Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2016 Aug 22;56(8):1597-607.
doi: 10.1021/acs.jcim.6b00248. Epub 2016 Jul 25.

Fragment-Based Analysis of Ligand Dockings Improves Classification of Actives

Affiliations
Free PMC article

Fragment-Based Analysis of Ligand Dockings Improves Classification of Actives

Richard K Belew et al. J Chem Inf Model. .
Free PMC article

Abstract

We describe ADChemCast, a method for using results from virtual screening to create a richer representation of a target binding site, which may be used to improve ranking of compounds and characterize the determinants of ligand-receptor specificity. ADChemCast clusters docked conformations of ligands based on shared pairwise receptor-ligand interactions within chemically similar structural fragments, building a set of attributes characteristic of binders and nonbinders. Machine learning is then used to build rules from the most informational attributes for use in reranking of compounds. In this report, we use ADChemCast to improve the ranking of compounds in 11 diverse proteins from the Database of Useful Decoys-Enhanced (DUD-E) and demonstrate the utility of the method for characterizing relevant binding attributes in HIV reverse transcriptase.

Figures

Figure 1
Figure 1
Ligand fragments - RLIF interaction model
Figure 2
Figure 2
ADChemCast workflow
Figure 3
Figure 3
RECAP bond-breaking rules
Figure 4
Figure 4
RLIF-Ligand fragment interaction model
Figure 5
Figure 5
vdwPatch A106V:[CB,CG1,CG2];A227F:[CD2,CE2] associated with PDB:3LAN
Figure 6
Figure 6
Energy distribution of docking results of HIVRT ligands. Energy is in kcal/mol.
Figure 7
Figure 7
Classification performance across all experiments
Figure 8
Figure 8
Classifier performance on alternative HIVPR structures
Figure 9
Figure 9
Rilpivirine bound to the NNRTI site of reverse transcriptase (upper left), and the most informative examples of RLIF, RFQ and vdwPatch attributes found by ADChemCast for this site. One atom in rilpivirine is close to the site of interaction identified in all three attributes.

Similar articles

See all similar articles

Publication types

Feedback