Using deep mutational scanning to benchmark variant effect predictors and identify disease mutations

G protein-coupled receptor (GPCR) pharmacogenomics

The field of pharmacogenetics, the investigation of the influence of one or more sequence variants on drug response phenotypes, is a special case of pharmacogenomics, a discipline that takes a genome-wide approach. Massively parallel, next generation sequencing (NGS), has allowed pharmacogenetics to be subsumed by pharmacogenomics with respect to the identification of variants associated with responders and non-responders, optimal drug response, and adverse drug reactions. A plethora of rare and common naturally-occurring GPCR variants must be considered in the context of signals from across the genome. Many fundamentals of pharmacogenetics were established for G protein-coupled receptor (GPCR) genes because they are primary targets for a large number of therapeutic drugs. Functional studies, demonstrating likely-pathogenic and pathogenic GPCR variants, have been integral to establishing models used for in silico analysis. Variants in GPCR genes include both coding and non-coding single nucleotide variants and insertion or deletions (indels) that affect cell surface expression (trafficking, dimerization, and desensitization/downregulation), ligand binding and G protein coupling, and variants that result in alternate splicing encoding isoforms/variable expression. As the breadth of data on the GPCR genome increases, we may expect an increase in the use of drug labels that note variants that significantly impact the clinical use of GPCR-targeting agents. We discuss the implications of GPCR pharmacogenomic data derived from the genomes available from individuals who have been well-phenotyped for receptor structure and function and receptor-ligand interactions, and the potential benefits to patients of optimized drug selection. Examples discussed include the renin-angiotensin system in SARS-CoV-2 (COVID-19) infection, the probable role of chemokine receptors in the cytokine storm, and potential protease activating receptor (PAR) interventions. Resources dedicated to GPCRs, including publicly available computational tools, are also discussed.

Unsupervised evolution of protein and antibody complexes with a structure-informed language model

Large language models trained on sequence information alone can learn high-level principles of protein design. However, beyond sequence, the three-dimensional structures of proteins determine their specific function, activity, and evolvability. Here, we show that a general protein language model augmented with protein structure backbone coordinates can guide evolution for diverse proteins without the need to model individual functional tasks. We also demonstrate that ESM-IF1, which was only trained on single-chain structures, can be extended to engineer protein complexes. Using this approach, we screened about 30 variants of two therapeutic clinical antibodies used to treat severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. We achieved up to 25-fold improvement in neutralization and 37-fold improvement in affinity against antibody-escaped viral variants of concern BQ.1.1 and XBB.1.5, respectively. These findings highlight the advantage of integrating structural information to identify efficient protein evolution trajectories without requiring any task-specific training data.

PHACTboost: A Phylogeny-Aware Pathogenicity Predictor for Missense Mutations via Boosting

Most algorithms that are used to predict the effects of variants rely on evolutionary conservation. However, a majority of such techniques compute evolutionary conservation by solely using the alignment of multiple sequences while overlooking the evolutionary context of substitution events. We had introduced PHACT, a scoring-based pathogenicity predictor for missense mutations that can leverage phylogenetic trees, in our previous study. By building on this foundation, we now propose PHACTboost, a gradient boosting tree-based classifier that combines PHACT scores with information from multiple sequence alignments, phylogenetic trees, and ancestral reconstruction. By learning from data, PHACTboost outperforms PHACT. Furthermore, the results of comprehensive experiments on carefully constructed sets of variants demonstrated that PHACTboost can outperform 40 prevalent pathogenicity predictors reported in the dbNSFP, including conventional tools, metapredictors, and deep learning-based approaches as well as more recent tools such as AlphaMissense, EVE, and CPT-1. The superiority of PHACTboost over these methods was particularly evident in case of hard variants for which different pathogenicity predictors offered conflicting results. We provide predictions of 215 million amino acid alterations over 20,191 proteins. PHACTboost is available at https://github.com/CompGenomeLab/PHACTboost. PHACTboost can improve our understanding of genetic diseases and facilitate more accurate diagnoses.

Deep mutational scanning quantifies DNA binding and predicts clinical outcomes of PAX6 variants

Nonsense and missense mutations in the transcription factor PAX6 cause a wide range of eye development defects, including aniridia, microphthalmia and coloboma. To understand how changes of PAX6:DNA binding cause these phenotypes, we combined saturation mutagenesis of the paired domain of PAX6 with a yeast one-hybrid (Y1H) assay in which expression of a PAX6-GAL4 fusion gene drives antibiotic resistance. We quantified binding of more than 2700 single amino-acid variants to two DNA sequence elements. Mutations in DNA-facing residues of the N-terminal subdomain and linker region were most detrimental, as were mutations to prolines and to negatively charged residues. Many variants caused sequence-specific molecular gain-of-function effects, including variants in position 71 that increased binding to the LE9 enhancer but decreased binding to a SELEX-derived binding site. In the absence of antibiotic selection, variants that retained DNA binding slowed yeast growth, likely because such variants perturbed the yeast transcriptome. Benchmarking against known patient variants and applying ACMG/AMP guidelines to variant classification, we obtained supporting-to-moderate evidence that 977 variants are likely pathogenic and 1306 are likely benign. Our analysis shows that most pathogenic mutations in the paired domain of PAX6 can be explained simply by the effects of these mutations on PAX6:DNA association, and establishes Y1H as a generalisable assay for the interpretation of variant effects in transcription factors.

Benchmarking computational variant effect predictors by their ability to infer human traits

BACKGROUND

Computational variant effect predictors offer a scalable and increasingly reliable means of interpreting human genetic variation, but concerns of circularity and bias have limited previous methods for evaluating and comparing predictors. Population-level cohorts of genotyped and phenotyped participants that have not been used in predictor training can facilitate an unbiased benchmarking of available methods. Using a curated set of human gene-trait associations with a reported rare-variant burden association, we evaluate the correlations of 24 computational variant effect predictors with associated human traits in the UK Biobank and All of Us cohorts.

RESULTS

AlphaMissense outperformed all other predictors in inferring human traits based on rare missense variants in UK Biobank and All of Us participants. The overall rankings of computational variant effect predictors in these two cohorts showed a significant positive correlation.

CONCLUSION

We describe a method to assess computational variant effect predictors that sidesteps the limitations of previous evaluations. This approach is generalizable to future predictors and could continue to inform predictor choice for personal and clinical genetics.

