: https://orcid.org/0000-0002-1804-2343)
- Adriana Salcedo (ORCID: https://orcid.org/0000-0002-3365-2705)
- Mark T. Ross (ORCID: https://orcid.org/0000-0001-7851-1167)
- Ziming Weng (ORCID: https://orcid.org/0009-0002-0321-9406)
Institutions
- Broad Institute (US)
- Boston Children's Hospital (US)
- Harvard University (US)
- Queen Mary University of London (GB)
- Illumina (United States) (US)
- University of California, San Francisco (US)
- University of Oxford (GB)
- Massachusetts General Hospital (US)
- William Harvey Research Institute (GB)
- New York Genome Center (US)
- Stanford University (US)
Publication Details
- Journal
- Science
- Published
- 2025-05-29
- DOI
- https://doi.org/10.1126/science.ads7373
- Citations
- 26
- Primary Topic
- Genomics and Rare Diseases
- Type
- article
- Field-Weighted Citation Impact
- 47.25