Swiss-PO: a new tool to analyze the impact of mutations on protein three-dimensional structures for precision oncology

A computational workflow for analysis of missense mutations in precision oncology

Every year, more than 19 million cancer cases are diagnosed, and this number continues to increase annually. Since standard treatment options have varying success rates for different types of cancer, understanding the biology of an individual's tumour becomes crucial, especially for cases that are difficult to treat. Personalised high-throughput profiling, using next-generation sequencing, allows for a comprehensive examination of biopsy specimens. Furthermore, the widespread use of this technology has generated a wealth of information on cancer-specific gene alterations. However, there exists a significant gap between identified alterations and their proven impact on protein function. Here, we present a bioinformatics pipeline that enables fast analysis of a missense mutation's effect on stability and function in known oncogenic proteins. This pipeline is coupled with a predictor that summarises the outputs of different tools used throughout the pipeline, providing a single probability score, achieving a balanced accuracy above 86%. The pipeline incorporates a virtual screening method to suggest potential FDA/EMA-approved drugs to be considered for treatment. We showcase three case studies to demonstrate the timely utility of this pipeline. To facilitate access and analysis of cancer-related mutations, we have packaged the pipeline as a web server, which is freely available at https://loschmidt.chemi.muni.cz/predictonco/ .Scientific contributionThis work presents a novel bioinformatics pipeline that integrates multiple computational tools to predict the effects of missense mutations on proteins of oncological interest. The pipeline uniquely combines fast protein modelling, stability prediction, and evolutionary analysis with virtual drug screening, while offering actionable insights for precision oncology. This comprehensive approach surpasses existing tools by automating the interpretation of mutations and suggesting potential treatments, thereby striving to bridge the gap between sequencing data and clinical application.

Mutation Space of Spatially Conserved Amino Acid Sites in Proteins

The mutation space of spatially conserved (MSSC) amino acid residues is a protein structural quantity developed and described in this work. The MSSC quantifies how many mutations and which different mutations, i.e., the mutation space, occur in each amino acid site in a protein. The MSSC calculates the mutation space of amino acids in a target protein from the spatially conserved residues in a group of multiple protein structures. Spatially conserved amino acid residues are identified based on their relative positions in the protein structure. The MSSC examines each residue in a target protein, compares it to the residues present in the same relative position in other protein structures, and uses physicochemical criteria of mutations found in each conserved spatial site to quantify the mutation space of each amino acid in the target protein. The MSSC is analogous to scoring each site in a multiple sequence alignment but in three-dimensional space considering the spatial location of residues instead of solely the order in which they appear in a protein sequence. MSSC analysis was performed on example cases, and it reproduces the well-known observation that, regardless of secondary structure, solvent-exposed residues are more likely to be mutated than internal ones. The MSSC code is available on GitHub: "https://github.com/Cantu-Research-Group/Mutation_Space".

PSnpBind-ML: predicting the effect of binding site mutations on protein-ligand binding affinity

Protein mutations, especially those which occur in the binding site, play an important role in inter-individual drug response and may alter binding affinity and thus impact the drug's efficacy and side effects. Unfortunately, large-scale experimental screening of ligand-binding against protein variants is still time-consuming and expensive. Alternatively, in silico approaches can play a role in guiding those experiments. Methods ranging from computationally cheaper machine learning (ML) to the more expensive molecular dynamics have been applied to accurately predict the mutation effects. However, these effects have been mostly studied on limited and small datasets, while ideally a large dataset of binding affinity changes due to binding site mutations is needed. In this work, we used the PSnpBind database with six hundred thousand docking experiments to train a machine learning model predicting protein-ligand binding affinity for both wild-type proteins and their variants with a single-point mutation in the binding site. A numerical representation of the protein, binding site, mutation, and ligand information was encoded using 256 features, half of them were manually selected based on domain knowledge. A machine learning approach composed of two regression models is proposed, the first predicting wild-type protein-ligand binding affinity while the second predicting the mutated protein-ligand binding affinity. The best performing models reported an RMSE value within 0.5 [Formula: see text] 0.6 kcal/mol^-1 on an independent test set with an R² value of 0.87 [Formula: see text] 0.90. We report an improvement in the prediction performance compared to several reported models developed for protein-ligand binding affinity prediction. The obtained models can be used as a complementary method in early-stage drug discovery. They can be applied to rapidly obtain a better overview of the ligand binding affinity changes across protein variants carried by people in the population and narrow down the search space where more time-demanding methods can be used to identify potential leads that achieve a better affinity for all protein variants.