Deep Mutational Scanning in Disease-related Genes with Saturation Mutagenesis-Reinforced Functional Assays (SMuRF)

Interpretation of disease-causing genetic variants remains a challenge in human genetics. Current costs and complexity of deep mutational scanning methods hamper crowd-sourcing approaches toward genome-wide resolution of variants in disease-related genes. Our framework, Saturation Mutagenesis-Reinforced Functional assays (SMuRF), addresses these issues by offering simple and cost-effective saturation mutagenesis, as well as streamlining functional assays to enhance the interpretation of unresolved variants. Applying SMuRF to neuromuscular disease genes FKRP and LARGE1, we generated functional scores for all possible coding single nucleotide variants, which aid in resolving clinically reported variants of uncertain significance. SMuRF also demonstrates utility in predicting disease severity, resolving critical structural regions, and providing training datasets for the development of computational predictors. Our approach opens new directions for enabling variant-to-function insights for disease genes in a manner that is broadly useful for crowd-sourcing implementation across standard research laboratories.

ProteoMutaMetrics: machine learning approaches for solute carrier family 6 mutation pathogenicity prediction

The solute carrier transporter family 6 (SLC6) is of key interest for their critical role in the transport of small amino acids or amino acid-like molecules. Their dysfunction is strongly associated with human diseases such as including schizophrenia, depression, and Parkinson's disease. Linking single point mutations to disease may support insights into the structure-function relationship of these transporters. This work aimed to develop a computational model for predicting the potential pathogenic effect of single point mutations in the SLC6 family. Missense mutation data was retrieved from UniProt, LitVar, and ClinVar, covering multiple protein-coding transcripts. As encoding approach, amino acid descriptors were used to calculate the average sequence properties for both original and mutated sequences. In addition to the full-sequence calculation, the sequences were cut into twelve domains. The domains are defined according to the transmembrane domains of the SLC6 transporters to analyse the regions' contributions to the pathogenicity prediction. Subsequently, several classification models, namely Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) with the hyperparameters optimized through grid search were built. For estimation of model performance, repeated stratified k-fold cross-validation was used. The accuracy values of the generated models are in the range of 0.72 to 0.80. Analysis of feature importance indicates that mutations in distinct regions of SLC6 transporters are associated with an increased risk for pathogenicity. When applying the model on an independent validation set, the performance in accuracy dropped to averagely 0.6 with high precision but low sensitivity scores.

Fitness Effects of Phenotypic Mutations at Proteome-Scale Reveal Optimality of Translation Machinery

Errors in protein translation can lead to non-genetic, phenotypic mutations, including amino acid misincorporations. While phenotypic mutations can increase protein diversity, the systematic characterization of their proteome-wide frequencies and their evolutionary impact has been lacking. Here, we developed a mechanistic model of translation errors to investigate how selection acts on protein populations produced by amino acid misincorporations. We fitted the model to empirical observations of misincorporations obtained from over a hundred mass spectrometry datasets of E. coli and S. cerevisiae. We found that on average 20% to 23% of proteins synthesized in the cell are expected to harbor at least one amino acid misincorporation, and that deleterious misincorporations are less likely to occur. Combining misincorporation probabilities and the estimated fitness effects of amino acid substitutions in a population genetics framework, we found 74% of mistranslation events in E. coli and 94% in S. cerevisiae to be neutral. We further show that the set of available synonymous tRNAs is subject to evolutionary pressure, as the presence of missing tRNAs would increase codon-anticodon cross-reactivity and misincorporation error rates. Overall, we find that the translation machinery is likely optimal in E. coli and S. cerevisiae and that both local solutions at the level of codons and a global solution such as the tRNA pool can mitigate the impact of translation errors. We provide a framework to study the evolutionary impact of codon-specific translation errors and a method for their proteome-wide detection across organisms and conditions.

Efficient evolution of human antibodies from general protein language models

Natural evolution must explore a vast landscape of possible sequences for desirable yet rare mutations, suggesting that learning from natural evolutionary strategies could guide artificial evolution. Here we report that general protein language models can efficiently evolve human antibodies by suggesting mutations that are evolutionarily plausible, despite providing the model with no information about the target antigen, binding specificity or protein structure. We performed language-model-guided affinity maturation of seven antibodies, screening 20 or fewer variants of each antibody across only two rounds of laboratory evolution, and improved the binding affinities of four clinically relevant, highly mature antibodies up to sevenfold and three unmatured antibodies up to 160-fold, with many designs also demonstrating favorable thermostability and viral neutralization activity against Ebola and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pseudoviruses. The same models that improve antibody binding also guide efficient evolution across diverse protein families and selection pressures, including antibiotic resistance and enzyme activity, suggesting that these results generalize to many settings.

Highly parameterized polygenic scores tend to overfit to population stratification via random effects

Polygenic scores (PGSs), increasingly used in clinical settings, frequently include many genetic variants, with performance typically peaking at thousands of variants. Such highly parameterized PGSs often include variants that do not pass a genome-wide significance threshold. We propose a mathematical perspective that renders the effects of many of these non-significant variants random rather than causal, with the randomness capturing population structure. We devise methods to assess variant effect randomness and population stratification bias. Applying these methods to 141 traits from the UK Biobank, we find that, for many PGSs, the effects of non-significant variants are considerably random, with the extent of randomness associated with the degree of overfitting to population structure of the discovery cohort. Our findings explain why highly parameterized PGSs simultaneously have superior cohort-specific performance and limited generalizability, suggesting the critical need for variant randomness tests in PGS evaluation. Supporting code and a dashboard are available at https://github.com/songlab-cal/StratPGS.

Prediction of cancer driver genes and mutations: the potential of integrative computational frameworks

The vast amount of available sequencing data allows the scientific community to explore different genetic alterations that may drive cancer or favor cancer progression. Software developers have proposed a myriad of predictive tools, allowing researchers and clinicians to compare and prioritize driver genes and mutations and their relative pathogenicity. However, there is little consensus on the computational approach or a golden standard for comparison. Hence, benchmarking the different tools depends highly on the input data, indicating that overfitting is still a massive problem. One of the solutions is to limit the scope and usage of specific tools. However, such limitations force researchers to walk on a tightrope between creating and using high-quality tools for a specific purpose and describing the complex alterations driving cancer. While the knowledge of cancer development increases daily, many bioinformatic pipelines rely on single nucleotide variants or alterations in a vacuum without accounting for cellular compartments, mutational burden or disease progression. Even within bioinformatics and computational cancer biology, the research fields work in silos, risking overlooking potential synergies or breakthroughs. Here, we provide an overview of databases and datasets for building or testing predictive cancer driver tools. Furthermore, we introduce predictive tools for driver genes, driver mutations, and the impact of these based on structural analysis. Additionally, we suggest and recommend directions in the field to avoid silo-research, moving towards integrative frameworks.

