Accurate proteome-wide missense variant effect prediction with AlphaMissense

• DOI: 10.1126/science.adg7492
• Publication Date: 2023-09-19T16:06:00Z
• Authors: Jun Cheng; Guido Novati; Joshua Pan; Clare Bycroft; Akvilė Žemgulytė; Taylor Applebaum; Alexander Pritzel; Lai Hong Wong; Michal Zielinski; Tobias Sargeant; Rosalia G. Schneider; Andrew W. Senior; John Jumper; Demis Hassabis; Pushmeet Kohli; Žiga Avsec
• Keywords: Proteome

The vast majority of missense variants observed in the human genome are unknown clinical significance. We present AlphaMissense, an adaptation AlphaFold fine-tuned on and primate variant population frequency databases to predict pathogenicity. By combining structural context evolutionary conservation, our model achieves state-of-the-art results across a wide range genetic experimental benchmarks, all without explicitly training such data. average pathogenicity score genes is also predictive for their cell essentiality, capable identifying short essential that existing statistical approaches underpowered detect. As resource community, we provide database predictions possible single amino acid substitutions classify 89% as either likely benign or pathogenic.