Are You Learning Biological Signal or Shortcuts? Auditing and Mitigating Bias in Protein-Protein Interaction Datasets

TL;DR - This study systematically audits shortcut learning in protein-protein interaction datasets and finds that common splitting and negative-sampling practices can expose non-biological signals. It introduces an open Nextflow pipeline that uses optimization-based methods to reduce these biases.

• Random train-test splits create strong shortcuts from interaction-network topology.
• Even without train-test protein overlap, models can exploit self-interactions, taxonomy, and functional relatedness, with bias prevalence varying by data source.
• Sampling negatives from high-confidence non-interactors can unintentionally amplify functional-relatedness shortcuts.
• The pipeline combines similarity-aware, data-preserving splits with bias-minimizing negative sampling, both formulated as integer linear programs.