skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Genome scale enzyme–metabolite and drug–target interaction predictions using the signature molecular descriptor

Abstract

Motivation: Identifying protein enzymatic or pharmacological activities are important areas of research in biology and chemistry. Biological and chemical databases are increasingly being populated with linkages between protein sequences and chemical structures. Additionally, there is now sufficient information to apply machine-learning techniques to predict interactions between chemicals and proteins at a genome scale. Current machine-learning techniques use as input either protein sequences and structures or chemical information. We propose here a method to infer protein–chemical interactions using heterogeneous input consisting of both protein sequence and chemical information. Results: Our method relies on expressing proteins and chemicals with a common cheminformatics representation. We demonstrate our approach by predicting whether proteins can catalyze reactions not present in training sets. We also predict whether a given drug can bind a target, in the absence of prior binding information for that drug and target. Lastly, such predictions cannot be made with current machine-learning techniques requiring binding information for individual reactions or individual targets.

Authors:
 [1];  [1];  [2];  [3];  [3]
  1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States). Computational Biosciences Dept.
  2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States). Computer Science & Informatics Department
  3. Sandia National Lab. (SNL-CA), Livermore, CA (United States). Biosystems Research
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1426948
Report Number(s):
SAND-2007-1648J
Journal ID: ISSN 1367-4803; 526857
Grant/Contract Number:  
AC04-94AL85000
Resource Type:
Accepted Manuscript
Journal Name:
Bioinformatics
Additional Journal Information:
Journal Volume: 24; Journal Issue: 2; Journal ID: ISSN 1367-4803
Publisher:
Oxford University Press
Country of Publication:
United States
Language:
English
Subject:
59 BASIC BIOLOGICAL SCIENCES; 37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY

Citation Formats

Faulon, Jean-Loup, Misra, Milind, Martin, Shawn, Sale, Ken, and Sapra, Rajat. Genome scale enzyme–metabolite and drug–target interaction predictions using the signature molecular descriptor. United States: N. p., 2007. Web. doi:10.1093/bioinformatics/btm580.
Faulon, Jean-Loup, Misra, Milind, Martin, Shawn, Sale, Ken, & Sapra, Rajat. Genome scale enzyme–metabolite and drug–target interaction predictions using the signature molecular descriptor. United States. doi:10.1093/bioinformatics/btm580.
Faulon, Jean-Loup, Misra, Milind, Martin, Shawn, Sale, Ken, and Sapra, Rajat. Fri . "Genome scale enzyme–metabolite and drug–target interaction predictions using the signature molecular descriptor". United States. doi:10.1093/bioinformatics/btm580. https://www.osti.gov/servlets/purl/1426948.
@article{osti_1426948,
title = {Genome scale enzyme–metabolite and drug–target interaction predictions using the signature molecular descriptor},
author = {Faulon, Jean-Loup and Misra, Milind and Martin, Shawn and Sale, Ken and Sapra, Rajat},
abstractNote = {Motivation: Identifying protein enzymatic or pharmacological activities are important areas of research in biology and chemistry. Biological and chemical databases are increasingly being populated with linkages between protein sequences and chemical structures. Additionally, there is now sufficient information to apply machine-learning techniques to predict interactions between chemicals and proteins at a genome scale. Current machine-learning techniques use as input either protein sequences and structures or chemical information. We propose here a method to infer protein–chemical interactions using heterogeneous input consisting of both protein sequence and chemical information. Results: Our method relies on expressing proteins and chemicals with a common cheminformatics representation. We demonstrate our approach by predicting whether proteins can catalyze reactions not present in training sets. We also predict whether a given drug can bind a target, in the absence of prior binding information for that drug and target. Lastly, such predictions cannot be made with current machine-learning techniques requiring binding information for individual reactions or individual targets.},
doi = {10.1093/bioinformatics/btm580},
journal = {Bioinformatics},
number = 2,
volume = 24,
place = {United States},
year = {2007},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 89 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Stochastic Generator of Chemical Structure. 1. Application to the Structure Elucidation of Large Molecules
journal, September 1994

  • Faulon, Jean-Loup
  • Journal of Chemical Information and Modeling, Vol. 34, Issue 5
  • DOI: 10.1021/ci00021a031

Mathematical Correction for Fingerprint Similarity Measures to Improve Chemical Retrieval
journal, March 2007

  • Swamidass, S. Joshua; Baldi, Pierre
  • Journal of Chemical Information and Modeling, Vol. 47, Issue 3
  • DOI: 10.1021/ci600526a

The European Bioinformatics Institute's data resources: towards systems biology
journal, December 2004

  • Brooksbank, C.
  • Nucleic Acids Research, Vol. 33, Issue Database issue
  • DOI: 10.1093/nar/gki026

The signature molecular descriptor
journal, March 2004

  • Churchwell, Carla J.; Rintoul, Mark D.; Martin, Shawn
  • Journal of Molecular Graphics and Modelling, Vol. 22, Issue 4
  • DOI: 10.1016/j.jmgm.2003.10.002

SDPpred: a tool for prediction of amino acid residues that determine differences in functional specificity of homologous proteins
journal, July 2004

  • Kalinina, O. V.; Novichkov, P. S.; Mironov, A. A.
  • Nucleic Acids Research, Vol. 32, Issue Web Server
  • DOI: 10.1093/nar/gkh391

MOLECULAR BIOLOGY: NIH Molecular Libraries Initiative
journal, November 2004


Computational Assignment of the EC Numbers for Genomic-Scale Analysis of Enzymatic Reactions
journal, December 2004

