Deep generative modeling of the human proteome reveals over a hundred novel genes involved in rare genetic disorders.

Identifying causal mutations accelerates genetic disease diagnosis, and therapeutic development. Missense variants present a bottleneck in genetic diagnoses as their effects are less straightforward than truncations or nonsense mutations. While computational prediction methods are increasingly successful at prediction for variants in known disease genes, they do not generalize well to other genes as the scores are not calibrated across the proteome1-6. To address this, we developed a deep generative model, popEVE, that combines evolutionary information with population sequence data7 and achieves state-of-the-art performance at ranking variants by severity to distinguish patients with severe developmental disorders8 from potentially healthy individuals9. popEVE identifies 442 genes in patients this developmental disorder cohort, including evidence of 123 novel genetic disorders, many without the need for gene-level enrichment and without overestimating the prevalence of pathogenic variants in the population. A majority of these variants are close to interacting partners in 3D complexes. Preliminary analyses on child exomes indicate that popEVE can identify candidate variants without the need for inheritance labels. By placing variants on a unified scale, our model offers a comprehensive perspective on the distribution of fitness effects across the entire proteome and the broader human population. popEVE provides compelling evidence for genetic diagnoses even in exceptionally rare single-patient disorders where conventional techniques relying on repeated observations may not be applicable.

Continuous evolution of user-defined genes at 1-million-times the genomic mutation rate.

When nature maintains or evolves a gene's function over millions of years at scale, it produces a diversity of homologous sequences whose patterns of conservation and change contain rich structural, functional, and historical information about the gene. However, natural gene diversity likely excludes vast regions of functional sequence space and includes phylogenetic and evolutionary eccentricities, limiting what information we can extract. We introduce an accessible experimental approach for compressing long-term gene evolution to laboratory timescales, allowing for the direct observation of extensive adaptation and divergence followed by inference of structural, functional, and environmental constraints for any selectable gene. To enable this approach, we developed a new orthogonal DNA replication (OrthoRep) system that durably hypermutates chosen genes at a rate of >10 -4 substitutions per base in vivo . When OrthoRep was used to evolve a conditionally essential maladapted enzyme, we obtained thousands of unique multi-mutation sequences with many pairs >60 amino acids apart (>15% divergence), revealing known and new factors influencing enzyme adaptation. The fitness of evolved sequences was not predictable by advanced machine learning models trained on natural variation. We suggest that OrthoRep supports the prospective and systematic discovery of constraints shaping gene evolution, uncovering of new regions in fitness landscapes, and general applications in biomolecular engineering.

Deep generative modeling of the human proteome reveals over a hundred novel genes involved in rare genetic disorders.

Identifying causal mutations accelerates genetic disease diagnosis, and therapeutic development. Missense variants present a bottleneck in genetic diagnoses as their effects are less straightforward than truncations or nonsense mutations. While computational prediction methods are increasingly successful at prediction for variants in known disease genes, they do not generalize well to other genes as the scores are not calibrated across the proteome. To address this, we developed a deep generative model, popEVE, that combines evolutionary information with population sequence data and achieves state-of-the-art performance at ranking variants by severity to distinguish patients with severe developmental disorders from potentially healthy individuals. popEVE identifies 442 genes in a cohort of developmental disorder cases, including evidence of 119 novel genetic disorders without the need for gene-level enrichment and without overestimating the prevalence of pathogenic variants in the population. By placing variants on a unified scale, our model offers a comprehensive perspective on the distribution of fitness effects across the entire proteome and the broader human population. popEVE provides compelling evidence for genetic diagnoses even in exceptionally rare single-patient disorders where conventional techniques relying on repeated observations may not be applicable. Interactive web viewer and downloads available at pop.evemodel.org.

ProteinGym: Large-Scale Benchmarks for Protein Design and Fitness Prediction.

Predicting the effects of mutations in proteins is critical to many applications, from understanding genetic disease to designing novel proteins that can address our most pressing challenges in climate, agriculture and healthcare. Despite a surge in machine learning-based protein models to tackle these questions, an assessment of their respective benefits is challenging due to the use of distinct, often contrived, experimental datasets, and the variable performance of models across different protein families. Addressing these challenges requires scale. To that end we introduce ProteinGym, a large-scale and holistic set of benchmarks specifically designed for protein fitness prediction and design. It encompasses both a broad collection of over 250 standardized deep mutational scanning assays, spanning millions of mutated sequences, as well as curated clinical datasets providing high-quality expert annotations about mutation effects. We devise a robust evaluation framework that combines metrics for both fitness prediction and design, factors in known limitations of the underlying experimental methods, and covers both zero-shot and supervised settings. We report the performance of a diverse set of over 70 high-performing models from various subfields (eg., alignment-based, inverse folding) into a unified benchmark suite. We open source the corresponding codebase, datasets, MSAs, structures, model predictions and develop a user-friendly website that facilitates data access and analysis.