Classification of Protein Crystallization X-Ray Images Using Major Convolutional Neural Network Architectures

TL;DR

This study applies advanced convolutional neural networks to classify protein crystallization X-ray images, significantly improving accuracy over previous methods and aiding automated crystal detection.

Contribution

The paper demonstrates that modern CNN architectures like ResNet, Inception, VGG, and AlexNet outperform simpler models in classifying protein crystallization images, achieving over 81% accuracy.

Findings

ResNet achieved 81.43% accuracy.

Top-3 classification reduces missed crystal rate to below 0.1%.

Dataset of over 486,000 images augmented to over a million.

Abstract

The generation of protein crystals is necessary for the study of protein molecular function and structure. This is done empirically by processing large numbers of crystallization trials and inspecting them regularly in search of those with forming crystals. To avoid missing the hard-gained crystals, this visual inspection of the trial X-ray images is done manually as opposed to the existing less accurate machine learning methods. To achieve higher accuracy for automation, we applied some of the most successful convolutional neural networks (ResNet, Inception, VGG, and AlexNet) for 10-way classification of the X-ray images. We showed that substantial classification accuracy is gained by using such networks compared to two simpler ones previously proposed for this purpose. The best accuracy was obtained from ResNet (81.43%), which corresponds to a missed crystal rate of 5.9%. This rate could be lowered to less than 0.1% by using a top-3 classification strategy. Our dataset consisted of 486,000 internally annotated images, which was augmented to more than a million to address class imbalance. We also provide a label-wise analysis of the results, identifying the main sources of error and inaccuracy.