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.

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

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

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

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

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

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

Pervasiveness of HLA allele-specific expression loss across tumor types.

BACKGROUND: Efficient presentation of mutant peptide fragments by the human leukocyte antigen class I (HLA-I) genes is necessary for immune-mediated killing of cancer cells. According to recent reports, patient HLA-I genotypes can impact the efficacy of cancer immunotherapy, and the somatic loss of HLA-I heterozygosity has been established as a factor in immune evasion. While global deregulated expression of HLA-I has also been reported in different tumor types, the role of HLA-I allele-specific expression loss - that is, the preferential RNA expression loss of specific HLA-I alleles - has not been fully characterized in cancer. METHODS: Here, we use RNA and whole-exome sequencing data to quantify HLA-I allele-specific expression (ASE) in cancer using our novel method arcasHLA-quant. RESULTS: We show that HLA-I ASE loss in at least one of the three HLA-I genes is a pervasive phenomenon across TCGA tumor types. In pancreatic adenocarcinoma, tumor-specific HLA-I ASE loss is associated with decreased overall survival specifically in the basal-like subtype, a finding that we validated in an independent cohort through laser-capture microdissection. Additionally, we show that HLA-I ASE loss is associated with poor immunotherapy outcomes in metastatic melanoma through retrospective analyses. CONCLUSIONS: Together, our results highlight the prevalence of HLA-I ASE loss and provide initial evidence of its clinical significance in cancer prognosis and immunotherapy treatment.

HLA Typing from RNA Sequencing and Applications to Cancer.

The human leukocyte antigen (HLA) complex is necessary for antigen presentation and regulates both innate and adaptive immune responses. In the context of cancer and treatment therapies, the HLA locus plays a critical role in tumor recognition and tolerance mechanisms. In silico HLA class I and class II typing, as well as expression quantification from next-generation RNA sequencing, can therefore have great potential clinical applications. However, HLA typing from short-read data is a challenging task given the high polymorphism and homology at the HLA locus. In this chapter, we present our highly accurate HLA typing solution, arcasHLA. We provide a detailed outline for practitioners using our protocol to perform HLA typing and demonstrate the applicability of arcasHLA in several clinical samples from tumors.

arcasHLA: high-resolution HLA typing from RNAseq.

MOTIVATION: The human leukocyte antigen (HLA) locus plays a critical role in tissue compatibility and regulates the host response to many diseases, including cancers and autoimmune di3orders. Recent improvements in the quality and accessibility of next-generation sequencing have made HLA typing from standard short-read data practical. However, this task remains challenging given the high level of polymorphism and homology between HLA genes. HLA typing from RNA sequencing is further complicated by post-transcriptional modifications and bias due to amplification. RESULTS: Here, we present arcasHLA: a fast and accurate in silico tool that infers HLA genotypes from RNA-sequencing data. Our tool outperforms established tools on the gold-standard benchmark dataset for HLA typing in terms of both accuracy and speed, with an accuracy rate of 100% at two-field resolution for Class I genes, and over 99.7% for Class II. Furthermore, we evaluate the performance of our tool on a new biological dataset of 447 single-end total RNA samples from nasopharyngeal swabs, and establish the applicability of arcasHLA in metatranscriptome studies. AVAILABILITY AND IMPLEMENTATION: arcasHLA is available at https://github.com/RabadanLab/arcasHLA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Author Correction: Immune and genomic correlates of response to anti-PD-1 immunotherapy in glioblastoma.

In the version of this article originally published, the graph in Extended Data Fig. 2c was a duplication of Extended Data Fig. 2b. The correct version of Extended Data Fig. 2c is now available online.

Immune and genomic correlates of response to anti-PD-1 immunotherapy in glioblastoma.

Immune checkpoint inhibitors have been successful across several tumor types; however, their efficacy has been uncommon and unpredictable in glioblastomas (GBM), where <10% of patients show long-term responses. To understand the molecular determinants of immunotherapeutic response in GBM, we longitudinally profiled 66 patients, including 17 long-term responders, during standard therapy and after treatment with PD-1 inhibitors (nivolumab or pembrolizumab). Genomic and transcriptomic analysis revealed a significant enrichment of PTEN mutations associated with immunosuppressive expression signatures in non-responders, and an enrichment of MAPK pathway alterations (PTPN11, BRAF) in responders. Responsive tumors were also associated with branched patterns of evolution from the elimination of neoepitopes as well as with differences in T cell clonal diversity and tumor microenvironment profiles. Our study shows that clinical response to anti-PD-1 immunotherapy in GBM is associated with specific molecular alterations, immune expression signatures, and immune infiltration that reflect the tumor's clonal evolution during treatment.