Future De Novo Drug Design

Generative deep learning enables the discovery of a potent and selective RIPK1 inhibitor

The retrieval of hit/lead compounds with novel scaffolds during early drug development is an important but challenging task. Various generative models have been proposed to create drug-like molecules. However, the capacity of these generative models to design wet-lab-validated and target-specific molecules with novel scaffolds has hardly been verified. We herein propose a generative deep learning (GDL) model, a distribution-learning conditional recurrent neural network (cRNN), to generate tailor-made virtual compound libraries for given biological targets. The GDL model is then applied to RIPK1. Virtual screening against the generated tailor-made compound library and subsequent bioactivity evaluation lead to the discovery of a potent and selective RIPK1 inhibitor with a previously unreported scaffold, RI-962. This compound displays potent in vitro activity in protecting cells from necroptosis, and good in vivo efficacy in two inflammatory models. Collectively, the findings prove the capacity of our GDL model in generating hit/lead compounds with unreported scaffolds, highlighting a great potential of deep learning in drug discovery.

Concepts and applications of chemical fingerprint for hit and lead screening

Molecular fingerprints are used to represent chemical (structural, physicochemical, etc.) properties of large-scale chemical sets in a low computational cost way. They have a prominent role in transforming chemical data sets into consistent input formats (bit strings or numeric values) suitable for in silico approaches. In this review, we summarize and classify common and state-of-the-art fingerprints into eight different types (dictionary based, circular, topological, pharmacophore, protein-ligand interaction, shape based, reinforced, and multi). We also highlight applications of fingerprints in early drug research and development (R&D). Thus, this review provides a guide for the selection of appropriate fingerprints of compounds (or ligand-protein complexes) for use in drug R&D.

Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: State-of-the-arts and future directions

Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML-driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML-powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state-of-the-art of AI/ML-guided CNS drug discovery, focusing on blood-brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.

Advances in de Novo Drug Design: From Conventional to Machine Learning Methods

. De novo drug design is a computational approach that generates novel molecular structures from atomic building blocks with no a priori relationships. Conventional methods include structure-based and ligand-based design, which depend on the properties of the active site of a biological target or its known active binders, respectively. Artificial intelligence, including machine learning, is an emerging field that has positively impacted the drug discovery process. Deep reinforcement learning is a subdivision of machine learning that combines artificial neural networks with reinforcement-learning architectures. This method has successfully been employed to develop novel de novo drug design approaches using a variety of artificial networks including recurrent neural networks, convolutional neural networks, generative adversarial networks, and autoencoders. This review article summarizes advances in de novo drug design, from conventional growth algorithms to advanced machine-learning methodologies and highlights hot topics for further development.

Control of Synthetic Feasibility of Compounds Generated with CReM

Synthetic feasibility of compounds generated with de novo approaches is one of the main issues, which may limit their applicability. Many of the de novo generation approaches do not address this issue. Here, we studied the recently implemented chemically reasonable mutations approach (CReM) and the ways how one could indirectly control synthetic complexity of generated compounds and how this affected the target scores for Guacamol benchmark tasks. We found a clear trade-off between synthetic complexity and target scores and demonstrated that CReM-based solutions were competitive to reference approaches, which were explicitly biased by synthetic feasibility of generated compounds.

Design of novel ROCK inhibitors using fragment-based de novo drug design approach

Rho-associated coiled-coil protein kinase (ROCK) is playing a vital role in the regulation of key cellular events and also responsible for causing several pathological conditions such as cancer, hypertension, Alzheimer's, cerebral vasospasm, and cardiac stroke. Therefore, it has attracted us to target ROCK protein as a potential therapeutic target for combating various diseases. Consequently, we investigated the active site of ROCK I protein and designed novel leads against the target using the de novo evolution drug design approach. Caffeic acid (an aglycone of acteoside) as a scaffold and fragments from 336 reported ROCK inhibitors were used for the design of novel leads. Multiple copy simultaneous search docking was used to identify the suitable fragments to be linked with the scaffold. Basic medicinal chemistry rules, coupled with structural insights generated by docking, led to the design of 7a, 8a, 9a, and 10a as potential ROCK I inhibitors. The designed leads showed better binding than the approved drug fasudil and also interacted with the key hinge region residue Met156 of ROCK I. Further, molecular dynamics (MD) simulation revealed that the protein-ligand complexes were stable and maintained the hydrogen bond with Met156 throughout the MD run. The promising in silico outcomes suggest that the designed compounds could be suitable anti-cancer leads that need to be synthesized and tested in various cancer cell lines. Graphical abstract.

