Agentic AI platforms for autonomous training and rule induction of human-human and virus-human protein-protein interactions

TL;DR

This paper presents two agentic AI platforms: one for autonomous training of PPI predictive models achieving over 86% accuracy, and another for inducing human-readable rules that align with model features.

Contribution

The work introduces a novel dual-platform approach enabling autonomous model training and explicit rule induction for protein-protein interactions.

Findings

Predictive models achieved 87.3% and 86.5% accuracy for human-human and virus-human PPI.

The rule induction platform generates interpretable rules consistent with model explanations.

Demonstrates AI's capability to automate data handling, model training, and rule extraction in PPI analysis.

Abstract

We instruct an AI agent to construct two separate agentic AI platforms: one for autonomous training of predictive ML models for human-human and virus-human PPI, and the other for inducing explicit general rules governing human-human and virus-human PPI. The first agentic AI platform for autonomous training of predictive ML models for PPI is designed to consist of five AI agents that handle autonomous data collection, data verification, feature embedding, model design, and training and validation on three-way protein-disjoint cross-fold datasets. For human-human and human-virus PPIs, the final three-way protein-disjoint ensemble achieves an accuracy of 87.3% and 86.5%, respectively. For cross-checking and interpretability purposes, the second agentic AI platform is designed to replace ML predictions with human-readable rules derived from protein embeddings, physicochemical autocovariance descriptors, compartment annotations, pathway-domain overlap, and graph contexts. For human-human PPI, it is defined by a two-rule induction, whereas human-virus is induced by a more complex set of weighted rules. The rules induced by the second agentic platform align with the SHAP-identified features from the predictive ML models built by the first agentic platform. Taken together, our work demonstrates the agentic AI's ability to orchestrate from data planning to execution, and from rule induction to explanation in ML, opening the door to various applications.