MTPpilot: An Interactive Software for Visualization of Next-Generation Sequencing Results in Molecular Tumor Boards

Comprehensive targeted next-generation sequencing (NGS) panels are routinely used in modern molecular cancer diagnostics. In molecular tumor boards, the detected genomic alterations are often discussed to decide the next treatment options for patients with cancer. With the increasing size and complexity of NGS panels, the discussion of these results becomes increasingly complex, especially if they are reported in a text-based form, as it is the standard in current molecular pathology.

Computational Prediction of the Pathogenic Status of Cancer-Specific Somatic Variants

In-silico classification of the pathogenic status of somatic variants is shown to be promising in promoting the clinical utilization of genetic tests. Majority of the available classification tools are designed based on the characteristics of germline variants or the combination of germline and somatic variants. Significance of somatic variants in cancer initiation and progression urges for development of classifiers specialized for classifying pathogenic status of cancer somatic variants based on the model trained on cancer somatic variants. We established a gold standard exclusively for cancer somatic single nucleotide variants (SNVs) collected from the catalogue of somatic mutations in cancer. We developed two support vector machine (SVM) classifiers based on genomic features of cancer somatic SNVs located in coding and non-coding regions of the genome, respectively. The SVM classifiers achieved the area under the ROC curve of 0.94 and 0.89 regarding the classification of the pathogenic status of coding and non-coding cancer somatic SNVs, respectively. Our models outperform two well-known classification tools including FATHMM-FX and CScape in classifying both coding and non-coding cancer somatic variants. Furthermore, we applied our models to predict the pathogenic status of somatic variants identified in young breast cancer patients from METABRIC and TCGA-BRCA studies. The results indicated that using the classification threshold of 0.8 our “coding” model predicted 1853 positive SNVs (out of 6,910) from the TCGA-BRCA dataset, and 500 positive SNVs (out of 1882) from the METABRIC dataset. Interestingly, through comparative survival analysis of the positive predictions from our models, we identified a young-specific pathogenic somatic variant with potential for the prognosis of early onset of breast cancer in young women.

Structure-based classification of EGFR mutations informs inhibitor selection for lung cancer therapy

EGFR oncogenic mutations predict sensitivity to EGFR inhibitors in NSCLC, but less is known about EGFR "variants of unknown significance." Using preclinical models, 3D structure analyses, and patient response data, Robichaux et al. show in Nature that mutations in structural regions of EGFR predict responses to different EGFR inhibitors.

Protein domain-based approaches for the identification and prioritization of therapeutically actionable cancer variants

The tremendous number of cancer variants that can be detected by NGS analyses has required the development of computational approaches to prioritize mutations on the basis of their biological and clinical significance. Standard strategies take a gene-centric approach to the problem, allowing exclusively the identification of highly frequent variants. On the contrary, protein domain (PD)-based approaches allow to identify functionally relevant low frequency variants by searching for mutations that recur on analogous residues across homologous proteins (i.e. containing the same PD). Such approaches enable to transfer information about the effects and druggability from one known mutation to unknown ones. Here we describe how PD-based strategies work, and discuss how they could be exploited for mutation prioritization. The principle that mutations clustered on specific residues of PDs have the same functional consequences and are therapeutically actionable in a similar manner could help the choice of patient-specific targeted drugs, eventually improving the management of cancer patients.