Global NASH congress
ABSTRACT
Using the power of the world’s largest proteomic platform coupled with machine learning , clinical samples and known biopsy results were used to build proteomic models capable of staging steatosis, inflammation, ballooning and fibrosis, and diagnosing at-risk NASH. These models exhibit competitive performance vs. existing standard methods. Use-cases in drug development include a participant rule-out prior to biopsy and precision demonstration of pharmacodynamic mechanistic impacts on individual liver components with multiple longitudinal measurements. Combination of the liquid liver biopsy with other proteomic tests on the same platform can expand the assessment of drug impact to include changes in cardiovascular risk, insulin resistance, kidney function and body composition. This will result in smaller, faster and more comprehensive clinical trials in the future.
Highlights:
- Proteomic models capable of staging and diagnosing conditions for “at-risk” NASH
- Assessment of pharmacodynamic mechanisms over time
- Simultaneous drug impact assessment of multiple biological metrics
Stephen A. Williams, MD, PhD
Chief Medical Officer, SomaLogic
Steve Williams, MD, Ph.D, practiced medicine for over a decade at Charing Cross Hospital before joining Pfizer, where he became the VP and Worldwide Head of Clinical Technology. Since 2009 he has been the Chief Medical Officer at SomaLogic, where his focus has been on developing clinical tests using proteomic signatures.
2021 Global NASH Congress | The “liquid liver biopsy”: Development of serum proteomic tests for liver biopsy components and diagnosos of at-rish NASH
A presentation by Stephen A. Williams, MD, PhD
More webinars
WebinarBoutique Webinar Aptamers with protein-like side chains as a versatile tool for high-content proteomics
Proteins, encoded in 20,000 genes in humans, do much of the work in biology. Measuring proteins, which change in response to various perturbations and represent targets for almost all drugs, offers insights about the health status of an organism. Since proteins operate in complex networks rather than in isolation, measuring multiple proteins simultaneously offers richer insights compared to single protein measurements.
WebinarUsing Proteomics To Advance Understanding of Alzheimer’s Disease
Limited understanding due to its complex pathophysiology and lack of definitive biomarkers currently constrains the diagnosis and treatment of Alzheimer’s disease (AD). But new research is uncovering dynamic brain changes during Alzheimer’s progression, offering potential therapeutic targets. This webinar explores how proteomics and systems biology can be integrated to elucidate AD pathology.
WebinarPredictive modeling and reliable biomarker discovery in clinical omics studies
High-content omic technologies coupled machine learning methods have transformed the biomarker discovery process. However, the translation of computational results into scalable clinical biomarkers remains challenging. A rate-limiting step is the rigorous selection of reliable biomarker candidates among a host of biological features. Drawing examples from real-world clinical omics studies, I will introduce Stabl, a general machine learning framework that identifies a sparse, reliable set of biomarkers by integrating noise injection and a data-driven signal-to-noise threshold into multivariable predictive modeling.