Experimental and Computational Analysis of Newly Identified Pathogenic Mutations in the Creatine Transporter SLC6A8

Creatine is an essential metabolite for the storage and rapid supply of energy in muscle and nerve cells. In humans, impaired metabolism, transport, and distribution of creatine throughout tissues can cause varying forms of mental disability, also known as creatine deficiency syndrome (CDS). So far, 80 mutations in the creatine transporter (SLC6A8) have been associated to CDS. To better understand the effect of human genetic variants on the physiology of SLC6A8 and their possible impact on CDS, we studied 30 missense variants including 15 variants of unknown significance, two of which are reported here for the first time. We expressed these variants in HEK293 cells and explored their subcellular localization and transport activity. We also applied computational methods to predict variant effect and estimate site-specific changes in thermodynamic stability. To explore variants that might have a differential effect on the transporter's conformers along the transport cycle, we constructed homology models of the inward facing, and outward facing conformations. In addition, we used mass-spectrometry to study proteins that interact with wild type SLC6A8 and five selected variants in HEK293 cells. In silico models of the protein complexes revealed how two variants impact the interaction interface of SLC6A8 with other proteins and how pathogenic variants lead to an enrichment of ER protein partners. Overall, our integrated analysis disambiguates the pathogenicity of 15 variants of unknown significance revealing diverse mechanisms of pathogenicity, including two previously unreported variants obtained from patients suffering from the creatine deficiency syndrome.

Classification of MLH1 Missense VUS Using Protein Structure-Based Deep Learning-Ramachandran Plot-Molecular Dynamics Simulations Method

Pathogenic variation in DNA mismatch repair (MMR) gene MLH1 is associated with Lynch syndrome (LS), an autosomal dominant hereditary cancer. Of the 3798 MLH1 germline variants collected in the ClinVar database, 38.7% (1469) were missense variants, of which 81.6% (1199) were classified as Variants of Uncertain Significance (VUS) due to the lack of functional evidence. Further determination of the impact of VUS on MLH1 function is important for the VUS carriers to take preventive action. We recently developed a protein structure-based method named "Deep Learning-Ramachandran Plot-Molecular Dynamics Simulation (DL-RP-MDS)" to evaluate the deleteriousness of MLH1 missense VUS. The method extracts protein structural information by using the Ramachandran plot-molecular dynamics simulation (RP-MDS) method, then combines the variation data with an unsupervised learning model composed of auto-encoder and neural network classifier to identify the variants causing significant change in protein structure. In this report, we applied the method to classify 447 MLH1 missense VUS. We predicted 126/447 (28.2%) MLH1 missense VUS were deleterious. Our study demonstrates that DL-RP-MDS is able to classify the missense VUS based solely on their impact on protein structure.

Inverse folding of protein complexes with a structure-informed language model enables unsupervised antibody evolution

Large language models trained on sequence information alone are capable of learning high level principles of protein design. However, beyond sequence, the three-dimensional structures of proteins determine their specific function, activity, and evolvability. Here we show that a general protein language model augmented with protein structure backbone coordinates and trained on the inverse folding problem can guide evolution for diverse proteins without needing to explicitly model individual functional tasks. We demonstrate inverse folding to be an effective unsupervised, structure-based sequence optimization strategy that also generalizes to multimeric complexes by implicitly learning features of binding and amino acid epistasis. Using this approach, we screened ~30 variants of two therapeutic clinical antibodies used to treat SARS-CoV-2 infection and achieved up to 26-fold improvement in neutralization and 37-fold improvement in affinity against antibody-escaped viral variants-of-concern BQ.1.1 and XBB.1.5, respectively. In addition to substantial overall improvements in protein function, we find inverse folding performs with leading experimental success rates among other reported machine learning-guided directed evolution methods, without requiring any task-specific training data.

The functional mutational landscape of the lacZ gene

The lacZ gene of Escherichia coli encodes β-galactosidase (β-gal), a lactose metabolism enzyme of the lactose operon. Previous chemical modification or site-directed mutagenesis experiments have identified 21 amino acids that are essential for β-gal catalytic activity. We have assembled over 10,000 lacZ mutations from published studies that were collected using a positive selection assay to identify mutations in lacZ that disrupted β-gal function. We analyzed 6,465 independent lacZ mutations that resulted in 2,732 missense mutations that impaired β-gal function. Those mutations affected 492 of the 1,023 lacZ codons, including most of the 21 previously known residues critical for catalytic activity. Most missense mutations occurred near the catalytic site and in regions important for subunit tetramerization. Overall, our work provides a comprehensive and detailed map of the amino acid residues affecting the structure and catalytic activity of the β-gal enzyme.

Saturation genome editing of DDX3X clarifies pathogenicity of germline and somatic variation

Loss-of-function of DDX3X is a leading cause of neurodevelopmental disorders (NDD) in females. DDX3X is also a somatically mutated cancer driver gene proposed to have tumour promoting and suppressing effects. We perform saturation genome editing of DDX3X, testing in vitro the functional impact of 12,776 nucleotide variants. We identify 3432 functionally abnormal variants, in three distinct classes. We train a machine learning classifier to identify functionally abnormal variants of NDD-relevance. This classifier has at least 97% sensitivity and 99% specificity to detect variants pathogenic for NDD, substantially out-performing in silico predictors, and resolving up to 93% of variants of uncertain significance. Moreover, functionally-abnormal variants can account for almost all of the excess nonsynonymous DDX3X somatic mutations seen in DDX3X-driven cancers. Systematic maps of variant effects generated in experimentally tractable cell types have the potential to transform clinical interpretation of both germline and somatic disease-associated variation.

Infer global, predict local: Quantity-relevance trade-off in protein fitness predictions from sequence data

Predicting the effects of mutations on protein function is an important issue in evolutionary biology and biomedical applications. Computational approaches, ranging from graphical models to deep-learning architectures, can capture the statistical properties of sequence data and predict the outcome of high-throughput mutagenesis experiments probing the fitness landscape around some wild-type protein. However, how the complexity of the models and the characteristics of the data combine to determine the predictive performance remains unclear. Here, based on a theoretical analysis of the prediction error, we propose descriptors of the sequence data, characterizing their quantity and relevance relative to the model. Our theoretical framework identifies a trade-off between these two quantities, and determines the optimal subset of data for the prediction task, showing that simple models can outperform complex ones when inferred from adequately-selected sequences. We also show how repeated subsampling of the sequence data is informative about how much epistasis in the fitness landscape is not captured by the computational model. Our approach is illustrated on several protein families, as well as on in silico solvable protein models.

