- A description of the data analysis process and the statistical methods used: e.g. principal component analysis, statistical tests, correlation analysis and enrichment analysis including pathway analysis. We also show-case how we work with predictive modelling (or machine learning).
- How algorithms and a full set of methods are tailored to quantitative lipid data
- Applications of big datasets in lipidomics such as for biomarker identification in clinical research and clinical diagnostics, in drug discovery for mode-of-action studies as well as for food and cosmetics applications.
- Lipid biomarker identification and validation (pharmacodynamic, pharmacokinetic, CDx) for biotech and pharma industry as well as (pre-)clinical research
- Lipid biomarker identification and validation for clinical diagnostics (prognostic, diagnostic, patient stratification)
- Identification of novel, lipid-related therapeutic targets and mode-of-action studies in drug discovery phases
- Intervention studies for development of functional food/nutraceuticals
- Cosmetic claim support for (active) ingredients for cosmetic industry
In this white paper a cohort of healthy subjects is compared with a cohort of diseased persons to identify lipid signatures that discriminate health from disease. Such signatures could potentially be useful for disease stratification or for diagnosis by means of predictive modelling (machine learning). In this white paper, we will guide you through the data analysis process aiming at the identification of lipid biomarkers and the evaluations of their performance.
Learn more about Big Data Lipidomics: Our White Paper guides you through the data analysis process aiming at the identification of lipid biomarkers and the evaluations of their performance. It includes:
Discover the free White Paper about Big Data Lipidomics. Just fill out the form!
Big Data Lipidomics – just fill out the form
Applications for big data lipidomics
Prof. Kai Simons, CEO of Lipotype