{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T11:45:57Z","timestamp":1785843957777,"version":"3.56.0"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:00:00Z","timestamp":1785801600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Syst. Biol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Variant interpretation remains a major bottleneck in clinical genomics, with variants of uncertain significance (VUS) representing a critical unresolved challenge due to insufficient evidence for definitive classification. Existing in silico tools exhibit variable and often inconsistent performance complicating clinical decision-making, particularly in the context of hereditary cancer genomics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, we developed a machine learning framework trained on 1,04,646 high-confidence ClinVar germline variants (3-star+ review status) annotated with Ensembl VEP (v114, GRCh38) and CADD v1.6 pathogenicity scores to classify variants as Pathogenic or Benign, subsequently applying the trained model to reclassify 40894 ClinVar VUS. Train\/test partitioning was performed at the variant level (80\/20 split) to prevent data leakage, with hyperparameter optimization via GridSearchCV and performance assessed by 10-fold cross-validation. Four classifiers were evaluated viz. Logistic Regression, Support Vector Machine, Random Forest and XGBoost, with Random Forest achieving the highest performance (AUC-ROC = 0.9995, 95% CI: 0.9993\u20130.9997; 10-fold CV AUC = 0.9992 \u00b1 0.0004). Probability thresholds of P \u2265 0.80 (Pathogenic) and P &amp;lt;= 0.20 (Benign) were derived from Precision-Recall curve analysis, achieving empirically validated precision of 99.63% and 99.77% respectively on held-out test variants.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results and Discussion<\/jats:title>\n                    <jats:p>Applied to 40,894 ClinVar VUS, the model reclassified 19393 (47.4%) as Likely Pathogenic and 8,957 (21.9%) as Likely Benign, while 12,544 (30.7%) were conservatively retained as uncertain. External validation on 7,462 ENIGMA-classified BRCA1\/BRCA2 variants from the BRCA Exchange database, completely independent of the ClinVar training data demonstrated an overall concordance of 98.83% (AUC = 1.0000). Further validation of VUS reclassification against 671 variants classified as VUS in ClinVar but definitively classified by ENIGMA yielded an overall concordance of 89.57% (Pathogenic: 96.4%, Benign: 87.4%). SHAP-based explainability analysis confirmed that predictions were predominantly driven by biologically interpretable features, including CADD Phred score, VEP functional impact tier, variant consequence class and population allele frequency, consistent with ACMG\/AMP evidence criteria. This reproducible pipeline provides a clinically grounded computational approach to VUS triaging in precision oncology, with external validation supporting its generalizability to independent hereditary cancer gene datasets.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fsysb.2026.1828263","type":"journal-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T11:16:25Z","timestamp":1785842185000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A machine learning framework for predictive interpretation of variants of uncertain significance in hereditary cancer"],"prefix":"10.3389","volume":"6","author":[{"given":"Nayeema","family":"Nizamuddin","sequence":"first","affiliation":[{"name":"Bioclues.org, Hayatnagar","place":["Hyderabad, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soham","family":"Biswas","sequence":"additional","affiliation":[{"name":"Department of Biosciences, Systems Genomics Lab, Manipal University Jaipur","place":["Jaipur, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akshaykumar","family":"Zawar","sequence":"additional","affiliation":[{"name":"GeneSpectrum Life Sciences LLP","place":["Pune, Maharashtra, India"]},{"name":"Department of Life Sciences, School of Science and Mathematics, DES Pune University","place":["Pune, Maharashtra, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Poonam","family":"Deshpande","sequence":"additional","affiliation":[{"name":"Department of Life Sciences, School of Science and Mathematics, DES Pune University","place":["Pune, Maharashtra, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Layal","family":"Yasin","sequence":"additional","affiliation":[{"name":"Department of Pediatric Oncology, Haematology and Clinical Immunology, Medical Faculty, Heinrich-Heine-University","place":["D\u00fcsseldorf, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prashanth N.","family":"Suravajhala","sequence":"additional","affiliation":[{"name":"Department of Biosciences, Systems Genomics Lab, Manipal University Jaipur","place":["Jaipur, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1002\/0471142905.hg0720s76","article-title":"Predicting functional effect of human missense mutations using PolyPhen-2","volume":"7","author":"Adzhubei","year":"2013","journal-title":"Curr. Protoc. Hum. Genet."