Accurate proteome-wide missense variant effect prediction with AlphaMissense

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

Artificial intelligence-aided protein engineering: from topological data analysis to deep protein language models

Protein engineering is an emerging field in biotechnology that has the potential to revolutionize various areas, such as antibody design, drug discovery, food security, ecology, and more. However, the mutational space involved is too vast to be handled through experimental means alone. Leveraging accumulative protein databases, machine learning (ML) models, particularly those based on natural language processing (NLP), have considerably expedited protein engineering. Moreover, advances in topological data analysis (TDA) and artificial intelligence-based protein structure prediction, such as AlphaFold2, have made more powerful structure-based ML-assisted protein engineering strategies possible. This review aims to offer a comprehensive, systematic, and indispensable set of methodological components, including TDA and NLP, for protein engineering and to facilitate their future development.

ASCARIS: Positional feature annotation and protein structure-based representation of single amino acid variations

Background

Genomic variations may cause deleterious effects on protein functionality and perturb biological processes. Elucidating the effects of variations is critical for developing novel treatment strategies for diseases of genetic origin. Computational approaches have been aiding the work in this field by modeling and analyzing the mutational landscape. However, new approaches are required, especially for accurate representation and data-centric analysis of sequence variations.

Method

In this study, we propose ASCARIS (Annotation and StruCture-bAsed RepresentatIon of Single amino acid variations), a method for the featurization (i.e., quantitative representation) of single amino acid variations (SAVs), which could be used for a variety of purposes, such as predicting their functional effects or building multi-omics-based integrative models. ASCARIS utilizes the direct and spatial correspondence between the location of the SAV on the sequence/structure and 30 different types of positional feature annotations (e.g., active/lipidation/glycosylation sites; calcium/metal/DNA binding, inter/transmembrane regions, etc.), along with structural features and physicochemical properties. The main novelty of this method lies in constructing reusable numerical representations of SAVs via functional annotations.

Results

We statistically analyzed the relationship between these features and the consequences of variations and found that each carries information in this regard. To investigate potential applications of ASCARIS, we trained variant effect prediction models that utilize our SAV representations as input. We carried out an ablation study and a comparison against the state-of-the-art methods and observed that ASCARIS has a competing and complementary performance against widely-used predictors. ASCARIS can be used alone or in combination with other approaches to represent SAVs from a functional perspective. ASCARIS is available as a programmatic tool at https://github.com/HUBioDataLab/ASCARIS and as a web-service at https://huggingface.co/spaces/HUBioDataLab/ASCARIS.

Updated benchmarking of variant effect predictors using deep mutational scanning

The assessment of variant effect predictor (VEP) performance is fraught with biases introduced by benchmarking against clinical observations. In this study, building on our previous work, we use independently generated measurements of protein function from deep mutational scanning (DMS) experiments for 26 human proteins to benchmark 55 different VEPs, while introducing minimal data circularity. Many top-performing VEPs are unsupervised methods including EVE, DeepSequence and ESM-1v, a protein language model that ranked first overall. However, the strong performance of recent supervised VEPs, in particular VARITY, shows that developers are taking data circularity and bias issues seriously. We also assess the performance of DMS and unsupervised VEPs for discriminating between known pathogenic and putatively benign missense variants. Our findings are mixed, demonstrating that some DMS datasets perform exceptionally at variant classification, while others are poor. Notably, we observe a striking correlation between VEP agreement with DMS data and performance in identifying clinically relevant variants, strongly supporting the validity of our rankings and the utility of DMS for independent benchmarking.

Cross-protein transfer learning substantially improves disease variant prediction

BACKGROUND

Genetic variation in the human genome is a major determinant of individual disease risk, but the vast majority of missense variants have unknown etiological effects. Here, we present a robust learning framework for leveraging saturation mutagenesis experiments to construct accurate computational predictors of proteome-wide missense variant pathogenicity.

RESULTS

We train cross-protein transfer (CPT) models using deep mutational scanning (DMS) data from only five proteins and achieve state-of-the-art performance on clinical variant interpretation for unseen proteins across the human proteome. We also improve predictive accuracy on DMS data from held-out proteins. High sensitivity is crucial for clinical applications and our model CPT-1 particularly excels in this regime. For instance, at 95% sensitivity of detecting human disease variants annotated in ClinVar, CPT-1 improves specificity to 68%, from 27% for ESM-1v and 55% for EVE. Furthermore, for genes not used to train REVEL, a supervised method widely used by clinicians, we show that CPT-1 compares favorably with REVEL. Our framework combines predictive features derived from general protein sequence models, vertebrate sequence alignments, and AlphaFold structures, and it is adaptable to the future inclusion of other sources of information. We find that vertebrate alignments, albeit rather shallow with only 100 genomes, provide a strong signal for variant pathogenicity prediction that is complementary to recent deep learning-based models trained on massive amounts of protein sequence data. We release predictions for all possible missense variants in 90% of human genes.

CONCLUSIONS

Our results demonstrate the utility of mutational scanning data for learning properties of variants that transfer to unseen proteins.

Artificial intelligence-aided protein engineering: from topological data analysis to deep protein language models

Protein engineering is an emerging field in biotechnology that has the potential to revolutionize various areas, such as antibody design, drug discovery, food security, ecology, and more. However, the mutational space involved is too vast to be handled through experimental means alone. Leveraging accumulative protein databases, machine learning (ML) models, particularly those based on natural language processing (NLP), have considerably expedited protein engineering. Moreover, advances in topological data analysis (TDA) and artificial intelligence-based protein structure prediction, such as AlphaFold2, have made more powerful structure-based ML-assisted protein engineering strategies possible. This review aims to offer a comprehensive, systematic, and indispensable set of methodological components, including TDA and NLP, for protein engineering and to facilitate their future development.

Discovering functionally important sites in proteins

Proteins play important roles in biology, biotechnology and pharmacology, and missense variants are a common cause of disease. Discovering functionally important sites in proteins is a central but difficult problem because of the lack of large, systematic data sets. Sequence conservation can highlight residues that are functionally important but is often convoluted with a signal for preserving structural stability. We here present a machine learning method to predict functional sites by combining statistical models for protein sequences with biophysical models of stability. We train the model using multiplexed experimental data on variant effects and validate it broadly. We show how the model can be used to discover active sites, as well as regulatory and binding sites. We illustrate the utility of the model by prospective prediction and subsequent experimental validation on the functional consequences of missense variants in HPRT1 which may cause Lesch-Nyhan syndrome, and pinpoint the molecular mechanisms by which they cause disease.

