Prediction of the functional impact of missense variants in BRCA1 and BRCA2 with BRCA-ML.
Ontology highlight
ABSTRACT:
SUBMITTER: Hart SN
PROVIDER: S-EPMC7190647 | biostudies-literature | 2020
REPOSITORIES: biostudies-literature
Publications
Prediction of the functional impact of missense variants in BRCA1 and BRCA2 with BRCA-ML.
Hart Steven N SN Polley Eric C EC Shimelis Hermella H Yadav Siddhartha S Couch Fergus J FJ
NPJ breast cancer 20200429
In silico predictions of missense variants is an important consideration when interpreting variants of uncertain significance (VUS) in the <i>BRCA1</i> and <i>BRCA2</i> genes. We trained and evaluated hundreds of machine learning algorithms based on results from validated functional assays to better predict missense variants in these genes as damaging or neutral. This new optimal "BRCA-ML" model yielded a substantially more accurate method than current algorithms for interpreting the functional ...[more]
Similar Datasets
Project description:Machine learning-based pathogenicity prediction helps interpret rare missense variants of BRCA1 and BRCA2, which are associated with hereditary cancers. Recent studies have shown that classifiers trained using variants of a specific gene or a set of genes related to a particular disease perform better than those trained using all variants, due to their higher specificity, despite the smaller training dataset size. In this study, we further investigated the advantages of "gene-specific" machine learning compared to "disease-specific" machine learning. We used 1068 rare (gnomAD minor allele frequency (MAF) < 0.005) missense variants of 28 genes associated with hereditary cancers for our investigation. Popular machine learning classifiers were employed: regularized logistic regression, extreme gradient boosting, random forests, support vector machines, and deep neural networks. As features, we used MAFs from multiple populations, functional prediction and conservation scores, and positions of variants. The disease-specific training dataset included the gene-specific training dataset and was > 7 × larger. However, we observed that gene-specific training variants were sufficient to produce the optimal pathogenicity predictor if a suitable machine learning classifier was employed. Therefore, we recommend gene-specific over disease-specific machine learning as an efficient and effective method for predicting the pathogenicity of rare BRCA1 and BRCA2 missense variants.
| S-EPMC10307865 | biostudies-literature
Project description:The BRCA Challenge is a long-term data-sharing project initiated within the Global Alliance for Genomics and Health (GA4GH) to aggregate BRCA1 and BRCA2 data to support highly collaborative research activities. Its goal is to generate an informed and current understanding of the impact of genetic variation on cancer risk across the iconic cancer predisposition genes, BRCA1 and BRCA2. Initially, reported variants in BRCA1 and BRCA2 available from public databases were integrated into a single, newly created site, www.brcaexchange.org. The purpose of the BRCA Exchange is to provide the community with a reliable and easily accessible record of variants interpreted for a high-penetrance phenotype. More than 20,000 variants have been aggregated, three times the number found in the next-largest public database at the project's outset, of which approximately 7,250 have expert classifications. The data set is based on shared information from existing clinical databases-Breast Cancer Information Core (BIC), ClinVar, and the Leiden Open Variation Database (LOVD)-as well as population databases, all linked to a single point of access. The BRCA Challenge has brought together the existing international Evidence-based Network for the Interpretation of Germline Mutant Alleles (ENIGMA) consortium expert panel, along with expert clinicians, diagnosticians, researchers, and database providers, all with a common goal of advancing our understanding of BRCA1 and BRCA2 variation. Ongoing work includes direct contact with national centers with access to BRCA1 and BRCA2 diagnostic data to encourage data sharing, development of methods suitable for extraction of genetic variation at the level of individual laboratory reports, and engagement with participant communities to enable a more comprehensive understanding of the clinical significance of genetic variation in BRCA1 and BRCA2.
