GEMME: a simple and fast global epistatic model predicting mutational effects

Fifty years after the first identification of Toscana virus in Italy: Genomic characterization of viral isolates within lineage A and aminoacidic markers of evolution

Toscana Virus (TosV) was firstly isolated from phlebotomine in our Institute about fifty years ago. Later, in 1984-1985, TosV infection, although asymptomatic in most cases, was shown to cause disease in humans, mainly fever and meningitis. By means of genetic analysis of part of M segment, we describe 3 new viral isolates obtained directly from cerebrospinal fluid or sera samples of patients diagnosed with TosV infection in July 2020 in Tuscany region. Phylogenesis was used to propose the clustering of TosV lineage A strains in 3 main groups, whereas deep mutational analysis based on 12 amino acid positions, allowed the identification of 9 putative strains. We discuss deep mutational analysis as a method to identify molecular signature of host adaptation and/or pathogenesis.

QAFI: a novel method for quantitative estimation of missense variant impact using protein-specific predictors and ensemble learning

Next-generation sequencing (NGS) has revolutionized genetic diagnostics, yet its application in precision medicine remains incomplete, despite significant advances in computational tools for variant annotation. Many variants remain unannotated, and existing tools often fail to accurately predict the range of impacts that variants have on protein function. This limitation restricts their utility in relevant applications such as predicting disease severity and onset age. In response to these challenges, a new generation of computational models is emerging, aimed at producing quantitative predictions of genetic variant impacts. However, the field is still in its early stages, and several issues need to be addressed, including improved performance and better interpretability. This study introduces QAFI, a novel methodology that integrates protein-specific regression models within an ensemble learning framework, utilizing conservation-based and structure-related features derived from AlphaFold models. Our findings indicate that QAFI significantly enhances the accuracy of quantitative predictions across various proteins. The approach has been rigorously validated through its application in the CAGI6 contest, focusing on ARSA protein variants, and further tested on a comprehensive set of clinically labeled variants, demonstrating its generalizability and robust predictive power. The straightforward nature of our models may also contribute to better interpretability of the results.

MuToN Quantifies Binding Affinity Changes upon Protein Mutations by Geometric Deep Learning

Assessing changes in protein-protein binding affinity due to mutations helps understanding a wide range of crucial biological processes within cells. Despite significant efforts to create accurate computational models, predicting how mutations affect affinity remains challenging due to the complexity of the biological mechanisms involved. In the present work, a geometric deep learning framework called MuToN is introduced for quantifying protein binding affinity change upon residue mutations. The method, designed with geometric attention networks, is mechanism-aware. It captures changes in the protein binding interfaces of mutated complexes and assesses the allosteric effects of amino acids. Experimental results highlight MuToN's superiority compared to existing methods. Additionally, MuToN's flexibility and effectiveness are illustrated by its precise predictions of binding affinity changes between SARS-CoV-2 variants and the ACE2 complex.

Zero-shot prediction of mutation effects with multimodal deep representation learning guides protein engineering

Mutations in amino acid sequences can provoke changes in protein function. Accurate and unsupervised prediction of mutation effects is critical in biotechnology and biomedicine, but remains a fundamental challenge. To resolve this challenge, here we present Protein Mutational Effect Predictor (ProMEP), a general and multiple sequence alignment-free method that enables zero-shot prediction of mutation effects. A multimodal deep representation learning model embedded in ProMEP was developed to comprehensively learn both sequence and structure contexts from ~160 million proteins. ProMEP achieves state-of-the-art performance in mutational effect prediction and accomplishes a tremendous improvement in speed, enabling efficient and intelligent protein engineering. Specifically, ProMEP accurately forecasts mutational consequences on the gene-editing enzymes TnpB and TadA, and successfully guides the development of high-performance gene-editing tools with their engineered variants. The gene-editing efficiency of a 5-site mutant of TnpB reaches up to 74.04% (vs 24.66% for the wild type); and the base editing tool developed on the basis of a TadA 15-site mutant (in addition to the A106V/D108N double mutation that renders deoxyadenosine deaminase activity to TadA) exhibits an A-to-G conversion frequency of up to 77.27% (vs 69.80% for ABE8e, a previous TadA-based adenine base editor) with significantly reduced bystander and off-target effects compared to ABE8e. ProMEP not only showcases superior performance in predicting mutational effects on proteins but also demonstrates a great capability to guide protein engineering. Therefore, ProMEP enables efficient exploration of the gigantic protein space and facilitates practical design of proteins, thereby advancing studies in biomedicine and synthetic biology.

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.

Enhancing efficiency of protein language models with minimal wet-lab data through few-shot learning

Accurately modeling the protein fitness landscapes holds great importance for protein engineering. Pre-trained protein language models have achieved state-of-the-art performance in predicting protein fitness without wet-lab experimental data, but their accuracy and interpretability remain limited. On the other hand, traditional supervised deep learning models require abundant labeled training examples for performance improvements, posing a practical barrier. In this work, we introduce FSFP, a training strategy that can effectively optimize protein language models under extreme data scarcity for fitness prediction. By combining meta-transfer learning, learning to rank, and parameter-efficient fine-tuning, FSFP can significantly boost the performance of various protein language models using merely tens of labeled single-site mutants from the target protein. In silico benchmarks across 87 deep mutational scanning datasets demonstrate FSFP's superiority over both unsupervised and supervised baselines. Furthermore, we successfully apply FSFP to engineer the Phi29 DNA polymerase through wet-lab experiments, achieving a 25% increase in the positive rate. These results underscore the potential of our approach in aiding AI-guided protein engineering.