Understanding structure-guided variant effect predictions using 3D convolutional neural networks

Predicting pathogenicity of missense variants in molecular diagnostics remains a challenge despite the available wealth of data, such as evolutionary information, and the wealth of tools to integrate that data. We describe DeepRank-Mut, a configurable framework designed to extract and learn from physicochemically relevant features of amino acids surrounding missense variants in 3D space. For each variant, various atomic and residue-level features are extracted from its structural environment, including sequence conservation scores of the surrounding amino acids, and stored in multi-channel 3D voxel grids which are then used to train a 3D convolutional neural network (3D-CNN). The resultant model gives a probabilistic estimate of whether a given input variant is disease-causing or benign. We find that the performance of our 3D-CNN model, on independent test datasets, is comparable to other widely used resources which also combine sequence and structural features. Based on the 10-fold cross-validation experiments, we achieve an average accuracy of 0.77 on the independent test datasets. We discuss the contribution of the variant neighborhood in the model's predictive power, in addition to the impact of individual features on the model's performance. Two key features: evolutionary information of residues in the variant neighborhood and their solvent accessibilities were observed to influence the predictions. We also highlight how predictions are impacted by the underlying disease mechanisms of missense mutations and offer insights into understanding these to improve pathogenicity predictions. Our study presents aspects to take into consideration when adopting deep learning approaches for protein structure-guided pathogenicity predictions.

From genotype to phenotype: computational approaches for inferring microbial traits relevant to the food industry

When selecting microbial strains for the production of fermented foods, various microbial phenotypes need to be taken into account to achieve target product characteristics, such as biosafety, flavor, texture, and health-promoting effects. Through continuous advances in sequencing technologies, microbial whole-genome sequences of increasing quality can now be obtained both cheaper and faster, which increases the relevance of genome-based characterization of microbial phenotypes. Prediction of microbial phenotypes from genome sequences makes it possible to quickly screen large strain collections in silico to identify candidates with desirable traits. Several microbial phenotypes relevant to the production of fermented foods can be predicted using knowledge-based approaches, leveraging our existing understanding of the genetic and molecular mechanisms underlying those phenotypes. In the absence of this knowledge, data-driven approaches can be applied to estimate genotype-phenotype relationships based on large experimental datasets. Here, we review computational methods that implement knowledge- and data-driven approaches for phenotype prediction, as well as methods that combine elements from both approaches. Furthermore, we provide examples of how these methods have been applied in industrial biotechnology, with special focus on the fermented food industry.

An Atlas of Variant Effects to understand the genome at nucleotide resolution

Sequencing has revealed hundreds of millions of human genetic variants, and continued efforts will only add to this variant avalanche. Insufficient information exists to interpret the effects of most variants, limiting opportunities for precision medicine and comprehension of genome function. A solution lies in experimental assessment of the functional effect of variants, which can reveal their biological and clinical impact. However, variant effect assays have generally been undertaken reactively for individual variants only after and, in most cases long after, their first observation. Now, multiplexed assays of variant effect can characterise massive numbers of variants simultaneously, yielding variant effect maps that reveal the function of every possible single nucleotide change in a gene or regulatory element. Generating maps for every protein encoding gene and regulatory element in the human genome would create an 'Atlas' of variant effect maps and transform our understanding of genetics and usher in a new era of nucleotide-resolution functional knowledge of the genome. An Atlas would reveal the fundamental biology of the human genome, inform human evolution, empower the development and use of therapeutics and maximize the utility of genomics for diagnosing and treating disease. The Atlas of Variant Effects Alliance is an international collaborative group comprising hundreds of researchers, technologists and clinicians dedicated to realising an Atlas of Variant Effects to help deliver on the promise of genomics.

High-throughput deep learning variant effect prediction with Sequence UNET

Understanding coding mutations is important for many applications in biology and medicine but the vast mutation space makes comprehensive experimental characterisation impossible. Current predictors are often computationally intensive and difficult to scale, including recent deep learning models. We introduce Sequence UNET, a highly scalable deep learning architecture that classifies and predicts variant frequency from sequence alone using multi-scale representations from a fully convolutional compression/expansion architecture. It achieves comparable pathogenicity prediction to recent methods. We demonstrate scalability by analysing 8.3B variants in 904,134 proteins detected through large-scale proteomics. Sequence UNET runs on modest hardware with a simple Python package.

DeMAG predicts the effects of variants in clinically actionable genes by integrating structural and evolutionary epistatic features

Despite the increasing use of genomic sequencing in clinical practice, the interpretation of rare genetic variants remains challenging even in well-studied disease genes, resulting in many patients with Variants of Uncertain Significance (VUSs). Computational Variant Effect Predictors (VEPs) provide valuable evidence in variant assessment, but they are prone to misclassifying benign variants, contributing to false positives. Here, we develop Deciphering Mutations in Actionable Genes (DeMAG), a supervised classifier for missense variants trained using extensive diagnostic data available in 59 actionable disease genes (American College of Medical Genetics and Genomics Secondary Findings v2.0, ACMG SF v2.0). DeMAG improves performance over existing VEPs by reaching balanced specificity (82%) and sensitivity (94%) on clinical data, and includes a novel epistatic feature, the 'partners score', which leverages evolutionary and structural partnerships of residues. The 'partners score' provides a general framework for modeling epistatic interactions, integrating both clinical and functional information. We provide our tool and predictions for all missense variants in 316 clinically actionable disease genes (demag.org) to facilitate the interpretation of variants and improve clinical decision-making.

Machine Learning Guided Design of High-Affinity ACE2 Decoys for SARS-CoV-2 Neutralization

A potential therapeutic strategy for neutralizing SARS-CoV-2 infection is engineering high-affinity soluble ACE2 decoy proteins to compete for binding to the viral spike (S) protein. Previously, a deep mutational scan of ACE2 was performed and has led to the identification of a triple mutant variant, named sACE22.v.2.4, that exhibits subnanomolar affinity to the receptor-binding domain (RBD) of S. Using a recently developed transfer learning algorithm, TLmutation, we sought to identify other ACE2 variants that may exhibit similar binding affinity with decreased mutational load. Upon training a TLmutation model on the effects of single mutations, we identified multiple ACE2 double mutants that bind SARS-CoV-2 S with tighter affinity as compared to the wild type, most notably L79V;N90D that binds RBD similarly to ACE22.v.2.4. The experimental validation of the double mutants successfully demonstrates the use of machine learning approaches for engineering protein-protein interactions and identifying high-affinity ACE2 peptides for targeting SARS-CoV-2.

