Predictive models for protein crystallization

Bernhard Rupp, Junwen Wang

Research output: Contribution to journalReview article

59 Citations (Scopus)

Abstract

Crystallization of proteins is a nontrivial task, and despite the substantial efforts in robotic automation, crystallization screening is still largely based on trial-and-error sampling of a limited subset of suitable reagents and experimental parameters. Funding of high throughput crystallography pilot projects through the NIH Protein Structure Initiative provides the opportunity to collect crystallization data in a comprehensive and statistically valid form. Data mining and machine learning algorithms thus have the potential to deliver predictive models for protein crystallization. However, the underlying complex physical reality of crystallization, combined with a generally ill-defined and sparsely populated sampling space, and inconsistent scoring and annotation make the development of predictive models non-trivial. We discuss the conceptual problems, and review strengths and limitations of current approaches towards crystallization prediction, emphasizing the importance of comprehensive and valid sampling protocols. In view of limited overlap in techniques and sampling parameters between the publicly funded high throughput crystallography initiatives, exchange of information and standardization should be encouraged, aiming to effectively integrate data mining and machine learning efforts into a comprehensive predictive framework for protein crystallization. Similar experimental design and knowledge discovery strategies should be applied to valid analysis and prediction of protein expression, solubilization, and purification, as well as crystal handling and cryo-protection.

Original languageEnglish (US)
Pages (from-to)390-407
Number of pages18
JournalMethods
Volume34
Issue number3
DOIs
StatePublished - Nov 2004
Externally publishedYes

Fingerprint

Crystallization
Proteins
Sampling
Data mining
Crystallography
Data Mining
Learning systems
Throughput
Selection Bias
Automation
Robotics
Set theory
Design of experiments
Standardization
Learning algorithms
Purification
Screening
Research Design
Crystals

Keywords

  • High throughput crystallization
  • Machine learning
  • Predictive models
  • Statistical analysis
  • Structural genomics

ASJC Scopus subject areas

  • Molecular Biology

Cite this

Predictive models for protein crystallization. / Rupp, Bernhard; Wang, Junwen.

In: Methods, Vol. 34, No. 3, 11.2004, p. 390-407.

Research output: Contribution to journalReview article

Rupp, Bernhard ; Wang, Junwen. / Predictive models for protein crystallization. In: Methods. 2004 ; Vol. 34, No. 3. pp. 390-407.
@article{c9c57f54423849aea5c7184aa8c535b4,
title = "Predictive models for protein crystallization",
abstract = "Crystallization of proteins is a nontrivial task, and despite the substantial efforts in robotic automation, crystallization screening is still largely based on trial-and-error sampling of a limited subset of suitable reagents and experimental parameters. Funding of high throughput crystallography pilot projects through the NIH Protein Structure Initiative provides the opportunity to collect crystallization data in a comprehensive and statistically valid form. Data mining and machine learning algorithms thus have the potential to deliver predictive models for protein crystallization. However, the underlying complex physical reality of crystallization, combined with a generally ill-defined and sparsely populated sampling space, and inconsistent scoring and annotation make the development of predictive models non-trivial. We discuss the conceptual problems, and review strengths and limitations of current approaches towards crystallization prediction, emphasizing the importance of comprehensive and valid sampling protocols. In view of limited overlap in techniques and sampling parameters between the publicly funded high throughput crystallography initiatives, exchange of information and standardization should be encouraged, aiming to effectively integrate data mining and machine learning efforts into a comprehensive predictive framework for protein crystallization. Similar experimental design and knowledge discovery strategies should be applied to valid analysis and prediction of protein expression, solubilization, and purification, as well as crystal handling and cryo-protection.",
keywords = "High throughput crystallization, Machine learning, Predictive models, Statistical analysis, Structural genomics",
author = "Bernhard Rupp and Junwen Wang",
year = "2004",
month = "11",
doi = "10.1016/j.ymeth.2004.03.031",
language = "English (US)",
volume = "34",
pages = "390--407",
journal = "ImmunoMethods",
issn = "1046-2023",
publisher = "Academic Press Inc.",
number = "3",

}

TY - JOUR

T1 - Predictive models for protein crystallization

AU - Rupp, Bernhard

AU - Wang, Junwen

PY - 2004/11

Y1 - 2004/11

N2 - Crystallization of proteins is a nontrivial task, and despite the substantial efforts in robotic automation, crystallization screening is still largely based on trial-and-error sampling of a limited subset of suitable reagents and experimental parameters. Funding of high throughput crystallography pilot projects through the NIH Protein Structure Initiative provides the opportunity to collect crystallization data in a comprehensive and statistically valid form. Data mining and machine learning algorithms thus have the potential to deliver predictive models for protein crystallization. However, the underlying complex physical reality of crystallization, combined with a generally ill-defined and sparsely populated sampling space, and inconsistent scoring and annotation make the development of predictive models non-trivial. We discuss the conceptual problems, and review strengths and limitations of current approaches towards crystallization prediction, emphasizing the importance of comprehensive and valid sampling protocols. In view of limited overlap in techniques and sampling parameters between the publicly funded high throughput crystallography initiatives, exchange of information and standardization should be encouraged, aiming to effectively integrate data mining and machine learning efforts into a comprehensive predictive framework for protein crystallization. Similar experimental design and knowledge discovery strategies should be applied to valid analysis and prediction of protein expression, solubilization, and purification, as well as crystal handling and cryo-protection.

AB - Crystallization of proteins is a nontrivial task, and despite the substantial efforts in robotic automation, crystallization screening is still largely based on trial-and-error sampling of a limited subset of suitable reagents and experimental parameters. Funding of high throughput crystallography pilot projects through the NIH Protein Structure Initiative provides the opportunity to collect crystallization data in a comprehensive and statistically valid form. Data mining and machine learning algorithms thus have the potential to deliver predictive models for protein crystallization. However, the underlying complex physical reality of crystallization, combined with a generally ill-defined and sparsely populated sampling space, and inconsistent scoring and annotation make the development of predictive models non-trivial. We discuss the conceptual problems, and review strengths and limitations of current approaches towards crystallization prediction, emphasizing the importance of comprehensive and valid sampling protocols. In view of limited overlap in techniques and sampling parameters between the publicly funded high throughput crystallography initiatives, exchange of information and standardization should be encouraged, aiming to effectively integrate data mining and machine learning efforts into a comprehensive predictive framework for protein crystallization. Similar experimental design and knowledge discovery strategies should be applied to valid analysis and prediction of protein expression, solubilization, and purification, as well as crystal handling and cryo-protection.

KW - High throughput crystallization

KW - Machine learning

KW - Predictive models

KW - Statistical analysis

KW - Structural genomics

UR - http://www.scopus.com/inward/record.url?scp=4344704198&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4344704198&partnerID=8YFLogxK

U2 - 10.1016/j.ymeth.2004.03.031

DO - 10.1016/j.ymeth.2004.03.031

M3 - Review article

C2 - 15325656

AN - SCOPUS:4344704198

VL - 34

SP - 390

EP - 407

JO - ImmunoMethods

JF - ImmunoMethods

SN - 1046-2023

IS - 3

ER -