LigBuilder V3: A Multi-Target de novo Drug Design Approach

Toward structure-multiple activity relationships (SMARts) using computational approaches: A polypharmacological perspective

In the current era of biological big data, which are rapidly populating the biological chemical space, in silico polypharmacology drug design approaches help to decode structure-multiple activity relationships (SMARts). Current computational methods can predict or categorize multiple properties simultaneously, which aids the generation, identification, curation, prioritization, optimization, and repurposing of molecules. Computational methods have generated opportunities and challenges in medicinal chemistry, pharmacology, food chemistry, toxicology, bioinformatics, and chemoinformatics. It is anticipated that computer-guided SMARts could contribute to the full automatization of drug design and drug repurposing campaigns, facilitating the prediction of new biological targets, side and off-target effects, and drug-drug interactions.

Recent Advances in Automated Structure-Based De Novo Drug Design

As the number of determined and predicted protein structures and the size of druglike 'make-on-demand' libraries soar, the time-consuming nature of structure-based computer-aided drug design calls for innovative computational algorithms. De novo drug design introduces in silico heuristics to accelerate searching in the vast chemical space. This review focuses on recent advances in structure-based de novo drug design, ranging from conventional fragment-based methods, evolutionary algorithms, and Metropolis Monte Carlo methods to deep generative models. Due to the historical limitation of de novo drug design generating readily available drug-like molecules, we highlight the synthetic accessibility efforts in each category and the benchmarking strategies taken to validate the proposed framework.

MARS Plus: An Improved Molecular Design Tool for Complex Compounds Involving Ionic, Stereo, and Cis-Trans Isomeric Structures

MARS (Molecular Assembling and Representation Suite) (Hsu et al. J. Chem. Inf. Model. 2019, 59, 3703-3713) is a toolbox for the molecular design of organic molecules. MARS uses integer arrays to represent the elements and connectivity between elements of a molecule. It provides a collection of operations to manipulate the elemental composition and connectivity of a molecule (or a pair of molecules), enabling the creation of novel chemical compounds. In this work, the original MARS is extended to handle complex molecular structures, including geometric (cis-trans) isomers, stereo isomers, cyclic compounds, and ionic species. The extended version of MARS, referred to as MARS+, has a more comprehensive coverage of the chemical space and therefore can explore molecules with a greater chemical and physical diversity. Compared to other molecular design tools, MARS+ is designed to perform all possible manipulations on a given molecule or a pair of molecules. Molecular structure manipulation can be conducted in either a controlled or a random fashion. Furthermore, every structure manipulation has a counterpart so that the operation can be reversed. Nearly any possible chemical structure can be generated with MARS+ via a combination of molecular operations. The capabilities of MARS+ are examined by the design of new ionic liquids (ILs). The results show that MARS+ is a useful tool for computer-aided molecular design (CAMD) and molecular structure enumeration.

Dual Targeting of DNA Damage Response Proteins Implicated in Cancer Radioresistance

Ionizing radiation can induce different types of DNA lesions, leading to genomic instability and ultimately cell death. Radiation therapy or radiotherapy, a major modality in cancer treatment, harnesses the genotoxic potential of radiation to target and destroy cancer cells. Nevertheless, cancer cells have the capacity to develop resistance to radiation treatment (radioresistance), which poses a major obstacle in the effective management of cancer. It has been shown that administration of platinum-based drugs to cancer patients can increase tumor radiosensitivity, but despite this, it is associated with severe adverse effects. Several lines of evidence support that activation of the DNA damage response and repair machinery in the irradiated cancer cells enhances radioresistance and cellular survival through the efficient repair of DNA lesions. Therefore, targeting of key DNA damage repair factors would render cancer cells vulnerable to the irradiation effects, increase cancer cell killing, and reduce the risk of side effects on healthy tissue. Herein, we have employed a computer-aided drug design approach for generating ab initio a chemical compound with drug-like properties potentially targeting two proteins implicated in multiple DNA repair pathways. The findings of this study could be taken into consideration in clinical decision-making in terms of co-administering radiation with DNA damage repair factor-based drugs.

Fast fragment and compound screening pipeline at the Swiss Light Source

Crystallography-based fragment screening is a highly effective technique employed in structure-based drug discovery to expand the range of lead development opportunities. It allows screening and sorting of weakly binding, low molecular mass fragments, which can be developed into larger high-affinity lead compounds. Technical improvements at synchrotron beamlines, design of innovative libraries mapping chemical space efficiently, effective soaking methods and enhanced data analysis have enabled the implementation of high-throughput fragment screening pipelines at multiple synchrotron facilities. This widened access to CBFS beyond the pharma industry has allowed academic users to rapidly screen large quantities of fragment-soaked protein crystals. The positive outcome of a CBFS campaign is a set of structures that present the three-dimensional arrangement of fragment-protein complexes in detail, thereby providing information on the location and the mode of interaction of bound fragments. Through this review, we provide users with a comprehensive guide that sets clear expectations before embarking on a crystallography-based fragment screening campaign. We present a list of essential pre-requirements that must be assessed, including the suitability of your current crystal system for a fragment screening campaign. Furthermore, we extensively discuss the available methodological options, addressing their limitations and providing strategies to overcome them. Additionally, we provide a brief perspective on how to proceed once hits are obtained. Notably, we emphasize the solutions we have implemented for instrumentation and software development within our Fast Fragment and Compound Screening pipeline. We also highlight third-party software options that can be utilized for rapid refinement and hit assessment.

