A de novo substructure generation algorithm for identifying the privileged chemical fragments of liver X receptorβ agonists

Abstract

Liver X receptorβ (LXRβ) is a promising therapeutic target for lipid disorders, atherosclerosis, chronic inflammation, autoimmunity, cancer and neurodegenerative diseases. Druggable LXRβ agonists have been explored over the past decades. However, the pocket of LXRβ ligand-binding domain (LBD) is too large to predict LXRβ agonists with novel scaffolds based on either receptor or agonist structures. In this paper, we report a de novo algorithm which drives privileged LXRβ agonist fragments by starting with individual chemical bonds (de novo) from every molecule in a LXRβ agonist library, growing the bonds into substructures based on the agonist structures with isomorphic and homomorphic restrictions, and electing the privileged fragments from the substructures with a popularity threshold and background chemical and biological knowledge. Using these privileged fragments as queries, we were able to figure out the rules to reconstruct LXRβ agonist molecules from the fragments. The privileged fragments were validated by building regularized logistic regression (RLR) and supporting vector machine (SVM) models as descriptors to predict a LXRβ agonist activities.

Figure 1

The flow-chart for using de novo substructure generation algorithm to discover LXRβ agonist privileged fragments and elucidate the assembly rules.

Figure 2

LXRβ, PPARα and VR libraries were discriminated by the frequent substructure descriptors derived from the ZINC library.

Figure 3

The performances of three substructure-based SVM regression models. (A) LXRβ, (B) PPARα, (C) VR.

Figure 4

The schema of Rule 1.

Figure 5

The schema of Rule 2.

Figure 6

LXRβ ligands created by merging Fragments B, C and F (Rule 3).

Figure 7

Bioisostere definitions for Fragments A’ and D’.

Figure 8

LXRβ ligands generated by Rule 4.

Figure 9

LXRβ agonists constructed by Rule 5.

Figure 10

Scaffold constructed by rule 6.

Figure 11

Scaffold constructed by Rule 7. The structure on the right is GW3965.

Figure 12

Scaffold constructed by Rule 8.

Figure 13

PCA plot for the compounds in the LXRβ library using the frequent fragment descriptors derived from ZINC database. Privileged fragments and their combinations are coded in different colors. The compounds with the same color are aggregated.

Figure 14

The experimentally confirmed LXRβ agonistic compounds found based upon the rules of privileged fragments and their combinations. At compound 3, R is a halogenated long-hydrocarbon substituent.

Figure 15

The activities of the confirmed LXRβ agonistic compounds and their fragment combination patterns. The letters above the bars represent the privileged fragments discovered by our algorithm. The structure of GW3965 is depicted in Fig. 11.

Figure 16

An example of a substructure generation tree. The tree started with a four compounds library with a C-C root fragment with a subID vector containing {An Bm Ch De Dk}. The popularity of this root fragment is 4. The root node produced two successor nodes (Node-11 and Node-12) by generating two new substructures. The process is repeated till all successor nodes are undividable. The substructures in the thick boxes are all possible fragment substructures created from a C-C root fragment. Other types of root fragments will be used to generate more substructure generation trees.

Figure 17

Pruning a substructure generation tree. The tree was growing while a depth-first search was proceeding. The nodes in black boxes were calculated on the fly. The nodes in green boxes were kept in an substructure library. The nodes in red boxes were pruned.

Figure 18

FFID and frequent substructures. Case 1: One FFID could have more than one fragments, one of the fragments was the substructure of another. The larger fragment was kept in this case. Case 2: One FFID could have more than one fragments, they were not topologically included to each other. Both fragments would be assigned to the same FFID.