Lynch syndrome, molecular mechanisms and variant classification

Patients with the heritable cancer disease, Lynch syndrome, carry germline variants in the MLH1, MSH2, MSH6 and PMS2 genes, encoding the central components of the DNA mismatch repair system. Loss-of-function variants disrupt the DNA mismatch repair system and give rise to a detrimental increase in the cellular mutational burden and cancer development. The treatment prospects for Lynch syndrome rely heavily on early diagnosis; however, accurate diagnosis is inextricably linked to correct clinical interpretation of individual variants. Protein variant classification traditionally relies on cumulative information from occurrence in patients, as well as experimental testing of the individual variants. The complexity of variant classification is due to (1) that variants of unknown significance are rare in the population and phenotypic information on the specific variants is missing, and (2) that individual variant testing is challenging, costly and slow. Here, we summarise recent developments in high-throughput technologies and computational prediction tools for the assessment of variants of unknown significance in Lynch syndrome. These approaches may vastly increase the number of interpretable variants and could also provide important mechanistic insights into the disease. These insights may in turn pave the road towards developing personalised treatment approaches for Lynch syndrome.

Base editing screens map mutations affecting interferon-γ signaling in cancer

Interferon-γ (IFN-γ) signaling mediates host responses to infection, inflammation and anti-tumor immunity. Mutations in the IFN-γ signaling pathway cause immunological disorders, hematological malignancies, and resistance to immune checkpoint blockade (ICB) in cancer; however, the function of most clinically observed variants remains unknown. Here, we systematically investigate the genetic determinants of IFN-γ response in colorectal cancer cells using CRISPR-Cas9 screens and base editing mutagenesis. Deep mutagenesis of JAK1 with cytidine and adenine base editors, combined with pathway-wide screens, reveal loss-of-function and gain-of-function mutations, including causal variants in hematological malignancies and mutations detected in patients refractory to ICB. We functionally validate variants of uncertain significance in primary tumor organoids, where engineering missense mutations in JAK1 enhanced or reduced sensitivity to autologous tumor-reactive T cells. We identify more than 300 predicted missense mutations altering IFN-γ pathway activity, generating a valuable resource for interpreting gene variant function.

Persistent spectral theory-guided protein engineering

While protein engineering, which iteratively optimizes protein fitness by screening the gigantic mutational space, is constrained by experimental capacity, various machine learning models have substantially expedited protein engineering. Three-dimensional protein structures promise further advantages, but their intricate geometric complexity hinders their applications in deep mutational screening. Persistent homology, an established algebraic topology tool for protein structural complexity reduction, fails to capture the homotopic shape evolution during the filtration of a given data. This work introduces a Topology-offered protein Fitness (TopFit) framework to complement protein sequence and structure embeddings. Equipped with an ensemble regression strategy, TopFit integrates the persistent spectral theory, a new topological Laplacian, and two auxiliary sequence embeddings to capture mutation-induced topological invariant, shape evolution, and sequence disparity in the protein fitness landscape. The performance of TopFit is assessed by 34 benchmark datasets with 128,634 variants, involving a vast variety of protein structure acquisition modalities and training set size variations.

Deep mutational scanning: A versatile tool in systematically mapping genotypes to phenotypes

Unveiling how genetic variations lead to phenotypic variations is one of the key questions in evolutionary biology, genetics, and biomedical research. Deep mutational scanning (DMS) technology has allowed the mapping of tens of thousands of genetic variations to phenotypic variations efficiently and economically. Since its first systematic introduction about a decade ago, we have witnessed the use of deep mutational scanning in many research areas leading to scientific breakthroughs. Also, the methods in each step of deep mutational scanning have become much more versatile thanks to the oligo-synthesizing technology, high-throughput phenotyping methods and deep sequencing technology. However, each specific possible step of deep mutational scanning has its pros and cons, and some limitations still await further technological development. Here, we discuss recent scientific accomplishments achieved through the deep mutational scanning and describe widely used methods in each step of deep mutational scanning. We also compare these different methods and analyze their advantages and disadvantages, providing insight into how to design a deep mutational scanning study that best suits the aims of the readers' projects.

Shared Cancer Dataset Analysis Identifies and Predicts the Quantitative Effects of Pan-Cancer Somatic Driver Variants

Driver mutations endow tumors with selective advantages and produce an array of pathogenic effects. Determining the function of somatic variants is important for understanding cancer biology and identifying optimal therapies. Here, we compiled a shared dataset from several cancer genomic databases. Two measures were applied to 535 cancer genes based on observed and expected frequencies of driver variants as derived from cancer-specific rates of somatic mutagenesis. The first measure comprised a binary classifier based on a binomial test; the second was tumor variant amplitude (TVA), a continuous measure representing the selective advantage of individual variants. TVA outperformed all other computational tools in terms of its correlation with experimentally derived functional scores of cancer mutations. TVA also highly correlated with drug response, overall survival, and other clinical implications in relevant cancer genes. This study demonstrates how a selective advantage measure based on a large cancer dataset significantly impacts our understanding of the spectral effect of driver variants in cancer. The impact of this information will increase as cancer treatment becomes more precise and personalized to tumor-specific mutations.

SIGNIFICANCE

A new selective advantage estimation assists in oncogenic driver identification and relative effect measurements, enabling better prognostication, therapy selection, and prioritization.

Saturation-scale functional evidence supports clinical variant interpretation in Lynch syndrome

BACKGROUND

Lynch syndrome (LS) is a cancer predisposition syndrome affecting more than 1 in every 300 individuals worldwide. Clinical genetic testing for LS can be life-saving but is complicated by the heavy burden of variants of uncertain significance (VUS), especially missense changes.

RESULT

To address this challenge, we leverage a multiplexed analysis of variant effect (MAVE) map covering >94% of the 17,746 possible missense variants in the key LS gene MSH2. To establish this map's utility in large-scale variant reclassification, we overlay it on clinical databases of >15,000 individuals with LS gene variants uncovered during clinical genetic testing. We validate these functional measurements in a cohort of individuals with paired tumor-normal test results and find that MAVE-based function scores agree with the clinical interpretation for every one of the MSH2 missense variants with an available classification. We use these scores to attempt reclassification for 682 unique missense VUS, among which 34 scored as deleterious by our function map, in line with previously published rates for other cancer predisposition genes. Combining functional data and other evidence, ten missense VUS are reclassified as pathogenic/likely pathogenic, and another 497 could be moved to benign/likely benign. Finally, we apply these functional scores to paired tumor-normal genetic tests and identify a subset of patients with biallelic somatic loss of function, reflecting a sporadic Lynch-like Syndrome with distinct implications for treatment and relatives' risk.