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

Approaching Target Selectivity by De Novo Drug Design

Introduction: The development of drug candidates with a defined selectivity profile and a unique molecular structure is of fundamental interest for drug discovery. In contrast to the costly screening of large substance libraries, the targeted de novo design of a drug by using structural information of either the biological target and/or structure-activity relationship data of active modulators offers an efficient and intellectually appealing alternative. Areas covered: This review provides an overview on the different techniques of de novo drug design (ligand-based drug design, structure-based drug design, and fragment-based drug design) and highlights successful examples of this targeted approach toward selective modulators of therapeutically relevant targets. Expert opinion: De novo drug design has established itself as a very efficient method for the development of potent and selective modulators for a variety of different biological target classes. The ever-growing wealth of structural data on therapeutic targets will certainly further enhance the importance of de novo design for the drug discovery process in the future. However, a consistent use of the terminology of de novo drug design in the scientific literature should be sought.

Diarylcyclopropane hydroxamic acid inhibitors of histone deacetylase 4 designed by combinatorial approach and QM/MM calculations

Inhibitors of histone deacetylase superfamily (HDAC), which induce cell cycle arrest, trigger cell death and reduce angiogenesis appear as promising anti-cancer drugs targeting the epigenetic regulation of gene expression. Approved HDAC inhibitors were found effective against haematological and solid malignancies, other HDACIs are currently in clinical trials for the treatment of neurological diseases or immune disorders. Among those, diarylcyclopropane hydroxamic acids (DCHA) were found to be potent and selective inhibitors of the class IIa HDACs, specifically HDAC4, a pharmacological target for the treatment of Huntington's disease and muscular atrophy. Crystallographic analysis revealed that one of the aryl groups of the DCHA fills the lower specificity pocket of the HDAC4 catalytic site that is specific for the class IIa HDACs. We have used computer-assisted combinatorial chemistry, hybrid quantum mechanics/molecular mechanics (QM/MM) with implicit solvation and QSAR models to optimize DCHA inhibitors and propose more potent DCHA analogues. The QM/MM approach has been selected since the process of inhibitor binding to the catalytic zinc and polar amino acid residues of the deacetylase active site induces considerable rearrangement of electron density of the inhibitor. Virtual combinatorial library consisting of 12180 DCHA analogues was focused by means of structure-based evaluation to form a small combinatorial subset enriched in potentially interesting inhibitor candidates. Two validated QSAR models making use of computed relative binding affinities of the DCHA inhibitors to the HDAC4 (ΔΔG_com^QM/MM) were utilized to estimate the inhibitory potencies of the new analogues. The predicted half-maximal inhibitory concentrations (IC₅₀^pre) of the designed analogues fall into the low nanomolar concentration range and their predicted ADME properties are also favourable. The best designed DCHA analogues contain indazole, phenylpiperidine, phenyloxazole or hydroxypyridine moieties and stabilize bound inhibitors by hydrogen bonds to the catalytic water molecule and backbone carbonyl groups of the deacetylase active site residues. This makes them more potent and more specific inhibitors towards the HDAC4 isoform than the known diarylcyclopropane hydroxamic acids. The analogues are recommended for synthesis and experimental verification of inhibitory potencies in medicinal chemistry laboratories.

Molecular structures enumeration and virtual screening in the chemical space with RetroPath2.0

BACKGROUND

Network generation tools coupled with chemical reaction rules have been mainly developed for synthesis planning and more recently for metabolic engineering. Using the same core algorithm, these tools apply a set of rules to a source set of compounds, stopping when a sink set of compounds has been produced. When using the appropriate sink, source and rules, this core algorithm can be used for a variety of applications beyond those it has been developed for.

RESULTS

Here, we showcase the use of the open source workflow RetroPath2.0. First, we mathematically prove that we can generate all structural isomers of a molecule using a reduced set of reaction rules. We then use this enumeration strategy to screen the chemical space around a set of monomers and predict their glass transition temperatures, as well as around aminoglycosides to search structures maximizing antibacterial activity. We also perform a screening around aminoglycosides with enzymatic reaction rules to ensure biosynthetic accessibility. We finally use our workflow on an E. coli model to complete E. coli metabolome, with novel molecules generated using promiscuous enzymatic reaction rules. These novel molecules are searched on the MS spectra of an E. coli cell lysate interfacing our workflow with OpenMS through the KNIME Analytics Platform.

