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

• URL: http://arxiv.org/abs/2609.10193v1
• Date: Wed, 09 Sep 2026 14:02:18 GMT
• Title: Are You Learning Biological Signal or Shortcuts? Auditing and Mitigating Bias in Protein-Protein Interaction Datasets
• Abstract summary: Protein-protein interaction (PPI) databases do not faithfully reflect biological realities.<n>Machine learning models can exploit these as learning shortcuts if the negative dataset is not constructed with care.<n>Here, we systematically characterize both reported and, to our knowledge, previously unreported biases in PPI datasets that lead machine learning models to learn shortcuts instead of biological signal.
• Score: 0.9003755151302326
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Protein-protein interaction (PPI) databases do not faithfully reflect biological realities. Instead, they are influenced by study and technical biases that distort certain protein and interaction attributes. Machine learning models can exploit these as learning shortcuts if the negative dataset is not constructed with care. So far, the shortcuts introduced during PPI dataset construction have only been examined in isolation. Here, we systematically characterize both reported and, to our knowledge, previously unreported biases in PPI datasets that lead machine learning models to learn shortcuts instead of biological signal. We analyze HIPPIE, IntAct, and STRING, dedicated PPI databases, as well as two datasets derived from 3D-structural information in the Protein Data Bank (PDB). We show that random data splitting introduces strong topological shortcuts. When train-test protein overlap is removed, the resulting datasets still retain usable shortcuts stemming from self-interactions, taxonomic identity, and functional relatedness, whose prevalence interestingly depends on the data source. We further show that sampling negatives from a set of high-confidence non-interactors, an intuitively appealing choice, can amplify the shortcut stemming from functional relatedness. To detect and mitigate these biases, we provide an open Nextflow pipeline that combines similarity-aware, data-loss-minimizing dataset splitting with bias-minimizing negative sampling, both formulated as integer linear programs. Its key concept of quantifying biases to minimize them through optimization-based negative sampling can, in principle, be extended to any machine learning problem where the pool of negative candidates is much larger than the positives and is thus of interest also beyond PPI prediction.

Related papers

• Refnd: Preventing Data Leakage in Relational Datasets [3.5410731310203]
  Refnd is a splitting algorithm that leverages a proximity graph computed in log time using Navigable Navi Small World (HNSW)<n>We validate on an antimicrobial peptide dataset, showing that Refnd splits yield lower but more realistic evaluation than traditional splits.
  arXiv  Detail & Related papers  (2026-06-30T19:53:33Z)
• PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs [88.98041407783502]
  PRING is the first benchmark that evaluates protein-protein interaction prediction from a graph-level perspective.<n> PRING curates a high-quality, multi-species PPI network dataset comprising 21,484 proteins and 186,818 interactions.
  arXiv  Detail & Related papers  (2025-07-07T15:21:05Z)
• PEEL the Layers and Find Yourself: Revisiting Inference-time Data Leakage for Residual Neural Networks [64.90981115460937]
  This paper explores inference-time data leakage risks of deep neural networks (NNs)<n>We propose a novel backward feature inversion method, textbfPEEL, which can effectively recover block-wise input features from the intermediate output of residual NNs.<n>Our results show that PEEL outperforms the state-of-the-art recovery methods by an order of magnitude when evaluated by mean squared error (MSE)
  arXiv  Detail & Related papers  (2025-04-08T20:11:05Z)
• Extracting Protein-Protein Interactions (PPIs) from Biomedical Literature using Attention-based Relational Context Information [5.456047952635665]
  This work presents a unified, multi-source PPI corpora with vetted interaction definitions augmented by binary interaction type labels. A Transformer-based deep learning method exploits entities' relational context information for relation representation to improve relation classification performance. The model's performance is evaluated on four widely studied biomedical relation extraction datasets.
  arXiv  Detail & Related papers  (2024-03-08T01:43:21Z)
• Stubborn Lexical Bias in Data and Models [50.79738900885665]
  We use a new statistical method to examine whether spurious patterns in data appear in models trained on the data. We apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations. Surprisingly, though this method can successfully reduce lexical biases in the training data, we still find strong evidence of corresponding bias in the trained models.
  arXiv  Detail & Related papers  (2023-06-03T20:12:27Z)
• A Supervised Machine Learning Approach for Sequence Based Protein-protein Interaction (PPI) Prediction [4.916874464940376]
  Computational protein-protein interaction (PPI) prediction techniques can contribute greatly in reducing time, cost and false-positive interactions. We have described our submitted solution with the results of the SeqPIP competition.
  arXiv  Detail & Related papers  (2022-03-23T18:27:25Z)
• Combining Feature and Instance Attribution to Detect Artifacts [62.63504976810927]
  We propose methods to facilitate identification of training data artifacts. We show that this proposed training-feature attribution approach can be used to uncover artifacts in training data. We execute a small user study to evaluate whether these methods are useful to NLP researchers in practice.
  arXiv  Detail & Related papers  (2021-07-01T09:26:13Z)
• Examining and Combating Spurious Features under Distribution Shift [94.31956965507085]
  We define and analyze robust and spurious representations using the information-theoretic concept of minimal sufficient statistics. We prove that even when there is only bias of the input distribution, models can still pick up spurious features from their training data. Inspired by our analysis, we demonstrate that group DRO can fail when groups do not directly account for various spurious correlations.
  arXiv  Detail & Related papers  (2021-06-14T05:39:09Z)
• Bayesian neural network with pretrained protein embedding enhances prediction accuracy of drug-protein interaction [3.499870393443268]
  Deep learning approaches can predict drug-protein interactions without trial-and-error by humans. We propose two methods to construct a deep learning framework that exhibits superior performance with a small labeled dataset.
  arXiv  Detail & Related papers  (2020-12-15T10:24:34Z)
• Provably Efficient Causal Reinforcement Learning with Confounded Observational Data [135.64775986546505]
  We study how to incorporate the dataset (observational data) collected offline, which is often abundantly available in practice, to improve the sample efficiency in the online setting. We propose the deconfounded optimistic value iteration (DOVI) algorithm, which incorporates the confounded observational data in a provably efficient manner.
  arXiv  Detail & Related papers  (2020-06-22T14:49:33Z)
• Enzyme promiscuity prediction using hierarchy-informed multi-label classification [6.6828647808002595]
  We present and evaluate machine-learning models to predict which of 983 distinct enzymes are likely to interact with a query molecule. Some interactions are attributed to natural selection and involve the enzyme's natural substrates. The majority of the interactions however involve non-natural substrates, thus reflecting promiscuous enzymatic activities.
  arXiv  Detail & Related papers  (2020-02-18T01:39:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.