Open AccessImage‐based crystal detection: a machine‐learning approach
Author(s) -
Liu Roy,
Freund Yoav,
Spraggon Glen
Publication year - 2008
Publication title -
acta crystallographica section d
Language(s) - English
Resource type - Journals
ISSN - 1399-0047
DOI - 10.1107/s090744490802982x
Subject(s) - pipeline (software) , computer science , crystallization , set (abstract data type) , rank (graph theory) , artificial intelligence , machine learning , image (mathematics) , workload , reduction (mathematics) , matching (statistics) , data mining , mathematics , statistics , engineering , programming language , geometry , combinatorics , chemical engineering , operating system
The ability of computers to learn from and annotate large databases of crystallization‐trial images provides not only the ability to reduce the workload of crystallization studies, but also an opportunity to annotate crystallization trials as part of a framework for improving screening methods. Here, a system is presented that scores sets of images based on the likelihood of containing crystalline material as perceived by a machine‐learning algorithm. The system can be incorporated into existing crystallization‐analysis pipelines, whereby specialists examine images as they normally would with the exception that the images appear in rank order according to a simple real‐valued score. Promising results are shown for 319 112 images associated with 150 structures solved by the Joint Center for Structural Genomics pipeline during the 2006–2007 year. Overall, the algorithm achieves a mean receiver operating characteristic score of 0.919 and a 78% reduction in human effort per set when considering an absolute score cutoff for screening images, while incurring a loss of five out of 150 structures.