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

Krebs, Fanny S.; Zoete, Vincent; Trottet, Maxence; Pouchon, Timothée Noé; Bovigny, Christophe; Michielin, Olivier

doi:10.1038/s41698-021-00156-5

Cited by 12 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following our subsequent investigations, it was found that “17:7674220_C > T” SNV, which is regarded as a “hotspot mutation” in the literature, is an arginine to glutamine single nucleotide substitution occurring at 248th residue of TP53 ( Shajani-Yi et al, 2018 ). We also explored the location of the identified mutation “17:7674220_C > T” (R248) in the three-dimentional structure of TP53 protein using the web service Swiss-PO ( Krebs et al, 2021 ). The structure is shown in Supplementary Figure S1 .…”

Section: Resultsmentioning

confidence: 99%

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

et al. 2022

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

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

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The problem of predicting mutation's effect on protein structure and function is well studied in the literature with a scope ranging from predicting mutation effect from protein sequence [15,16,17] to 3D mapping of mutations onto protein structures with visualization and highlighting their impact [18,19]. However, the specific impact of missense mutations in the binding site on protein-ligand binding affinity is much less covered.…”

Section: Related Workmentioning

confidence: 99%

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

Ammar¹,

Cavill²,

Evelo³

et al. 2022

Preprint

View full text Add to dashboard Cite

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 and the effect of binding site single-point mutations on it. A numerical representation of the protein, binding site, mutation, and ligand information was encoded using 256 features among which about half of which 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 performance model reported an RMSE value within 0.5-0.6~kcal/mol\textsuperscript{-1} on an independent test set with an R\textsuperscript{2} value of 0.87-0.90. 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.

show abstract

“…This general workflow can be integrated or complemented with tools to predict the functional impact of the identified mutations [46], resources to map the mutations on the 3D structure of a given protein [47][48][49][50][51], software that align the 3D structures instead of linear amino acid sequences [52], methods to visualize the position of the mutations in single proteins or the analysis of co-occurrence and mutual exclusivity of mutations [53]. Altogether this workflow defines a 'domain-based mutation prioritization'.…”

Section: Domain-based Approaches For the Identification Of Mutation Hotspotsmentioning

confidence: 99%

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

Grillo¹,

Ravelli²,

Corsini³

et al. 2021

Biochimica et Biophysica Acta (BBA) - Reviews on Cancer

View full text Add to dashboard Cite

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.

show abstract

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

Cited by 12 publications

References 37 publications

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

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

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

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

Contact Info

Product

Resources

About