| S-EPMC6324924 | biostudies-literature
Project description:PurposeGuidelines for variant interpretation incorporate variant hotspots in critical functional domains as evidence for pathogenicity (e.g., PM1 and PP2), but do not use "coldspots," that is, regions without essential functions that tolerate variation, as evidence a variant is benign. To improve variant classification we evaluated BRCA1 and BRCA2 missense variants reported in ClinVar to identify regions where pathogenic missenses are extremely infrequent, defined as coldspots.MethodsWe used Bayesian approaches to model variant classification in these regions.ResultsBRCA1 exon 11 (~60% of the coding sequence), and BRCA2 exons 10 and 11 (~65% of the coding sequence), are coldspots. Of 89 pathogenic (P) or likely pathogenic (LP) missense variants in BRCA1, none are in exon 11 (odds <0.01, 95% confidence interval [CI] 0.0-0.01). Of 34?P or LP missense variants in BRCA2, none are in exons 10-11 (odds <0.01, 95% CI 0.0-0.01). More than half of reported missense variants of uncertain significance (VUS) in BRCA1 and BRCA2 are in coldspots (3115/5301?=?58.8%). Reclassifying these 3115 VUS as likely benign would substantially improve variant classification.ConclusionIn BRCA1 and BRCA2 coldspots, missense variants are very unlikely to be pathogenic. Classification schemes that incorporate coldspots can reduce the number of VUS and mitigate risks from reporting benign variation as VUS.
| S-EPMC7200594 | biostudies-literature
Project description:PurposeTo improve methods for predicting the impact of missense variants of uncertain significance (VUS) in BRCA1 and BRCA2 on protein function.MethodsFunctional data for 248 BRCA1 and 207 BRCA2 variants from assays with established high sensitivity and specificity for damaging variants were used to recalibrate 40 in silico algorithms predicting the impact of variants on protein activity. Additional random forest (RF) and naïve voting method (NVM) metapredictors for both BRCA1 and BRCA2 were developed to increase predictive accuracy.ResultsOptimized thresholds for in silico prediction models significantly improved the accuracy of predicted functional effects for BRCA1 and BRCA2 variants. In addition, new BRCA1-RF and BRCA2-RF metapredictors showed area under the curve (AUC) values of 0.92 (95% confidence interval [CI]: 0.88-0.96) and 0.90 (95% CI: 0.84-0.95), respectively. Similarly, the BRCA1-NVM and BRCA2-NVM models had AUCs of 0.93 and 0.90. The RF and NVM models were used to predict the pathogenicity of all possible missense variants in BRCA1 and BRCA2.ConclusionThe recalibrated algorithms and new metapredictors significantly improved upon current models for predicting the impact of variants in cancer risk-associated domains of BRCA1 and BRCA2. Prediction of the functional impact of all possible variants in BRCA1 and BRCA2 provides important information about the clinical relevance of variants in these genes.
| S-EPMC6287763 | biostudies-literature
Project description:Many individuals tested for inherited cancer susceptibility at the BRCA1 gene locus are discovered to have variants of unknown clinical significance (UCVs). Most UCVs cause a single amino acid residue (missense) change in the BRCA1 protein. They can be biochemically assayed, but such evaluations are time-consuming and labor-intensive. Computational methods that classify and suggest explanations for UCV impact on protein function can complement functional tests. Here we describe a supervised learning approach to classification of BRCA1 UCVs. Using a novel combination of 16 predictive features, the algorithms were applied to retrospectively classify the impact of 36 BRCA1 C-terminal (BRCT) domain UCVs biochemically assayed to measure transactivation function and to blindly classify 54 documented UCVs. Majority vote of three supervised learning algorithms is in agreement with the assay for more than 94% of the UCVs. Two UCVs found deleterious by both the assay and the classifiers reveal a previously uncharacterized putative binding site. Clinicians may soon be able to use computational classifiers such as those described here to better inform patients. These classifiers can be adapted to other cancer susceptibility genes and systematically applied to prioritize the growing number of potential causative loci and variants found by large-scale disease association studies.