CONCLUSION

This study demonstrates how high-throughput functional assays can empower scalable VUS resolution and prospectively generate strong evidence for variant classification.

Recent advances and challenges of rare variant association analysis in the biobank sequencing era

Causal variants for rare genetic diseases are often rare in the general population. Rare variants may also contribute to common complex traits and can have much larger per-allele effect sizes than common variants, although power to detect these associations can be limited. Sequencing costs have steadily declined with technological advancements, making it feasible to adopt whole-exome and whole-genome profiling for large biobank-scale sample sizes. These large amounts of sequencing data provide both opportunities and challenges for rare-variant association analysis. Herein, we review the basic concepts of rare-variant analysis methods, the current state-of-the-art methods in utilizing variant annotations or external controls to improve the statistical power, and particular challenges facing rare variant analysis such as accounting for population structure, extremely unbalanced case-control design. We also review recent advances and challenges in rare variant analysis for familial sequencing data and for more complex phenotypes such as survival data. Finally, we discuss other potential directions for further methodology investigation.

Intragenic compensation through the lens of deep mutational scanning

A significant fraction of mutations in proteins are deleterious and result in adverse consequences for protein function, stability, or interaction with other molecules. Intragenic compensation is a specific case of positive epistasis when a neutral missense mutation cancels effect of a deleterious mutation in the same protein. Permissive compensatory mutations facilitate protein evolution, since without them all sequences would be extremely conserved. Understanding compensatory mechanisms is an important scientific challenge at the intersection of protein biophysics and evolution. In human genetics, intragenic compensatory interactions are important since they may result in variable penetrance of pathogenic mutations or fixation of pathogenic human alleles in orthologous proteins from related species. The latter phenomenon complicates computational and clinical inference of an allele's pathogenicity. Deep mutational scanning is a relatively new technique that enables experimental studies of functional effects of thousands of mutations in proteins. We review the important aspects of the field and discuss existing limitations of current datasets. We reviewed ten published DMS datasets with quantified functional effects of single and double mutations and described rates and patterns of intragenic compensation in eight of them.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12551-022-01005-w.

High-throughput approaches to functional characterization of genetic variation in yeast

Expansion of sequencing efforts to include thousands of genomes is providing a fundamental resource for determining the genetic diversity that exists in a population. Now, high-throughput approaches are necessary to begin to understand the role these genotypic changes play in affecting phenotypic variation. Saccharomyces cerevisiae maintains its position as an excellent model system to determine the function of unknown variants with its exceptional genetic diversity, phenotypic diversity, and reliable genetic manipulation tools. Here, we review strategies and techniques developed in yeast that scale classic approaches of assessing variant function. These approaches improve our ability to better map quantitative trait loci at a higher resolution, even for rare variants, and are already providing greater insight into the role that different types of mutations play in phenotypic variation and evolution not just in yeast but across taxa.

Embeddings from protein language models predict conservation and variant effects

The emergence of SARS-CoV-2 variants stressed the demand for tools allowing to interpret the effect of single amino acid variants (SAVs) on protein function. While Deep Mutational Scanning (DMS) sets continue to expand our understanding of the mutational landscape of single proteins, the results continue to challenge analyses. Protein Language Models (pLMs) use the latest deep learning (DL) algorithms to leverage growing databases of protein sequences. These methods learn to predict missing or masked amino acids from the context of entire sequence regions. Here, we used pLM representations (embeddings) to predict sequence conservation and SAV effects without multiple sequence alignments (MSAs). Embeddings alone predicted residue conservation almost as accurately from single sequences as ConSeq using MSAs (two-state Matthews Correlation Coefficient-MCC-for ProtT5 embeddings of 0.596 ± 0.006 vs. 0.608 ± 0.006 for ConSeq). Inputting the conservation prediction along with BLOSUM62 substitution scores and pLM mask reconstruction probabilities into a simplistic logistic regression (LR) ensemble for Variant Effect Score Prediction without Alignments (VESPA) predicted SAV effect magnitude without any optimization on DMS data. Comparing predictions for a standard set of 39 DMS experiments to other methods (incl. ESM-1v, DeepSequence, and GEMME) revealed our approach as competitive with the state-of-the-art (SOTA) methods using MSA input. No method outperformed all others, neither consistently nor statistically significantly, independently of the performance measure applied (Spearman and Pearson correlation). Finally, we investigated binary effect predictions on DMS experiments for four human proteins. Overall, embedding-based methods have become competitive with methods relying on MSAs for SAV effect prediction at a fraction of the costs in computing/energy. Our method predicted SAV effects for the entire human proteome (~ 20 k proteins) within 40 min on one Nvidia Quadro RTX 8000. All methods and data sets are freely available for local and online execution through bioembeddings.com, https://github.com/Rostlab/VESPA , and PredictProtein.

Understanding molecular mechanisms and predicting phenotypic effects of pathogenic tubulin mutations

Cells rely heavily on microtubules for several processes, including cell division and molecular trafficking. Mutations in the different tubulin-α and -β proteins that comprise microtubules have been associated with various diseases and are often dominant, sporadic and congenital. While the earliest reported tubulin mutations affect neurodevelopment, mutations are also associated with other disorders such as bleeding disorders and infertility. We performed a systematic survey of tubulin mutations across all isotypes in order to improve our understanding of how they cause disease, and increase our ability to predict their phenotypic effects. Both protein structural analyses and computational variant effect predictors were very limited in their utility for differentiating between pathogenic and benign mutations. This was even worse for those genes associated with non-neurodevelopmental disorders. We selected tubulin-α and -β disease mutations that were most poorly predicted for experimental characterisation. These mutants co-localise to the mitotic spindle in HeLa cells, suggesting they may exert dominant-negative effects by altering microtubule properties. Our results show that tubulin mutations represent a blind spot for current computational approaches, being much more poorly predicted than mutations in most human disease genes. We suggest that this is likely due to their strong association with dominant-negative and gain-of-function mechanisms.

