The Machine Recognition of Crystallization Outcomes (MARCO) initiative has assembled roughly half a million annotated images of macromolecular crystallization experiments from various sources and setups. Here, state-of-the-art machine learning algorithms are trained and tested on different parts of this data set. We find that more than 94% of the test images can be correctly labeled, irrespective of their experimental origin. Because crystal recognition is key to high-density screening and the systematic analysis of crystallization experiments, this approach opens the door to both industrial and fundamental research applications.
@article{arxiv.1803.10342,
title = {Classification of crystallization outcomes using deep convolutional neural networks},
author = {Andrew E. Bruno and Patrick Charbonneau and Janet Newman and Edward H. Snell and David R. So and Vincent Vanhoucke and Christopher J. Watkins and Shawn Williams and Julie Wilson},
journal= {arXiv preprint arXiv:1803.10342},
year = {2018}
}
Comments
11 pages, 4 figures, minor text and figure updates