Nikolas Fechner

Summary

Country: Germany

Publications

  1. ncbi jCompoundMapper: An open source Java library and command-line tool for chemical fingerprints
    Georg Hinselmann
    University of Tubingen, Center for Bioinformatics Tübingen ZBIT, Sand 1, 72076 Tubingen, Germany
    J Cheminform 3:3. 2011
  2. ncbi Optimal assignment methods for ligand-based virtual screening
    Andreas Jahn
    University of Tubingen, Center for Bioinformatics Tübingen ZBIT, Sand 1, 72076 Tubingen, Germany
    J Cheminform 1:14. 2009
  3. ncbi Atomic local neighborhood flexibility incorporation into a structured similarity measure for QSAR
    Nikolas Fechner
    Center of Bioinformatics ZBIT, University of Tubingen, Tubingen, Germany
    J Chem Inf Model 49:549-60. 2009
  4. ncbi Estimation of the applicability domain of kernel-based machine learning models for virtual screening
    Nikolas Fechner
    Center for Bioinformatics Tübingen ZBIT, University of Tubingen, Sand 1, 72076 Tubingen, Germany
    J Cheminform 2:2. 2010
  5. ncbi Large-scale learning of structure-activity relationships using a linear support vector machine and problem-specific metrics
    Georg Hinselmann
    Center for Bioinformatics ZBIT, University of Tübingen, Tübingen, Germany
    J Chem Inf Model 51:203-13. 2011

Collaborators

  • Georg Hinselmann
  • Andreas Jahn
  • Andreas Zell
  • Lars Rosenbaum
  • Claude Ostermann

Detail Information

Publications5

  1. ncbi jCompoundMapper: An open source Java library and command-line tool for chemical fingerprints
    Georg Hinselmann
    University of Tubingen, Center for Bioinformatics Tübingen ZBIT, Sand 1, 72076 Tubingen, Germany
    J Cheminform 3:3. 2011
    ..abstract:..
  2. ncbi Optimal assignment methods for ligand-based virtual screening
    Andreas Jahn
    University of Tubingen, Center for Bioinformatics Tübingen ZBIT, Sand 1, 72076 Tubingen, Germany
    J Cheminform 1:14. 2009
    ..The optimal assignment approach on molecular graphs, a successful method in the field of quantitative structure-activity relationships, has not been tested as a ligand-based virtual screening method so far...
  3. ncbi Atomic local neighborhood flexibility incorporation into a structured similarity measure for QSAR
    Nikolas Fechner
    Center of Bioinformatics ZBIT, University of Tubingen, Tubingen, Germany
    J Chem Inf Model 49:549-60. 2009
    ..The impact of the local flexibility was evaluated on several published QSAR data sets. This lead to an improvement of the model quality on 9 out of 10 data sets compared to the unmodified optimal assignment kernel...
  4. ncbi Estimation of the applicability domain of kernel-based machine learning models for virtual screening
    Nikolas Fechner
    Center for Bioinformatics Tübingen ZBIT, University of Tubingen, Sand 1, 72076 Tubingen, Germany
    J Cheminform 2:2. 2010
    ..Unfortunately, these cannot be extended easily to structured kernel-based machine learning models. For this reason, we propose three approaches to estimate the domain of applicability of a kernel-based QSAR model...
  5. ncbi Large-scale learning of structure-activity relationships using a linear support vector machine and problem-specific metrics
    Georg Hinselmann
    Center for Bioinformatics ZBIT, University of Tübingen, Tübingen, Germany
    J Chem Inf Model 51:203-13. 2011
    ..However, considering the overall convincing performance and computation time of the large-scale support vector machine, the approach provides an excellent alternative to established large-scale classification approaches...