Mak Christopher C Y, Klinkhammer Hannah, Choufani Sanaa, Reko Nikola, Christman Angela K, Pisan Elise, Chui Martin M C, Lee Mianne, Leduc Fiona, Dempsey Jennifer C, Sanchez-Lara Pedro A, Bombei Hannah M, Bernat John A, Faivre Laurence, Mau-Them Frederic Tran, Palafoll Irene Valenzuela, Canham Natalie, Sarkar Ajoy, Zarate Yuri A, Callewaert Bert, Bukowska-Olech Ewelina, Jamsheer Aleksander, Zankl Andreas, Willems Marjolaine, Duncan Laura, Isidor Bertrand, Cogne Benjamin, Boute Odile, Vanlerberghe Clémence, Goldenberg Alice, Stolerman Elliot, Low Karen J, Gilard Vianney, Amiel Jeanne, Lin Angela E, Gordon Christopher T, Doherty Dan, Krawitz Peter M, Weksberg Rosanna, Hsieh Tzung-Chien, Chung Brian H Y
Department of Paediatrics and Adolescent Medicine, School of Clinical Medicine, The University of Hong Kong, Hong Kong SAR, China.
Institute for Genomic Statistics and Bioinformatics, University Hospital Bonn, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany; Institute for Medical Biometry, Informatics and Epidemiology, University Hospital Bonn, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany.
EBioMedicine. 2025 May;115:105677. doi: 10.1016/j.ebiom.2025.105677. Epub 2025 Apr 24.
Decisions to split two or more phenotypic manifestations related to genetic variations within the same gene can be challenging, especially during the early stages of syndrome discovery. Genotype-based diagnostics with artificial intelligence (AI)-driven approaches using next-generation phenotyping (NGP) and DNA methylation (DNAm) can be utilized to expedite syndrome delineation within a single gene.
We utilized an expanded cohort of 56 patients (22 previously unpublished individuals) with truncating variants in the MN1 gene and attempted different methods to assess plausible strategies to objectively delineate phenotypic differences between the C-Terminal Truncation (CTT) and N-Terminal Truncation (NTT) groups. This involved transcriptomics analysis on available patient fibroblast samples and AI-assisted approaches, including a new statistical method of GestaltMatcher on facial photos and blood DNAm analysis using a support vector machine (SVM) model.
RNA-seq analysis was unable to show a significant difference in transcript expression despite our previous hypothesis that NTT variants would induce nonsense mediated decay. DNAm analysis on nine blood DNA samples revealed an episignature for the CTT group. In parallel, the new statistical method of GestaltMatcher objectively distinguished the CTT and NTT groups with a low requirement for cohort number. Validation of this approach was performed on syndromes with known DNAm signatures of SRCAP, SMARCA2 and ADNP to demonstrate the effectiveness of this approach.
We demonstrate the potential of using AI-based technologies to leverage genotype, phenotype and epigenetics data in facilitating splitting decisions in diagnosis of syndromes with minimal sample requirement.
The specific funding of this article is provided in the acknowledgements section.
对于与同一基因内遗传变异相关的两种或更多种表型表现进行区分的决策可能具有挑战性，尤其是在综合征发现的早期阶段。利用人工智能（AI）驱动的基于基因型的诊断方法，结合下一代表型分析（NGP）和DNA甲基化（DNAm），可用于加快单个基因内综合征的界定。
我们对56例MN1基因存在截短变异的患者（其中22例为先前未发表的个体）组成的扩大队列进行研究，尝试采用不同方法评估合理策略，以客观界定C端截短（CTT）组和N端截短（NTT）组之间的表型差异。这包括对可用的患者成纤维细胞样本进行转录组学分析以及AI辅助方法，包括一种用于面部照片的新统计方法GestaltMatcher和使用支持向量机（SVM）模型的血液DNAm分析。
尽管我们先前假设NTT变异会诱导无义介导的衰变，但RNA测序分析未能显示转录表达的显著差异。对9份血液DNA样本的DNAm分析揭示了CTT组的一种表观特征。同时，GestaltMatcher新统计方法以对队列数量要求较低的方式客观地区分了CTT组和NTT组。在具有已知SRCAP、SMARCA2和ADNP的DNAm特征的综合征上对该方法进行了验证，以证明该方法的有效性。
我们证明了使用基于AI的技术利用基因型、表型和表观遗传学数据在以最少样本需求促进综合征诊断中的区分决策方面的潜力。
本文的具体资金情况在致谢部分提供。
