SPINE

An integrated tracking database and data mining approach for identifying feasible targets in high-throughput structural proteomics

Paul Bertone, Yuval Kluger, Ning Lan, Deyou Zheng, Dinesh Christendat, Adelinda Yee, Aled M. Edwards, Cheryl H. Arrowsmith, Gaetano T. Montelione, Mark Gerstein

Research output: Contribution to journalArticle

93 Citations (Scopus)

Abstract

High-throughput structural proteomiscs is expected to generate considerable amounts of data on the progress of structure determination for many proteins. For each protein this includes information about cloning, expression, purification, biophysical characterization and structure determination via NMR spectroscopy or X-ray crystallography. It will be essential to develop specifications and ontologies for standardizing this information to make it amenable to retrospective analysis. To this end we created the SPINE database and analysis system for the Northeast Structural Genomics Consortium. SPINE, which is available at bioinfo.mbb.yale.edu/nesg or nesg.org, is specifically designed to enable distributed scientific collaboration via the Internet. It was designed not just as an information repository but as an active vehicle to standardize proteomics data in a form that would enable systematic data mining. The system features an intuitive user interface for interactive retrieval and modification of expression construct data, query forms designed to track global project progress and external links to many other resources. Currently the database contains experimental data on 985 constructs, of which 740 are drawn from Methanobacterium thermoatotrophicum, 123 from Saccharomyces cerevisiae, 93 from Caenorhabditis elegans and the remainder from other organisms. We developed a comprehensive set of data mining features for each protein, including several related to experimental progress (e.g. expression level, solubility and crystallization) and 42 based on the underlying protein sequence (e.g. amino acid composition, secondary structure and occurrence of low complexity regions). We demonstrate in detail the application of a particular machine learning approach, decision trees, to the tasks of predicting a protein's solubility and propensity to crystallize based on sequence features. We are able to extract a number of key rules from our trees, in particular that soluble proteins tend to have significantly more acidic residues and fewer hydrophobic stretches than insoluble ones. One of the characteristics of proteomics data sets, currently and in the foreseeable future, is their intermediate size (∼500-5000 data points). This creates a number of issues in relation to error estimation. Initially we estimate the overall error in our trees based on standard cross-validation. However, this leaves out a significant fraction of the data in model construction and does not give error estimates on individual rules. Therefore, we present alternative methods to estimate the error in particular rules.

Original languageEnglish (US)
Pages (from-to)2884-2898
Number of pages15
JournalNucleic Acids Research
Volume29
Issue number13
StatePublished - Jul 1 2001
Externally publishedYes

Fingerprint

Data Mining
Proteomics
Databases
Proteins
Solubility
Imino Acids
Methanobacterium
Decision Trees
X Ray Crystallography
Caenorhabditis elegans
Genomics
Crystallization
Internet
Saccharomyces cerevisiae
Organism Cloning
Amino Acid Sequence
Magnetic Resonance Spectroscopy

ASJC Scopus subject areas

  • Genetics

Cite this

SPINE : An integrated tracking database and data mining approach for identifying feasible targets in high-throughput structural proteomics. / Bertone, Paul; Kluger, Yuval; Lan, Ning; Zheng, Deyou; Christendat, Dinesh; Yee, Adelinda; Edwards, Aled M.; Arrowsmith, Cheryl H.; Montelione, Gaetano T.; Gerstein, Mark.

In: Nucleic Acids Research, Vol. 29, No. 13, 01.07.2001, p. 2884-2898.