Functional effects of mutations in proteins can be predicted and interpreted by guided selection of sequence covariation information

Predicting the effects of one or more mutations to the in vivo or in vitro properties of a wild-type protein is a major computational challenge, due to the presence of epistasis, that is, of interactions between amino acids in the sequence. We introduce a computationally efficient procedure to build minimal epistatic models to predict mutational effects by combining evolutionary (homologous sequence) and few mutational-scan data. Mutagenesis measurements guide the selection of links in a sparse graphical model, while the parameters on the nodes and the edges are inferred from sequence data. We show, on 10 mutational scans, that our pipeline exhibits performances comparable to state-of-the-art deep networks trained on many more data, while requiring much less parameters and being hence more interpretable. In particular, the identified interactions adapt to the wild-type protein and to the fitness or biochemical property experimentally measured, mostly focus on key functional sites, and are not necessarily related to structural contacts. Therefore, our method is able to extract information relevant for one mutational experiment from homologous sequence data reflecting the multitude of structural and functional constraints acting on proteins throughout evolution.

Destabilization and Degradation of a Disease-Linked PGM1 Protein Variant

PGM1-linked congenital disorder of glycosylation (PGM1-CDG) is an autosomal recessive disease characterized by several phenotypes, some of which are life-threatening. Research focusing on the disease-related variants of the α-D-phosphoglucomutase 1 (PGM1) protein has shown that several are insoluble in vitro and expressed at low levels in patient fibroblasts. Due to these observations, we hypothesized that some disease-linked PGM1 protein variants are structurally destabilized and subject to protein quality control (PQC) and rapid intracellular degradation. Employing yeast-based assays, we show that a disease-associated human variant, PGM1 L516P, is insoluble, inactive, and highly susceptible to ubiquitylation and rapid degradation by the proteasome. In addition, we show that PGM1 L516P forms aggregates in S. cerevisiae and that both the aggregation pattern and the abundance of PGM1 L516P are chaperone-dependent. Finally, using computational methods, we perform saturation mutagenesis to assess the impact of all possible single residue substitutions in the PGM1 protein. These analyses identify numerous missense variants with predicted detrimental effects on protein function and stability. We suggest that many disease-linked PGM1 variants are subject to PQC-linked degradation and that our in silico site-saturated data set may assist in the mechanistic interpretation of PGM1 variants.

Illuminating the function of the orphan transporter, SLC22A10, in humans and other primates

SLC22A10 is an orphan transporter with unknown substrates and function. The goal of this study is to elucidate its substrate specificity and functional characteristics. In contrast to orthologs from great apes, human SLC22A10, tagged with green fluorescent protein, is not expressed on the plasma membrane. Cells expressing great ape SLC22A10 orthologs exhibit significant accumulation of estradiol-17β-glucuronide, unlike those expressing human SLC22A10. Sequence alignments reveal a proline at position 220 in humans, which is a leucine in great apes. Replacing proline with leucine in SLC22A10-P220L restores plasma membrane localization and uptake function. Neanderthal and Denisovan genomes show proline at position 220, akin to modern humans, indicating functional loss during hominin evolution. Human SLC22A10 is a unitary pseudogene due to a fixed missense mutation, P220, while in great apes, its orthologs transport sex steroid conjugates. Characterizing SLC22A10 across species sheds light on its biological role, influencing organism development and steroid homeostasis.

Deep mutational scanning reveals a correlation between degradation and toxicity of thousands of aspartoacylase variants

Unstable proteins are prone to form non-native interactions with other proteins and thereby may become toxic. To mitigate this, destabilized proteins are targeted by the protein quality control network. Here we present systematic studies of the cytosolic aspartoacylase, ASPA, where variants are linked to Canavan disease, a lethal neurological disorder. We determine the abundance of 6152 of the 6260 ( ~ 98%) possible single amino acid substitutions and nonsense ASPA variants in human cells. Most low abundance variants are degraded through the ubiquitin-proteasome pathway and become toxic upon prolonged expression. The data correlates with predicted changes in thermodynamic stability, evolutionary conservation, and separate disease-linked variants from benign variants. Mapping of degradation signals (degrons) shows that these are often buried and the C-terminal region functions as a degron. The data can be used to interpret Canavan disease variants and provide insight into the relationship between protein stability, degradation and cell fitness.

Changing selection on amino acid substitutions in Gag protein between major HIV-1 subtypes

Amino acid preferences at a protein site depend on the role of this site in protein function and structure as well as on external constraints. All these factors can change in the course of evolution, making amino acid propensities of a site time-dependent. When viral subtypes divergently evolve in different host subpopulations, such changes may depend on genetic, medical, and sociocultural differences between these subpopulations. Here, using our previously developed phylogenetic approach, we describe sixty-nine amino acid sites of the Gag protein of human immunodeficiency virus type 1 (HIV-1) where amino acids have different impact on viral fitness in six major subtypes of the type M. These changes in preferences trigger adaptive evolution; indeed, 32 (46 per cent) of these sites experienced strong positive selection at least in one of the subtypes. At some of the sites, changes in amino acid preferences may be associated with differences in immune escape between subtypes. The prevalence of an amino acid in a protein site within a subtype is only a poor predictor for whether this amino acid is preferred in this subtype according to the phylogenetic analysis. Therefore, attempts to identify the factors of viral evolution from comparative genomics data should integrate across multiple sources of information.

Guidelines for releasing a variant effect predictor

Computational methods for assessing the likely impacts of mutations, known as variant effect predictors (VEPs), are widely used in the assessment and interpretation of human genetic variation, as well as in other applications like protein engineering. Many different VEPs have been released to date, and there is tremendous variability in their underlying algorithms and outputs, and in the ways in which the methodologies and predictions are shared. This leads to considerable challenges for end users in knowing which VEPs to use and how to use them. Here, to address these issues, we provide guidelines and recommendations for the release of novel VEPs. Emphasising open-source availability, transparent methodologies, clear variant effect score interpretations, standardised scales, accessible predictions, and rigorous training data disclosure, we aim to improve the usability and interpretability of VEPs, and promote their integration into analysis and evaluation pipelines. We also provide a large, categorised list of currently available VEPs, aiming to facilitate the discovery and encourage the usage of novel methods within the scientific community.

