{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:30:20Z","timestamp":1787725820308,"version":"build-2784847793"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"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. Digit. Health"],"abstract":"<jats:p>A major challenge in clinical genomics is to classify genetic variations correctly, since it directly affects disease diagnosis and personal care. The existing methods tend to be based on the combination of different factors, such as protein structure, population frequencies, phenotypic annotations, and sequence conservation. Nevertheless, these methods often cannot be used to achieve the necessary interpretability, quantify uncertainty, and address rare cases. This paper presents a probabilistic gradient boosting model on variant pathogenicity prediction. The suggested framework applies biological characteristics at both level of DNA and protein levels while also scaling the level of uncertainty in clinical decision making. Our machine learning aims to solve the issues of variant interpretation by managing the features and through probability-based pathogenicity prediction. The framework formulation is aimed at generalizing over various datasets and minimizing overfitting. At the same time, it can ensure reasonable performance to facilitate clinical experiments. The model has also been tested on three standard datasets and demonstrated to be more predictive of the pathogenic effect of variants, in comparison with a variety of existing tools. The probabilistic gradient boosting model proposed had ROC AUC values of 0.9293, 0.9610, and 0.9646 on ClinVar variants, GRCh37, and GRCh38 human genome respectively. Furthermore, the dataset was ensured to include both exonic and intronic variants, and Variants of Uncertain Significance were also taken into consideration for Performance Testing. Through this it also aims to provide better clinical significance which will lead to a good interpretable tool for priority of variants for a large variety of disease conditions.<\/jats:p>","DOI":"10.3389\/fdgth.2026.1845955","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:03:25Z","timestamp":1787724205000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep DNA and protein level feature integration for robust clinical variant interpretation using probabilistic gradient boosting"],"prefix":"10.3389","volume":"8","author":[{"given":"V.","family":"Karthik","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.","family":"Prejesh","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sumedh Deepak","family":"Kudale","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chandra Umakanthan","family":"OmKumar","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Chennai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1038\/s41586-025-09140-6","article-title":"Complex genetic variation in nearly complete human genomes","volume":"644","author":"Logsdon","year":"2025","journal-title":"Nature"},{"key":"B2","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1038\/s41586-024-08370-4","article-title":"Site-saturation mutagenesis of 500 human protein domains","volume":"637","author":"Beltran","year":"2025","journal-title":"Nature"},{"key":"B3","doi-asserted-by":"publisher","first-page":"994","DOI":"10.7326\/M21-4109","article-title":"The challenge of genetic variants of uncertain clinical significance: a narrative review","volume":"175","author":"Burke","year":"2022","journal-title":"Ann Intern Med"},{"key":"B4","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":"B5","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1016\/j.ajhg.2016.08.016","article-title":"REVEL: an ensemble method for predicting the pathogenicity of rare missense variants","volume":"99","author":"Ioannidis","year":"2016","journal-title":"Am J Hum Genet"},{"key":"B6","doi-asserted-by":"publisher","first-page":"baaf017","DOI":"10.1093\/database\/baaf017","article-title":"Varguideatlas: a repository of variant interpretation guidelines","volume":"2025","author":"Costa","year":"2025","journal-title":"Database"},{"key":"B7","doi-asserted-by":"publisher","first-page":"22411","DOI":"10.1038\/s41598-024-72470-4","article-title":"CNVoyant: a machine learning framework for accurate and explainable copy number variant classification","volume":"14","author":"Schuetz","year":"2024","journal-title":"Sci Rep"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e001966","DOI":"10.1136\/bmjpo-2023-001966","article-title":"NeuroCNVscore: a tissue-specific framework to prioritise the pathogenicity of CNVs in neurodevelopmental disorders","volume":"7","author":"Liu","year":"2023","journal-title":"BMJ Paediatr Open"},{"key":"B9","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.ajhg.2021.12.007","article-title":"StrVCTVRE: a supervised learning method to predict the pathogenicity of human genome structural variants","volume":"109","author":"Sharo","year":"2022","journal-title":"Am J Hum Genet"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e1011540","DOI":"10.1371\/journal.pgen.1011540","article-title":"Leveraging cancer mutation data to inform the pathogenicity classification of germline missense variants","volume":"21","author":"Haque","year":"2025","journal-title":"PLoS Genet"},{"key":"B11","doi-asserted-by":"publisher","first-page":"8136","DOI":"10.1038\/s41598-024-51489-7","article-title":"Enhancing missense variant pathogenicity prediction with protein language models using VariPred","volume":"14","author":"Lin","year":"2024","journal-title":"Sci Rep"},{"key":"B12","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1186\/s13059-022-02631-z","article-title":"TADA\u2014a machine learning tool for functional annotation-based prioritisation of pathogenic CNVs","volume":"23","author":"Hertzberg","year":"2022","journal-title":"Genome Biol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"7805","DOI":"10.1038\/s41467-023-43651-y","article-title":"PhenoSV: interpretable phenotype-aware model for prioritization of genes affected by structural variants","volume":"14","author":"Xu","year":"2023","journal-title":"Nat Commun"},{"key":"B14","doi-asserted-by":"publisher","first-page":"100862","DOI":"10.1016\/j.gim.2023.100862","article-title":"Eyevarp: computational framework for identification of pathogenic variants specific to eye