Prev. Article Next Article Table of Contents

Article

Three Descriptor Model Sets a High Standard for the CSAR-NRC HiQ Benchmark

Figures

Your current credentials do not allow retrieval of the full text.

Purchase the full-text

PDF/HTML,
figures/images,
references and tables,
(where available)

Christian Kramer*† and Peter Gedeck†

Novartis Institutes for BioMedical Research, Novartis Pharma AG, Forum 1, Novartis Campus, CH-4056 Basel, Switzerland

J. Chem. Inf. Model., 2011, 51 (9), pp 2139–2145

DOI: 10.1021/ci200030h

Publication Date (Web): May 30, 2011

E-mail: christian.kramer@novartis.com.

This article is part of the

CSAR 2010 Scoring Exercise

special issue.

Section:

Biochemical Methods

Abstract

Here we report the results we obtained with a proteochemometric approach for predicting ligand binding free energies of the CSAR-NRC HiQ benchmark data set. Using distance-dependent atom-type pair descriptors in a bagged stepwise multiple-linear regression (MLR) model with subsequent complexity reduction we were able to identify three descriptors that can be used to build a very robust regression model for the CSAR-NRC HiQ data set. The model has an R²_cv of 0.55, a MUE_cv of 1.19, and an RMSE_cv of 1.49 on the out-of-bag test set. The descriptors selected are the count of protein atoms in a shell between 4.5 Å and 6 Å around each heavy ligand atom excluding oxygen and phosphorus, the count of sulfur atoms in the vicinity of tryptophan, and the count of aliphatic ligand hydroxy hydrogens. The first two descriptors have a positive sign indicating that they contribute favorably to the binding energy, whereas the count of hydroxy hydrogens contributes unfavorably to the binding free energy observed. The fact that such a simple model can be so effective raises a couple of questions that are addressed in the article.

View: Full Text HTML | Hi-Res PDF | PDF w/ Links

Tools

SciFinder Links

Explore by:

Author of this Article Any Author Research Topic

History

Published In Issue September 26, 2011
Article ASAPJune 27, 2011
Just Accepted ManuscriptMay 30, 2011
Received: January 21, 2011

Recommend & Share

Related Content

CSAR Benchmark Exercise of 2010: Combined Evaluation Across All Submitted Scoring FunctionsJournal of Chemical Information and Modeling
- CSAR Benchmark Exercise of 2010: Combined Evaluation Across All Submitted Scoring Functions
  Richard D. Smith, James B. Dunbar, Jr., Peter Man-Un Ung, Emilio X. Esposito, Chao-Yie Yang, Shaomeng Wang, and Heather A. Carlson
  Journal of Chemical Information and Modeling 2011 51 (9), pp 2115–2131
  Abstract: As part of the Community Structure-Activity Resource (CSAR) center, a set of 343 high-quality, protein–ligand crystal structures were assembled with experimentally determined K_d or K_i information from the literature. We encouraged the community to score ...
  Abstract | Full Text HTML | PDF w/ Links | Hi-Res PDF
CSAR Scoring Challenge Reveals the Need for New Concepts in Estimating Protein–Ligand Binding AffinityJournal of Chemical Information and Modeling
- CSAR Scoring Challenge Reveals the Need for New Concepts in Estimating Protein–Ligand Binding Affinity
  Fedor N. Novikov, Alexey A. Zeifman, Oleg V. Stroganov, Viktor S. Stroylov, Val Kulkov, and Ghermes G. Chilov
  Journal of Chemical Information and Modeling 2011 51 (9), pp 2090–2096
  Abstract: The dG prediction accuracy by the Lead Finder docking software on the CSAR test set was characterized by R²=0.62 and rmsd=1.93 kcal/mol, and the method of preparation of the full-atom structures of the test set did not significantly affect the resulting ...
  Abstract | Full Text HTML | PDF w/ Links | Hi-Res PDF
Scoring and Lessons Learned with the CSAR Benchmark Using an Improved Iterative Knowledge-Based Scoring FunctionJournal of Chemical Information and Modeling
- Scoring and Lessons Learned with the CSAR Benchmark Using an Improved Iterative Knowledge-Based Scoring Function
  Sheng-You Huang and Xiaoqin Zou
  Journal of Chemical Information and Modeling 2011 51 (9), pp 2097–2106
  Abstract: Based on a statistical mechanics-based iterative method, we have extracted a set of distance-dependent, all-atom pairwise potentials for protein–ligand interactions from the crystal structures of 1300 protein–ligand complexes. The iterative method ...
  Abstract | Full Text HTML | PDF w/ Links | Hi-Res PDF

Select a CAS section from the 5 main topical divisions below:

Article

Three Descriptor Model Sets a High Standard for the CSAR-NRC HiQ Benchmark

Abstract

Tools

SciFinder Links

History

Recommend & Share

Related Content

CSAR Benchmark Exercise of 2010: Combined Evaluation Across All Submitted Scoring Functions

CSAR Scoring Challenge Reveals the Need for New Concepts in Estimating Protein–Ligand Binding Affinity

Scoring and Lessons Learned with the CSAR Benchmark Using an Improved Iterative Knowledge-Based Scoring Function

Other ACS content by these authors:

JOURNALS

BOOKS

C&EN

TOOLS

COMMUNITIES

DIRECTORIES & DATABASES

LEGACY MAGAZINES

Products

User Resources

Support

Partners

Search ACS Publications