Cellular and molecular mechanisms of aspartoacylase and its role in Canavan disease

Canavan disease is an autosomal recessive and lethal neurological disorder, characterized by the spongy degeneration of the white matter in the brain. The disease is caused by a deficiency of the cytosolic aspartoacylase (ASPA) enzyme, which catalyzes the hydrolysis of N-acetyl-aspartate (NAA), an abundant brain metabolite, into aspartate and acetate. On the physiological level, the mechanism of pathogenicity remains somewhat obscure, with multiple, not mutually exclusive, suggested hypotheses. At the molecular level, recent studies have shown that most disease linked ASPA gene variants lead to a structural destabilization and subsequent proteasomal degradation of the ASPA protein variants, and accordingly Canavan disease should in general be considered a protein misfolding disorder. Here, we comprehensively summarize the molecular and cell biology of ASPA, with a particular focus on disease-linked gene variants and the pathophysiology of Canavan disease. We highlight the importance of high-throughput technologies and computational prediction tools for making genotype-phenotype predictions as we await the results of ongoing trials with gene therapy for Canavan disease.

Cryptic genetic variation shapes the fate of gene duplicates in a protein interaction network

Paralogous genes are often redundant for long periods of time before they diverge in function. While their functions are preserved, paralogous proteins can accumulate mutations that, through epistasis, could impact their fate in the future. By quantifying the impact of all single-amino acid substitutions on the binding of two myosin proteins to their interaction partners, we find that the future evolution of these proteins is highly contingent on their regulatory divergence and the mutations that have silently accumulated in their protein binding domains. Differences in the promoter strength of the two paralogs amplify the impact of mutations on binding in the lowly expressed one. While some mutations would be sufficient to non-functionalize one paralog, they would have minimal impact on the other. Our results reveal how functionally equivalent protein domains could be destined to specific fates by regulatory and cryptic coding sequence changes that currently have little to no functional impact.

Empowering Protein Engineering through Recombination of Beneficial Substitutions

Directed evolution stands as a seminal technology for generating novel protein functionalities, a cornerstone in biocatalysis, metabolic engineering, and synthetic biology. Today, with the development of various mutagenesis methods and advanced analytical machines, the challenge of diversity generation and high-throughput screening platforms is largely solved, and one of the remaining challenges is: how to empower the potential of single beneficial substitutions with recombination to achieve the epistatic effect. This review overviews experimental and computer-assisted recombination methods in protein engineering campaigns. In addition, integrated and machine learning-guided strategies were highlighted to discuss how these recombination approaches contribute to generating the screening library with better diversity, coverage, and size. A decision tree was finally summarized to guide the further selection of proper recombination strategies in practice, which was beneficial for accelerating protein engineering.

MLe-KCNQ2: An Artificial Intelligence Model for the Prognosis of Missense KCNQ2 Gene Variants

Despite the increasing availability of genomic data and enhanced data analysis procedures, predicting the severity of associated diseases remains elusive in the absence of clinical descriptors. To address this challenge, we have focused on the KV7.2 voltage-gated potassium channel gene (KCNQ2), known for its link to developmental delays and various epilepsies, including self-limited benign familial neonatal epilepsy and epileptic encephalopathy. Genome-wide tools often exhibit a tendency to overestimate deleterious mutations, frequently overlooking tolerated variants, and lack the capacity to discriminate variant severity. This study introduces a novel approach by evaluating multiple machine learning (ML) protocols and descriptors. The combination of genomic information with a novel Variant Frequency Index (VFI) builds a robust foundation for constructing reliable gene-specific ML models. The ensemble model, MLe-KCNQ2, formed through logistic regression, support vector machine, random forest and gradient boosting algorithms, achieves specificity and sensitivity values surpassing 0.95 (AUC-ROC > 0.98). The ensemble MLe-KCNQ2 model also categorizes pathogenic mutations as benign or severe, with an area under the receiver operating characteristic curve (AUC-ROC) above 0.67. This study not only presents a transferable methodology for accurately classifying KCNQ2 missense variants, but also provides valuable insights for clinical counseling and aids in the determination of variant severity. The research context emphasizes the necessity of precise variant classification, especially for genes like KCNQ2, contributing to the broader understanding of gene-specific challenges in the field of genomic research. The MLe-KCNQ2 model stands as a promising tool for enhancing clinical decision making and prognosis in the realm of KCNQ2-related pathologies.

A mutational atlas for Parkin proteostasis

Proteostasis can be disturbed by mutations affecting folding and stability of the encoded protein. An example is the ubiquitin ligase Parkin, where gene variants result in autosomal recessive Parkinsonism. To uncover the pathological mechanism and provide comprehensive genotype-phenotype information, variant abundance by massively parallel sequencing (VAMP-seq) is leveraged to quantify the abundance of Parkin variants in cultured human cells. The resulting mutational map, covering 9219 out of the 9300 possible single-site amino acid substitutions and nonsense Parkin variants, shows that most low abundance variants are proteasome targets and are located within the structured domains of the protein. Half of the known disease-linked variants are found at low abundance. Systematic mapping of degradation signals (degrons) reveals an exposed degron region proximal to the so-called "activation element". This work provides examples of how missense variants may cause degradation either via destabilization of the native protein, or by introducing local signals for degradation.

