MARiO : Predicting Cancer Variant Pathogenicity by Integrating In Silico Evaluation and Patient‐Level Mutational Contexts
Year: 2026
Type: article
Abstract: Comprehensive genomic profiling (CGP) supports precision medicine in cancer care, but accurate assessment of missense variant pathogenicity, especially for variants without established consensus, remains challenging. Various computational tools have been developed for variant functional prediction, but most current tools rely solely on variant-level features and do not capture the clinical context of individual patients. To address this limitation, we developed MARiO (Missense Alteration Risk identifier in Oncology), a machine-learning model that integrates variant-level features and patient-level clinical and genomic contexts to effectively predict the pathogenicity of missense variants in cancer. We collected a total of 10,180 missense variants from 1271 patients and evaluated candidate features for their association with variant pathogenicity, identifying informative features including in silico functional predictions, population allele frequency, variant allele frequency, and tumor mutational burden. Using these selected features, MARiO was developed with extreme gradient boosting. The model integrates multiple in silico prediction tools and patient-specific genomic contexts while accommodating missing values frequently observed in real-world data. MARiO outperformed existing tools, achieving an area under the receiver operating characteristic curve of 0.922. The model demonstrated strong generalizability across multiple external datasets and showed consistency with real-world molecular treatment proposals. MARiO offers a robust and clinically relevant approach for missense variant pathogenicity assessment by integrating variant- and patient-level features and serves as a valuable tool to support clinical decision-making.
Source: Cancer Science
DOI: 10.1111/cas.70597
Authors: Haruko Nakagawa(Conceptualization, Funding acquisition, Investigation, Methodology, Software, Visualization, Writing – original draft), Takashi Kamatani(Conceptualization, Funding acquisition, Methodology, Software, Supervision, Writing – original draft), Naoya Ishibashi(Data curation, Writing – review & editing), Satoru Aoyama(Data curation, Writing – review & editing), Michina Morioka(Data curation, Writing – review & editing), Fuyuki Miya(Funding acquisition, Software, Writing – review & editing), Sadakatsu Ikeda(Supervision, Writing – review & editing)
Language: English
Topic: Genomics and Rare Diseases
Subfield: Genetics
Domain: Life Sciences
Open Access status: gold
Estimated APC paid: $2,600
Awards: G3801581099, Distinguishing Germline from Somatic Mutations in Cancer Genomes through Mathematical and Statistical Modeling, G5268479076, Prognostic modeling of myxoid liposarcoma by gene expression and histopathology with focus on tumor immunity., Multi-omics of ovarian cancer organoids for development of novel therapeutics against drug-resistant ovarian cancers, Identification of Treatment-Related Factors Using Multi-Region Analysis Before and After Cancer Immunotherapy
OpenAlex ID: W7168022937
