A machine learning approach utilizing DNA methylation as an accurate classifier of COVID-19 disease severity.
A machine learning approach utilizing DNA methylation as an accurate classifier of COVID-19 disease severity.
复制标题
DOI：
10.1038/s41598-022-22201-4
复制
发表时间：
2022-10-19
影响因子：
4.6
通讯作者：
中科院分区：
文献类型：
--
作者：
自2019冠状病毒病大流行爆发以来，尽管有疫苗和治疗，但由于变异，全球病例持续增加，结果各异。有必要及早发现有风险的个人，及时采取医疗干预措施将使他们受益。DNA甲基化提供了一个机会，以确定一个表观遗传签名的个人在增加的风险。我们利用机器学习从NCBI Gene Expression Omnibus提供的数据中识别COVID-19疾病的DNA甲基化特征。重新分析了由460名个体（164名COVID-19感染者和296名非感染者）组成的训练队列和由128名个体（102名COVID-19感染者和26名非COVID相关肺炎）组成的外部验证数据集。使用ChAMP处理数据，并将β值进行logit转换。利用JADBio AutoML平台来识别与严重COVID-19疾病相关的甲基化特征。我们从4个独特的甲基化位点中确定了一个随机森林分类模型，该模型具有识别患有严重COVID-19疾病的个体的能力。模型的平均受试者工作特征曲线下面积（AUC-ROC）为0.933，平均精确召回曲线下面积（AUC-PRC）为0.965。当应用于我们的外部验证时，该模型产生的AUC-ROC为0.898，AUC-PRC为0.864。这些结果进一步加深了我们对DNA甲基化在COVID-19疾病病理学中的效用的理解，并作为一个平台，为未来的COVID-19相关研究提供信息。
Since the onset of the COVID-19 pandemic, increasing cases with variable outcomes continue globally because of variants and despite vaccines and therapies. There is a need to identify at-risk individuals early that would benefit from timely medical interventions. DNA methylation provides an opportunity to identify an epigenetic signature of individuals at increased risk. We utilized machine learning to identify DNA methylation signatures of COVID-19 disease from data available through NCBI Gene Expression Omnibus. A training cohort of 460 individuals (164 COVID-19-infected and 296 non-infected) and an external validation dataset of 128 individuals (102 COVID-19-infected and 26 non-COVID-associated pneumonia) were reanalyzed. Data was processed using ChAMP and beta values were logit transformed. The JADBio AutoML platform was leveraged to identify a methylation signature associated with severe COVID-19 disease. We identified a random forest classification model from 4 unique methylation sites with the power to discern individuals with severe COVID-19 disease. The average area under the curve of receiver operator characteristic (AUC-ROC) of the model was 0.933 and the average area under the precision-recall curve (AUC-PRC) was 0.965. When applied to our external validation, this model produced an AUC-ROC of 0.898 and an AUC-PRC of 0.864. These results further our understanding of the utility of DNA methylation in COVID-19 disease pathology and serve as a platform to inform future COVID-19 related studies.
登录
查看更多内容
影响因子：
15.8
作者：
Antoun E;Kitaba NT;Titcombe P;Dalrymple KV;Garratt ES;Barton SJ;Murray R;Seed PT;Holbrook JD;Kobor MS;Lin DT;MacIsaac JL;Burdge GC;White SL;Poston L;Godfrey KM;Lillycrop KA;UPBEAT Consortium
通讯作者：
UPBEAT Consortium
影响因子：
5.8
作者：
Lagani, Vincenzo;Athineou, Giorgos;Tsamardinos, Ioannis
通讯作者：
Tsamardinos, Ioannis
影响因子：
168.9
作者：
Huang, Chaolin;Wang, Yeming;Cao, Bin
通讯作者：
Cao, Bin
DOI：
10.1038/s43856-021-00042-y
发表时间：
2021
期刊：
Communications medicine
影响因子：
--
作者：
Konigsberg IR;Barnes B;Campbell M;Davidson E;Zhen Y;Pallisard O;Boorgula MP;Cox C;Nandy D;Seal S;Crooks K;Sticca E;Harrison GF;Hopkinson A;Vest A;Arnold CG;Kahn MG;Kao DP;Peterson BR;Wicks SJ;Ghosh D;Horvath S;Zhou W;Mathias RA;Norman PJ;Porecha R;Yang IV;Gignoux CR;Monte AA;Taye A;Barnes KC
通讯作者：
Barnes KC
影响因子：
5.5
作者：
Corley, Michael J.;Pang, Alina P. S.;Ndhlovu, Lishomwa C.
通讯作者：
Ndhlovu, Lishomwa C.