Convolutional neural network approach for the automated identification of in cellulo crystals

被引：0

作者：

Kardoost, Amirhossein ^{[1
]}

Schonherr, Robert ^{[2
]}

Deiter, Carsten ^{[1
]}

Redecke, Lars ^{[2
,3
]}

Lorenzen, Kristina ^{[1
]}

Schulz, Joachim ^{[1
]}

de Diego, Inaki ^{[1
]}

机构：

[1] European XFEL GmbH, Sample Environm & Characterizat Grp, Holzkoppel 4, D-22869 Schenefeld, Schleswig Holst, Germany

[2] Univ Lubeck, Inst Biochem, Ratzeburger Allee 160, D-23562 Lubeck, Schleswig Holst, Germany

[3] Deutsch Elektronen Synchrotron DESY, Photon Sci, Notkestrasse 85, D-22607 Hamburg, Germany

来源：

JOURNAL OF APPLIED CRYSTALLOGRAPHY | 2024年 / 57卷 / Pt 2期

关键词：

Mask R-CNN; in cellulo crystallization; crystal detection; instance segmentation; PROTEIN CRYSTALLIZATION; SEGMENTATION;

D O I：

10.1107/S1600576724000682

中图分类号：

O6 [化学];

学科分类号：

0703 ;

摘要：

In cellulo crystallization is a rare event in nature. Recent advances that have made use of heterologous overexpression can promote the intracellular formation of protein crystals, but new tools are required to detect and characterize these targets in the complex cell environment. The present work makes use of Mask R-CNN, a convolutional neural network (CNN)-based instance segmentation method, for the identification of either single or multi-shaped crystals growing in living insect cells, using conventional bright field images. The algorithm can be rapidly adapted to recognize different targets, with the aim of extracting relevant information to support a semi-automated screening pipeline, in order to aid the development of the intracellular protein crystallization approach.

引用

页码：266 / 275

页数：10