PanEffect: a pan-genome visualization tool for variant effects in maize

SUMMARY

Understanding the effects of genetic variants is crucial for accurately predicting traits and functional outcomes. Recent approaches have utilized artificial intelligence and protein language models to score all possible missense variant effects at the proteome level for a single genome, but a reliable tool is needed to explore these effects at the pan-genome level. To address this gap, we introduce a new tool called PanEffect. We implemented PanEffect at MaizeGDB to enable a comprehensive examination of the potential effects of coding variants across 50 maize genomes. The tool allows users to visualize over 550 million possible amino acid substitutions in the B73 maize reference genome and to observe the effects of the 2.3 million natural variations in the maize pan-genome. Each variant effect score, calculated from the Evolutionary Scale Modeling (ESM) protein language model, shows the log-likelihood ratio difference between B73 and all variants in the pan-genome. These scores are shown using heatmaps spanning benign outcomes to potential functional consequences. In addition, PanEffect displays secondary structures and functional domains along with the variant effects, offering additional functional and structural context. Using PanEffect, researchers now have a platform to explore protein variants and identify genetic targets for crop enhancement.

AVAILABILITY AND IMPLEMENTATION

The PanEffect code is freely available on GitHub (https://github.com/Maize-Genetics-and-Genomics-Database/PanEffect). A maize implementation of PanEffect and underlying datasets are available at MaizeGDB (https://www.maizegdb.org/effect/maize/).

Is Novelty Predictable?

Machine learning-based design has gained traction in the sciences, most notably in the design of small molecules, materials, and proteins, with societal applications ranging from drug development and plastic degradation to carbon sequestration. When designing objects to achieve novel property values with machine learning, one faces a fundamental challenge: how to push past the frontier of current knowledge, distilled from the training data into the model, in a manner that rationally controls the risk of failure. If one trusts learned models too much in extrapolation, one is likely to design rubbish. In contrast, if one does not extrapolate, one cannot find novelty. Herein, we ponder how one might strike a useful balance between these two extremes. We focus in particular on designing proteins with novel property values, although much of our discussion is relevant to machine learning-based design more broadly.

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.

Rendering protein mutation movies with MutAmore

BACKGROUND

The success of AlphaFold2 in reliable protein three-dimensional (3D) structure prediction, assists the move of structural biology toward studies of protein dynamics and mutational impact on structure and function. This transition needs tools that qualitatively assess alternative 3D conformations.

RESULTS

We introduce MutAmore, a bioinformatics tool that renders individual images of protein 3D structures for, e.g., sequence mutations into a visually intuitive movie format. MutAmore streamlines a pipeline casting single amino-acid variations (SAVs) into a dynamic 3D mutation movie providing a qualitative perspective on the mutational landscape of a protein. By default, the tool first generates all possible variants of the sequence reachable through SAVs (L*19 for proteins with L residues). Next, it predicts the structural conformation for all L*19 variants using state-of-the-art models. Finally, it visualizes the mutation matrix and produces a color-coded 3D animation. Alternatively, users can input other types of variants, e.g., from experimental structures.

CONCLUSION

MutAmore samples alternative protein configurations to study the dynamical space accessible from SAVs in the post-AlphaFold2 era of structural biology. As the field shifts towards the exploration of alternative conformations of proteins, MutAmore aids in the understanding of the structural impact of mutations by providing a flexible pipeline for the generation of protein mutation movies using current and future structure prediction models.

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.

ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers

Protein design holds immense potential for optimizing naturally occurring proteins, with broad applications in drug discovery, material design, and sustainability. However, computational methods for protein engineering are confronted with significant challenges, such as an expansive design space, sparse functional regions, and a scarcity of available labels. These issues are further exacerbated in practice by the fact most real-life design scenarios necessitate the simultaneous optimization of multiple properties. In this work, we introduce ProteinNPT, a non-parametric transformer variant tailored to protein sequences and particularly suited to label-scarce and multi-task learning settings. We first focus on the supervised fitness prediction setting and develop several cross-validation schemes which support robust performance assessment. We subsequently reimplement prior top-performing baselines, introduce several extensions of these baselines by integrating diverse branches of the protein engineering literature, and demonstrate that ProteinNPT consistently outperforms all of them across a diverse set of protein property prediction tasks. Finally, we demonstrate the value of our approach for iterative protein design across extensive in silico Bayesian optimization and conditional sampling experiments.

Alignment-based Protein Mutational Landscape Prediction: Doing More with Less

The wealth of genomic data has boosted the development of computational methods predicting the phenotypic outcomes of missense variants. The most accurate ones exploit multiple sequence alignments, which can be costly to generate. Recent efforts for democratizing protein structure prediction have overcome this bottleneck by leveraging the fast homology search of MMseqs2. Here, we show the usefulness of this strategy for mutational outcome prediction through a large-scale assessment of 1.5M missense variants across 72 protein families. Our study demonstrates the feasibility of producing alignment-based mutational landscape predictions that are both high-quality and compute-efficient for entire proteomes. We provide the community with the whole human proteome mutational landscape and simplified access to our predictive pipeline.

The fitness cost of spurious phosphorylation

The fidelity of signal transduction requires the binding of regulatory molecules to their cognate targets. However, the crowded cell interior risks off-target interactions between proteins that are functionally unrelated. How such off-target interactions impact fitness is not generally known, but quantifying this is required to understand the constraints faced by cell systems as they evolve. Here, we use the model organism S. cerevisiae to inducibly express tyrosine kinases. Because yeast lacks bona fide tyrosine kinases, most of the resulting tyrosine phosphorylation is spurious. This provides a suitable system to measure the impact of artificial protein interactions on fitness. We engineered 44 yeast strains each expressing a tyrosine kinase, and quantitatively analysed their phosphoproteomes. This analysis resulted in ~30,000 phosphosites mapping to ~3,500 proteins. Examination of the fitness costs in each strain revealed a strong correlation between the number of spurious pY sites and decreased growth. Moreover, the analysis of pY effects on protein structure and on protein function revealed over 1000 pY events that we predict to be deleterious. However, we also find that a large number of the spurious pY sites have a negligible effect on fitness, possibly because of their low stoichiometry. This result is consistent with our evolutionary analyses demonstrating a lack of phosphotyrosine counter-selection in species with bona fide tyrosine kinases. Taken together, our results suggest that, alongside the risk for toxicity, the cell can tolerate a large degree of non-functional crosstalk as interaction networks evolve.

