Classification of crystallization outcomes using deep convolutional neural networks

TY - JOUR

T1 - Classification of crystallization outcomes using deep convolutional neural networks

AU - Wilson, Julie Carol

AU - Bruno, A

AU - Charbonneau, P

AU - Newman, J

AU - Snell, E

AU - So, D

AU - Vanhoucke, V

AU - Watkins, C

AU - Williams, S

PY - 2018/6/20

Y1 - 2018/6/20

N2 - 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.

AB - 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.

KW - Algorithms

KW - Crystallization

KW - Crystallography, X-Ray

KW - Datasets as Topic

KW - Image Processing, Computer-Assisted

KW - Neural Networks (Computer)

UR - http://www.scopus.com/inward/record.url?scp=85048811290&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0198883

DO - 10.1371/journal.pone.0198883

M3 - Article

C2 - 29924841

SN - 1932-6203

VL - 13

JO - PLOS one

JF - PLOS one

IS - 6

M1 - e0198883

ER -