TY - JOUR
T1 - LipidIN: a comprehensive repository for flash platform-independent annotation and reverse lipidomics
AU - Xu, Hao
AU - Jiang, Tianhang
AU - Lin, Yuxiang
AU - Zhang, Lei
AU - Yang, Huan
AU - Huang, Xiaoyun
AU - Mao, Ridong
AU - Yang, Zhu
AU - Zeng, Changchun
AU - Zhao, Shuang
AU - Di, Lijun
AU - Zhang, Wenbin
AU - Zeng, Jun
AU - Cai, Zongwei
AU - Lin, Shu-Hai
N1 - This work was supported by grants from the National Key Research and Development Program of China (2022YFE0205800, 2022YFA1105300), the National Natural Science Foundation of China (91957120, 21974114), Major Science and Technology Special Project of Fujian Province (2022YZ036012), the Fundamental Research Funds for the Central Universities (20720220003), Project “111” sponsored by the State Bureau of Foreign Experts and Ministry of Education of China (BP0618017) as well as grant support from Guangzhou Hybribio Medicine Technology Ltd. to S.-H.L. Natural Science Foundation of Fujian Province of China (2022J01330), Natural Science Foundation of Xiamen City of China (3502Z20227208), and China Scholarship Council (202308350047) to J.Z.
PY - 2025/5/16
Y1 - 2025/5/16
N2 - Improving annotation accuracy, coverage, speed and depth of lipid profiles remains a significant challenge in traditional lipid annotation. We introduce LipidIN, an advanced framework designed for flash platform-independent annotation. LipidIN features a 168.5-million lipid fragmentation hierarchical library that encompasses all potential chain compositions and carbon-carbon double bond locations. The expeditious querying module achieves speeds exceeding one hundred billion queries per second across all mass spectral libraries. The lipid categories intelligence model is developed using three relative retention time rules, reducing false positive annotations and predicting unannotated lipids with a 5.7% estimated false discovery rate, covering 8923 lipids cross various species. More importantly, LipidIN integrates a Wide-spectrum Modeling Yield network for regenerating lipid fragment fingerprints to further improve accuracy and coverage with a 20% estimated recall boosting. We further demonstrate the utility of LipidIN in multiple tasks for lipid annotation and biomarker discovery in clinical cohorts.
AB - Improving annotation accuracy, coverage, speed and depth of lipid profiles remains a significant challenge in traditional lipid annotation. We introduce LipidIN, an advanced framework designed for flash platform-independent annotation. LipidIN features a 168.5-million lipid fragmentation hierarchical library that encompasses all potential chain compositions and carbon-carbon double bond locations. The expeditious querying module achieves speeds exceeding one hundred billion queries per second across all mass spectral libraries. The lipid categories intelligence model is developed using three relative retention time rules, reducing false positive annotations and predicting unannotated lipids with a 5.7% estimated false discovery rate, covering 8923 lipids cross various species. More importantly, LipidIN integrates a Wide-spectrum Modeling Yield network for regenerating lipid fragment fingerprints to further improve accuracy and coverage with a 20% estimated recall boosting. We further demonstrate the utility of LipidIN in multiple tasks for lipid annotation and biomarker discovery in clinical cohorts.
UR - http://www.scopus.com/inward/record.url?scp=105005469789&partnerID=8YFLogxK
U2 - 10.1038/s41467-025-59683-5
DO - 10.1038/s41467-025-59683-5
M3 - Journal article
SN - 2041-1723
VL - 16
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 4566
ER -