disease","volume":"25","author":"Kumaran","year":"2023","journal-title":"Genet Med"},{"key":"B15","author":"Requena","year":"2022"},{"key":"B16","doi-asserted-by":"publisher","first-page":"166915","DOI":"10.1016\/j.jmb.2021.166915","article-title":"The DBSAV database: predicting deleteriousness of single amino acid variations","volume":"433","author":"Pei","year":"2021","journal-title":"J Mol Biol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"btad280","DOI":"10.1093\/bioinformatics\/btad280","article-title":"Predicting the pathogenicity of missense variants using features derived from AlphaFold2","volume":"39","author":"Schmidt","year":"2023","journal-title":"Bioinformatics"},{"key":"B18","doi-asserted-by":"publisher","first-page":"6667201","DOI":"10.1155\/2021\/6667201","article-title":"Predicting ovarian\/breast cancer pathogenic risks of BRCA1 VUS","volume":"2021","author":"Lin","year":"2021","journal-title":"Biomed Res Int"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1765","DOI":"10.3390\/genes14091765","article-title":"Fexsplice: a LightGBM-based model for predicting the splicing effect of SNV affecting first nucleotide G","volume":"14","author":"Joudaki","year":"2023","journal-title":"Genes (Basel)"},{"key":"B20","doi-asserted-by":"publisher","first-page":"4626","DOI":"10.1093\/bioinformatics\/btab529","article-title":"3Cnet: pathogenicity prediction of human variants using multitask learning with evolutionary constraints","volume":"37","author":"Won","year":"2021","journal-title":"Bioinformatics"},{"key":"B21","doi-asserted-by":"publisher","first-page":"e1010191","DOI":"10.1371\/journal.pgen.1010191","article-title":"Classification of non-coding variants with high pathogenic impact","volume":"18","author":"Moyon","year":"2022","journal-title":"PLoS Genet"},{"key":"B22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1038\/s41525-023-00386-5","article-title":"Characterizing the pathogenicity of genetic variants: the consequences of context","volume":"9","author":"Ciesielski","year":"2024","journal-title":"npj Genom Med"},{"key":"B23","doi-asserted-by":"publisher","first-page":"116947","DOI":"10.1016\/j.bone.2023.116947","article-title":"The global ALPL gene variant classification project: dedicated to deciphering variants","volume":"178","author":"Farman","year":"2024","journal-title":"Bone"},{"key":"B24","doi-asserted-by":"publisher","first-page":"101402","DOI":"10.1016\/j.gim.2025.101402","article-title":"Clingen sequence variant interpretation working group. Calibration of additional computational tools expands ClinGen recommendation options for variant classification with PP3\/BP4 criteria","volume":"27","author":"Bergquist","year":"2025","journal-title":"Genet Med"},{"key":"B25","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s13059-023-03113-6","article-title":"CAGI, the critical assessment of genome interpretation, establishes progress and prospects for computational genetic variant interpretation methods","volume":"25","year":"2024","journal-title":"Genome Biol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1186\/s40246-024-00663-z","article-title":"Variant impact predictor database (VIPdb), version 2: trends from three decades of genetic variant impact predictors","volume":"18","author":"Lin","year":"2024","journal-title":"Hum Genomics"},{"key":"B27","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/s12920-023-01454-6","article-title":"Evaluation of in silico pathogenicity prediction tools for the classification of small in-frame indels","volume":"16","author":"Cannon","year":"2023","journal-title":"BMC Med Genomics"},{"key":"B28","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1186\/s12864-022-08498-5","article-title":"Probc: joint modeling of epigenome and transcriptome effects in 3D genome","volume":"23","author":"Sefer","year":"2022","journal-title":"BMC Genomics"},{"key":"B29","doi-asserted-by":"publisher","first-page":"37562","DOI":"10.1038\/s41598-025-21746-4","article-title":"Joint analysis of sQTL and hi-C reveals spatial proximity between sQTLs and target genes in cancer tissues","volume":"15","author":"Eralp","year":"2025","journal-title":"Sci Rep"},{"key":"B30","doi-asserted-by":"publisher","first-page":"eadg7492","DOI":"10.1126\/science.adg7492","article-title":"Accurate proteome-wide missense variant effect prediction with AlphaMissense","volume":"381","author":"Cheng","year":"2023","journal-title":"Science"},{"key":"B31","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1038\/s41586-021-04043-8","article-title":"Disease variant prediction with deep generative models of evolutionary data","volume":"599","author":"Frazer","year":"2021","journal-title":"Nature"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1038\/s41588-018-0167-z","article-title":"Predicting the clinical impact of human mutation with deep neural networks","volume":"50","author":"Sundaram","year":"2018","journal-title":"Nat Genet"},{"key":"B33","first-page":"1510","article-title":"Probabilistic gradient boosting machines for large-scale probabilistic regression","author":"Sprangers","year":"2021"},{"key":"B34","doi-asserted-by":"crossref","DOI":"10.1145\/3292500.3330701","article-title":"Optuna: a next-generation hyperparameter optimization framework","author":"Akiba","year":"2019"},{"key":"B35","doi-asserted-by":"publisher","first-page":"D1062","DOI":"10.1093\/nar\/gkx1153","article-title":"Clinvar: improving access to variant interpretations and supporting evidence","volume":"46","author":"Landrum","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"B36","first-page":"44","article-title":"The complete sequence of a human genome","volume-title":"Science","author":"Nurk","year":"2022"},{"key":"B37","first-page":"849","article-title":"Evaluation of GRCh38 and de novo haploid genome assemblies demonstrates the enduring quality of the reference assembly","volume-title":"Genome Res","author":"Schneider","year":"2017"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1845955\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:03:26Z","timestamp":1787724206000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1845955\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":37,"alternative-id":["10.3389\/fdgth.2026.1845955"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1845955","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]},"article-number":"1845955"}}