Interpretation of Ligand-Based Activity Cliff Prediction Models Using the Matched Molecular Pair Kernel

Activity cliffs (ACs) are formed by two structurally similar compounds with a large difference in potency. Accurate AC prediction is expected to help researchers’ decisions in the early stages of drug discovery. Previously, predictive models based on matched molecular pair (MMP) cliffs have been proposed. However, the proposed methods face a challenge of interpretability due to the black-box character of the predictive models. In this study, we developed interpretable MMP fingerprints and modified a model-specific interpretation approach for models based on a support vector machine (SVM) and MMP kernel. We compared important features highlighted by this SVM-based interpretation approach and the SHapley Additive exPlanations (SHAP) as a major model-independent approach. The model-specific approach could capture the difference between AC and non-AC, while SHAP assigned high weights to the features not present in the test instances. For specific MMPs, the feature weights mapped by the SVM-based interpretation method were in agreement with the previously confirmed binding knowledge from X-ray co-crystal structures, indicating that this method is able to interpret the AC prediction model in a chemically intuitive manner.

Riminophenazine Derivatives as Potential Antituberculosis Agents: Synthesis, Biological, and Electrochemical Evaluations

A series of novel riminophenazine derivatives, having ionizable alkyl substituents at N-5 and a variety of substituents on the C-3 imino nitrogen, at C-8 and on the pendant aryl group, have been designed and synthesized. Preliminary investigations into the relationship between lipophilicity, redox potential, and antimycobacterial activity were conducted, using the in vitro activity against Mycobacterium tuberculosis H37Rv, mammalian cytotoxicity, and the redox potential of the compounds determined by cyclic voltammetry as measures. Results revealed an activity “cliff” associated with C-8 substitution (10l and 10m) that, along with defined redox activity, point to a new class of riminophenazines as potential anti-tuberculosis agents having reasonable activity (MIC99 ~1 µM).

Prediction of activity cliffs on the basis of images using convolutional neural networks

An activity cliff (AC) is formed by a pair of structurally similar compounds with a large difference in potency. Accordingly, ACs reveal structure–activity relationship (SAR) discontinuity and provide SAR information for compound optimization. Herein, we have investigated the question if ACs could be predicted from image data. Therefore, pairs of structural analogs were extracted from different compound activity classes that formed or did not form ACs. From these compound pairs, consistently formatted images were generated. Image sets were used to train and test convolutional neural network (CNN) models to systematically distinguish between ACs and non-ACs. The CNN models were found to predict ACs with overall high accuracy, as assessed using alternative performance measures, hence establishing proof-of-principle. Moreover, gradient weights from convolutional layers were mapped to test compounds and identified characteristic structural features that contributed to successful predictions. Weight-based feature visualization revealed the ability of CNN models to learn chemistry from images at a high level of resolution and aided in the interpretation of model decisions with intrinsic black box character.

Identification and Analysis of Activity Cliffs Using 3D Similarity Techniques

<p>The analysis of activity landscapes and activity cliffs is a widely used method to locate critical regions of SAR. Knowledge of what changes in a series of molecules caused unexpectedly large changes in affinity allows the chemist to focus on the molecular features which are crucial for activity. We examine the usefulness of activity cliff analysis with a metric based on 3D shape and electrostatic similarity, utilizing a ligand-based alignment method. We demonstrate that 3D activity cliff analysis is complementary to the more usual 2D fingerprint-based methods, in that each finds cliffs that the other misses. Moreover, we show that analysis of the activity landscape in the context of a consensus 3D alignment allows the source of the activity cliff to be investigated in terms of the effect that a structural change has on the steric and electrostatic properties of a molecule. The technique is illustrated with two set of compounds with activity against acetylcholinesterase and dipeptidyl peptidase.</p>

Identification and Analysis of Activity Cliffs Using 3D Similarity Techniques

<p>The analysis of activity landscapes and activity cliffs is a widely used method to locate critical regions of SAR. Knowledge of what changes in a series of molecules caused unexpectedly large changes in affinity allows the chemist to focus on the molecular features which are crucial for activity. We examine the usefulness of activity cliff analysis with a metric based on 3D shape and electrostatic similarity, utilizing a ligand-based alignment method. We demonstrate that 3D activity cliff analysis is complementary to the more usual 2D fingerprint-based methods, in that each finds cliffs that the other misses. Moreover, we show that analysis of the activity landscape in the context of a consensus 3D alignment allows the source of the activity cliff to be investigated in terms of the effect that a structural change has on the steric and electrostatic properties of a molecule. The technique is illustrated with two set of compounds with activity against acetylcholinesterase and dipeptidyl peptidase.</p>

Prediction of an MMP-1 inhibitor activity cliff using the SAR matrix approach and its experimental validation

A matrix metalloproteinase 1 (MMP-1) inhibitor activity cliff was predicted using the SAR Matrix method. Compound 4 was predicted as a highly potent activity cliff partner and found to possess 60 times higher inhibitory activity against MMP-1 than the structurally related compound 3. Furthermore, pharmacophore fitting of synthesized compounds indicated that the correctly predicted activity cliff was caused by interactions between the trifluoromethyl group at para position in compound 4 and residue ARG214 of MMP-1.

Increasing the public activity cliff knowledge base with new categories of activity cliffs

Aim: Extending the public knowledge base of activity cliffs (ACs) with new categories of ACs having special structural characteristics. Methodology: Dual-site ACs, isomer ACs and ACs with privileged substructures are described and their systematic identification is detailed. Exemplary results & data: More than 7400 new ACs belonging to different categories with activity against more than 200 targets were identified and are made publicly available. Limitations & next steps: For dual-site ACs, limited numbers of isomers are available as structural analogs for rationalizing contributions to AC formation. The search for such analogs will continue. In addition, the target distribution of ACs containing privileged substructures will be further analyzed.