Structure-based optimization of potent 4- and 6-azaindole-3-carboxamides as renin inhibitors

Impact of Applicability Domains to Generative Artificial Intelligence

Molecular generative artificial intelligence is drawing significant attention in the drug design community, with several experimentally validated proof of concepts already published. Nevertheless, generative models are known for sometimes generating unrealistic, unstable, unsynthesizable, or uninteresting structures. This calls for methods to constrain those algorithms to generate structures in drug-like portions of the chemical space. While the concept of applicability domains for predictive models is well studied, its counterpart for generative models is not yet well-defined. In this work, we empirically examine various possibilities and propose applicability domains suited for generative models. Using both public and internal data sets, we use generative methods to generate novel structures that are predicted to be actives by a corresponding quantitative structure-activity relationships model while constraining the generative model to stay within a given applicability domain. Our work looks at several applicability domain definitions, combining various criteria, such as structural similarity to the training set, similarity of physicochemical properties, unwanted substructures, and quantitative estimate of drug-likeness. We assess the structures generated from both qualitative and quantitative points of view and find that the applicability domain definitions have a strong influence on the drug-likeness of generated molecules. An extensive analysis of our results allows us to identify applicability domain definitions that are best suited for generating drug-like molecules with generative models. We anticipate that this work will help foster the adoption of generative models in an industrial context.

Interpretation of Structure-Activity Relationships in Real-World Drug Design Data Sets Using Explainable Artificial Intelligence

In silico models based on Deep Neural Networks (DNNs) are promising for predicting activities and properties of new molecules. Unfortunately, their inherent black-box character hinders our understanding, as to which structural features are important for activity. However, this information is crucial for capturing the underlying structure-activity relationships (SARs) to guide further optimization. To address this interpretation gap, "Explainable Artificial Intelligence" (XAI) methods recently became popular. Herein, we apply and compare multiple XAI methods to projects of lead optimization data sets with well-established SARs and available X-ray crystal structures. As we can show, easily understandable and comprehensive interpretations are obtained by combining DNN models with some powerful interpretation methods. In particular, SHAP-based methods are promising for this task. A novel visualization scheme using atom-based heatmaps provides useful insights into the underlying SAR. It is important to note that all interpretations are only meaningful in the context of the underlying models and associated data.

Application of Deep Neural Network Models in Drug Discovery Programs

In silico driven optimization of compound properties related to pharmacokinetics, pharmacodynamics, and safety is a key requirement in modern drug discovery. Nowadays, large and harmonized datasets allow to implement deep neural networks (DNNs) as a framework for leveraging predictive models. Nevertheless, various available model architectures differ in their global applicability and performance in lead optimization projects, such as stability over time and interpretability of the results. Here, we describe and compare the value of established DNN-based methods for the prediction of key ADME property trends and biological activity in an industrial drug discovery environment, represented by microsomal lability, CYP3A4 inhibition and factor Xa inhibition. Three architectures are exemplified, our earlier described multilayer perceptron approach (MLP), graph convolutional network-based models (GCN) and a vector representation approach, Mol2Vec. From a statistical perspective, MLP and GCN were found to perform superior over Mol2Vec, when applied to external validation sets. Interestingly, GCN-based predictions are most stable over a longer period in a time series validation study. Apart from those statistical observations, DNN prove of value to guide local SAR. To illustrate this important aspect in pharmaceutical research projects, we discuss challenging applications in medicinal chemistry towards a more realistic picture of artificial intelligence in drug discovery.

Exploring the pH-Dependent Structure-Dynamics-Function Relationship of Human Renin

Renin is a pepsin-like aspartyl protease and an important drug target for the treatment of hypertension; despite three decades' research, its pH-dependent structure-function relationship remains poorly understood. Here, we employed continuous constant pH molecular dynamics (CpHMD) simulations to decipher the acid/base roles of renin's catalytic dyad and the conformational dynamics of the flap, which is a common structural feature among aspartyl proteases. The calculated pK_a's suggest that catalytic Asp38 and Asp226 serve as the general base and acid, respectively, in agreement with experiment and supporting the hypothesis that renin's neutral optimum pH is due to the substrate-induced pK_a shifts of the aspartic dyad. The CpHMD data confirmed our previous hypothesis that hydrogen bond formation is the major determinant of the dyad pK_a order. Additionally, our simulations showed that renin's flap remains open regardless of pH, although a Tyr-inhibited state is occasionally formed above pH 5. These findings are discussed in comparison to the related aspartyl proteases, including β-secretases 1 and 2, cathepsin D, and plasmepsin II. Our work represents a first step toward a systematic understanding of the pH-dependent structure-dynamics-function relationships of pepsin-like aspartyl proteases that play important roles in biology and human disease states.

Artificial intelligence in the early stages of drug discovery

Although the use of computational methods within the pharmaceutical industry is well established, there is an urgent need for new approaches that can improve and optimize the pipeline of drug discovery and development. In spite of the fact that there is no unique solution for this need for innovation, there has recently been a strong interest in the use of Artificial Intelligence for this purpose. As a matter of fact, not only there have been major contributions from the scientific community in this respect, but there has also been a growing partnership between the pharmaceutical industry and Artificial Intelligence companies. Beyond these contributions and efforts there is an underlying question, which we intend to discuss in this review: can the intrinsic difficulties within the drug discovery process be overcome with the implementation of Artificial Intelligence? While this is an open question, in this work we will focus on the advantages that these algorithms provide over the traditional methods in the context of early drug discovery.

Synthetic strategies, SAR studies, and computer modeling of indole 2 and 3-carboxamides as the strong enzyme inhibitors: a review

Abstract

Indole derivatives have been the focus of many researchers in the study of pharmaceutical compounds for many years. Researchers have investigated the effect of carboxamide moiety at positions 2 and 3, giving unique inhibitory properties to these compounds. The presence of carboxamide moiety in indole derivatives causes hydrogen bonds with a variety of enzymes and proteins, which in many cases, inhibits their activity. In this review, synthetic strategies of indole 2 and 3-carboxamide derivatives, the type, and mode of interaction of these derivatives against HLGP, HIV-1, renin enzyme, and structure–activity studies of these compounds were investigated. It is hoped that indole scaffolds will be tested in the future for maximum activity in pharmacological compounds.

Graphic abstract

Facile synthesis of 4- and 7-azaindoles from the corresponding imines by palladium-catalyzed cascade C-C and C-N coupling

The cyclization of 2,3-dihalopyridines with readily available imines provides a convenient and regioselective approach to 4- and 7-azaindoles. The regioselectivity can be controlled by the choice of the halogen atoms at the pyridine ring (chlorine versus bromine).

Enantioselective synthesis of C2-functionalized, N-protected morpholines and orthogonally N,N'-protected piperazines via organocatalysis

In this Letter, we describe a novel three-step, one-pot procedure for the enantioselective synthesis of N-benzyl protected morpholines and orthogonally N,N'-protected piperazines with chiral alkyl groups installed at the C2 position of each heterocyclic core via organocatalysis. This methodology allows for the rapid preparation of functionalized morpholines and piperazines that are not readily accessible through any other chemistry in good to excellent % ee (55-98% ee).