Drug-like Chemical Space Research Articles

Navigating a 1E+60 Chemical Space of Peptide/Peptoid Oligomers.

Herein we report a virtual library of 1E+60 members, a common estimate for the size of the drug-like chemical space. The library consists of linear or cyclic oligomers forming molecules within the size range of peptide drugs. We demonstrate ligand-based virtual screening using a genetic algorithm.

Equivariant score-based generative diffusion framework for 3D molecules

BackgroundMolecular biology is crucial for drug discovery, protein design, and human health. Due to the vastness of the drug-like chemical space, depending on biomedical experts to manually design molecules is exceedingly expensive. Utilizing generative methods with deep learning technology offers an effective approach to streamline the search space for molecular design and save costs. This paper introduces a novel E(3)-equivariant score-based diffusion framework for 3D molecular generation via SDEs, aiming to address the constraints of unified Gaussian diffusion methods. Within the proposed framework EMDS, the complete diffusion is decomposed into separate diffusion processes for distinct components of the molecular feature space, while the modeling processes also capture the complex dependency among these components. Moreover, angle and torsion angle information is integrated into the networks to enhance the modeling of atom coordinates and utilize spatial information more effectively.ResultsExperiments on the widely utilized QM9 dataset demonstrate that our proposed framework significantly outperforms the state-of-the-art methods in all evaluation metrics for 3D molecular generation. Additionally, ablation experiments are conducted to highlight the contribution of key components in our framework, demonstrating the effectiveness of the proposed framework and the performance improvements of incorporating angle and torsion angle information for molecular generation. Finally, the comparative results of distribution show that our method is highly effective in generating molecules that closely resemble the actual scenario.ConclusionThrough the experiments and comparative results, our framework clearly outperforms previous 3D molecular generation methods, exhibiting significantly better capacity for modeling chemically realistic molecules. The excellent performance of EMDS in 3D molecular generation brings novel and encouraging opportunities for tackling challenging biomedical molecule and protein scenarios.

COATI: Multimodal Contrastive Pretraining for Representing and Traversing Chemical Space.

Creating a successful small molecule drug is a challenging multiparameter optimization problem in an effectively infinite space of possible molecules. Generative models have emerged as powerful tools for traversing data manifolds composed of images, sounds, and text and offer an opportunity to dramatically improve the drug discovery and design process. To create generative optimization methods that are more useful than brute-force molecular generation and filtering via virtual screening, we propose that four integrated features are necessary: large, quantitative data sets of molecular structure and activity, an invertible vector representation of realistic accessible molecules, smooth and differentiable regressors that quantify uncertainty, and algorithms to simultaneously optimize properties of interest. Over the course of 12 months, Terray Therapeutics has collected a data set of 2 billion quantitative binding measurements of small molecules to therapeutic targets, which directly motivates multiparameter generative optimization of molecules conditioned on these data. To this end, we present contrastive optimization for accelerated therapeutic inference (COATI), a pretrained, multimodal encoder-decoder model of druglike chemical space. COATI is constructed without any human biasing of features, using contrastive learning from text and 3D representations of molecules to allow for downstream use with structural models. We demonstrate that COATI possesses many of the desired properties of universal molecular embedding: fixed-dimension, invertibility, autoencoding, accurate regression, and low computation cost. Finally, we present a novel metadynamics algorithm for generative optimization using a small subset of our proprietary data collected for a model protein, carbonic anhydrase, designing molecules that satisfy the multiparameter optimization task of potency, solubility, and drug likeness. This work sets the stage for fully integrated generative molecular design and optimization for small molecules.

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.

Evaluating Scalable Supervised Learning for Synthesize-on-Demand Chemical Libraries.

