CPSM

CPSM provides a comprehensive computational pipeline for predicting survival probability and risk groups in cancer patients.

Key Features:

• Data Preprocessing: The package includes steps for data preprocessing, training/test split, and normalization.
• Feature Selection: It enables feature selection using univariate survival analysis.
• Prognostic Index Scoring: CPSM computes a LASSO-based prognostic index (PI) score.
• Predictive Model Development: CPSM supports the development of predictive models using various feature sets.
• Visualization Tools: The package offers survival curves based on predicted probabilities, barplots for predicted mean and median survival times, KM plots overlaid with individual survival predictions, and nomograms for estimating 1-, 3-, 5-, and 10-year survival probabilities.

Scientific Applications:

• Cancer Survival Prediction: CPSM provides individualized survival predictions for cancer patients through machine learning models.
• Multi-omics Data Integration: The pipeline enables end-to-end analysis of high-throughput multi-omics data for survival modeling.
• Biomarker Discovery: CPSM aids in discovering clinically relevant biomarkers through feature selection and prognostic modeling.
• Clinical Decision Support: Visual tools facilitate interpretation of survival predictions to enhance clinical decision-making.

Methodology:

The pipeline is organized into four stages: (1) Data Preprocessing and Normalization, (2) Feature Selection using univariate survival analysis, (3) Survival Prediction Model Development with LASSO-based prognostic index computation, and (4) Visualization of predicted survival probabilities and risk groups.