Venous thromboembolism is the third common cardiovascular disease and is composed of two entities, deep vein thrombosis (DVT) and its fatal form, pulmonary embolism (PE). While PE is observed in ~40% of patients with documented DVT, there is limited biomarkers that can help identifying patients at high PE risk. To fill this need, we implemented a two hidden-layers artificial neural networks (ANN) on 376 antibodies and 19 biological traits measured in the plasma of 1388 DVT patients, with or without PE, of the MARTHA study. We used the LIME algorithm to obtain a linear approximate of the resulting ANN prediction model. As MARTHA patients were typed for genotyping DNA arrays, a genome wide association study (GWAS) was conducted on the LIME estimate. Detected single nucleotide polymorphisms (SNPs) were tested for association with PE risk in MARTHA. Main findings were replicated in the EOVT study composed of 143 PE patients and 196 DVT only patients. The derived ANN model for PE achieved an accuracy of 0.89 and 0.79 in our training and testing sets, respectively. A GWAS on the LIME approximate identified a strong statistical association peak (p = 5.3x10-7) at the PLXNA4 locus, with lead SNP rs1424597 at which the minor A allele was further shown to associate with an increased risk of PE (OR = 1.49 [1.12 − 1.98], p = 6.1x10-3). Further association analysis in EOVT revealed that, in the combined MARTHA and EOVT samples, the rs1424597-A allele was associated with increased PE risk (OR = 1.74 [1.27 − 2.38, p = 5.42x10-4) in patients over 37 years of age but not in younger patients (OR = 0.96 [0.65 − 1.41], p = 0.848). Using an original integrated proteomics and genetics strategy, we identified PLXNA4 as a new susceptibility gene for PE whose exact role now needs to be further elucidated.

中文翻译：

---

结合血浆蛋白质组学和遗传数据的人工神经网络方法将PLXNA4鉴定为肺栓塞的新易感性位点。

静脉血栓栓塞是第三种常见的心血管疾病，由深静脉血栓形成（DVT）及其致命形式肺栓塞（PE）两个实体组成。虽然在约40％的DVT患者中观察到PE，但有限的生物标志物可以帮助识别高PE风险的患者。为了满足这一需求，我们对MARTHA研究的1388名DVT患者（有或没有PE）在血浆中测得的376种抗体和19种生物学特征实施了两个隐藏层人工神经网络（ANN）。我们使用LIME算法获得了所得ANN预测模型的线性近似。由于对MARTHA患者进行了基因分型DNA阵列分型，因此对LIME评估进行了全基因组关联研究（GWAS）。测试检测到的单核苷酸多态性（SNP）与MARTHA中PE风险的关联。主要发现在143名PE患者和196名仅DVT患者组成的EOVT研究中得以重复。在我们的训练和测试集中，派生的PE神经网络模型分别达到0.89和0.79的精度。在LIME上的GWAS近似值在PLXNA4基因座处发现了一个强大的统计关联峰（p = 5.3x10-7），这与铅SNP rs1424597有关，在该处进一步显示未成年人A等位基因与PE风险增加相关（OR = 1.49 [1.12-1.98]，p = 6.1x10-3）。EOVT中的进一步关联分析显示，在合并的MARTHA和EOVT样本中，rs1424597-A等位基因与37岁以上患者的PE风险增加相关（OR = 1.74 [1.27-2.38，p = 5.42x10-4）但在年轻患者中则没有（OR = 0.96 [0.65-1.41]，p = 0.848）。使用原始的综合蛋白质组学和遗传学策略，