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.

ETLD: an encoder-transformation layer-decoder architecture for protein contact and mutation effects prediction

The latent features extracted from the multiple sequence alignments (MSAs) of homologous protein families are useful for identifying residue-residue contacts, predicting mutation effects, shaping protein evolution, etc. Over the past three decades, a growing body of supervised and unsupervised machine learning methods have been applied to this field, yielding fruitful results. Here, we propose a novel self-supervised model, called encoder-transformation layer-decoder (ETLD) architecture, capable of capturing protein sequence latent features directly from MSAs. Compared to the typical autoencoder model, ETLD introduces a transformation layer with the ability to learn inter-site couplings, which can be used to parse out the two-dimensional residue-residue contacts map after a simple mathematical derivation or an additional supervised neural network. ETLD retains the process of encoding and decoding sequences, and the predicted probabilities of amino acids at each site can be further used to construct the mutation landscapes for mutation effects prediction, outperforming advanced models such as GEMME, DeepSequence and EVmutation in general. Overall, ETLD is a highly interpretable unsupervised model with great potential for improvement and can be further combined with supervised methods for more extensive and accurate predictions.

Illuminating the Function of the Orphan Transporter, SLC22A10 in Humans and Other Primates

SLC22A10 is classified as an orphan transporter with unknown substrates and function. Here we describe the discovery of the substrate specificity and functional characteristics of SLC22A10. The human SLC22A10 tagged with green fluorescent protein was found to be absent from the plasma membrane, in contrast to the SLC22A10 orthologs found in great apes. Estradiol-17β-glucuronide accumulated in cells expressing great ape SLC22A10 orthologs (over 4-fold, p<0.001). In contrast, human SLC22A10 displayed no uptake function. Sequence alignments revealed two amino acid differences including a proline at position 220 of the human SLC22A10 and a leucine at the same position of great ape orthologs. Site-directed mutagenesis yielding the human SLC22A10-P220L produced a protein with excellent plasma membrane localization and associated uptake function. Neanderthal and Denisovan genomes show human-like sequences at proline 220 position, corroborating that SLC22A10 were rendered nonfunctional during hominin evolution after the divergence from the pan lineage (chimpanzees and bonobos). These findings demonstrate that human SLC22A10 is a unitary pseudogene and was inactivated by a missense mutation that is fixed in humans, whereas orthologs in great apes transport sex steroid conjugates.

Illuminating the Function of the Orphan Transporter, SLC22A10 in Humans and Other Primates

SLC22A10 is classified as an orphan transporter with unknown substrates and function. Here we describe the discovery of the substrate specificity and functional characteristics of SLC22A10. The human SLC22A10 tagged with green fluorescent protein was found to be absent from the plasma membrane, in contrast to the SLC22A10 orthologs found in great apes. Estradiol-17β-glucuronide accumulated in cells expressing great ape SLC22A10 orthologs (over 4-fold, p<0.001). In contrast, human SLC22A10 displayed no uptake function. Sequence alignments revealed two amino acid differences including a proline at position 220 of the human SLC22A10 and a leucine at the same position of great ape orthologs. Site-directed mutagenesis yielding the human SLC22A10-P220L produced a protein with excellent plasma membrane localization and associated uptake function. Neanderthal and Denisovan genomes show human-like sequences at proline 220 position, corroborating that SLC22A10 were rendered nonfunctional during hominin evolution after the divergence from the pan lineage (chimpanzees and bonobos). These findings demonstrate that human SLC22A10 is a unitary pseudogene and was inactivated by a missense mutation that is fixed in humans, whereas orthologs in great apes transport sex steroid conjugates.

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.

Mega-scale experimental analysis of protein folding stability in biology and design

Advances in DNA sequencing and machine learning are providing insights into protein sequences and structures on an enormous scale1. However, the energetics driving folding are invisible in these structures and remain largely unknown2. The hidden thermodynamics of folding can drive disease3,4, shape protein evolution5-7 and guide protein engineering8-10, and new approaches are needed to reveal these thermodynamics for every sequence and structure. Here we present cDNA display proteolysis, a method for measuring thermodynamic folding stability for up to 900,000 protein domains in a one-week experiment. From 1.8 million measurements in total, we curated a set of around 776,000 high-quality folding stabilities covering all single amino acid variants and selected double mutants of 331 natural and 148 de novo designed protein domains 40-72 amino acids in length. Using this extensive dataset, we quantified (1) environmental factors influencing amino acid fitness, (2) thermodynamic couplings (including unexpected interactions) between protein sites, and (3) the global divergence between evolutionary amino acid usage and protein folding stability. We also examined how our approach could identify stability determinants in designed proteins and evaluate design methods. The cDNA display proteolysis method is fast, accurate and uniquely scalable, and promises to reveal the quantitative rules for how amino acid sequences encode folding stability.

