Deep learning model to discriminate diverse infection types based on pairwise analysis of host gene expression
Jize Xie,
Xubin Zheng,
Jianlong Yan,
Qizhi Li,
Nana Jin,
Shuojia Wang,
Pengfei Zhao,
Shuai Li,
Wanfu Ding,
Lixin Cheng,
Qingshan Geng
Affiliations
Jize Xie
Guangdong Provincial Clinical Research Center for Geriatrics, Shenzhen People’s Hospital (First Affiliated Hospital of Southern University of Science and Technology, Second Clinical Medicine College of Jinan University), Shenzhen 518020, China; John Hopcroft Center for Computer Science, Shanghai Jiao Tong University, Shanghai, China
Xubin Zheng
Guangdong Provincial Clinical Research Center for Geriatrics, Shenzhen People’s Hospital (First Affiliated Hospital of Southern University of Science and Technology, Second Clinical Medicine College of Jinan University), Shenzhen 518020, China; Great Bay University, Dongguan, China
Jianlong Yan
Guangdong Provincial Clinical Research Center for Geriatrics, Shenzhen People’s Hospital (First Affiliated Hospital of Southern University of Science and Technology, Second Clinical Medicine College of Jinan University), Shenzhen 518020, China
Qizhi Li
John Hopcroft Center for Computer Science, Shanghai Jiao Tong University, Shanghai, China
Nana Jin
Guangdong Provincial Clinical Research Center for Geriatrics, Shenzhen People’s Hospital (First Affiliated Hospital of Southern University of Science and Technology, Second Clinical Medicine College of Jinan University), Shenzhen 518020, China; Health Data Science Center, Shenzhen People’s Hospital, Shenzhen 518020, China
Shuojia Wang
Guangdong Provincial Clinical Research Center for Geriatrics, Shenzhen People’s Hospital (First Affiliated Hospital of Southern University of Science and Technology, Second Clinical Medicine College of Jinan University), Shenzhen 518020, China
Pengfei Zhao
Guangdong Provincial Clinical Research Center for Geriatrics, Shenzhen People’s Hospital (First Affiliated Hospital of Southern University of Science and Technology, Second Clinical Medicine College of Jinan University), Shenzhen 518020, China
Shuai Li
John Hopcroft Center for Computer Science, Shanghai Jiao Tong University, Shanghai, China
Wanfu Ding
Guangdong Provincial Clinical Research Center for Geriatrics, Shenzhen People’s Hospital (First Affiliated Hospital of Southern University of Science and Technology, Second Clinical Medicine College of Jinan University), Shenzhen 518020, China; Corresponding author
Lixin Cheng
Guangdong Provincial Clinical Research Center for Geriatrics, Shenzhen People’s Hospital (First Affiliated Hospital of Southern University of Science and Technology, Second Clinical Medicine College of Jinan University), Shenzhen 518020, China; Health Data Science Center, Shenzhen People’s Hospital, Shenzhen 518020, China; Corresponding author
Qingshan Geng
Guangdong Provincial Clinical Research Center for Geriatrics, Shenzhen People’s Hospital (First Affiliated Hospital of Southern University of Science and Technology, Second Clinical Medicine College of Jinan University), Shenzhen 518020, China; Corresponding author
Summary: Accurate detection of pathogens, particularly distinguishing between Gram-positive and Gram-negative bacteria, could improve disease treatment. Host gene expression can capture the immune system’s response to infections caused by various pathogens. Here, we present a deep neural network model, bvnGPS2, which incorporates the attention mechanism based on a large-scale integrated host transcriptome dataset to precisely identify Gram-positive and Gram-negative bacterial infections as well as viral infections. We performed analysis of 4,949 blood samples across 40 cohorts from 10 countries using our previously designed omics data integration method, iPAGE, to select discriminant gene pairs and train the bvnGPS2. The performance of the model was evaluated on six independent cohorts comprising 374 samples. Overall, our deep neural network model shows robust capability to accurately identify specific infections, paving the way for precise medicine strategies in infection treatment and potentially also for identifying subtypes of other diseases.