},{"key":"B2","first-page":"785","article-title":"XGBoost: a scalable tree boosting system","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '16)","author":"Chen","year":"2016"},{"key":"B3","doi-asserted-by":"publisher","first-page":"e1007752","DOI":"10.1371\/journal.pgen.1007752","article-title":"BRCA challenge: BRCA exchange as a global resource for variants in BRCA1 and BRCA2","volume":"14","author":"Cline","year":"2018","journal-title":"PLoS Genet."},{"key":"B4","doi-asserted-by":"publisher","first-page":"giab008","DOI":"10.1093\/gigascience\/giab008","article-title":"Twelve years of SAMtools and BCFtools","volume":"10","author":"Danecek","year":"2021","journal-title":"Gigascience"},{"key":"B5","first-page":"249","volume-title":"Support Vector Machines: Theory and Applications","author":"Evgeniou","year":"2001"},{"key":"B6","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1016\/j.ajhg.2021.03.010","article-title":"Machine learning-based reclassification of germline variants of unknown significance: the RENOVO algorithm","volume":"108","author":"Favalli","year":"2021","journal-title":"Am. J. Hum. Genet."},{"key":"B7","doi-asserted-by":"publisher","first-page":"eadm7066","DOI":"10.1126\/science.adm7066","article-title":"Machine learning-based penetrance of genetic variants","volume":"389","author":"Forrest","year":"2025","journal-title":"Science"},{"key":"B8","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/j.ajhg.2023.11.005","article-title":"Will variants of uncertain significance still exist in 2030?","volume":"111","author":"Fowler","year":"2024","journal-title":"Am. J. Hum. Genet."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1012","DOI":"10.1002\/humu.24309","article-title":"Variant interpretation using population databases: lessons from gnomAD","volume":"43","author":"Gudmundsson","year":"2022","journal-title":"Hum. Mutat."},{"key":"B10","doi-asserted-by":"publisher","first-page":"986","DOI":"10.1002\/humu.24298","article-title":"Annotating and prioritizing genomic variants using the ensembl variant effect Predictor-A tutorial","volume":"43","author":"Hunt","year":"2022","journal-title":"Hum. Mutat."},{"key":"B11","doi-asserted-by":"publisher","first-page":"10478","DOI":"10.1038\/s41598-023-37698-6","article-title":"Gene-specific machine learning for pathogenicity prediction of rare BRCA1 and BRCA2 missense variants","volume":"13","author":"Kang","year":"2023","journal-title":"Sci. Rep."},{"key":"B12","doi-asserted-by":"publisher","first-page":"1552","DOI":"10.3390\/biom12111552","article-title":"MARGINAL: an automatic classification of variants in BRCA1 and BRCA2 genes using a machine learning model","volume":"12","author":"Karalidou","year":"2022","journal-title":"Biomolecules"},{"key":"B13","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1038\/s41586-020-2308-7","article-title":"The mutational constraint spectrum quantified from variation in 141,456 humans","volume":"581","author":"Karczewski","year":"2020","journal-title":"Nature"},{"key":"B14","doi-asserted-by":"publisher","first-page":"982930","DOI":"10.3389\/fgene.2022.982930","article-title":"Gene-specific machine learning model to predict the pathogenicity of BRCA2 variants","volume":"13","author":"Khandakji","year":"2022","journal-title":"Front. Genet."},{"key":"B15","doi-asserted-by":"publisher","first-page":"e2444526","DOI":"10.1001\/jamanetworkopen.2024.44526","article-title":"Clinical variant reclassification in hereditary disease genetic testing","volume":"7","author":"Kobayashi","year":"2024","journal-title":"JAMA Netw. Open"},{"key":"B16","doi-asserted-by":"publisher","first-page":"eabj1624","DOI":"10.1126\/sciadv.abj1624","article-title":"CancerVar: an artificial intelligence-empowered platform for clinical interpretation of somatic mutations in cancer","volume":"8","author":"Li","year":"2022","journal-title":"Sci. Adv."},{"key":"B17","doi-asserted-by":"publisher","first-page":"981005","DOI":"10.3389\/fgene.2022.981005","article-title":"Computational approaches for predicting variant impact: an overview from resources, principles to applications","volume":"13","author":"Liu","year":"2022","journal-title":"Front. Genet."},{"key":"B18","doi-asserted-by":"crossref","first-page":"2102","DOI":"10.1038\/s41598-024-52023-5","article-title":"Identifying top ten predictors of type 2 diabetes through machine learning analysis of UK biobank data","volume":"14","author":"Lugner","year":"2024","journal-title":"Sci. Rep."