LipidIN: a comprehensive repository for flash platform-independent annotation and reverse lipidomics

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 166.3-million lipid fragmentation hierarchical library that encompasses all potential chain compositions and carbon-carbon double bond locations. Developed an expeditious querying module speeds to over 100 billion times’ querying in 1 second for all mass spectral libraries. Furthermore, we leverage three relative retention time rules to develop lipid categories intelligence model for 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 demonstrated the utility of LipidIN in multiple tasks for lipid annotation and biomarker discovery in clinical cohorts.