EvoRator2: Predicting Site-specific Amino Acid Substitutions Based on Protein Structural Information Using Deep Learning

Multiple sequence alignments (MSAs) are the workhorse of molecular evolution and structural biology research. From MSAs, the amino acids that are tolerated at each site during protein evolution can be inferred. However, little is known regarding the repertoire of tolerated amino acids in proteins when only a few or no sequence homologs are available, such as orphan and de novo designed proteins. Here we present EvoRator2, a deep-learning algorithm trained on over 15,000 protein structures that can predict which amino acids are tolerated at any given site, based exclusively on protein structural information mined from atomic coordinate files. We show that EvoRator2 obtained satisfying results for the prediction of position-weighted scoring matrices (PSSM). We further show that EvoRator2 obtained near state-of-the-art performance on proteins with high quality structures in predicting the effect of mutations in deep mutation scanning (DMS) experiments and that for certain DMS targets, EvoRator2 outperformed state-of-the-art methods. We also show that by combining EvoRator2's predictions with those obtained by a state-of-the-art deep-learning method that accounts for the information in the MSA, the prediction of the effect of mutation in DMS experiments was improved in terms of both accuracy and stability. EvoRator2 is designed to predict which amino-acid substitutions are tolerated in such proteins without many homologous sequences, including orphan or de novo designed proteins. We implemented our approach in the EvoRator web server (https://evorator.tau.ac.il).

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.

Deep Local Analysis deconstructs protein-protein interfaces and accurately estimates binding affinity changes upon mutation

MOTIVATION

The spectacular recent advances in protein and protein complex structure prediction hold promise for reconstructing interactomes at large-scale and residue resolution. Beyond determining the 3D arrangement of interacting partners, modeling approaches should be able to unravel the impact of sequence variations on the strength of the association.

RESULTS

In this work, we report on Deep Local Analysis, a novel and efficient deep learning framework that relies on a strikingly simple deconstruction of protein interfaces into small locally oriented residue-centered cubes and on 3D convolutions recognizing patterns within cubes. Merely based on the two cubes associated with the wild-type and the mutant residues, DLA accurately estimates the binding affinity change for the associated complexes. It achieves a Pearson correlation coefficient of 0.735 on about 400 mutations on unseen complexes. Its generalization capability on blind datasets of complexes is higher than the state-of-the-art methods. We show that taking into account the evolutionary constraints on residues contributes to predictions. We also discuss the influence of conformational variability on performance. Beyond the predictive power on the effects of mutations, DLA is a general framework for transferring the knowledge gained from the available non-redundant set of complex protein structures to various tasks. For instance, given a single partially masked cube, it recovers the identity and physicochemical class of the central residue. Given an ensemble of cubes representing an interface, it predicts the function of the complex.

AVAILABILITY AND IMPLEMENTATION

Source code and models are available at http://gitlab.lcqb.upmc.fr/DLA/DLA.git.

Lysine deserts prevent adventitious ubiquitylation of ubiquitin-proteasome components

In terms of its relative frequency, lysine is a common amino acid in the human proteome. However, by bioinformatics we find hundreds of proteins that contain long and evolutionarily conserved stretches completely devoid of lysine residues. These so-called lysine deserts show a high prevalence in intrinsically disordered proteins with known or predicted functions within the ubiquitin-proteasome system (UPS), including many E3 ubiquitin-protein ligases and UBL domain proteasome substrate shuttles, such as BAG6, RAD23A, UBQLN1 and UBQLN2. We show that introduction of lysine residues into the deserts leads to a striking increase in ubiquitylation of some of these proteins. In case of BAG6, we show that ubiquitylation is catalyzed by the E3 RNF126, while RAD23A is ubiquitylated by E6AP. Despite the elevated ubiquitylation, mutant RAD23A appears stable, but displays a partial loss of function phenotype in fission yeast. In case of UBQLN1 and BAG6, introducing lysine leads to a reduced abundance due to proteasomal degradation of the proteins. For UBQLN1 we show that arginine residues within the lysine depleted region are critical for its ability to form cytosolic speckles/inclusions. We propose that selective pressure to avoid lysine residues may be a common evolutionary mechanism to prevent unwarranted ubiquitylation and/or perhaps other lysine post-translational modifications. This may be particularly relevant for UPS components as they closely and frequently encounter the ubiquitylation machinery and are thus more susceptible to nonspecific ubiquitylation.

A comprehensive map of human glucokinase variant activity

BACKGROUND

Glucokinase (GCK) regulates insulin secretion to maintain appropriate blood glucose levels. Sequence variants can alter GCK activity to cause hyperinsulinemic hypoglycemia or hyperglycemia associated with GCK-maturity-onset diabetes of the young (GCK-MODY), collectively affecting up to 10 million people worldwide. Patients with GCK-MODY are frequently misdiagnosed and treated unnecessarily. Genetic testing can prevent this but is hampered by the challenge of interpreting novel missense variants.

RESULT

Here, we exploit a multiplexed yeast complementation assay to measure both hyper- and hypoactive GCK variation, capturing 97% of all possible missense and nonsense variants. Activity scores correlate with in vitro catalytic efficiency, fasting glucose levels in carriers of GCK variants and with evolutionary conservation. Hypoactive variants are concentrated at buried positions, near the active site, and at a region of known importance for GCK conformational dynamics. Some hyperactive variants shift the conformational equilibrium towards the active state through a relative destabilization of the inactive conformation.

CONCLUSION

Our comprehensive assessment of GCK variant activity promises to facilitate variant interpretation and diagnosis, expand our mechanistic understanding of hyperactive variants, and inform development of therapeutics targeting GCK.

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.

Epistasis between promoter activity and coding mutations shapes gene evolvability

The evolution of protein-coding genes proceeds as mutations act on two main dimensions: regulation of transcription level and the coding sequence. The extent and impact of the connection between these two dimensions are largely unknown because they have generally been studied independently. By measuring the fitness effects of all possible mutations on a protein complex at various levels of promoter activity, we show that promoter activity at the optimal level for the wild-type protein masks the effects of both deleterious and beneficial coding mutations. Mutations that are deleterious at low activity but masked at optimal activity are slightly destabilizing for individual subunits and binding interfaces. Coding mutations that increase protein abundance are beneficial at low expression but could potentially incur a cost at high promoter activity. We thereby demonstrate that promoter activity in interaction with protein properties can dictate which coding mutations are beneficial, neutral, or deleterious.

