Interpretable Machine Learning Models for Molecular Design of Tyrosine Kinase Inhibitors Using Variational Autoencoders and Perturbation-Based Approach of Chemical Space Exploration

Abstract

In the current study, we introduce an integrative machine learning strategy for the autonomous molecular design of protein kinase inhibitors using variational autoencoders and a novel cluster-based perturbation approach for exploration of the chemical latent space. The proposed strategy combines autoencoder-based embedding of small molecules with a cluster-based perturbation approach for efficient navigation of the latent space and a feature-based kinase inhibition likelihood classifier that guides optimization of the molecular properties and targeted molecular design. In the proposed generative approach, molecules sharing similar structures tend to cluster in the latent space, and interpolating between two molecules in the latent space enables smooth changes in the molecular structures and properties. The results demonstrated that the proposed strategy can efficiently explore the latent space of small molecules and kinase inhibitors along interpretable directions to guide the generation of novel family-specific kinase molecules that display a significant scaffold diversity and optimal biochemical properties. Through assessment of the latent-based and chemical feature-based binary and multiclass classifiers, we developed a robust probabilistic evaluator of kinase inhibition likelihood that is specifically tailored to guide the molecular design of novel SRC kinase molecules. The generated molecules originating from LCK and ABL1 kinase inhibitors yielded ~40% of novel and valid SRC kinase compounds with high kinase inhibition likelihood probability values (p > 0.75) and high similarity (Tanimoto coefficient > 0.6) to the known SRC inhibitors. By combining the molecular perturbation design with the kinase inhibition likelihood analysis and similarity assessments, we showed that the proposed molecular design strategy can produce novel valid molecules and transform known inhibitors of different kinase families into potential chemical probes of the SRC kinase with excellent physicochemical profiles and high similarity to the known SRC kinase drugs. The results of our study suggest that task-specific manipulation of a biased latent space may be an important direction for more effective task-oriented and target-specific autonomous chemical design models.

Searching for Structure: Characterizing the Protein Conformational Landscape with Clustering-Based Algorithms

“…The customarily used representation of the FEL in the literature is in the PC space. For example, the representation of the FEL in the principal components 1 (PC1) and 2 (PC2) space has been used in the past couple of years for various systems from globular proteins to IDPs (including tau). ,,,− Therefore, to evaluate the performance of the clustering methods, we chose to plot the FELs in the (PC1, PC2) space. We evaluated the PCs based on the C-α atom of each residue using the GROMACS command gmx anaeig .…”

Bayesian Optimization in the Latent Space of a Variational Autoencoder for the Generation of Selective FLT3 Inhibitors

“…Although several generative methods have been already reported to identify kinase inhibitors, − to our knowledge, the problem of specificity for this class of targets − has received less attention using generative modeling. Our results indicate that the pipeline that we report is effective in generating small molecules with a predicted high affinity and high specificity for the intended target.…”