COPICAT: A software system for predicting interactions between proteins and chemical compounds

Yasubumi Sakakibara, Tsuyoshi Hachiya, Miho Uchida, Nobuyoshi Nagamine, Yohei Sugawara, Masahiro Yokota, Masaomi Nakamura, Kris Popendorf, Takashi Komori, Kengo Sato

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Summary: Since tens of millions of chemical compounds have been accumulated in public chemical databases, fast comprehensive computational methods to predict interactions between chemical compounds and proteins are needed for virtual screening of lead compounds. Previously, we proposed a novel method for predicting protein-chemical interactions using two-layer Support Vector Machine classifiers that require only readily available biochemical data, i.e. amino acid sequences of proteins and structure formulas of chemical compounds. In this article, the method has been implemented as the COPICAT web service, with an easy-to-use front-end interface. Users can simply submit a protein-chemical interaction prediction job using a pre-trained classifier, or can even train their own classification model by uploading training data. COPICAT's fast and accurate computational prediction has enhanced lead compound discovery against a database of tens of millions of chemical compounds, implying that the search space for drug discovery is extended by >1000 times compared with currently well-used high-throughput screening methodologies.

Original languageEnglish
Article numberbts031
Pages (from-to)745-746
Number of pages2
JournalBioinformatics
Volume28
Issue number5
DOIs
Publication statusPublished - 2012 Mar

Fingerprint

Chemical compounds
Software System
Software
Lead compounds
Proteins
Protein
Interaction
Screening
Classifiers
Chemical Databases
Drug Discovery
Computational methods
Web services
Support vector machines
Amino acids
Classifier
Amino Acid Sequence
High-throughput Screening
Virtual Screening
Throughput

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computational Theory and Mathematics
  • Computer Science Applications
  • Computational Mathematics
  • Statistics and Probability
  • Medicine(all)

Cite this

COPICAT : A software system for predicting interactions between proteins and chemical compounds. / Sakakibara, Yasubumi; Hachiya, Tsuyoshi; Uchida, Miho; Nagamine, Nobuyoshi; Sugawara, Yohei; Yokota, Masahiro; Nakamura, Masaomi; Popendorf, Kris; Komori, Takashi; Sato, Kengo.

In: Bioinformatics, Vol. 28, No. 5, bts031, 03.2012, p. 745-746.

Research output: Contribution to journalArticle

Sakakibara, Y, Hachiya, T, Uchida, M, Nagamine, N, Sugawara, Y, Yokota, M, Nakamura, M, Popendorf, K, Komori, T & Sato, K 2012, 'COPICAT: A software system for predicting interactions between proteins and chemical compounds', Bioinformatics, vol. 28, no. 5, bts031, pp. 745-746. https://doi.org/10.1093/bioinformatics/bts031
Sakakibara, Yasubumi ; Hachiya, Tsuyoshi ; Uchida, Miho ; Nagamine, Nobuyoshi ; Sugawara, Yohei ; Yokota, Masahiro ; Nakamura, Masaomi ; Popendorf, Kris ; Komori, Takashi ; Sato, Kengo. / COPICAT : A software system for predicting interactions between proteins and chemical compounds. In: Bioinformatics. 2012 ; Vol. 28, No. 5. pp. 745-746.
@article{977e4e863dc64ebabc26aa3103bce965,
title = "COPICAT: A software system for predicting interactions between proteins and chemical compounds",
abstract = "Summary: Since tens of millions of chemical compounds have been accumulated in public chemical databases, fast comprehensive computational methods to predict interactions between chemical compounds and proteins are needed for virtual screening of lead compounds. Previously, we proposed a novel method for predicting protein-chemical interactions using two-layer Support Vector Machine classifiers that require only readily available biochemical data, i.e. amino acid sequences of proteins and structure formulas of chemical compounds. In this article, the method has been implemented as the COPICAT web service, with an easy-to-use front-end interface. Users can simply submit a protein-chemical interaction prediction job using a pre-trained classifier, or can even train their own classification model by uploading training data. COPICAT's fast and accurate computational prediction has enhanced lead compound discovery against a database of tens of millions of chemical compounds, implying that the search space for drug discovery is extended by >1000 times compared with currently well-used high-throughput screening methodologies.",
author = "Yasubumi Sakakibara and Tsuyoshi Hachiya and Miho Uchida and Nobuyoshi Nagamine and Yohei Sugawara and Masahiro Yokota and Masaomi Nakamura and Kris Popendorf and Takashi Komori and Kengo Sato",
year = "2012",
month = "3",
doi = "10.1093/bioinformatics/bts031",
language = "English",
volume = "28",
pages = "745--746",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "5",

}

TY - JOUR

T1 - COPICAT

T2 - A software system for predicting interactions between proteins and chemical compounds

AU - Sakakibara, Yasubumi

AU - Hachiya, Tsuyoshi

AU - Uchida, Miho

AU - Nagamine, Nobuyoshi

AU - Sugawara, Yohei

AU - Yokota, Masahiro

AU - Nakamura, Masaomi

AU - Popendorf, Kris

AU - Komori, Takashi

AU - Sato, Kengo

PY - 2012/3

Y1 - 2012/3

N2 - Summary: Since tens of millions of chemical compounds have been accumulated in public chemical databases, fast comprehensive computational methods to predict interactions between chemical compounds and proteins are needed for virtual screening of lead compounds. Previously, we proposed a novel method for predicting protein-chemical interactions using two-layer Support Vector Machine classifiers that require only readily available biochemical data, i.e. amino acid sequences of proteins and structure formulas of chemical compounds. In this article, the method has been implemented as the COPICAT web service, with an easy-to-use front-end interface. Users can simply submit a protein-chemical interaction prediction job using a pre-trained classifier, or can even train their own classification model by uploading training data. COPICAT's fast and accurate computational prediction has enhanced lead compound discovery against a database of tens of millions of chemical compounds, implying that the search space for drug discovery is extended by >1000 times compared with currently well-used high-throughput screening methodologies.

AB - Summary: Since tens of millions of chemical compounds have been accumulated in public chemical databases, fast comprehensive computational methods to predict interactions between chemical compounds and proteins are needed for virtual screening of lead compounds. Previously, we proposed a novel method for predicting protein-chemical interactions using two-layer Support Vector Machine classifiers that require only readily available biochemical data, i.e. amino acid sequences of proteins and structure formulas of chemical compounds. In this article, the method has been implemented as the COPICAT web service, with an easy-to-use front-end interface. Users can simply submit a protein-chemical interaction prediction job using a pre-trained classifier, or can even train their own classification model by uploading training data. COPICAT's fast and accurate computational prediction has enhanced lead compound discovery against a database of tens of millions of chemical compounds, implying that the search space for drug discovery is extended by >1000 times compared with currently well-used high-throughput screening methodologies.

UR - http://www.scopus.com/inward/record.url?scp=84863277948&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863277948&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/bts031

DO - 10.1093/bioinformatics/bts031

M3 - Article

C2 - 22257668

AN - SCOPUS:84863277948

VL - 28

SP - 745

EP - 746

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 5

M1 - bts031

ER -