Introduction: 3q29 deletion syndrome (3q29del) is a recurrent deletion syndrome associated with neuropsychiatric disorders and congenital anomalies. Dysmorphic facial features have been described but not systematically characterized. This study aims to detail the 3q29del craniofacial phenotype and use a machine learning approach to categorize individuals with 3q29del through analysis of 2D photos. Methods: Detailed dysmorphology exam and 2D facial photos were ascertained from 31 individuals with 3q29del. Photos were used to train the next generation phenotyping platform Face2Gene (FDNA, Inc, Boston, MA) to distinguish 3q29del cases from controls, using a proprietary algorithm. Area under the curve of receiver operating characteristic curves (AUC-ROC) were used to determine the capacity of Face2Gene to identify 3q29del cases against controls. Results: In this cohort, the most common observed craniofacial features were prominent forehead (48.4%), prominent nose tip (35.5%), and thin upper lip vermillion (25.8%). The FDNA technology showed an ability to distinguish cases from controls with an AUC-ROC value of 0.873 (p = 0.006). Conclusion: This study found a recognizable facial pattern in 3q29del, as observed by trained clinical geneticists and next generation phenotyping technology. These results expand the potential application of automated technology such as FDNA in identifying rare genetic syndromes, even when facial dysmorphology is subtle.

中文翻译：

---

3q29缺失综合征的颅面特征：下一代表型技术的应用。

简介：3q29缺失综合征（3q29del）是与神经精神疾病和先天性异常相关的复发性缺失综合征。已经描述了畸形的面部特征，但没有系统地表征。这项研究旨在详细分析3q29del颅面表型，并使用机器学习方法通​​过分析2D照片对3q29del进行个体分类。方法：从31名3q29del患者中确定详细的畸形检查和2D面部照片。使用专有算法，照片被用于训练下一代表型平台Face2Gene（FDNA，Inc，Boston，MA），以将3q29del病例与对照区分开。接收器工作特征曲线（AUC-ROC）曲线下的面积用于确定Face2Gene识别对照的3q29del病例的能力。结果：在该队列中，最常见的颅面特征是前额突出（48.4％），鼻尖突出（35.5％）和上唇朱红色稀薄（25.8％）。FDNA技术显示了将病例与对照组的AUC-ROC值为0.873（p = 0.006）的能力。结论：这项研究发现了3q29del中可识别的面部模式，这是由训练有素的临床遗传学家和下一代表型技术所观察到的。这些结果扩大了自动化技术（例如FDNA）在识别罕见遗传综合征中的潜在应用，即使面部畸形非常微妙。FDNA技术显示了将病例与对照组的AUC-ROC值为0.873（p = 0.006）的能力。结论：这项研究发现了3q29del中可识别的面部模式，这是由训练有素的临床遗传学家和下一代表型技术所观察到的。这些结果扩大了自动化技术（例如FDNA）在识别罕见遗传综合征中的潜在应用，即使面部畸形非常微妙。FDNA技术显示了将病例与对照组的AUC-ROC值为0.873（p = 0.006）的能力。结论：这项研究发现了3q29del中可识别的面部模式，这是由训练有素的临床遗传学家和下一代表型技术所观察到的。这些结果扩大了自动化技术（例如FDNA）在识别罕见遗传综合征中的潜在应用，即使面部畸形非常微妙。