AI in Atomic Force Microscopy: Advancing Biological Nanoscale Imaging and Autonomous Discovery.

Area of Science:

• Biophysics
• Nanotechnology
• Artificial Intelligence

Background:

• Atomic force microscopy (AFM) offers label-free nanoscale imaging and nanomechanical profiling.
• Current AFM limitations include low throughput, operator dependence, and data interpretation variability.

Purpose of the Study:

• To review the integration of artificial intelligence (AI) with AFM for enhanced capabilities.
• To highlight AI-AFM applications in mechanobiology and biomedical engineering.

Main Methods:

• Surveying AI applications in AFM, including probe optimization, adaptive control, and multimodal data integration.
• Examining AI-driven denoising, structural recognition, and 3D reconstruction for biological samples.
• Analyzing studies on amyloid fibrils, extracellular vesicles, membranes, and living cells.

Main Results:

• AI transforms AFM into a scalable and adaptive platform, overcoming traditional limitations.
• AI enhances soft matter mapping, automated recognition of heterogeneous structures, and biomolecular assembly reconstruction.
• AI-AFM convergence improves reproducibility, throughput, and clinical utility in biological studies.

Conclusions:

• AI-driven AFM is a next-generation tool for biomedical discovery, enabling disease modeling, therapeutic screening, and precision diagnostics.
• The convergence of AI and AFM significantly advances research in mechanobiology and biomedical engineering.