Friend or Foe

2025-08-29

AI Summary

This study investigates the principles governing bacterial interactions—competition and cooperation—under environmental drivers. To this end, we constructed the largest standardized bacterial interaction dataset to date, encompassing 64 environmental conditions, over 10,000 bacterial pairs, and more than 26 million coexistence scenarios, generated via genome-scale metabolic modeling (GEM) simulations and experimentally validated. Methodologically, we pioneered the deep integration of GEMs with supervised, unsupervised, and generative machine learning to mine interaction patterns, infer pairwise relationships, and disentangle environmental effects. Our contributions are threefold: (1) a first-of-its-kind machine-learning-ready benchmark dataset for microbial interactions; (2) quantitative evidence that environmental variables—particularly pH and carbon source—systematically modulate interaction types and mechanistic insights into their regulatory roles; and (3) an interpretable predictive framework that advances microbial ecology from descriptive to predictive science.

Technology Category

• Machine Learning: Matrix & Tensor Methods
• Game Theory and Economic Paradigms: Cooperative Game Theory
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

A fundamental challenge in microbial ecology is determining whether bacteria compete or cooperate in different environmental conditions. With recent advances in genome-scale metabolic models, we are now capable of simulating interactions between thousands of pairs of bacteria in thousands of different environmental settings at a scale infeasible experimentally. These approaches can generate tremendous amounts of data that can be exploited by state-of-the-art machine learning algorithms to uncover the mechanisms driving interactions. Here, we present Friend or Foe, a compendium of 64 tabular environmental datasets, consisting of more than 26M shared environments for more than 10K pairs of bacteria sampled from two of the largest collections of metabolic models. The Friend or Foe datasets are curated for a wide range of machine learning tasks -- supervised, unsupervised, and generative -- to address specific questions underlying bacterial interactions. We benchmarked a selection of the most recent models for each of these tasks and our results indicate that machine learning can be successful in this application to microbial ecology. Going beyond, analyses of the Friend or Foe compendium can shed light on the predictability of bacterial interactions and highlight novel research directions into how bacteria infer and navigate their relationships.

Problem

• Determining bacterial competition or cooperation in diverse environments
• Simulating thousands of bacterial interactions across environmental conditions
• Uncovering mechanisms driving microbial interactions using machine learning

Innovation

• Genome-scale metabolic models simulate bacterial interactions
• Machine learning algorithms analyze large-scale interaction data
• Tabular datasets enable diverse machine learning tasks