CONCLUSION

We provide an easy to use and modify, modular, and open-source workflow. We demonstrate its versatility through a variety of use cases including molecular structure enumeration, virtual screening in the chemical space, and metabolome completion. Because it is open source and freely available on MyExperiment.org, workflow community contributions should likely expand further the features of the tool, even beyond the use cases presented in the paper.

Computational Multitarget Drug Design

Designing drugs that can simultaneously interact with multiple targets is a promising approach for treating complicated diseases. Compared to using combinations of single target drugs, multitarget drugs have advantages of higher efficacy, improved safety profile, and simpler administration. Many in silico methods have been developed to approach different aspects of this polypharmacology-guided drug design, particularly for drug repurposing and multitarget drug design. In this review, we summarize recent progress in computational multitarget drug design and discuss their advantages and limitations. Perspectives for future drug development will also be discussed.

Multistep Reaction Based De Novo Drug Design: Generating Synthetically Feasible Design Ideas

We describe a "multistep reaction driven" evolutionary algorithm approach to de novo molecular design. Structures generated by the approach include a proposed synthesis path intended to aid the chemist in assessing the synthetic feasibility of the ideas that are generated. The methodology is independent of how the design ideas are scored, allowing multicriteria drug design to address multiple issues including activity at one or more pharmacological targets, selectivity, physical and ADME properties, and off target liabilities; the methods are compatible with common computer-aided drug discovery "scoring" methodologies such as 2D- and 3D-ligand similarity, docking, desirability functions based on physiochemical properties, and/or predictions from 2D/3D QSAR or machine learning models and combinations thereof to be used to guide design. We have performed experiments to assess the extent to which known drug space can be covered by our approach. Using a library of 88 generic reactions and a database of ∼20 000 reactants, we find that our methods can identify "close" analogs for ∼50% of the known small molecule drugs with molecular weight less than 300. To assess the quality of the in silico generated synthetic pathways, synthesis chemists were asked to rate the viability of synthesis pathways: both "real" and in silico generated. In silico reaction schemes generated by our methods were rated as very plausible with scores similar to known literature synthesis schemes.

In silico methods to address polypharmacology: current status, applications and future perspectives

Polypharmacology, a new paradigm in drug discovery that focuses on multi-target drugs (MTDs), has potential application for drug repurposing, the process of finding new uses for existing approved drugs, prediction of off-target toxicities and rational design of MTDs. In this scenario, computational strategies have demonstrated great potential in predicting polypharmacology and in facilitating drug repurposing. Here, we provide a comprehensive overview of various computational approaches that enable the prediction and analysis of in vitro and in vivo drug-response phenotypes and outline their potential for drug discovery. We give an outlook on the latest advances in rational design of MTDs and discuss possible future directions of algorithm development in this field.

SCUBIDOO: A Large yet Screenable and Easily Searchable Database of Computationally Created Chemical Compounds Optimized toward High Likelihood of Synthetic Tractability

De novo drug design is widely assisted by computational approaches that enable the generation of a tremendous amount of new virtual molecules within a short time frame. While the novelty of the computationally generated compounds can easily be assessed, such approaches often neglect the synthetic feasibility of the molecules, thus creating a potential hurdle that can be a barrier to further investigation. Therefore, we have developed SCUBIDOO, a freely accessible database concept that currently holds 21 million virtual products originating from a small library of building blocks and a collection of robust organic reactions. This large data set was reduced to three representative and computationally tractable samples denoted as S, M, and L, containing 9994, 99,977, and 999,794 products, respectively. These small sets are useful as starting points for ligand identification and optimization projects. The generated products come with synthesis instructions and alerts of possible side reactions, and we show that they exhibit drug-like properties while still extending into unexplored quadrants of chemical space, thus suggesting novelty. We show multiple examples that demonstrate how SCUBIDOO can facilitate the search around initial hits. This database might be a useful idea generator for early ligand discovery projects since it allows a focus on those molecules that are likely to be synthetically feasible and can therefore be studied further. Together with its modular building block construction principle, this database is also suitable for structure-activity relationship studies or fragment-growing strategies.

Considerations of Protein Subpockets in Fragment-Based Drug Design

While the fragment-based drug design approach continues to gain importance, gaps in the tools and methods available in the identification and accurate utilization of protein subpockets have limited the scope. The importance of these features of small molecule-protein recognition is highlighted with several examples. A generalized solution for the identification of subpockets and corresponding chemical fragments remains elusive, but there are numerous advancements in methods that can be used in combination to address subpockets. Finally, additional examples of approaches that consider the relative importance of small-molecule co-dependence of protein conformations are highlighted to emphasize an increased significance of subpockets, especially at protein interfaces.