Revisiting Gene Ontology Knowledge Discovery with Hierarchical Feature Selection and Virtual Study Group of AI Agents

TL;DR

This paper introduces an agentic AI virtual study group that uses hierarchical feature selection to extract and validate ageing-related biological knowledge from Gene Ontology terms across multiple model organisms, enhancing scientific discovery.

Contribution

It presents a novel agentic AI framework for knowledge discovery that integrates hierarchical feature selection and validation through literature review, advancing AI-assisted biological research.

Findings

Most AI-generated claims are supported by existing literature.

The virtual study group's internal mechanisms significantly aid knowledge discovery.

Framework successfully identifies meaningful ageing-related biological insights.

Abstract

Large language models have achieved great success in multiple challenging tasks, and their capacity can be further boosted by the emerging agentic AI techniques. This new computing paradigm has already started revolutionising the traditional scientific discovery pipelines. In this work, we propose a novel agentic AI-based knowledge discovery-oriented virtual study group that aims to extract meaningful ageing-related biological knowledge considering highly ageing-related Gene Ontology terms that are selected by hierarchical feature selection methods. We investigate the performance of the proposed agentic AI framework by considering four different model organisms' ageing-related Gene Ontology terms and validate the biological findings by reviewing existing research articles. It is found that the majority of the AI agent-generated scientific claims can be supported by existing literatures and the proposed internal mechanisms of the virtual study group also play an important role in the designed agentic AI-based knowledge discovery framework.