| S-EPMC1797820 | biostudies-literature
Project description:BACKGROUND: BRCA1 and BRCA2 germline mutations predispose heterozygous carriers to hereditary breast/ovarian cancer. However, unclassified variants (UVs) (variants with unknown clinical significance) and missense polymorphisms in BRCA1 and BRCA2 genes pose a problem in genetic counseling, as their impact on risk of breast and ovarian cancer is still unclear. The objective of our study was to identify UVs and missense polymorphisms in Algerian breast/ovarian cancer patients and relatives tested previously for BRCA1 and BRCA2 genes germline mutations analysis. METHODS: We analyzed 101 DNA samples from 79 breast/ovarian cancer families. The approach used is based on BRCA1 and BRCA2 sequence variants screening by SSCP or High-Resolution Melting (HRM) curve analysis followed by direct sequencing. In silico analyses have been performed using different bioinformatics programs to individualize genetics variations that can disrupt the BRCA1 and BRCA2 genes function. RESULTS: Among 80 UVs and polymorphisms detected in BRCA1/2 genes (33 BRCA1 and 47 BRCA2), 31 were new UVs (10 BRCA1 and 21 BRCA2), 7 were rare UVs (4 BRCA1 and 3 BRCA2) and 42 were polymorphic variants (19 BRCA1 and 23 BRCA2). Moreover, 8 new missense UVs identified in this study: two BRCA1 (c.4066C>A/p.Gln1356Lys, c.4901G>T/p.Arg1634Met) located respectively in exons 11 and 16, and six BRCA2 (c.1099G>A/p.Asp367Asn, c.2636C>A/p.Ser879Tyr, c.3868T>A/p.Cys1290Ser, c.5428G>T/p.Val1810Phe, c.6346C>G/p.His2116Asp and c.9256G>A/p.Gly3086Arg) located respectively in exons 10, 11 and 24, show a damaging PSIC score yielded by PolyPhen2 program and could be pathogenic. In addition, 5 new BRCA} missense UVs out of six that were found to be damaging by PolyPhen2 program, also were deleterious according to SIFT program. The rare BRCA1 UV c.5332G>A/p.Asp1778Asn was found here for the first time in co-occurrence in trans with the deleterious BRCA1 mutation c.798_799delTT/p.Ser267LysfsX19 in young breast cancer patient. Moreover, 10 new identified intronic variants with unknown clinical significance (3 BRCA1 and 7 BRCA2) in the present study, could be considered as benign, because GeneSplicer, SpliceSiteFinder and MaxEntScan prediction programs show no splice site alteration for these variants. Several missense polymorphisms of BRCA1 c.2612C>T/p.Pro871Leu, c.3548A>G/p.Lys1183Arg, c.4837A>G/p.Ser1613Gly and BRCA2 c.865A>C/p.Asn289His, c.1114A>C/p.Asn372His, c.2971A>G/p.Asn991Asp, c.7150C>A/p.Gly2384Lys have been identified with high frequency in patients who were tested negative for BRCA1 and BRCA2 mutations. These missense polymorphisms could have a role as susceptibility breast cancer markers in Algerian breast/ovarian cancer families where pathological BRCA1 and BRCA2 mutations were not present. CONCLUSIONS: For the first time, UVs and missense polymorphisms in BRCA1 and BRCA2 genes have been identified in Algerian breast/ovarian cancer families. Evaluation of breast/ovarian cancer risk induced by the eight new missense UVs and common polymorphisms detected in our present work is on going in a larger study.
| S-EPMC3826381 | biostudies-other
Project description:Missense substitutions in high-risk cancer susceptibility genes create clinical uncertainty in the genetic counseling process. Multifactorial likelihood classification approaches and in vitro assays are useful for the classification of exonic sequence variants in BRCA1 and BRCA2, but these currently rely on the assumption that changes in protein function are the major biological mechanism of pathogenicity. This study investigates the potentially pathogenic role of aberrant splicing for exonic variants predicted to encode missense substitutions using patient-derived RNA. No splicing aberrations were identified for BRCA1c.5054C>T and BRCA2c.7336A>G, c.8839G>A, and c.9154C>T. However, RT-PCR analysis identified a major splicing aberration for BRCA1c.4868C>G(p.Ala1623Gly), a variant encoding a missense substitution considered likely to be neutral. Splicing aberrations were also observed for BRCA2c.7988A>T(p.Glu2663Val) and c.8168A>G(p.Asp2723Gly), but both variant and wildtype alleles were shown to be present in full-length mRNA transcripts, suggesting that variant protein may be translated. BRCA2 protein function assays indicated that BRCA2p.Glu2663Val, p.Asp2723Gly and p.Arg3052Trp missense proteins have abrogated function consistent with pathogenicity. Multifactorial likelihood analysis provided evidence for pathogenicity for BRCA1 c.5054C>T(p.Thr1685Ile) and BRCA2c.7988A>T(p.Glu2663Val), c.8168A>G(p.Asp2723Gly) and c.9154C>T(p.Arg3052Trp), supporting experimentally derived evidence. These findings highlight the need for improved bioinformatic prediction of splicing aberrations and to refine multifactorial likelihood models used to assess clinical significance.
