High-Quality Conformer Generation with CONFORGE: Algorithm and Performance Assessment.

Knowledge of the putative bound-state conformation of a molecule is an essential prerequisite for the successful application of many computer-aided drug design methods that aim to assess or predict its capability to bind to a particular target receptor. An established approach to predict bioactive conformers in the absence of receptor structure information is to sample the low-energy conformational space of the investigated molecules and derive representative conformer ensembles that can be expected to comprise members closely resembling possible bound-state ligand conformations. The high relevance of such conformer generation functionality led to the development of a wide panel of dedicated commercial and open-source software tools throughout the last decades. Several published benchmarking studies have shown that open-source tools usually lag behind their commercial competitors in many key aspects. In this work, we introduce the open-source conformer ensemble generator CONFORGE, which aims at delivering state-of-the-art performance for all types of organic molecules in drug-like chemical space. The ability of CONFORGE and several well-known commercial and open-source conformer ensemble generators to reproduce experimental 3D structures as well as their computational efficiency and robustness has been assessed thoroughly for both typical drug-like molecules and macrocyclic structures. For small molecules, CONFORGE clearly outperformed all other tested open-source conformer generators and performed at least equally well as the evaluated commercial generators in terms of both processing speed and accuracy. In the case of macrocyclic structures, CONFORGE achieved the best average accuracy among all benchmarked generators, with RDKit's generator coming close in second place.

Improving Small Molecule pK a Prediction Using Transfer Learning With Graph Neural Networks.

Enumerating protonation states and calculating microstate pK a values of small molecules is an important yet challenging task for lead optimization and molecular modeling. Commercial and non-commercial solutions have notable limitations such as restrictive and expensive licenses, high CPU/GPU hour requirements, or the need for expert knowledge to set up and use. We present a graph neural network model that is trained on 714,906 calculated microstate pK a predictions from molecules obtained from the ChEMBL database. The model is fine-tuned on a set of 5,994 experimental pK a values significantly improving its performance on two challenging test sets. Combining the graph neural network model with Dimorphite-DL, an open-source program for enumerating ionization states, we have developed the open-source Python package pkasolver, which is able to generate and enumerate protonation states and calculate pK a values with high accuracy.

Improved Lipophilicity and Aqueous Solubility Prediction with Composite Graph Neural Networks.

The accurate prediction of molecular properties, such as lipophilicity and aqueous solubility, are of great importance and pose challenges in several stages of the drug discovery pipeline. Machine learning methods, such as graph-based neural networks (GNNs), have shown exceptionally good performance in predicting these properties. In this work, we introduce a novel GNN architecture, called directed edge graph isomorphism network (D-GIN). It is composed of two distinct sub-architectures (D-MPNN, GIN) and achieves an improvement in accuracy over its sub-architectures employing various learning, and featurization strategies. We argue that combining models with different key aspects help make graph neural networks deeper and simultaneously increase their predictive power. Furthermore, we address current limitations in assessment of deep-learning models, namely, comparison of single training run performance metrics, and offer a more robust solution.

Reinstatement of synaptic plasticity in the aging brain through specific dopamine transporter inhibition.

Aging-related neurological deficits negatively impact mental health, productivity, and social interactions leading to a pronounced socioeconomic burden. Since declining brain dopamine signaling during aging is associated with the onset of neurological impairments, we produced a selective dopamine transporter (DAT) inhibitor to restore endogenous dopamine levels and improve cognitive function. We describe the synthesis and pharmacological profile of (S,S)-CE-158, a highly specific DAT inhibitor, which increases dopamine levels in brain regions associated with cognition. We find both a potentiation of neurotransmission and coincident restoration of dendritic spines in the dorsal hippocampus, indicative of reinstatement of dopamine-induced synaptic plasticity in aging rodents. Treatment with (S,S)-CE-158 significantly improved behavioral flexibility in scopolamine-compromised animals and increased the number of spontaneously active prefrontal cortical neurons, both in young and aging rodents. In addition, (S,S)-CE-158 restored learning and memory recall in aging rats comparable to their young performance in a hippocampus-dependent hole board test. In sum, we present a well-tolerated, highly selective DAT inhibitor that normalizes the age-related decline in cognitive function at a synaptic level through increased dopamine signaling.

A Computational Approach to Identify Potential Novel Inhibitors against the Coronavirus SARS-CoV-2.

The current pandemic threat of COVID-19, caused by the novel coronavirus SARS-CoV-2, not only gives rise to a high number of deaths around the world but also has immense consequences for the worldwide health systems and global economy. Given the fact that this pandemic is still ongoing and there are currently no drugs or vaccines against this novel coronavirus available, this in silico study was conducted to identify a potential novel SARS-CoV-2-inhibitor. Two different approaches were pursued: 1) The Docking Consensus Approach (DCA) is a novel approach, which combines molecular dynamics simulations with molecular docking. 2) The Common Hits Approach (CHA) in contrast focuses on the combination of the feature information of pharmacophore modeling and the flexibility of molecular dynamics simulations. The application of both methods resulted in the identification of 10 compounds with high coronavirus inhibition potential.

Applications of the Pharmacophore Concept in Natural Product inspired Drug Design.

Pharmacophore-based techniques are nowadays an important part of many computer-aided drug design workflows and have been successfully applied for tasks such as virtual screening, lead optimization and de novo design. Natural products, on the other hand, can serve as a valuable source for unconventional molecular scaffolds that stimulate ideas for novel lead compounds in a more diverse chemical space that does not follow the rules of traditional medicinal chemistry. The first part of this review provides a brief introduction to the pharmacophore concept, the methods for pharmacophore model generation, and their applications. The second, concluding part, presents examples for recent, pharmacophore method related research in the field of natural product chemistry. The selected examples show, that pharmacophore-based methods which get mainly applied on synthetic drug-like molecules work equally well in the realm of natural products and thus can serve as a valuable tool for researchers in the field of natural product inspired drug design.

A compact review of molecular property prediction with graph neural networks.

As graph neural networks are becoming more and more powerful and useful in the field of drug discovery, many pharmaceutical companies are getting interested in utilizing these methods for their own in-house frameworks. This is especially compelling for tasks such as the prediction of molecular properties which is often one of the most crucial tasks in computer-aided drug discovery workflows. The immense hype surrounding these kinds of algorithms has led to the development of many different types of promising architectures and in this review we try to structure this highly dynamic field of AI-research by collecting and classifying 80 GNNs that have been used to predict more than 20 molecular properties using 48 different datasets.