View in EDS

One- to Four-Dimensional Kernels for Virtual Screening and the Prediction of Physical, Chemical, and Biological Properties.

Saved in:
Bibliographic Details
Title: One- to Four-Dimensional Kernels for Virtual Screening and the Prediction of Physical, Chemical, and Biological Properties.
Authors: Chloé-Agathe Azencott1, Alexandre Ksikes1, S. Joshua Swamidass1, Jonathan H. Chen1, Liva Ralaivola1, Pierre Baldi1
Source: Journal of Chemical Information & Modeling. May2007, Vol. 47 Issue 3, p965-974. 10p.
Subjects: Logical prediction, High throughput screening (Drug development), Cheminformatics, Kernel functions, Machine learning, Molecular structure, Regression analysis, Properties of matter
Abstract: Many chemoinformatics applications, including high-throughput virtual screening, benefit from being able to rapidly predict the physical, chemical, and biological properties of small molecules to screen large repositories and identify suitable candidates. When training sets are available, machine learning methods provide an effective alternative to ab initio methods for these predictions. Here, we leverage rich molecular representations including 1D SMILES strings, 2D graphs of bonds, and 3D coordinates to derive efficient machine learning kernels to address regression problems. We further expand the library of available spectral kernels for small molecules developed for classification problems to include 2.5D surface and 3D kernels using Delaunay tetrahedrization and other techniques from computational geometry, 3D pharmacophore kernels, and 3.5D or 4D kernels capable of taking into account multiple molecular configurations, such as conformers. The kernels are comprehensively tested using cross-validation and redundancy-reduction methods on regression problems using several available data sets to predict boiling points, melting points, aqueous solubility, octanol/water partition coefficients, and biological activity with state-of-the art results. When sufficient training data are available, 2D spectral kernels in general tend to yield the best and most robust results, better than state-of-the art. On data sets containing thousands of molecules, the kernels achieve a squared correlation coefficient of 0.91 for aqueous solubility prediction and 0.94 for octanol/water partition coefficient prediction. Averaging over conformations improves the performance of kernels based on the three-dimensional structure of molecules, especially on challenging data sets. Kernel predictors for aqueous solubility (kSOL), LogP (kLOGP), and melting point (kMELT) are available over the Web through:  http://cdb.ics.uci.edu. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Chemical Information & Modeling is the property of American Chemical Society and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 35371851
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: One- to Four-Dimensional Kernels for Virtual Screening and the Prediction of Physical, Chemical, and Biological Properties.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Chloé-Agathe+Azencott%22">Chloé-Agathe Azencott</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Alexandre+Ksikes%22">Alexandre Ksikes</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22S%2E+Joshua+Swamidass%22">S. Joshua Swamidass</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Jonathan+H%2E+Chen%22">Jonathan H. Chen</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Liva+Ralaivola%22">Liva Ralaivola</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Pierre+Baldi%22">Pierre Baldi</searchLink><relatesTo>1</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Chemical+Information+%26+Modeling%22">Journal of Chemical Information & Modeling</searchLink>. May2007, Vol. 47 Issue 3, p965-974. 10p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Logical+prediction%22">Logical prediction</searchLink><br /><searchLink fieldCode="DE" term="%22High+throughput+screening+%28Drug+development%29%22">High throughput screening (Drug development)</searchLink><br /><searchLink fieldCode="DE" term="%22Cheminformatics%22">Cheminformatics</searchLink><br /><searchLink fieldCode="DE" term="%22Kernel+functions%22">Kernel functions</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Molecular+structure%22">Molecular structure</searchLink><br /><searchLink fieldCode="DE" term="%22Regression+analysis%22">Regression analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Properties+of+matter%22">Properties of matter</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Many chemoinformatics applications, including high-throughput virtual screening, benefit from being able to rapidly predict the physical, chemical, and biological properties of small molecules to screen large repositories and identify suitable candidates. When training sets are available, machine learning methods provide an effective alternative to ab initio methods for these predictions. Here, we leverage rich molecular representations including 1D SMILES strings, 2D graphs of bonds, and 3D coordinates to derive efficient machine learning kernels to address regression problems. We further expand the library of available spectral kernels for small molecules developed for classification problems to include 2.5D surface and 3D kernels using Delaunay tetrahedrization and other techniques from computational geometry, 3D pharmacophore kernels, and 3.5D or 4D kernels capable of taking into account multiple molecular configurations, such as conformers. The kernels are comprehensively tested using cross-validation and redundancy-reduction methods on regression problems using several available data sets to predict boiling points, melting points, aqueous solubility, octanol/water partition coefficients, and biological activity with state-of-the art results. When sufficient training data are available, 2D spectral kernels in general tend to yield the best and most robust results, better than state-of-the art. On data sets containing thousands of molecules, the kernels achieve a squared correlation coefficient of 0.91 for aqueous solubility prediction and 0.94 for octanol/water partition coefficient prediction. Averaging over conformations improves the performance of kernels based on the three-dimensional structure of molecules, especially on challenging data sets. Kernel predictors for aqueous solubility (kSOL), LogP (kLOGP), and melting point (kMELT) are available over the Web through:  http://cdb.ics.uci.edu. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Chemical Information & Modeling is the property of American Chemical Society and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=35371851
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1021/ci600397p
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 965
    Subjects:
      – SubjectFull: Logical prediction
        Type: general
      – SubjectFull: High throughput screening (Drug development)
        Type: general
      – SubjectFull: Cheminformatics
        Type: general
      – SubjectFull: Kernel functions
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Molecular structure
        Type: general
      – SubjectFull: Regression analysis
        Type: general
      – SubjectFull: Properties of matter
        Type: general
    Titles:
      – TitleFull: One- to Four-Dimensional Kernels for Virtual Screening and the Prediction of Physical, Chemical, and Biological Properties.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Chloé-Agathe Azencott
      – PersonEntity:
          Name:
            NameFull: Alexandre Ksikes
      – PersonEntity:
          Name:
            NameFull: S. Joshua Swamidass
      – PersonEntity:
          Name:
            NameFull: Jonathan H. Chen
      – PersonEntity:
          Name:
            NameFull: Liva Ralaivola
      – PersonEntity:
          Name:
            NameFull: Pierre Baldi
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 29
              M: 05
              Text: May2007
              Type: published
              Y: 2007
          Identifiers:
            – Type: issn-print
              Value: 15499596
          Numbering:
            – Type: volume
              Value: 47
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: Journal of Chemical Information & Modeling
              Type: main
ResultId 1