MicrobeDiscover: A Knowledge Graph-Enabled AI Framework for Identifying Microbes for Inorganic Nanomaterial...

Area of Science:

• Microbiology
• Materials Science
• Artificial Intelligence

Background:

• Microbial synthesis of nanomaterials (NMs) offers a sustainable approach but is limited by the small number of known microbe-NM combinations.
• Current research relies on inefficient empirical methods for identifying suitable microbes.

Purpose of the Study:

• To develop an AI-based framework, MicrobeDiscover, for efficient identification of microorganisms capable of synthesizing NMs.
• To expand the scope of microbial NM synthesis beyond previously reported combinations.

Main Methods:

• Developed MicrobeDiscover, an AI framework integrating microorganisms, NMs, and their interactions using a knowledge graph.
• The framework bridges microbiology and materials science for robust screening and predictive modeling.
• Validated predictions by attempting synthesis of trimetallic NMs using AI-identified microbes.

Main Results:

• MicrobeDiscover achieved an 80.77% success rate in identifying suitable microorganisms from its top 20 predictions.
• Successfully synthesized novel trimetallic NMs using *Shewanella oneidensis* MR-1, as predicted by the framework.
• Demonstrated the framework's capability to predict microbes for synthesizing NMs not previously reported in biosynthetic contexts.

Conclusions:

• MicrobeDiscover significantly enhances the efficiency of screening microorganisms for NM synthesis.
• The AI framework facilitates the discovery of novel microbe-NM combinations and controllable NM synthesis.
• This approach promises to advance sustainable nanomaterial production and microbe-material hybrid systems.