Comprehensive Identification of Deleterious TP53 Missense VUS Variants Based on Their Impact on TP53 Structural Stability

Comprehensive classification of TP53 somatic missense variants based on their impact on p53 structural stability

Somatic variation is a major type of genetic variation contributing to human diseases including cancer. Of the vast quantities of somatic variants identified, the functional impact of many somatic variants, in particular the missense variants, remains unclear. Lack of the functional information prevents the translation of rich variation data into clinical applications. We previously developed a method named Ramachandran Plot-Molecular Dynamics Simulations (RP-MDS), aiming to predict the function of germline missense variants based on their effects on protein structure stability, and successfully applied to predict the deleteriousness of unclassified germline missense variants in multiple cancer genes. We hypothesized that regardless of their different genetic origins, somatic missense variants and germline missense variants could have similar effects on the stability of their affected protein structure. As such, the RP-MDS method designed for germline missense variants should also be applicable to predict the function of somatic missense variants. In the current study, we tested our hypothesis by using the somatic missense variants in TP53 as a model. Of the 397 somatic missense variants analyzed, RP-MDS predicted that 195 (49.1%) variants were deleterious as they significantly disturbed p53 structure. The results were largely validated by using a p53-p21 promoter-green fluorescent protein (GFP) reporter gene assay. Our study demonstrated that deleterious somatic missense variants can be identified by referring to their effects on protein structural stability.

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

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

DARVIC: Dihedral angle-reliant variant impact classifier for functional prediction of missense VUS

BACKGROUND

Of the large number of genetic variants identified, the functional impact for most of them remains unknown. Mutations in DNA damage repair genes such as MUTYH, which is involved in repairing A:8-oxoG mismatches caused by reactive oxygen species, can cause a higher risk of cancer. Mutations happening in other key genes such as TP53 also pose huge health threats and risk of cancer. The interpretation of genetic variants' functional impact is a forefront issue that needs to be addressed. Many different in silico methods based on different principles have been developed and applied in interpreting genetic variants. However, a current challenge is that many existing methods tend to overpredict the pathogenicity of benign variants. A new approach is needed to tackle this issue to improve genetic variant interpretation through the use of in silico methods.

METHODS

In this study, we developed another protein structural-based approach called Dihedral angle-reliant variant impact classifier (DARVIC) to predict the deleterious impact of the coding-changing missense variants. DARVIC uses Ramachandran's principle of protein stereochemistry as the theoretical foundation and uses molecular dynamics simulations coupled with a supervised machine learning algorithm XGBoost to determine the functional impact of missense variants on protein structural stability.

RESULTS

We characterized the features of dihedral angles in dynamic protein structures. We also tested the performance of DARVIC in MUTYH and TP53 missense variants and achieved satisfactory results in reflecting the functional impacts of the variants on protein structure. The method achieved a balanced accuracy of 84% in a functionally validated MUTYH dataset containing both benign and pathogenic missense variants, higher than other existing in silico methods. Along with that, DARVIC was able to predict 119 (47%) deleterious variants from a dataset of 254 MUTYH VUS. Further application of DARVIC to a functionally validated TP53 dataset had a balanced accuracy of 94%, topping other methods, demonstrating DARVIC's robustness.

CONCLUSION

DARVIC provides a valuable tool to predict the functional impacts of missense variants based on their effects on protein structural stability and motion. At its current state, DARVIC performed well in predicting the functional impact of the missense variants both in MUTYH and TP53. We expect its high potential to predict functional impact for the missense variants in other genes.

Integration of deep learning with Ramachandran plot molecular dynamics simulation for genetic variant classification

Functional classification of genetic variants is a key for their clinical applications in patient care. However, abundant variant data generated by the next-generation DNA sequencing technologies limit the use of experimental methods for their classification. Here, we developed a protein structure and deep learning (DL)-based system for genetic variant classification, DL-RP-MDS, which comprises two principles: 1) Extracting protein structural and thermodynamics information using the Ramachandran plot-molecular dynamics simulation (RP-MDS) method, 2) combining those data with an unsupervised learning model of auto-encoder and a neural network classifier to identify the statistical significance patterns of the structural changes. We observed that DL-RP-MDS provided higher specificity than over 20 widely used in silico methods in classifying the variants of three DNA damage repair genes: TP53, MLH1, and MSH2. DL-RP-MDS offers a powerful platform for high-throughput genetic variant classification. The software and online application are available at https://genemutation.fhs.um.edu.mo/DL-RP-MDS/.

Ethnic-specificity, evolution origin and deleteriousness of Asian BRCA variation revealed by over 7500 BRCA variants derived from Asian population

Pathogenic variation in BRCA1 and BRCA2 (BRCA) causes high risk of breast and ovarian cancer, and BRCA variation data are important markers for BRCA-related clinical cancer applications. However, comprehensive BRCA variation data are lacking from the Asian population despite its large population size, heterogenous genetic background and diversified living environment across the Asia continent. We performed a systematic study on BRCA variation in Asian population including extensive data mining, standardization, annotation and characterization. We identified 7587 BRCA variants from 685 592 Asian individuals in 40 Asia countries and regions, including 1762 clinically actionable pathogenic variants and 4915 functionally unknown variants (https://genemutation.fhs.um.edu.mo/Asian-BRCA/). We observed the highly ethnic-specific nature of Asian BRCA variants between Asian and non-Asian populations and within Asian populations, highlighting that the current European descendant population-based BRCA data is inadequate to reflect BRCA variation in the Asian population. We also provided archeological evidence for the evolutionary origin and arising time of Asian BRCA variation. We further provided structural-based evidence for the deleterious variants enriched within the functionally unknown Asian BRCA variants. The data from our study provide a current view of BRCA variation in the Asian population and a rich resource to guide clinical applications of BRCA-related cancer for the Asian population.