Connor Beveridge1,#, Sanjay Iyer1,#, Caitlin E. Randolph1,#, Matthew Muhoberac1, Palak Manchanda1, AmyC. Clingenpeel2, Shane Tichy3, Gaurav Chopra1,41- Department of Chemistry, 560 Oval Drive, Purdue University, West Lafaye:e, IN, 47907, 2- ExxonMobil Technology and Engineering Company, Annandale, NJ, 08801; 3- Agilent Technologies Inc. Santa Clara, CA 95051; 4- Department of Computer Science (by courtesy), Purdue University, West Lafaye:e, IN, 47907#These authors contributed equally to this workCorresponding Author: gchopra@purdue.eduAbstractProfiling the lipidome of biological systems generates large amounts of data that makes manual annotationand interpretation time consuming and challenging. Moreover, the vast chemical and structural diversityof the lipidome compounded by structural isomers further complicates annotation. Although severalcommercial and open-source software for targeted lipid identification exists, it lacks automated methodgeneraon workflows and integraon with existing statistical and bioinformatics tools. We have developedthe Comprehensive Lipidomic Automated Workflow (CLAW) platform with integrated workflow forparsing, detailed statistical analysis, and lipid annotaons based on custom multiple reaction monitoring(MRM) precursor and product ion pair transitions. CLAW is developed with several modules, including theability to identify carbon-carbon double bond position(s) in unsaturated lipids when combined with ozoneelectrospray ionization (OzESI)-MRM methodology. 1,2 To demonstrate the utility of the automatedworkflow in CLAW, large-scale lipidomics data was collected with traditional and OzESI-MRM profiling onbiological and non-biological samples. Specifically, a total of 1497 transions organized into 10 MRM basedmass spectrometry methods were used to profile lipid droplets isolated from different brain regionsof 18–24 month-old Alzheimer’s disease mice and age-matched wild-type controls. Additionally,triacyclglycerols (TGs) profiles with carbon-carbon double bond specificity were generated from canola oilsamples using OzESI-MRM profiling. We also developed an integrated language user interface with largelanguage models using artificially intelligent (AI) agents that permits users to interact with the CLAWplatform using a chatbot terminal to perform statistical and bioinformatic analyses. We envision CLAWpipeline to be used in high-throughput lipid structural identification tasks aiding users to generateautomated lipidomics workflows ranging from data acquisition to AI agent-based bioinformatic analysis.