Geographical classification of malaria parasites through applying machine learning to whole genome sequence data.
Geographical classification of malaria parasites through applying machine learning to whole genome sequence data.
复制标题
DOI：
10.1038/s41598-022-25568-6
复制
发表时间：
2022-12-07
影响因子：
4.6
通讯作者：
Clark, Taane G.
中科院分区：
文献类型：
--
作者：
Deelder, Wouter;Manko, Emilia;Phelan, Jody E.;Campino, Susana;Palla, Luigi;Clark, Taane G.
由疟原虫寄生虫引起的疟疾是一个重大的全球健康挑战。恶性疟原虫和间日疟原虫基因组的全基因组测序（WGS）提供了对寄生虫遗传多样性，传播模式的见解，并可以为临床和监测目的提供决策信息。测序技术的进步有助于生成及时和大的基因组数据集，具有应用人工智能分析技术的前景（例如，机器学习），以支持方案疟疾控制和消除。在这里，我们评估了应用深度学习卷积神经网络方法预测感染的地理来源（大陆，国家，GPS位置）的潜力，使用恶性疟原虫（n = 5957; 27个国家）和间日疟原虫（n = 659; 13个国家）分离株的WGS数据。使用已鉴定的高质量全基因组单核苷酸多态性（SNP）（恶性疟原虫：750 k，间日疟原虫：588 k），对人口结构和祖先的分析显示了国家一级的聚类。在预测这两个物种的位置时，分类（与回归相比）方法的距离误差最小，在国家一级的准确率> 90%。我们的工作证明了机器学习方法在疟疾寄生虫地理分类中的实用性。随着在更多受疟疾影响的地区及时生成WGS数据，用于地理分类的机器学习方法的性能将得到改善，从而支持疾病控制活动。
Malaria, caused by Plasmodium parasites, is a major global health challenge. Whole genome sequencing (WGS) of Plasmodium falciparum and Plasmodium vivax genomes is providing insights into parasite genetic diversity, transmission patterns, and can inform decision making for clinical and surveillance purposes. Advances in sequencing technologies are helping to generate timely and big genomic datasets, with the prospect of applying Artificial Intelligence analytical techniques (e.g., machine learning) to support programmatic malaria control and elimination. Here, we assess the potential of applying deep learning convolutional neural network approaches to predict the geographic origin of infections (continents, countries, GPS locations) using WGS data of P. falciparum (n = 5957; 27 countries) and P. vivax (n = 659; 13 countries) isolates. Using identified high-quality genome-wide single nucleotide polymorphisms (SNPs) (P. falciparum: 750 k, P. vivax: 588 k), an analysis of population structure and ancestry revealed clustering at the country-level. When predicting locations for both species, classification (compared to regression) methods had the lowest distance errors, and > 90% accuracy at a country level. Our work demonstrates the utility of machine learning approaches for geo-classification of malaria parasites. With timelier WGS data generation across more malaria-affected regions, the performance of machine learning approaches for geo-classification will improve, thereby supporting disease control activities.
登录
查看更多内容
影响因子：
4.3
作者：
Libiseller-Egger J;Phelan J;Campino S;Mohareb F;Clark TG
通讯作者：
Clark TG
影响因子：
3.7
作者：
Diez Benavente E;Ward Z;Chan W;Mohareb FR;Sutherland CJ;Roper C;Campino S;Clark TG
通讯作者：
Clark TG
影响因子：
5.8
作者：
Bhaskar, Anand;Javanmard, Adel;Tse, David
通讯作者：
Tse, David
影响因子：
4.3
作者：
Neves, Bruno J.;Braga, Rodolpho C.;Andrade, Carolina Horta
通讯作者：
Andrade, Carolina Horta
影响因子：
16.6
作者：
Benavente ED;Manko E;Phelan J;Campos M;Nolder D;Fernandez D;Velez-Tobon G;Castaño AT;Dombrowski JG;Marinho CRF;Aguiar ACC;Pereira DB;Sriprawat K;Nosten F;Moon R;Sutherland CJ;Campino S;Clark TG
通讯作者：
Clark TG