Artificial Intelligence-Assisted Automatic Raman-Activated Cell Sorting (AI-RACS) System for Mining Specific...

Area of Science:

• Microbiology
• Biotechnology
• Spectroscopy

Background:

• The microbiome plays a crucial role in life sciences, but analyzing microbial communities is challenging due to cultivation difficulties.
• Raman-activated cell sorting (RACS) links phenotype and genotype at the single-cell level, but manual methods are labor-intensive.
• Automating single-cell functional analysis is critical for advancing microbial community studies.

Purpose of the Study:

• To develop an automated system for microbial single-cell Raman-activated cell sorting (RACS).
• To address the limitations of manual RACS in analyzing microbial communities.
• To validate the system's efficacy in isolating functional microbial strains from environmental samples.

Main Methods:

• Development of an artificial intelligence-assisted Raman-activated cell sorting (AI-RACS) system.
• Integration of precise single-cell positioning, automated data collection, optical tweezers, and single-cell printing.
• Validation using acidic soil microbiota to isolate aluminum-tolerant microbes.

Main Results:

• The AI-RACS system successfully automated the RACS process for microbial single-cell analysis.
• Thirteen aluminum-tolerant microbial strains were isolated from red soil samples under near-in situ conditions.
• The system demonstrated efficient segregation of microbial cells from complex environmental samples.

Conclusions:

• AI-RACS provides a novel, automated tool for microbial research and applications.
• The system enables efficient functional attribute investigation of microbes from intricate environmental samples.
• This technology overcomes bottlenecks in microbial community functional analysis.