Efficient development of prognostic tests for detecting cancer risk using proteomic technology
Background
Prognostic models for assessing future health outcomes can be developed using time-to-event (also known as “survival”) data. This methodology is ubiquitous in statistical literature and in the analysis of cancer outcomes, but its use in high-dimensional analyses tends to be limited as the methods are difficult to implement in a machine learning environment. Additionally, development of certified prognostic clinical tests using proteomic biomarkers for detecting future cancer risk can be time-consuming, prone to overfitting issues, and difficult to navigate. We demonstrate the utility of combining SomaScan® proteomic data with pipeline machine learning tools and survival analysis methodology to identify powerful and robust LDT-certifiable prognostic tests for assessing future risk of cancer.
Methods
Data pipeline and analysis tools were developed using R. In addition to standard machine learning techniques, statistical methods include elastic net AFT models, subsampling survival techniques, and metrics for assessing predictive survival models. The pipeline takes the analyst from data processing and QC through identification of optimal models for prediction of clinical endpoints, and then through validation on a hold-out test set.
Results
Analysis time for identifying the optimal proteomic model to validation was reduced by at least 80%, with decreased prediction variability by up to 90%. This tool has led to 7 LDT certified SomaLogic prognostic tests (using survival methodology) in the last 3 years.
Conclusions
Not only are powerful, proteomics-driven, diagnostic tests realizable, but they can be LDT certified in an efficient, reproducible manner and made to be robust to real-life variability. Efficient analysis tools allow us to leverage proteomic technology in new ways, leading to tests that can be used for precision medicine applications.
Authors
Yolanda Hagar
Leigh Alexander
Jessica Chadwick
Gargi Datta
Joe Gogain
Rachel Ostroff
Clare Paterson
Laura Sampson
Caleb Scheidel
Sama Shrestha
Chi Zhang
Michael Hinterberg
SomaLogic Operating Co., Inc., Boulder, CO USA
More posters
PosterComparison of Proteomic CV Risk to Established ASCVD 10-Year Risk Decision Points
The ASCVD pooled cohort equation (PCE) is well-established for CV risk assessment. Decision points for determining treatment plans are low, intermediate and high risk over 10 years, however this approach over and underestimates risk in certain subgroups. The validated CV Risk SomaSignal® Test (SST) provides 4-year risk probability of MACE allowing for timely assessment of risk, but the shorter timescale makes comparison to 10-year PCE risk less intuitive.
PosterStatin signature: using proteomics to detect pharmacological fingerprints
Using a previously described metacohort (n=5,575) of patients with increased CV risk, we hypothesized that PCE would stratify patients differently than the CV Risk SST, and that CV Risk score scaled to 10 years would yield an improved net reclassification index (NRI).
PosterUsing a proteomics-based cardiovascular risk test to identify systemic changes in a clinical trial of nonalcoholic fatty liver disease
Improvement in hepaKc inflammaKon, NAFLD acKvity score and fibrosis were associated with improved proteomic CV risk scores regardless of treatment provided.