Traditional small-molecule drug discovery is a time-consuming and costly endeavor. High-throughput chemical screening can only assess a tiny fraction of drug-like chemical space. The strong predictive power of modern machine-learning methods for virtual chemical screening enables training models on known active and inactive compounds and extrapolating to much larger chemical libraries. However, there has been limited experimental validation of these methods in practical applications on large commercially available or synthesize-on-demand chemical libraries. Through a prospective evaluation with the bacterial protein-protein interaction PriA-SSB, we demonstrate that ligand-based virtual screening can identify many active compounds in large commercial libraries. We use cross-validation to compare different types of supervised learning models and select a random forest (RF) classifier as the best model for this target. When predicting the activity of more than 8 million compounds from Aldrich Market Select, the RF substantially outperforms a naïve baseline based on chemical structure similarity. 48% of the RF's 701 selected compounds are active. The RF model easily scales to score one billion compounds from the synthesize-on-demand Enamine REAL database. We tested 68 chemically diverse top predictions from Enamine REAL and observed 31 hits (46%), including one with an IC50 value of 1.3 μM.

DrugEx: Deep Learning Models and Tools for Exploration of Drug-Like Chemical Space.

The discovery of novel molecules with desirable properties is a classic challenge in medicinal chemistry. With the recent advancements of machine learning, there has been a surge of de novo drug design tools. However, few resources exist that are user-friendly as well as easily customizable. In this application note, we present the new versatile open-source software package DrugEx for multiobjective reinforcement learning. This package contains the consolidated and redesigned scripts from the prior DrugEx papers including multiple generator architectures, a variety of scoring tools, and multiobjective optimization methods. It has a flexible application programming interface and can readily be used via the command line interface or the graphical user interface GenUI. The DrugEx package is publicly available at https://github.com/CDDLeiden/DrugEx.

Accessing three-dimensional molecular diversity through benzylic C-H cross-coupling.

Pharmaceutical and agrochemical discovery efforts rely on robust methods for chemical synthesis that rapidly access diverse molecules1,2. Cross-coupling reactions are the most widely used synthetic methods3, but these methods typically form bonds to C(sp2)-hybridized carbon atoms (e.g., amide coupling, biaryl coupling) and lead to a prevalence of "flat" molecular structures with suboptimal physicochemical and topological properties4. Benzylic C(sp3)-H cross-coupling methods offer an appealing strategy to address this limitation by directly forming bonds to C(sp3)-hybridized carbon atoms, and emerging methods exhibit synthetic versatility that rivals conventional cross-coupling methods to access products with drug-like properties. Here, we use a virtual library of >350,000 benzylic ethers and ureas derived from benzylic C-H cross-coupling to test the widely held view that coupling at C(sp3)-hybridized carbon atoms affords products with improved three-dimensionality. The results show that the conformational rigidity of the benzylic scaffold strongly influences the product dimensionality. Products derived from flexible scaffolds often exhibit little or no improvement in three-dimensionality, unless they adopt higher energy conformations. This outcome introduces an important consideration when designing routes to topologically diverse molecular libraries. The concepts elaborated herein are validated experimentally through an informatics-guided synthesis of selected targets and the use of high-throughput experimentation to prepare a library of three-dimensional products that are broadly distributed across drug-like chemical space.

Past, Present, and Future Perspectives on Computer-Aided Drug Design Methodologies.

The application of computational approaches in drug discovery has been consolidated in the last decades. These families of techniques are usually grouped under the common name of "computer-aided drug design" (CADD), and they now constitute one of the pillars in the pharmaceutical discovery pipelines in many academic and industrial environments. Their implementation has been demonstrated to tremendously improve the speed of the early discovery steps, allowing for the proficient and rational choice of proper compounds for a desired therapeutic need among the extreme vastness of the drug-like chemical space. Moreover, the application of CADD approaches allows the rationalization of biochemical and interactive processes of pharmaceutical interest at the molecular level. Because of this, computational tools are now extensively used also in the field of rational 3D design and optimization of chemical entities starting from the structural information of the targets, which can be experimentally resolved or can also be obtained with other computer-based techniques. In this work, we revised the state-of-the-art computer-aided drug design methods, focusing on their application in different scenarios of pharmaceutical and biological interest, not only highlighting their great potential and their benefits, but also discussing their actual limitations and eventual weaknesses. This work can be considered a brief overview of computational methods for drug discovery.

DrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learning

Rational drug design often starts from specific scaffolds to which side chains/substituents are added or modified due to the large drug-like chemical space available to search for novel drug-like molecules. With the rapid growth of deep learning in drug discovery, a variety of effective approaches have been developed for de novo drug design. In previous work we proposed a method named DrugEx, which can be applied in polypharmacology based on multi-objective deep reinforcement learning. However, the previous version is trained under fixed objectives and does not allow users to input any prior information (i.e. a desired scaffold). In order to improve the general applicability, we updated DrugEx to design drug molecules based on scaffolds which consist of multiple fragments provided by users. Here, a Transformer model was employed to generate molecular structures. The Transformer is a multi-head self-attention deep learning model containing an encoder to receive scaffolds as input and a decoder to generate molecules as output. In order to deal with the graph representation of molecules a novel positional encoding for each atom and bond based on an adjacency matrix was proposed, extending the architecture of the Transformer. The graph Transformer model contains growing and connecting procedures for molecule generation starting from a given scaffold based on fragments. Moreover, the generator was trained under a reinforcement learning framework to increase the number of desired ligands. As a proof of concept, the method was applied to design ligands for the adenosine A2A receptor (A2AAR) and compared with SMILES-based methods. The results show that 100% of the generated molecules are valid and most of them had a high predicted affinity value towards A2AAR with given scaffolds.

Explore drug-like space with deep generative models.

The process of design/discovery of drugs involves the identification and design of novel molecules that have the desired properties and bind well to a given disease-relevant target. One of the main challenges to effectively identify potential drug candidates is to explore the vast drug-like chemical space to find novel chemical structures with desired physicochemical properties and biological characteristics. Moreover, the chemical space of currently available molecular libraries is only a small fraction of the total possible drug-like chemical space. Deep molecular generative models have received much attention and provide an alternative approach to the design and discovery of molecules. To efficiently explore the drug-like space, we first constructed the drug-like dataset and then performed the generative design of drug-like molecules using a Conditional Randomized Transformer approach with the molecular access system (MACCS) fingerprint as a condition and compared it with previously published molecular generative models. The results show that the deep molecular generative model explores the wider drug-like chemical space. The generated drug-like molecules share the chemical space with known drugs, and the drug-like space captured by the combination of quantitative estimation of drug-likeness (QED) and quantitative estimate of protein-protein interaction targeting drug-likeness (QEPPI) can cover a larger drug-like space. Finally, we show the potential application of the model in design of inhibitors of MDM2-p53 protein-protein interaction. Our results demonstrate the potential application of deep molecular generative models for guided exploration in drug-like chemical space and molecular design.

Recent Advances in the Synthesis of Nitrogen Heterocycles Using β-Nitrostyrenes as Substrates

Abstract:: The exploration of synthetic methodologies that allow rapid access to a wide variety of N-heterocycles is of critical importance to the medicinal chemist as it provides the ability to expand the available drug-like chemical space and drives more efficient drug discovery programs. β-Nitrostyrenes, as unique active intermediates, have been widely applied in synthetic organic chemistry because of their versatile utility as pharmaceutical agents and agrochemicals. In this review, we summarize the recent development and application of the elegant and efficient methods that enable the concise synthesis of N-heterocycles from β-nitrostyrenes and various partners in a step- and atom-economic manner, including cascade reactions, C-H activation, regio- and stereoselective syntheses, as well as other novel syntheses, which will potentially provide useful insights for further exploring and designing novel reactions.

SuperNatural 3.0-a database of natural products and natural product-based derivatives.

Natural products (NPs) are single chemical compounds, substances or mixtures produced by a living organism - found in nature. Evolutionarily, NPs have been used as healing agents since thousands of years and still today continue to be the most important source of new potential therapeutic preparations. Natural products have played a key role in modern drug discovery for several diseases. Furthermore, following consumers' increasing demand for natural food ingredients, many efforts have been made to discover natural low-calorie sweeteners in recent years. SuperNatural 3.0 is a freely available database of natural products and derivatives. The updated version contains 449 058 natural compounds along with their structural and physicochemical information. Additionally, information on pathways, mechanism of action, toxicity, vendor information if available, drug-like chemical space prediction for several diseases as antiviral, antibacterial, antimalarial, anticancer, and target specific cells like the central nervous system (CNS) are also provided for the natural compounds. The updated version of the database also provides a valuable pool of natural compounds in which potential highly sweet compounds are expected to be found. The possible taste profile of the natural compounds was predicted using our published VirtualTaste models. The SuperNatural 3.0 database is freely available via http://bioinf-applied.charite.de/supernatural_3, without any login or registration.

