PT  - JOURNAL ARTICLE
AU  - Hui Chong
AU  - Qingyang Yu
AU  - Yuguo Zha
AU  - Guangzhou Xiong
AU  - Nan Wang
AU  - Xinhe Huang
AU  - Shijuan Huang
AU  - Chuqing Sun
AU  - Sicheng Wu
AU  - Wei-Hua Chen
AU  - Luis Pedro Coelho
AU  - Kang Ning
TI  - EXPERT: Transfer Learning-enabled context-aware microbial source tracking
AID  - 10.1101/2021.01.29.428751
DP  - 2021 Jan 01
TA  - bioRxiv
PG  - 2021.01.29.428751
4099  - http://biorxiv.org/content/early/2021/12/14/2021.01.29.428751.short
4100  - http://biorxiv.org/content/early/2021/12/14/2021.01.29.428751.full
AB  - Microbial source tracking quantifies the potential origin of microbial communities, facilitates better understanding of how the taxonomic structure and community functions were formed and maintained. However, previous methods involve a tradeoff between speed and accuracy, and have encountered difficulty in source tracking under many context-dependent settings. Here, we present EXPERT for context-aware microbial source tracking, in which we adopted a Transfer Learning approach to profoundly elevate and expand the applicability of source tracking, enabling biologically informed novel microbial knowledge discovery. We demonstrate that EXPERT can predict microbial sources with performance superior to other methods in efficiency and accuracy. More importantly, we demonstrate EXPERT’s context-aware ability on several applications, including tracking the progression of infant gut microbiome development and monitoring the changes of gut microbiome for colorectal cancer patients. Broadly, transfer learning enables accurate and context-aware microbial source tracking and has the potential for novel microbial knowledge discovery.Competing Interest StatementThe authors have declared no competing interest.