Building Quantitative Bridges between Dynamics and Sequences of SARS-CoV-2 Main Protease and a Diverse Set of Thirty-Two Proteins

Proteases are major drug targets for many viral diseases. However, mutations can render several antiprotease drugs inefficient rapidly even though these mutations may not alter protein structures significantly. Understanding relations between quickly mutating residues, protease structures, and the dynamics of the proteases is crucial for designing potent drugs. Due to this reason, we studied relations between the evolutionary information on residues in the amino acid sequences and protein dynamics for SARS-CoV-2 main protease. More precisely, we analyzed three dynamical quantities (Schlitter entropy, root-mean-square fluctuations, and dynamical flexibility index) and their relation to the amino acid conservation extracted from multiple sequence alignments of the main protease. We showed that a quantifiable similarity can be built between a sequence-based quantity called Jensen-Shannon conservation and those three dynamical quantities. We validated this similarity for a diverse set of 32 different proteins, other than the SARS-CoV-2 main protease. We believe that establishing these kinds of quantitative bridges will have larger implications for all viral proteases as well as all proteins.

Interpreting the molecular mechanisms of disease variants in human transmembrane proteins

Next-generation sequencing of human genomes reveals millions of missense variants, some of which may lead to loss of protein function and ultimately disease. Here, we investigate missense variants in membrane proteins-key drivers in cell signaling and recognition. We find enrichment of pathogenic variants in the transmembrane region across 19,000 functionally classified variants in human membrane proteins. To accurately predict variant consequences, one fundamentally needs to understand the underlying molecular processes. A key mechanism underlying pathogenicity in missense variants of soluble proteins has been shown to be loss of stability. Membrane proteins, however, are widely understudied. Here, we interpret variant effects on a larger scale by performing structure-based estimations of changes in thermodynamic stability using a membrane-specific energy function and analyses of sequence conservation during evolution of 15 transmembrane proteins. We find evidence for loss of stability being the cause of pathogenicity in more than half of the pathogenic variants, indicating that this is a driving factor also in membrane-protein-associated diseases. Our findings show how computational tools aid in gaining mechanistic insights into variant consequences for membrane proteins. To enable broader analyses of disease-related and population variants, we include variant mappings for the entire human proteome.

LambdaPP: Fast and accessible protein-specific phenotype predictions

The availability of accurate and fast artificial intelligence (AI) solutions predicting aspects of proteins are revolutionizing experimental and computational molecular biology. The webserver LambdaPP aspires to supersede PredictProtein, the first internet server making AI protein predictions available in 1992. Given a protein sequence as input, LambdaPP provides easily accessible visualizations of protein 3D structure, along with predictions at the protein level (GeneOntology, subcellular location), and the residue level (binding to metal ions, small molecules, and nucleotides; conservation; intrinsic disorder; secondary structure; alpha-helical and beta-barrel transmembrane segments; signal-peptides; variant effect) in seconds. The structure prediction provided by LambdaPP-leveraging ColabFold and computed in minutes-is based on MMseqs2 multiple sequence alignments. All other feature prediction methods are based on the pLM ProtT5. Queried by a protein sequence, LambdaPP computes protein and residue predictions almost instantly for various phenotypes, including 3D structure and aspects of protein function. LambdaPP is freely available for everyone to use under embed.predictprotein.org, the interactive results for the case study can be found under https://embed.predictprotein.org/o/Q9NZC2. The frontend of LambdaPP can be found on GitHub (github.com/sacdallago/embed.predictprotein.org), and can be freely used and distributed under the academic free use license (AFL-2). For high-throughput applications, all methods can be executed locally via the bio-embeddings (bioembeddings.com) python package, or docker image at ghcr.io/bioembeddings/bio_embeddings, which also includes the backend of LambdaPP.

Integrating deep mutational scanning and low-throughput mutagenesis data to predict the impact of amino acid variants

BACKGROUND

Evaluating the impact of amino acid variants has been a critical challenge for studying protein function and interpreting genomic data. High-throughput experimental methods like deep mutational scanning (DMS) can measure the effect of large numbers of variants in a target protein, but because DMS studies have not been performed on all proteins, researchers also model DMS data computationally to estimate variant impacts by predictors.

RESULTS

In this study, we extended a linear regression-based predictor to explore whether incorporating data from alanine scanning (AS), a widely used low-throughput mutagenesis method, would improve prediction results. To evaluate our model, we collected 146 AS datasets, mapping to 54 DMS datasets across 22 distinct proteins.

CONCLUSIONS

We show that improved model performance depends on the compatibility of the DMS and AS assays, and the scale of improvement is closely related to the correlation between DMS and AS results.

14-fold increased prevalence of rare glucokinase gene variant carriers in unselected Danish patients with newly diagnosed type 2 diabetes

AIMS

Rare variants in the glucokinase gene (GCK) cause Maturity-Onset Diabetes of the Young (MODY2/GCK-MODY). We investigated the prevalence of GCK variants, phenotypic characteristics, micro- and macrovascular disease at baseline and follow-up, and treatment among individuals with and without pathogenic GCK variants.

METHODS

This is a cross-sectional study in a population-based cohort of 5,433 individuals without diabetes (Inter99 cohort) and in 2,855 patients with a new clinical diagnosis of type 2 diabetes (DD2 cohort) with sequencing of GCK. Phenotypic characteristics, presence of micro- and macrovascular disease and treatment information were available for patients in the DD2 cohort at baseline and after an average follow-up of 7.4 years.