Overlap of On-demand Ultra-large Combinatorial Spaces with On-the-shelf Drug-like Libraries.

On-demand combinatorial spaces are shifting paradigms in early drug discovery, by considerably increasing the searchable chemical space to several billions of compounds while securing their synthetic accessibility. We here systematically compared the on-the-shelf available drug-like chemical space (9 million compounds) to three on-demand ultra-large (ODUL) combinatorial fragment spaces (REAL, CHEMriya, GalaXi) covering 32 billion of readily accessible molecules. Surprisingly, only one space (REAL) intersects almost entirely the currently available drug-like space, suggesting that it is the only ODUL widely suitable for in-stock hit expansion. Of course, expanding a preliminary ODUL hit in the same chemical space is the best possible strategy to rapidly generate structure-activity relationships. All three spaces remain well suited to early hit finding initiatives since they all provide numerous unique scaffolds that are not described by on-the shelf collections.

Coverage Score: A Model Agnostic Method to Efficiently Explore Chemical Space.

Selecting the most appropriate compounds to synthesize and test is a vital aspect of drug discovery. Methods like clustering and diversity present weaknesses in selecting the optimal sets for information gain. Active learning techniques often rely on an initial model and computationally expensive semi-supervised batch selection. Herein, we describe a new subset-based selection method, Coverage Score, that combines Bayesian statistics and information entropy to balance representation and diversity to select a maximally informative subset. Coverage Score can be influenced by prior selections and desirable properties. In this paper, subsets selected through Coverage Score are compared against subsets selected through model-independent and model-dependent techniques for several datasets. In drug-like chemical space, Coverage Score consistently selects subsets that lead to more accurate predictions compared to other selection methods. Subsets selected through Coverage Score produced Random Forest models that have a root-mean-square-error up to 12.8% lower than subsets selected at random and can retain up to 99% of the structural dissimilarity of a diversity selection.

De Novo Molecule Design Using Molecular Generative Models Constrained by Ligand-Protein Interactions.

In recent years, molecular deep generative models have attracted much attention for its application in de novo drug design. The data-driven molecular deep generative model approximates the high dimensional distribution of the chemical space through learning from a large number of molecular structural data. So far, most of the molecular generative models rely on purely 2D ligand information in structure generation. Here, we propose a novel molecular deep generative model which adopts a recurrent neural network architecture coupled with a ligand-protein interaction fingerprint as constraints. The fingerprint was constructed on ligand docking poses and represents the 3D binding mode of ligands in the protein pocket. In the current work, generative models constrained with interaction fingerprints were trained and compared with normal RNN models. It has been shown that models trained with constraints of ligand-protein interaction fingerprint have a clear tendency to generating compounds maintaining similar binding modes. Our results demonstrate the potential application of the interaction fingerprint-constrained generative model for the targeted molecule generation and guided exploration on the drug-like chemical space.

Palladium-Mediated C-N Coupling of DNA-Conjugated (Hetero)aryl Halides with Aliphatic and (Hetero)aromatic Amines.

DNA-encoded chemical library (DEL) screens are a powerful hit generation tool in drug discovery, but the diversity of DEL chemical matter is dependent on developing robust reaction conditions that may be used on hundreds to millions of substrate combinations and that are compatible with the platform. Here, we disclose the first report of a general, aqueous, DNA-compatible C-N coupling condition that can now couple aliphatic amines, in addition to (hetero)aromatic amines, with a variety of (hetero)aryl iodides, bromides, and chlorides. The reported BippyPhos-Pd(OAc)2 catalyst system has a wide substrate scope for both coupling partners, is operationally feasible for large scale DEL productions, uses common DEL building block solution stocks, and enables an expansion of DEL-accessible, drug-like chemical space.

It all clicks together: In silico drug discovery becoming mainstream

It all clicks together: In silico drug discovery becoming mainstream

TorsionNet: A Deep Neural Network to Rapidly Predict Small-Molecule Torsional Energy Profiles with the Accuracy of Quantum Mechanics.

