Automated classification of crystallisation experiments

Julie C. Wilson; Naomi Chayen

Automated classification of crystallisation experiments

Julie C. Wilson, Naomi Chayen (Editor)

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

With robotic systems capable of performing tens of thousands of experiments a day in high-throughput mode, visual inspection of the results is becoming increasingly impractical and the development of tools to automate analysis is essential. Many laboratories now have imaging systems to record the results of crystallisation trials at regular intervals and the development of software to automatically analyse the images is discussed. Whilst the detection of crystals is the fundamental aim, reliable classification of other outcomes provides information for subsequent trials and allows experiments to be ordered so that only the highest scoring images need be checked by eye. Pattern recognition procedures require characteristic features to be quantified for classification and various methods for the extraction of features from crystallisation images are discussed. The different classes and most commonly used classification methods are also described.

Original language	English
Title of host publication	Protein crystallisation strategies for Structural Genomics
Publisher	International University Line
Pages	195-217
Number of pages	20
ISBN (Print)	978-0-9720774-3-9
Publication status	Published - 2006

Automated analysis of crystallisation experiments
Wilson, J. C.
BBSRC
20/09/04 → 19/09/07
Project: Research project (funded) › Research

Cite this

@inbook{2662dbe9952b43d0a9803403e5339317,

title = "Automated classification of crystallisation experiments",

abstract = "With robotic systems capable of performing tens of thousands of experiments a day in high-throughput mode, visual inspection of the results is becoming increasingly impractical and the development of tools to automate analysis is essential. Many laboratories now have imaging systems to record the results of crystallisation trials at regular intervals and the development of software to automatically analyse the images is discussed. Whilst the detection of crystals is the fundamental aim, reliable classification of other outcomes provides information for subsequent trials and allows experiments to be ordered so that only the highest scoring images need be checked by eye. Pattern recognition procedures require characteristic features to be quantified for classification and various methods for the extraction of features from crystallisation images are discussed. The different classes and most commonly used classification methods are also described.",

author = "Wilson, {Julie C.} and Naomi Chayen",

year = "2006",

language = "English",

isbn = "978-0-9720774-3-9",

pages = "195--217",

booktitle = "Protein crystallisation strategies for Structural Genomics",

publisher = "International University Line",

}

TY - CHAP

T1 - Automated classification of crystallisation experiments

AU - Wilson, Julie C.

A2 - Chayen, Naomi

PY - 2006

Y1 - 2006

N2 - With robotic systems capable of performing tens of thousands of experiments a day in high-throughput mode, visual inspection of the results is becoming increasingly impractical and the development of tools to automate analysis is essential. Many laboratories now have imaging systems to record the results of crystallisation trials at regular intervals and the development of software to automatically analyse the images is discussed. Whilst the detection of crystals is the fundamental aim, reliable classification of other outcomes provides information for subsequent trials and allows experiments to be ordered so that only the highest scoring images need be checked by eye. Pattern recognition procedures require characteristic features to be quantified for classification and various methods for the extraction of features from crystallisation images are discussed. The different classes and most commonly used classification methods are also described.

AB - With robotic systems capable of performing tens of thousands of experiments a day in high-throughput mode, visual inspection of the results is becoming increasingly impractical and the development of tools to automate analysis is essential. Many laboratories now have imaging systems to record the results of crystallisation trials at regular intervals and the development of software to automatically analyse the images is discussed. Whilst the detection of crystals is the fundamental aim, reliable classification of other outcomes provides information for subsequent trials and allows experiments to be ordered so that only the highest scoring images need be checked by eye. Pattern recognition procedures require characteristic features to be quantified for classification and various methods for the extraction of features from crystallisation images are discussed. The different classes and most commonly used classification methods are also described.

M3 - Chapter

SN - 978-0-9720774-3-9

SP - 195

EP - 217

BT - Protein crystallisation strategies for Structural Genomics

PB - International University Line

ER -

Automated classification of crystallisation experiments

Abstract

Projects

Automated analysis of crystallisation experiments

Cite this