Problem

A chemist needs to know which part of a compound is contributing to activity and/or which part is potentially inhibiting activity in order to make analogues with higher binding affinity.

Solution

Using ChemTree's multiple tree atom highlighting algorithm, you can automatically highlight which part of a molecule is enhancing activity, and/or which part may be inhibiting activity, relative to the structural features found within the whole screened library. This multiple tree atom highlighting methodology:

• Weights every atom by its contribution to activity across all models.
• Points to the “business end” of a molecule.
• Points to neutral or inhibiting fragments as candidates for substitution.

Step 1: Analyze your screening data with ChemTree. Then, use ChemTree to create a multiple tree model. A multiple tree model is a “forest” of many recursive partitioning (RP) trees where the descriptor to be split at each level of each tree is chosen at random from the best possibilities. By doing this, effects that may have been hidden from view when using only one tree are able to surface in at least some of the trees of the “forest”.

Step 2: From either a node in a recursive partitioning tree, or from the multiple tree clustering view, choose a interesting set of compounds to visualize. As described in the section on identifying lead series, we have identified two clusters of mao inhibitors:

Step 3: Once we have identified clusters of similar compounds with high activity, we can view the compounds in the cluster. The two clusters found by ChemTree correspond to two different classes of compounds with very different binding mechanisms. Further, ChemTree automatically highlights the portion of the molecule that was used in distinguishing the compounds from less active ones.

The upper right cluster corresponds to pargyline-like compounds: a triple bond, a tertiary nitrogen, and an aromatic ring. These suicide inhibitors covalently attach to the MAO flavin cofactor. Note that the pargyline portion of the molecule is highlighted in red.

The lower left cluster of compounds correspond to a second class of compounds: the N-N-C=(O) hydrolyzes to hydrazine and the resulting compound covalently binds to the protein as a suicide inhibitor.

We have also applied this process to a set of compounds assayed for mutagenicity using the Ames test. Below, we see some compound atoms are highlighted in red, indicating they may be responsible for mutagenicity, whereas blue atoms may mitigate the mutagenicity. White or not circled atoms are relatively neutral in their effect.