AutoSmarTrace: Automated chain tracing and flexibility analysis of biological filaments

• Published in: Biophysical journal 2021-07, Vol.120 (13), p.2599-2608
• Main Authors: Schneider, Mathew, Al-Shaer, Alaa, Forde, Nancy R.
• Format: Article
• Language: English
• Subjects: Computational Tool
• ISSN: 0006-3495; 1542-0086
• DOI: 10.1016/j.bpj.2021.05.011

Single-molecule imaging is widely used to determine statistical distributions of molecular properties. One such characteristic is the bending flexibility of biological filaments, which can be parameterized via the persistence length. Quantitative extraction of persistence length from images of individual filaments requires both the ability to trace the backbone of the chains in the images and sufficient chain statistics to accurately assess the persistence length. Chain tracing can be a tedious task, performed manually or using algorithms that require user input and/or supervision. Such interventions have the potential to introduce user-dependent bias into the chain selection and tracing. Here, we introduce a fully automated algorithm for chain tracing and determination of persistence lengths. Dubbed “AutoSmarTrace,” the algorithm is built off a neural network, trained via machine learning to identify filaments within images recorded using atomic force microscopy. We validate the performance of AutoSmarTrace on simulated images with widely varying levels of noise, demonstrating its ability to return persistence lengths in agreement with input simulation parameters. Persistence lengths returned from analysis of experimental images of collagen and DNA agree with previous values obtained from these images with different chain-tracing approaches. Although trained on atomic-force-microscopy-like images, the algorithm also shows promise to identify chains in other single-molecule imaging approaches, such as rotary-shadowing electron microscopy and fluorescence imaging.