Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes

@article{ubuk2021ClinicalLR,
  title={Clinical likelihood ratios and balanced accuracy for 44 in silico tools against multiple large-scale functional assays of cancer susceptibility genes},
  author={Cankut Çubuk and Alice Garrett and S. Choi and Laura King and Chey Loveday and Bethany Torr and George J Burghel and Miranda Durkie and Alison Callaway and Rachel Robinson and James Drummond and Ian Berry and Andrew L. Wallace and Diana M. Eccles and Marc Tischkowitz and Nicola Whiffin and James S. Ware and Helen Hanson and Clare Turnbull and CanVIG-UK},
  journal={Genetics in Medicine},
  year={2021},
  volume={23},
  pages={2096 - 2104},
  url={https://api.semanticscholar.org/CorpusID:235759052}
}
Overall, REVEL and Meta-SNP had best balanced accuracy and might potentially be used at stronger evidence weighting than current ACMG/AMP prescription, in particular for predictions of benignity.
View on Springer
gimjournal.org
48 Citations
Highly Influential Citations
2
Background Citations
15
Methods Citations
9
Results Citations
1

48 Citations

Quantifying prediction of pathogenicity for within-codon concordance (PM5) using 7541 functional classifications of BRCA1 and MSH2 missense variants

Calibration of computational tools for missense variant pathogenicity classification and ClinGen recommendations for PP3/BP4 criteria

Evidence-based calibration of computational tools for missense variant pathogenicity classification and ClinGen recommendations for clinical use of PP3/BP4 criteria

A probabilistic framework that quantified the strengths of evidence (Supporting, Moderate, Strong, Very Strong) within ACMG/AMP recommendations is extended to computational predictors and a new standard that converts a tool’s scores to PP3 and BP4 evidence strengths is introduced.

A Comprehensive Evaluation of the Performance of Prediction Algorithms on Clinically Relevant Missense Variants

It is demonstrated that type 1 circularity significantly impacts the performance of these tools and, if not accounted for, may confound the selection of the best performing algorithms.

Evaluating the impact of in silico predictors on clinical variant classification

This study demonstrates that in silico criteria PP3 and BP4 are commonly applied in variant classification and often affect the final classification, and suggests that when sufficient thresholds for insilico predictors are established, PP3 or BP4 may be appropriate to use at a moderate strength.

Saturation-scale functional evidence supports clinical variant interpretation in Lynch syndrome

This study demonstrates how high-throughput functional assays can empower scalable VUS resolution and prospectively generate strong evidence for variant classification.

Evaluation of in silico pathogenicity prediction tools for the classification of small in-frame indels

Algorithms designed for predicting the pathogenicity of in-frame indels perform well enough to aid clinical variant classification in a similar manner to missense prediction tools.

Artificial Intelligence-Driven Prediction Revealed CFTR Associated with Therapy Outcome of Breast Cancer: A Feasibility Study

This study indicates that CFTR may be involved in the processes influencing the effectiveness of oncotherapy or in the malignant progression of the disease itself, and provides an effective approach navigating for functional consequences across germline genetic background, which can be easily integrated into the overall decision-making process for future studies.

Benchmarking of variant pathogenicity prediction methods using a population genetics approach

CADD and REVEL are identified as the best-performing predictors for distinguishing extremely deleterious variants from moderately deleterious ones and CAPS can serve as a meta-analysis tool for interpreting variant annotations and highlight biases in ClinVar-based predictor training.

Validation and Data-Integration of Yeast-Based Assays for Functional Classification of BRCA1 Missense Variants

This study validated the two HR and the GR assays by testing 23 benign and 23 pathogenic variants and developed a reliable method, named yBRCA1, with high sensitivity to obtain an accurate VUS functional classification (benign or pathogenic).

51 References

Assessment of the Clinical Relevance of BRCA2 Missense Variants by Functional and Computational Approaches.

How good are pathogenicity predictors in detecting benign variants?

The performance of variant pathogenicity/tolerance prediction programs on benign variants is assessed for the first time, and the best methods were the best irrespective on how the data is filtered and grouped.

Variant effect prediction tools assessed using independent, functional assay-based datasets: implications for discovery and diagnostics

Genetic variant effect prediction algorithms are used extensively in clinical genomics and research to determine the likely consequences of amino acid substitutions on protein function. It is vital…

Evaluation of in silico algorithms for use with ACMG/AMP clinical variant interpretation guidelines

Recently developed algorithms with high predictive power and robust to variables such as disease mechanism, gene constraint, and mode of inheritance are identified, although poorer performing algorithms are more frequently used based on review of the clinical genetics literature (2011–2017).

Massively parallel functional testing of MSH2 missense variants conferring Lynch syndrome risk

Strong functional data for pathogenicity or neutrality classify BRCA2 DNA-binding-domain variants of uncertain significance

Functional Assays for Analysis of Variants of Uncertain Significance in BRCA2

Assays developed and currently utilized for studying missense variants in BRCA2 are summarized, details of each assay are depicted, including variants of uncertain significance analyzed, and a validation set of (genetically) proven pathogenic and neutralmissense variants are described to serve as a golden standard for the validation of each assays.

Accurate classification of BRCA1 variants with saturation genome editing

Saturation genome editing is used to assay 96.5% of all possible single-nucleotide variants (SNVs) in 13 exons that encode functionally critical domains of BRCA1, a tumour suppressor gene in which germline loss-of-function variants predispose women to breast and ovarian cancer.

Identifying Mendelian disease genes with the Variant Effect Scoring Tool

The Variant Effect Scoring Tool (VEST), a supervised machine learning-based classifier, is developed to prioritize rare missense variants with likely involvement in human disease, and the ability of an aggregate VEST gene score to identify candidate Mendelian disease genes is tested, based on whole-exome sequencing of a small number of disease cases.

Assessing performance of pathogenicity predictors using clinically relevant variant datasets

The results support the adoption of meta-predictors over traditional in silico tools, but do not support a consensus-based approach as in current practice.
...