RESULTS

Twenty-two carriers of potentially deleterious GCK variants were found among patients with type 2 diabetes compared to three among 5,433 nondiabetic individuals [OR = 14.1 (95 % CI 4.2; 47.0), p = 8.9*10^-6]. Patients with type 2 diabetes carrying GCK variants had significantly lower waist circumference, hip circumference and BMI, compared to non-carriers. Three GCK variant carriers with diabetes had microvascular complications during follow-up.

CONCLUSIONS

Approximately 0.8% of Danish patients with newly diagnosed type 2 diabetes carry non-synonymous variants in GCK and resemble patients with GCK-MODY. Glucose-lowering treatment cessation should be considered in this subset of diabetes patients.

Pey A. Effect of naturally-occurring mutations on the stability and function of cancer-associated NQO1: Comparison of experiments and computation

Recent advances in DNA sequencing technologies are revealing a large individual variability of the human genome. Our capacity to establish genotype-phenotype correlations in such large-scale is, however, limited. This task is particularly challenging due to the multifunctional nature of many proteins. Here we describe an extensive analysis of the stability and function of naturally-occurring variants (found in the COSMIC and gnomAD databases) of the cancer-associated human NAD(P)H:quinone oxidoreductase 1 (NQO1). First, we performed in silico saturation mutagenesis studies (>5,000 substitutions) aimed to identify regions in NQO1 important for stability and function. We then experimentally characterized twenty-two naturally-occurring variants in terms of protein levels during bacterial expression, solubility, thermal stability, and coenzyme binding. These studies showed a good overall correlation between experimental analysis and computational predictions; also the magnitude of the effects of the substitutions are similarly distributed in variants from the COSMIC and gnomAD databases. Outliers in these experimental-computational genotype-phenotype correlations remain, and we discuss these on the grounds and limitations of our approaches. Our work represents a further step to characterize the mutational landscape of NQO1 in the human genome and may help to improve high-throughput in silico tools for genotype-phenotype correlations in this multifunctional protein associated with disease.

The Cancermuts software package for the prioritization of missense cancer variants: a case study of AMBRA1 in melanoma

Cancer genomics and cancer mutation databases have made an available wealth of information about missense mutations found in cancer patient samples. Contextualizing by means of annotation and predicting the effect of amino acid change help identify which ones are more likely to have a pathogenic impact. Those can be validated by means of experimental approaches that assess the impact of protein mutations on the cellular functions or their tumorigenic potential. Here, we propose the integrative bioinformatic approach Cancermuts, implemented as a Python package. Cancermuts is able to gather known missense cancer mutations from databases such as cBioPortal and COSMIC, and annotate them with the pathogenicity score REVEL as well as information on their source. It is also able to add annotations about the protein context these mutations are found in, such as post-translational modification sites, structured/unstructured regions, presence of short linear motifs, and more. We applied Cancermuts to the intrinsically disordered protein AMBRA1, a key regulator of many cellular processes frequently deregulated in cancer. By these means, we classified mutations of AMBRA1 in melanoma, where AMBRA1 is highly mutated and displays a tumor-suppressive role. Next, based on REVEL score, position along the sequence, and their local context, we applied cellular and molecular approaches to validate the predicted pathogenicity of a subset of mutations in an in vitro melanoma model. By doing so, we have identified two AMBRA1 mutations which show enhanced tumorigenic potential and are worth further investigation, highlighting the usefulness of the tool. Cancermuts can be used on any protein targets starting from minimal information, and it is available at https://www.github.com/ELELAB/cancermuts as free software.

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.

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.

Deciphering polymorphism in 61,157 Escherichia coli genomes via epistatic sequence landscapes

Characterizing the effect of mutations is key to understand the evolution of protein sequences and to separate neutral amino-acid changes from deleterious ones. Epistatic interactions between residues can lead to a context dependence of mutation effects. Context dependence constrains the amino-acid changes that can contribute to polymorphism in the short term, and the ones that can accumulate between species in the long term. We use computational approaches to accurately predict the polymorphisms segregating in a panel of 61,157 Escherichia coli genomes from the analysis of distant homologues. By comparing a context-aware Direct-Coupling Analysis modelling to a non-epistatic approach, we show that the genetic context strongly constrains the tolerable amino acids in 30% to 50% of amino-acid sites. The study of more distant species suggests the gradual build-up of genetic context over long evolutionary timescales by the accumulation of small epistatic contributions.

Predicting the effects of mutations in a species is a major challenge in genetics. Here, the authors investigate protein sequence landscapes using diverged E. coli sequences, to predict tolerated mutations and capture interactions between mutations.

PHACT: Phylogeny-aware computing of tolerance for missense mutations

Evolutionary conservation is a fundamental resource for predicting the substitutability of amino acids and loss of function in proteins. The use of multiple sequence alignment alone-without considering the evolutionary relationships among sequences-results in the redundant counting of evolutionarily related alteration events as if they were independent. Here we propose a new method, PHACT that predicts the pathogenicity of missense mutations directly from the phylogenetic tree of proteins. PHACT travels through the nodes of the phylogenetic tree and evaluates the deleteriousness of a substitution based on the probability differences of ancestral amino acids between neighboring nodes in the tree. Moreover, PHACT assigns weights to each node in the tree based on their distance to the query organism. For each potential amino acid substitution, the algorithm generates a score that is used to calculate the effect of substitution on protein function. To analyze the predictive performance of PHACT, we performed various experiments over the subsets of two datasets that include 3023 proteins and 61662 variants in total. The experiments demonstrated that our method outperformed the widely used pathogenicity prediction tools (i.e., SIFT and PolyPhen-2) and achieved better predictive performance than did other conventional statistical approaches presented in dbNSFP. The PHACT source code is available at https://github.com/CompGenomeLab/PHACT.