Research output: Contribution to journalArticle

Bertone, P, Kluger, Y, Lan, N, Zheng, D, Christendat, D, Yee, A, Edwards, AM, Arrowsmith, CH, Montelione, GT & Gerstein, M 2001, 'SPINE: An integrated tracking database and data mining approach for identifying feasible targets in high-throughput structural proteomics', Nucleic Acids Research, vol. 29, no. 13, pp. 2884-2898.
Bertone, Paul ; Kluger, Yuval ; Lan, Ning ; Zheng, Deyou ; Christendat, Dinesh ; Yee, Adelinda ; Edwards, Aled M. ; Arrowsmith, Cheryl H. ; Montelione, Gaetano T. ; Gerstein, Mark. / SPINE : An integrated tracking database and data mining approach for identifying feasible targets in high-throughput structural proteomics. In: Nucleic Acids Research. 2001 ; Vol. 29, No. 13. pp. 2884-2898.
@article{00d4baf36f2c44c4a11d9346121c279f,
title = "SPINE: An integrated tracking database and data mining approach for identifying feasible targets in high-throughput structural proteomics",
abstract = "High-throughput structural proteomiscs is expected to generate considerable amounts of data on the progress of structure determination for many proteins. For each protein this includes information about cloning, expression, purification, biophysical characterization and structure determination via NMR spectroscopy or X-ray crystallography. It will be essential to develop specifications and ontologies for standardizing this information to make it amenable to retrospective analysis. To this end we created the SPINE database and analysis system for the Northeast Structural Genomics Consortium. SPINE, which is available at bioinfo.mbb.yale.edu/nesg or nesg.org, is specifically designed to enable distributed scientific collaboration via the Internet. It was designed not just as an information repository but as an active vehicle to standardize proteomics data in a form that would enable systematic data mining. The system features an intuitive user interface for interactive retrieval and modification of expression construct data, query forms designed to track global project progress and external links to many other resources. Currently the database contains experimental data on 985 constructs, of which 740 are drawn from Methanobacterium thermoatotrophicum, 123 from Saccharomyces cerevisiae, 93 from Caenorhabditis elegans and the remainder from other organisms. We developed a comprehensive set of data mining features for each protein, including several related to experimental progress (e.g. expression level, solubility and crystallization) and 42 based on the underlying protein sequence (e.g. amino acid composition, secondary structure and occurrence of low complexity regions). We demonstrate in detail the application of a particular machine learning approach, decision trees, to the tasks of predicting a protein's solubility and propensity to crystallize based on sequence features. We are able to extract a number of key rules from our trees, in particular that soluble proteins tend to have significantly more acidic residues and fewer hydrophobic stretches than insoluble ones. One of the characteristics of proteomics data sets, currently and in the foreseeable future, is their intermediate size (∼500-5000 data points). This creates a number of issues in relation to error estimation. Initially we estimate the overall error in our trees based on standard cross-validation. However, this leaves out a significant fraction of the data in model construction and does not give error estimates on individual rules. Therefore, we present alternative methods to estimate the error in particular rules.",
author = "Paul Bertone and Yuval Kluger and Ning Lan and Deyou Zheng and Dinesh Christendat and Adelinda Yee and Edwards, {Aled M.} and Arrowsmith, {Cheryl H.} and Montelione, {Gaetano T.} and Mark Gerstein",
year = "2001",
month = "7",
day = "1",
language = "English (US)",
volume = "29",
pages = "2884--2898",
journal = "Nucleic Acids Research",
issn = "0305-1048",
publisher = "Oxford University Press",
number = "13",

}

TY - JOUR

T1 - SPINE

T2 - An integrated tracking database and data mining approach for identifying feasible targets in high-throughput structural proteomics

AU - Bertone, Paul

AU - Kluger, Yuval

AU - Lan, Ning

AU - Zheng, Deyou

AU - Christendat, Dinesh

AU - Yee, Adelinda

AU - Edwards, Aled M.

AU - Arrowsmith, Cheryl H.

AU - Montelione, Gaetano T.

