CHiMP: deep-learning tools trained on protein crystallization micrographs to enable automation of experiments.

A group of three deep-learning tools, referred to collectively as CHiMP (Crystal Hits in My Plate), were created for analysis of micrographs of protein crystallization experiments at the Diamond Light Source (DLS) synchrotron, UK. The first tool, a classification network, assigns images into categories relating to experimental outcomes. The other two tools are networks that perform both object detection and instance segmentation, resulting in masks of individual crystals in the first case and masks of crystallization droplets in addition to crystals in the second case, allowing the positions and sizes of these entities to be recorded.

: an iOS app for ISPyB.

The macromolecular crystallography (MX) user experience at synchrotron radiation facilities continues to evolve, with the impact of developments in X-ray detectors, computer hardware and automation methods making it possible for complete data sets to be collected on timescales of tens of seconds. Data can be reduced in a couple of minutes and in favourable cases structures solved and refined shortly after. The information-rich database ISPyB, automatically populated by data acquisition software, data processing and structure solution pipelines at the Diamond Light Source beamlines, allows users to automatically track MX experiments in real time.

ISPyB: an information management system for synchrotron macromolecular crystallography.

Motivation: Individual research groups now analyze thousands of samples per year at synchrotron macromolecular crystallography (MX) resources. The efficient management of experimental data is thus essential if the best possible experiments are to be performed and the best possible data used in downstream processes in structure determination pipelines. Information System for Protein crystallography Beamlines (ISPyB), a Laboratory Information Management System (LIMS) with an underlying data model allowing for the integration of analyses down-stream of the data collection experiment was developed to facilitate such data management.