  • Kotera, Masaaki; Okuno, Yasushi; Hattori, Masahiro
  • Journal of the American Chemical Society, Vol. 126, Issue 50
  • DOI: 10.1021/ja0466457

Similarity Searching of Chemical Databases Using Atom Environment Descriptors (MOLPRINT 2D):  Evaluation of Performance
journal, September 2004

  • Bender, Andreas; Mussa, Hamse Y.; Glen, Robert C.
  • Journal of Chemical Information and Computer Sciences, Vol. 44, Issue 5
  • DOI: 10.1021/ci0498719

The Pharmacophore Kernel for Virtual Screening with Support Vector Machines
journal, August 2006

  • Mahé, Pierre; Ralaivola, Liva; Stoven, Véronique
  • Journal of Chemical Information and Modeling, Vol. 46, Issue 5
  • DOI: 10.1021/ci060138m

Predicting protein-protein interactions using signature products
journal, August 2004


Kernels for small molecules and the prediction of mutagenicity, toxicity and anti-cancer activity
journal, June 2005


The Predictive Toxicology Challenge 2000-2001
journal, January 2001


Kernel methods for predicting protein-protein interactions
journal, June 2005


The Signature Molecular Descriptor. 2. Enumerating Molecules from Their Extended Valence Sequences
journal, May 2003

  • Faulon, Jean-Loup; Churchwell, Carla J.; Visco, Donald P.
  • Journal of Chemical Information and Computer Sciences, Vol. 43, Issue 3
  • DOI: 10.1021/ci020346o

Amino acid substitution matrices from protein blocks.
journal, November 1992

  • Henikoff, S.; Henikoff, J. G.
  • Proceedings of the National Academy of Sciences, Vol. 89, Issue 22, p. 10915-10919
  • DOI: 10.1073/pnas.89.22.10915

Gapped BLAST and PSI-BLAST: a new generation of protein database search programs
journal, September 1997

  • Altschul, Stephen F.; Madden, Thomas L.; Schäffer, Alejandro A.
  • Nucleic Acids Research, Vol. 25, Issue 17, p. 3389-3402
  • DOI: 10.1093/nar/25.17.3389

Ab initio quantum mechanical study of the binding energies of human estrogen receptor ? with its ligands: An application of fragment molecular orbital method
journal, January 2004

  • Fukuzawa, Kaori; Kitaura, Kazuo; Uebayasi, Masami
  • Journal of Computational Chemistry, Vol. 26, Issue 1
  • DOI: 10.1002/jcc.20130

New developments in the InterPro database
journal, January 2007

  • Mulder, N. J.; Apweiler, R.; Attwood, T. K.
  • Nucleic Acids Research, Vol. 35, Issue Database
  • DOI: 10.1093/nar/gkl841

From genomics to chemical genomics: new developments in KEGG
journal, January 2006


DrugBank: a comprehensive resource for in silico drug discovery and exploration
journal, January 2006


The Difficult Road from Sequence to Function
journal, May 2006


A Critical Assessment of Docking Programs and Scoring Functions
journal, October 2006

  • Warren, Gregory L.; Andrews, C. Webster; Capelli, Anna-Maria
  • Journal of Medicinal Chemistry, Vol. 49, Issue 20
  • DOI: 10.1021/jm050362n

Predicting ligand-binding function in families of bacterial receptors
journal, March 2000

  • Johnson, J. M.; Church, G. M.
  • Proceedings of the National Academy of Sciences, Vol. 97, Issue 8
  • DOI: 10.1073/pnas.050580897

Predicting protein-protein interactions from primary structure
journal, May 2001


The Signature Molecular Descriptor. 4. Canonizing Molecules Using Extended Valence Sequences
journal, March 2004

  • Faulon, Jean-Loup; Collins, Michael J.; Carr, Robert D.
  • Journal of Chemical Information and Computer Sciences, Vol. 44, Issue 2
  • DOI: 10.1021/ci0341823

What is a support vector machine?
journal, December 2006


Solving the protein sequence metric problem
journal, April 2005

  • Atchley, W. R.; Zhao, J.; Fernandes, A. D.
  • Proceedings of the National Academy of Sciences, Vol. 102, Issue 18
  • DOI: 10.1073/pnas.0408677102

Protein function prediction via graph kernels
journal, June 2005


    Works referencing / citing this record:

    The continuous molecular fields approach to building 3D-QSAR models
    journal, May 2013

    • Baskin, Igor I.; Zhokhova, Nelly I.
    • Journal of Computer-Aided Molecular Design, Vol. 27, Issue 5
    • DOI: 10.1007/s10822-013-9656-4

    The continuous molecular fields approach to building 3D-QSAR models
    journal, May 2013

    • Baskin, Igor I.; Zhokhova, Nelly I.
    • Journal of Computer-Aided Molecular Design, Vol. 27, Issue 5
    • DOI: 10.1007/s10822-013-9656-4

    SensiPath: computer-aided design of sensing-enabling metabolic pathways
    journal, April 2016

    • Delépine, Baudoin; Libis, Vincent; Carbonell, Pablo
    • Nucleic Acids Research, Vol. 44, Issue W1
    • DOI: 10.1093/nar/gkw305

    Engineering antibiotic production and overcoming bacterial resistance
    journal, June 2011

    • Planson, Anne-Gaëlle; Carbonell, Pablo; Grigoras, Ioana
    • Biotechnology Journal, Vol. 6, Issue 7
    • DOI: 10.1002/biot.201100085