| S-EPMC3021973 | biostudies-literature
Project description:BRCA1 and BRCA2 are tumour suppressor genes that play a critical role in maintaining genomic stability via the DNA repair mechanism. DNA repair defects caused by BRCA1 and BRCA2 missense variants increase the risk of developing breast and ovarian cancers. Accurate identification of these variants becomes clinically relevant, as means to guide personalized patient management and early detection. Next-generation sequencing efforts have significantly increased data availability but also the discovery of variants of uncertain significance that need interpretation. Experimental approaches used to measure the molecular consequences of these variants, however, are usually costly and time-consuming. Therefore, computational tools have emerged as faster alternatives for assisting in the interpretation of the clinical significance of newly discovered variants. To better understand and predict variant pathogenicity in BRCA1 and BRCA2, various machine learning algorithms have been proposed, however presented limited performance. Here we present BRCA1 and BRCA2 gene-specific models and a generic model for quantifying the functional impacts of single-point missense variants in these genes. Across tenfold cross-validation, our final models achieved a Matthew's Correlation Coefficient (MCC) of up to 0.98 and comparable performance of up to 0.89 across independent, non-redundant blind tests, outperforming alternative approaches. We believe our predictive tool will be a valuable resource for providing insights into understanding and interpreting the functional consequences of missense variants in these genes and as a tool for guiding the interpretation of newly discovered variants and prioritizing mutations for experimental validation.
| S-EPMC9213547 | biostudies-literature
Project description:Mutations in BRCA1 and BRCA2 are responsible for a large proportion of breast-ovarian cancer families. Protein-truncating mutations have been effectively used in the clinical management of familial breast cancer due to their deleterious impact on protein function. However, the majority of missense variants identified throughout the genes continue to pose an obstacle for predictive informative testing due to low frequency and lack of information on how they affect BRCA1/2 function. Phosphorylation of BRCA1 and BRCA2 play an important role in their function as regulators of DNA repair, transcription and cell cycle in response to DNA damage but whether missense variants of uncertain significance (VUS) are able to disrupt this important process is not known. Here we employed a novel approach using NetworKIN which predicts in vivo kinase-substrate relationship, and evolutionary conservation algorithms SIFT, PolyPhen and Align-GVGD. We evaluated whether 191 BRCA1 and 43 BRCA2 VUS from the Breast Cancer Information Core (BIC) database can functionally alter the consensus phosphorylation motifs and abolish kinase recognition and binding to sites known to be phosphorylated in vivo. Our results show that 13.09% (25/191) BRCA1 and 13.95% (6/43) BRCA2 VUS altered the phosphorylation of BRCA1 and BRCA2. We highlight six BRCA1 (K309T, S632N, S1143F, Q1144H, Q1281P, S1542C) and three BRCA2 (S196I, T207A, P3292L) VUS as potentially clinically significant. These occurred rarely (n<2 in BIC), mutated evolutionarily conserved residues and abolished kinase binding to motifs established in the literature involved in DNA repair, cell cycle regulation, transcription or response to DNA damage. Additionally in vivo phosphorylation sites identified via through-put methods are also affected by VUS and are attractive targets for studying their biological and functional significance. We propose that rare VUS affecting phosphorylation may be a novel and important mechanism for which BRCA1 and BRCA2 functions are disrupted in breast cancer.
| S-EPMC3660339 | biostudies-literature
Project description:Germline inactivating mutations in BRCA1 and BRCA2 genes are responsible for Hereditary Breast and Ovarian Cancer Syndrome (HBOCS). Genetic testing of these genes is available, although approximately 15% of tests identify variants of uncertain significance (VUS). Classification of these variants into pathogenic or non-pathogenic type is an important challenge in genetic diagnosis and counseling. The aim of the present study is to functionally assess a set of 7 missense VUS (Q1409L, S1473P, E1586G, R1589H, Y1703S, W1718L and G1770V) located in the C-terminal region of BRCA1 by combining in silico prediction tools and structural analysis with a transcription activation (TA) assay. The in silico prediction programs gave discrepant results making its interpretation difficult. Structural analysis of the three variants located in the BRCT domains (Y1703S, W1718L and G1770V) reveals significant alterations of BRCT structure. The TA assay shows that variants Y1703S, W1718L and G1770V dramatically compromise the transcriptional activity of BRCA1, while variants Q1409L, S1473P, E1586G and R1589H behave like wild-type BRCA1. In conclusion, our results suggest that variants Y1703S, W1718L and G1770V can be classified as likely pathogenic BRCA1 mutations.
| S-EPMC3629201 | biostudies-literature