proteomics-clock

The elastic net aging clocks from Goeminne et al. (2025) predict organ-specific biological age by applying machine learning to Olink proteomic data. This method uses NPX protein expression levels to estimate the biological age of 23 distinct organs for aging research.

The accepted input formats for Olink NPX protein expression tables are CSV, TSV, and compressed file formats. These files are parsed using pandas to extract the protein expression data required for computing the biological age predictions.

You calculate biological age for specific organs by running the analysis tool with your Olink data file and specifying the desired organs and generation. For example, you can input 'Heart,Brain,Kidney --generation gen1' to generate age predictions for those specific tissues.

Yes, you need pandas, numpy, matplotlib, seaborn, and requests installed to run proteomic aging clock predictions. These dependencies are required for data processing, numerical computations, generating visualizations, and handling any required API requests during analysis.

Estimating biological age from Olink data generates a structured report containing age predictions, a missing protein report, and visualizations. These outputs are created using matplotlib and seaborn to help researchers assess biological aging across different organs visually.

Yes, you can use this biological age prediction method for clinical disease progression research. The organ-specific aging clocks are applicable to both research and clinical settings studying aging and disease, providing molecular-level insights into how specific organs age.