Fast and accurate assessment of small-molecule dihedral energetics is crucial for molecular design and optimization in medicinal chemistry. Yet, accurate prediction of torsion energy profiles remains challenging as the current molecular mechanics (MM) methods are limited by insufficient coverage of drug-like chemical space and accurate quantum mechanical (QM) methods are too expensive. To address this limitation, we introduce TorsionNet, a deep neural network (DNN) model specifically developed to predict small-molecule torsion energy profiles with QM-level accuracy. We applied active learning to identify nearly 50k fragments (with elements H, C, N, O, F, S, and Cl) that maximized the coverage of our corporate compound library and leveraged massively parallel cloud computing resources for density functional theory (DFT) torsion scans of these fragments, generating a training data set of 1.2 million DFT energies. After training TorsionNet on this data set, we obtain a model that can rapidly predict the torsion energy profile of typical drug-like fragments with DFT-level accuracy. Importantly, our method also provides an uncertainty estimate for the predicted profiles without any additional calculations. In this report, we show that TorsionNet can accurately identify the preferred dihedral geometries observed in crystal structures. Our TorsionNet-based analysis of a diverse set of protein-ligand complexes with measured binding affinity shows a strong association between high ligand strain and low potency. We also present practical applications of TorsionNet that demonstrate how consideration of DNN-based strain energy leads to substantial improvement in existing lead discovery and design workflows. TorsionNet500, a benchmark data set comprising 500 chemically diverse fragments with DFT torsion profiles (12k MM- and DFT-optimized geometries and energies), has been created and is made publicly available.

De Novo Molecule Design Through the Molecular Generative Model Conditioned by 3D Information of Protein Binding Sites.

De novo molecule design through the molecular generative model has gained increasing attention in recent years. Here, a novel generative model was proposed by integrating the three-dimensional (3D) structural information of the protein binding pocket into the conditional RNN (cRNN) model to control the generation of drug-like molecules. In this model, the composition of the protein binding pocket is effectively characterized through a coarse-grain strategy and the 3D information of the pocket can be represented by the sorted eigenvalues of the Coulomb matrix (EGCM) of the coarse-grained atoms composing the binding pocket. In current work, we used our EGCM method and a previously reported binding pocket descriptor, DeeplyTough, to train cRNN models and evaluated their performance. It has been shown that the model trained with the constraint of protein environment information has a clear tendency on generating compounds with higher similarity to the original X-ray-bound ligand than the normal RNN model and also better docking scores. Our results demonstrate the potential application of the controlled generative model for the targeted molecule generation and guided exploration on the drug-like chemical space.

Azoles containing naphthalene with activity against Gram-positive bacteria: in vitro studies and in silico predictions for flavohemoglobin inhibition

Azoles are first-line drugs used in fungal infections. Topical antifungals, such as miconazole and econazole, are known to be active against Gram-positive bacteria, which was reported to result from bacterial flavohemoglobin (flavoHb) inhibition. Dual antibacterial/antifungal action is believed to have benefits for antimicrobial chemotherapy. In this study, we tested antibacterial effects of an in-house library of naphthalene-bearing azoles, some of which were reported as potent antifungals, in an attempt to find dual-acting hits. Several potent derivatives were obtained against the Gram-positive bacteria, Enterococcus faecalis and Staphylococcus aureus. 9 was active at a minimum inhibitor concentration (MIC) less than 1 µg/ml against E. faecalis and S. aureus, and 10 against S. aureus. 16 was also potent against E. faecalis and S. aureus (MIC = 1 and 2 µg/ml, respectively). Six more were active against S. aureus with MIC ≤ 4 µg/ml. In vitro cytotoxicity studies showed that the active compounds were safe for healthy cells within their MIC ranges. According to the calculated descriptors, the library was found within the drug-like chemical space and free of pan-assay interference compounds (PAINS). Molecular docking studies suggested that the compounds might be bacterial flavohemoglobin (flavoHb) inhibitors and the azole and naphthalene rings were important pharmacophores, which was further supported by pharmacophore modeling study. As a result, the current study presents several non-toxic azole derivatives with antibacterial effects. In addition to their previously reported antifungal properties, they could set a promising starting point for the future design of dual acting antimicrobials. Communicated by Ramaswamy H. Sarma