Morphology Clustering Software for AFM Images, Based on Particle Isolation and Artificial Neural Networks

Abstract

Advanced microscopy techniques currently allow scientists to visualize biomolecules at high resolution. Among them, atomic force microscopy (AFM) shows the advantage of imaging molecules in their native state, without requiring any staining or coating of the sample. Biopolymers, including proteins and structured nucleic acids, are flexible molecules that can fold into alternative conformations for any given monomer sequence, as exemplified by the different three-dimensional structures adopted by RNA in solution. Therefore, the manual analysis of images visualized by AFM and other microscopy techniques becomes very laborious and time-consuming (and may also be inadvertently biased) when large populations of biomolecules are studied. Here we present a novel morphology clustering software, based on particle isolation and artificial neural networks, which allows the automatic image analysis and classification of biomolecules that can show alternative conformations. It has been tested with a set of AFM images of RNA molecules (a 574 nucleotides-long functinal region of the hepatitis C virus genome that contains its internal ribosome entry site element) structured in folding buffers containing 0, 2, 4, 6 or 10 mM Mg2+. The developed software shows a broad applicability in the microscopy-based analysis of biopolymers and other complex biomolecules.

Keywords

• Artificial neural networks
• atomic force microscopy (AFM)
• biomolecules
• growing cell structures (GCS)
• hepatitis C virus (HCV)
• Image analysis