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

Title: Ensemble-based docking: From hit discovery to metabolism and toxicity predictions

Abstract

The use of ensemble-based docking for the exploration of biochemical pathways and toxicity prediction of drug candidates is described. We describe the computational engineering work necessary to enable large ensemble docking campaigns on supercomputers. We show examples where ensemble-based docking has significantly increased the number and the diversity of validated drug candidates. Finally, we illustrate how ensemble-based docking can be extended beyond hit discovery and toward providing a structural basis for the prediction of metabolism and off-target binding relevant to pre-clinical and clinical trials.

Authors:
 [1];  [1];  [2];  [3];  [1];  [3];  [1]
  1. Univ. of Tennessee, Knoxville, TN (United States)
  2. Univ. of Kentucky, Lexington, KY (United States)
  3. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1337049
Grant/Contract Number:
AC05-00OR22725
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Bioorganic and Medicinal Chemistry
Additional Journal Information:
Journal Volume: 24; Journal Issue: 20; Journal ID: ISSN 0968-0896
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES

Citation Formats

Evangelista, Wilfredo, Weir, Rebecca, Ellingson, Sally, Harris, Jason B., Kapoor, Karan, Smith, Jeremy C., and Baudry, Jerome. Ensemble-based docking: From hit discovery to metabolism and toxicity predictions. United States: N. p., 2016. Web. doi:10.1016/j.bmc.2016.07.064.
Evangelista, Wilfredo, Weir, Rebecca, Ellingson, Sally, Harris, Jason B., Kapoor, Karan, Smith, Jeremy C., & Baudry, Jerome. Ensemble-based docking: From hit discovery to metabolism and toxicity predictions. United States. doi:10.1016/j.bmc.2016.07.064.
Evangelista, Wilfredo, Weir, Rebecca, Ellingson, Sally, Harris, Jason B., Kapoor, Karan, Smith, Jeremy C., and Baudry, Jerome. 2016. "Ensemble-based docking: From hit discovery to metabolism and toxicity predictions". United States. doi:10.1016/j.bmc.2016.07.064. https://www.osti.gov/servlets/purl/1337049.
@article{osti_1337049,
title = {Ensemble-based docking: From hit discovery to metabolism and toxicity predictions},
author = {Evangelista, Wilfredo and Weir, Rebecca and Ellingson, Sally and Harris, Jason B. and Kapoor, Karan and Smith, Jeremy C. and Baudry, Jerome},
abstractNote = {The use of ensemble-based docking for the exploration of biochemical pathways and toxicity prediction of drug candidates is described. We describe the computational engineering work necessary to enable large ensemble docking campaigns on supercomputers. We show examples where ensemble-based docking has significantly increased the number and the diversity of validated drug candidates. Finally, we illustrate how ensemble-based docking can be extended beyond hit discovery and toward providing a structural basis for the prediction of metabolism and off-target binding relevant to pre-clinical and clinical trials.},
doi = {10.1016/j.bmc.2016.07.064},
journal = {Bioorganic and Medicinal Chemistry},
number = 20,
volume = 24,
place = {United States},
year = 2016,
month = 7
}

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

Citation Metrics:
Cited by: 2works
Citation information provided by
Web of Science

Save / Share:
  • Cited by 2
  • Ensemble learning approach based decision treeboost (DTB) and decision tree forest (DTF) models are introduced in order to establish quantitative structure–toxicity relationship (QSTR) for the prediction of toxicity of 1450 diverse chemicals. Eight non-quantum mechanical molecular descriptors were derived. Structural diversity of the chemicals was evaluated using Tanimoto similarity index. Stochastic gradient boosting and bagging algorithms supplemented DTB and DTF models were constructed for classification and function optimization problems using the toxicity end-point in T. pyriformis. Special attention was drawn to prediction ability and robustness of the models, investigated both in external and 10-fold cross validation processes. In complete data,more » optimal DTB and DTF models rendered accuracies of 98.90%, 98.83% in two-category and 98.14%, 98.14% in four-category toxicity classifications. Both the models further yielded classification accuracies of 100% in external toxicity data of T. pyriformis. The constructed regression models (DTB and DTF) using five descriptors yielded correlation coefficients (R{sup 2}) of 0.945, 0.944 between the measured and predicted toxicities with mean squared errors (MSEs) of 0.059, and 0.064 in complete T. pyriformis data. The T. pyriformis regression models (DTB and DTF) applied to the external toxicity data sets yielded R{sup 2} and MSE values of 0.637, 0.655; 0.534, 0.507 (marine bacteria) and 0.741, 0.691; 0.155, 0.173 (algae). The results suggest for wide applicability of the inter-species models in predicting toxicity of new chemicals for regulatory purposes. These approaches provide useful strategy and robust tools in the screening of ecotoxicological risk or environmental hazard potential of chemicals. - Graphical abstract: Importance of input variables in DTB and DTF classification models for (a) two-category, and (b) four-category toxicity intervals in T. pyriformis data. Generalization and predictive abilities of the constructed (c) DTB and (d) DTF regression models to predict the T. pyriformis toxicity of diverse chemicals. - Highlights: • Ensemble learning (EL) based models constructed for toxicity prediction of chemicals • Predictive models used a few simple non-quantum mechanical molecular descriptors. • EL-based DTB/DTF models successfully discriminated toxic and non-toxic chemicals. • DTB/DTF regression models precisely predicted toxicity of chemicals in multi-species. • Proposed EL based models can be used as tool to predict toxicity of new chemicals.« less
  • We investigate large-scale ensemble docking using five proteins from the Directory of Useful Decoys (DUD, dud.docking.org) for which docking to crystal structures has proven difficult. Molecular dynamics trajectories are produced for each protein and an ensemble of representative conformational structures extracted from the trajectories. Docking calculations are performed on these selected simulation structures and ensemble-based enrichment factors compared with those obtained using docking in crystal structures of the same protein targets or random selection of compounds. We also found simulation-derived snapshots with improved enrichment factors that increased the chemical diversity of docking hits for four of the five selected proteins.more » A combination of all the docking results obtained from molecular dynamics simulation followed by selection of top-ranking compounds appears to be an effective strategy for increasing the number and diversity of hits when using docking to screen large libraries of chemicals against difficult protein targets.« less
  • Photosystem I (PSI) is a large membrane protein that catalyzes light-driven electron transfer across the thylakoid membrane from plastocyanin located in the lumen to ferredoxin in the stroma. Metal analysis reveals that PSI isolated from the cyanobacterial membranes of Synechococcus leopoliensis has a near-stoichiometric 1 molar equiv of Zn2+ per PSI monomer and two additional surface metal ion sites that favor Cu2+ binding. Two-dimensional hyperfine sublevel correlation (HYSCORE) spectroscopy reveals coupling to the so-called remote nitrogen of a single histidine coordinated to one of the Cu2+ centers. EPR and X-ray absorption fine structure (XAFS) studies of 2Cu?PSI complexes reveal themore » direct interaction of ferredoxin with the Cu2+ centers on PSI, establishing the location of native metal sites on the ferredoxin docking side of PSI. On the basis of these spectroscopic results and previously reported site-directed mutagenesis studies, inspection of the PSI crystal structure reveals a cluster of three highly conserved residues, His(D95), Glu(D103), and Asp(C23), as a likely Cu2+ binding site. The discovery of surface metal sites on the acceptor side of PSI provides a unique opportunity to probe the stromal region of PSI and the interactions of PSI with its reaction partner, the soluble electron carrier protein ferredoxin.« less