Search papers, labs, and topics across Lattice.
This paper introduces two agentic AI platforms: one for autonomously training ML models to predict human-human and virus-human protein-protein interactions (PPIs), and another for inducing explicit rules governing these interactions. The first platform uses five AI agents to handle data collection, verification, feature embedding, model design, and training, achieving 87.3% and 86.5% accuracy for human-human and human-virus PPIs, respectively. The second platform derives human-readable rules from protein embeddings and other features, aligning with SHAP-identified features from the first platform's ML models.
AI agents can autonomously orchestrate the entire machine learning pipeline for protein-protein interaction prediction, from data collection to rule induction, offering a new level of automation and interpretability.
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.
