Classification of crystallization outcomes using deep convolutional neural networks

TL;DR

This paper demonstrates that deep convolutional neural networks can accurately classify crystallization outcomes from a large dataset, achieving over 94% accuracy, thereby advancing automated analysis in crystallography.

Contribution

The study introduces a deep learning approach trained on a large, diverse dataset to classify crystallization images with high accuracy, improving automation in crystallography.

Findings

Over 94% accuracy in image classification

Effective across various experimental setups

Enables high-throughput crystallization analysis

Abstract

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.