AU - Gerstein, Mark

PY - 2001/7/1

Y1 - 2001/7/1

N2 - High-throughput structural proteomiscs is expected to generate considerable amounts of data on the progress of structure determination for many proteins. For each protein this includes information about cloning, expression, purification, biophysical characterization and structure determination via NMR spectroscopy or X-ray crystallography. It will be essential to develop specifications and ontologies for standardizing this information to make it amenable to retrospective analysis. To this end we created the SPINE database and analysis system for the Northeast Structural Genomics Consortium. SPINE, which is available at bioinfo.mbb.yale.edu/nesg or nesg.org, is specifically designed to enable distributed scientific collaboration via the Internet. It was designed not just as an information repository but as an active vehicle to standardize proteomics data in a form that would enable systematic data mining. The system features an intuitive user interface for interactive retrieval and modification of expression construct data, query forms designed to track global project progress and external links to many other resources. Currently the database contains experimental data on 985 constructs, of which 740 are drawn from Methanobacterium thermoatotrophicum, 123 from Saccharomyces cerevisiae, 93 from Caenorhabditis elegans and the remainder from other organisms. We developed a comprehensive set of data mining features for each protein, including several related to experimental progress (e.g. expression level, solubility and crystallization) and 42 based on the underlying protein sequence (e.g. amino acid composition, secondary structure and occurrence of low complexity regions). We demonstrate in detail the application of a particular machine learning approach, decision trees, to the tasks of predicting a protein's solubility and propensity to crystallize based on sequence features. We are able to extract a number of key rules from our trees, in particular that soluble proteins tend to have significantly more acidic residues and fewer hydrophobic stretches than insoluble ones. One of the characteristics of proteomics data sets, currently and in the foreseeable future, is their intermediate size (∼500-5000 data points). This creates a number of issues in relation to error estimation. Initially we estimate the overall error in our trees based on standard cross-validation. However, this leaves out a significant fraction of the data in model construction and does not give error estimates on individual rules. Therefore, we present alternative methods to estimate the error in particular rules.

AB - High-throughput structural proteomiscs is expected to generate considerable amounts of data on the progress of structure determination for many proteins. For each protein this includes information about cloning, expression, purification, biophysical characterization and structure determination via NMR spectroscopy or X-ray crystallography. It will be essential to develop specifications and ontologies for standardizing this information to make it amenable to retrospective analysis. To this end we created the SPINE database and analysis system for the Northeast Structural Genomics Consortium. SPINE, which is available at bioinfo.mbb.yale.edu/nesg or nesg.org, is specifically designed to enable distributed scientific collaboration via the Internet. It was designed not just as an information repository but as an active vehicle to standardize proteomics data in a form that would enable systematic data mining. The system features an intuitive user interface for interactive retrieval and modification of expression construct data, query forms designed to track global project progress and external links to many other resources. Currently the database contains experimental data on 985 constructs, of which 740 are drawn from Methanobacterium thermoatotrophicum, 123 from Saccharomyces cerevisiae, 93 from Caenorhabditis elegans and the remainder from other organisms. We developed a comprehensive set of data mining features for each protein, including several related to experimental progress (e.g. expression level, solubility and crystallization) and 42 based on the underlying protein sequence (e.g. amino acid composition, secondary structure and occurrence of low complexity regions). We demonstrate in detail the application of a particular machine learning approach, decision trees, to the tasks of predicting a protein's solubility and propensity to crystallize based on sequence features. We are able to extract a number of key rules from our trees, in particular that soluble proteins tend to have significantly more acidic residues and fewer hydrophobic stretches than insoluble ones. One of the characteristics of proteomics data sets, currently and in the foreseeable future, is their intermediate size (∼500-5000 data points). This creates a number of issues in relation to error estimation. Initially we estimate the overall error in our trees based on standard cross-validation. However, this leaves out a significant fraction of the data in model construction and does not give error estimates on individual rules. Therefore, we present alternative methods to estimate the error in particular rules.

UR - http://www.scopus.com/inward/record.url?scp=0035394771&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035394771&partnerID=8YFLogxK

M3 - Article

VL - 29

SP - 2884

EP - 2898

JO - Nucleic Acids Research

JF - Nucleic Acids Research

SN - 0305-1048

IS - 13

ER -