Home

Welcome to the MRS wiki

MRS (Metabolism-Related Score) is an R package designed for gene prioritization in positive-only scenarios using Spy-based positive-unlabeled (PU) learning. It integrates reliable negative identification, model comparison, ablation-based feature selection, and final model tuning to identify candidate genes from unlabeled gene sets.

Some jargons

• PU learning: Positive-unlabeled learning is a machine learning framework for binary classification using only positive and unlabeled data. MRS adopts a Spy-based mehtod, which injects a small fraction of positive samples into the unlabeled set ("spies") to estimate the class prior and identify reliable negatives.
• Ablation: A technique to evaluate feature importance by systematically removing features.

General introduction

MRS applies a PU-learning pipeline to estimate reliable negative samples from a set of known positive genes. The $i$ th classification model is evaluated using metrics including AUROC, AUPRC, F1, and MCC. Users can choose from multiple models (XGBoost, Random Forest, SVM, etc.) and optionally perform feature ablation. The final model is fine-tuned and visualized using ROC and PR curves. The pipeline is modular, reproducible, and tailored for gene prioritization tasks under limited positive labels.

Examples

• MRS toy example (simulated dataset)

Questions

Visit issues or contact @yang-qingxin regarding issues.