Clinical significance of genetic variation in hypertrophic cardiomyopathy: comparison of computational tools to prioritize missense variants

Hypertrophic cardiomyopathy (HCM) is a common heart disease associated with sudden cardiac death. Early diagnosis is critical to identify patients who may benefit from implantable cardioverter defibrillator therapy. Although genetic testing is an integral part of the clinical evaluation and management of patients with HCM and their families, in many cases the genetic analysis fails to identify a disease-causing mutation. This is in part due to difficulties in classifying newly detected rare genetic variants as well as variants-of-unknown-significance (VUS). Multiple computational algorithms have been developed to predict the potential pathogenicity of genetic variants, but their relative performance in HCM has not been comprehensively assessed. Here, we compared the performance of 39 currently available prediction tools in distinguishing between high-confidence HCM-causing missense variants and benign variants, and we developed an easy-to-use-tool to perform variant prediction benchmarks based on annotated VCF files (VETA). Our results show that tool performance increases after HCM-specific calibration of thresholds. After excluding potential biases due to circularity type I issues, we identified ClinPred, MISTIC, FATHMM, MPC and MetaLR as the five best performer tools in discriminating HCM-associated variants. We propose combining these tools in order to prioritize unknown HCM missense variants that should be closely followed-up in the clinic.

Loss-of-function, gain-of-function and dominant-negative mutations have profoundly different effects on protein structure

Most known pathogenic mutations occur in protein-coding regions of DNA and change the way proteins are made. Taking protein structure into account has therefore provided great insight into the molecular mechanisms underlying human genetic disease. While there has been much focus on how mutations can disrupt protein structure and thus cause a loss of function (LOF), alternative mechanisms, specifically dominant-negative (DN) and gain-of-function (GOF) effects, are less understood. Here, we investigate the protein-level effects of pathogenic missense mutations associated with different molecular mechanisms. We observe striking differences between recessive vs dominant, and LOF vs non-LOF mutations, with dominant, non-LOF disease mutations having much milder effects on protein structure, and DN mutations being highly enriched at protein interfaces. We also find that nearly all computational variant effect predictors, even those based solely on sequence conservation, underperform on non-LOF mutations. However, we do show that non-LOF mutations could potentially be identified by their tendency to cluster in three-dimensional space. Overall, our work suggests that many pathogenic mutations that act via DN and GOF mechanisms are likely being missed by current variant prioritisation strategies, but that there is considerable scope to improve computational predictions through consideration of molecular disease mechanisms.

Most known pathogenic mutations occur in protein-coding regions of DNA and change the way proteins are made. Here the authors analyse the locations of thousands of human disease mutations and their predicted effects on protein structure and show that,while loss-of-function mutations tend to be highly disruptive, non-loss-of-function mutations are in general much milder at a protein structural level.

How Functional Genomics Can Keep Pace With VUS Identification

Over the last two decades, an exponentially expanding number of genetic variants have been identified associated with inherited cardiac conditions. These tremendous gains also present challenges in deciphering the clinical relevance of unclassified variants or variants of uncertain significance (VUS). This review provides an overview of the advancements (and challenges) in functional and computational approaches to characterize variants and help keep pace with VUS identification related to inherited heart diseases.

Longitudinal dynamics of clonal hematopoiesis identifies gene-specific fitness effects

Clonal hematopoiesis of indeterminate potential (CHIP) increases rapidly in prevalence beyond age 60 and has been associated with increased risk for malignancy, heart disease and ischemic stroke. CHIP is driven by somatic mutations in hematopoietic stem and progenitor cells (HSPCs). Because mutations in HSPCs often drive leukemia, we hypothesized that HSPC fitness substantially contributes to transformation from CHIP to leukemia. HSPC fitness is defined as the proliferative advantage over cells carrying no or only neutral mutations. If mutations in different genes lead to distinct fitness advantages, this could enable patient stratification. We quantified the fitness effects of mutations over 12 years in older age using longitudinal sequencing and developed a filtering method that considers individual mutational context alongside mutation co-occurrence to quantify the growth potential of variants within individuals. We found that gene-specific fitness differences can outweigh inter-individual variation and, therefore, could form the basis for personalized clinical management.

The impact of rare germline variants on human somatic mutation processes

Somatic mutations are an inevitable component of ageing and the most important cause of cancer. The rates and types of somatic mutation vary across individuals, but relatively few inherited influences on mutation processes are known. We perform a gene-based rare variant association study with diverse mutational processes, using human cancer genomes from over 11,000 individuals of European ancestry. By combining burden and variance tests, we identify 207 associations involving 15 somatic mutational phenotypes and 42 genes that replicated in an independent data set at a false discovery rate of 1%. We associate rare inherited deleterious variants in genes such as MSH3, EXO1, SETD2, and MTOR with two phenotypically different forms of DNA mismatch repair deficiency, and variants in genes such as EXO1, PAXIP1, RIF1, and WRN with deficiency in homologous recombination repair. In addition, we identify associations with other mutational processes, such as APEX1 with APOBEC-signature mutagenesis. Many of the genes interact with each other and with known mutator genes within cellular sub-networks. Considered collectively, damaging variants in the identified genes are prevalent in the population. We suggest that rare germline variation in diverse genes commonly impacts mutational processes in somatic cells.

Interpreting protein variant effects with computational predictors and deep mutational scanning

Computational predictors of genetic variant effect have advanced rapidly in recent years. These programs provide clinical and research laboratories with a rapid and scalable method to assess the likely impacts of novel variants. However, it can be difficult to know to what extent we can trust their results. To benchmark their performance, predictors are often tested against large datasets of known pathogenic and benign variants. These benchmarking data may overlap with the data used to train some supervised predictors, which leads to data re-use or circularity, resulting in inflated performance estimates for those predictors. Furthermore, new predictors are usually found by their authors to be superior to all previous predictors, which suggests some degree of computational bias in their benchmarking. Large-scale functional assays known as deep mutational scans provide one possible solution to this problem, providing independent datasets of variant effect measurements. In this Review, we discuss some of the key advances in predictor methodology, current benchmarking strategies and how data derived from deep mutational scans can be used to overcome the issue of data circularity. We also discuss the ability of such functional assays to directly predict clinical impacts of mutations and how this might affect the future need for variant effect predictors.

Genome interpretation using in silico predictors of variant impact

Estimating the effects of variants found in disease driver genes opens the door to personalized therapeutic opportunities. Clinical associations and laboratory experiments can only characterize a tiny fraction of all the available variants, leaving the majority as variants of unknown significance (VUS). In silico methods bridge this gap by providing instant estimates on a large scale, most often based on the numerous genetic differences between species. Despite concerns that these methods may lack reliability in individual subjects, their numerous practical applications over cohorts suggest they are already helpful and have a role to play in genome interpretation when used at the proper scale and context. In this review, we aim to gain insights into the training and validation of these variant effect predicting methods and illustrate representative types of experimental and clinical applications. Objective performance assessments using various datasets that are not yet published indicate the strengths and limitations of each method. These show that cautious use of in silico variant impact predictors is essential for addressing genome interpretation challenges.