},{"key":"B19","volume-title":"A Unified Approach to Interpreting Model Predictions","author":"Lundberg","year":"2017"},{"key":"B20","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1186\/s13059-016-0974-4","article-title":"The ensembl variant effect predictor","volume":"17","author":"McLaren","year":"2016","journal-title":"Genome Biol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"3812","DOI":"10.1093\/nar\/gkg509","article-title":"Predicting amino acid changes that affect protein function","volume":"31","author":"Ng","year":"2003","journal-title":"Nucleic Acids Res."},{"key":"B22","doi-asserted-by":"publisher","first-page":"2517","DOI":"10.1038\/s41598-022-06547-3","article-title":"A machine learning approach based on ACMG\/AMP guidelines for genomic variant classification and prioritization","volume":"12","author":"Nicora","year":"2022","journal-title":"Sci. Rep."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1038\/gim.2017.37","article-title":"Sherloc: a comprehensive refinement of the ACMG-AMP variant classification criteria","volume":"19","author":"Nykamp","year":"2017","journal-title":"Genet. Med."},{"key":"B24","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.5555\/1953048.2078195","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"B25","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1177\/1099800417750746","article-title":"Inherited cancer in the age of next-generation sequencing","volume":"20","author":"Price","year":"2018","journal-title":"Biol. Res. Nurs."},{"key":"B26","doi-asserted-by":"publisher","first-page":"2116","DOI":"10.1038\/s41436-019-0463-8","article-title":"Toward automation of germline variant curation in clinical cancer genetics","volume":"21","author":"Ravichandran","year":"2019","journal-title":"Genet. Med."},{"key":"B27","doi-asserted-by":"publisher","first-page":"D886","DOI":"10.1093\/nar\/gky1016","article-title":"CADD: predicting the deleteriousness of variants throughout the human genome","volume":"47","author":"Rentzsch","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"B28","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1038\/gim.2015.30","article-title":"Standards and guidelines for the interpretation of sequence variants: a joint consensus recommendation of the American college of medical genetics and genomics and the association for molecular pathology","volume":"17","author":"Richards","year":"2015","journal-title":"Genet. Med."},{"key":"B29","doi-asserted-by":"publisher","first-page":"31","DOI":"10.17849\/insm-47-01-31-39.1","article-title":"Random forest","volume":"47","author":"Rigatti","year":"2017","journal-title":"J. Insur. Med."},{"key":"B30","doi-asserted-by":"publisher","first-page":"101914","DOI":"10.1016\/j.gimo.2024.101914","article-title":"Refining the interpretation of variants of uncertain significance in hereditary cancer screening through integrated RNA sequencing","volume":"3","author":"Sha","year":"2024","journal-title":"Genet. Med. Open"},{"key":"B31","doi-asserted-by":"publisher","first-page":"12","DOI":"10.11613\/BM.2014.003","article-title":"Understanding logistic regression analysis","volume":"24","author":"Sperandei","year":"2014","journal-title":"Biochem. Med. Zagreb."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1734","DOI":"10.1002\/humu.24088","article-title":"Fitting a naturally scaled point system to the ACMG\/AMP variant classification guidelines","volume":"41","author":"Tavtigian","year":"2020","journal-title":"Hum. Mutat."},{"key":"B33","doi-asserted-by":"publisher","first-page":"149587","DOI":"10.1016\/j.gene.2025.149587","article-title":"Variants of uncertain significance: at the crux of diagnostic odyssey","volume":"962","author":"Zawar","year":"2025","journal-title":"Gene"},{"key":"B34","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1186\/s12859-021-04400-4","article-title":"Deep learning for cancer type classification and driver gene identification","volume":"22","author":"Zeng","year":"2021","journal-title":"BMC Bioinforma."}],"container-title":["Frontiers in Systems Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fsysb.2026.1828263\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T11:16:27Z","timestamp":1785842187000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fsysb.2026.1828263\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"references-count":34,"alternative-id":["10.3389\/fsysb.2026.1828263"],"URL":"https:\/\/doi.org\/10.3389\/fsysb.2026.1828263","relation":{},"ISSN":["2674-0702"],"issn-type":[{"value":"2674-0702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,4]]},"article-number":"1828263"}}