Construction of Histone-Protein Complex Structures by Peptide Growing

The structures of histone complexes are master keys to epigenetics. Linear histone peptide tails often bind to shallow pockets of reader proteins via weak interactions, rendering their structure determination challenging. In the present study, a new protocol, PepGrow, is introduced. PepGrow uses docked histone fragments as seeds and grows the full peptide tails in the reader-binding pocket, producing atomic-resolution structures of histone-reader complexes. PepGrow is able to handle the flexibility of histone peptides, and it is demonstrated to be more efficient than linking pre-docked peptide fragments. The new protocol combines the advantages of popular program packages and allows fast generation of solution structures. AutoDock, a force-field-based program, is used to supply the docked peptide fragments used as structural seeds, and the building algorithm of Modeller is adopted and tested as a peptide growing engine. The performance of PepGrow is compared to ten other docking methods, and it is concluded that in situ growing of a ligand from a seed is a viable strategy for the production of complex structures of histone peptides at atomic resolution.

Linkers in fragment-based drug design: an overview of the literature

INTRODUCTION

In fragment-based drug design, fragment linking is a popular strategy where two fragments binding to different sub-pockets of a target are linked together. This attractive method remains challenging especially due to the design of ideal linkers.

AREAS COVERED

The authors review the types of linkers and chemical reactions commonly used to the synthesis of linkers, including those utilized in protein-templated fragment self-assembly, where fragments are directly linked in the presence of the protein. Finally, they detail computational workflows and software including generative models that have been developed for fragment linking.

EXPERT OPINION

The authors believe that fragment linking offers key advantages for compound design, particularly for the design of bivalent inhibitors linking two distinct pockets of the same or different subunits. On the other hand, more studies are needed to increase the potential of protein-templated approaches in FBDD. Important computational tools such as structure-based de novo software are emerging to select suitable linkers. Fragment linking will undoubtedly benefit from developments in computational approaches and machine learning models.

Artificial intelligence in multi-objective drug design

The factors determining a drug's success are manifold, making de novo drug design an inherently multi-objective optimisation (MOO) problem. With the advent of machine learning and optimisation methods, the field of multi-objective compound design has seen a rapid increase in developments and applications. Population-based metaheuris-tics and deep reinforcement learning are the most commonly used artificial intelligence methods in the field, but recently conditional learning methods are gaining popularity. The former approaches are coupled with a MOO strat-egy which is most commonly an aggregation function, but Pareto-based strategies are widespread too. Besides these and conditional learning, various innovative approaches to tackle MOO in drug design have been proposed. Here we provide a brief overview of the field and the latest innovations.

Docking-based generative approaches in the search for new drug candidates

Despite the popularity of virtual screening (VS) of existing compound libraries, the search for new potential drug candidates also takes advantage of generative protocols, where new compound suggestions are enumerated using various algorithms. To increase the activity potency of generative approaches, they have recently been coupled with molecular docking, a leading methodology of structure-based drug design (SBDD). In this review, we summarize progress since docking-based generative models emerged. We propose a new taxonomy for these methods and discuss their importance for the field of computer-aided drug design (CADD). In addition, we discuss the most promising directions for the further development of generative protocols coupled with docking.

A Comprehensive Survey of Prospective Structure-Based Virtual Screening for Early Drug Discovery in the Past Fifteen Years

Structure-based virtual screening (SBVS), also known as molecular docking, has been increasingly applied to discover small-molecule ligands based on the protein structures in the early stage of drug discovery. In this review, we comprehensively surveyed the prospective applications of molecular docking judged by solid experimental validations in the literature over the past fifteen years. Herein, we systematically analyzed the novelty of the targets and the docking hits, practical protocols of docking screening, and the following experimental validations. Among the 419 case studies we reviewed, most virtual screenings were carried out on widely studied targets, and only 22% were on less-explored new targets. Regarding docking software, GLIDE is the most popular one used in molecular docking, while the DOCK 3 series showed a strong capacity for large-scale virtual screening. Besides, the majority of identified hits are promising in structural novelty and one-quarter of the hits showed better potency than 1 μM, indicating that the primary advantage of SBVS is to discover new chemotypes rather than highly potent compounds. Furthermore, in most studies, only in vitro bioassays were carried out to validate the docking hits, which might limit the further characterization and development of the identified active compounds. Finally, several successful stories of SBVS with extensive experimental validations have been highlighted, which provide unique insights into future SBVS drug discovery campaigns.

Pharmacological insights into Chukrasia velutina bark: Experimental and computer-aided approaches

BACKGROUND

Chukrasia velutina is an enthnomedicinally used plant reported to have significant medicinal values. The present study aimed to explore the pharmacological activities of bark methanol extract using in vitro, in vivo and in silico models.

METHODS

The study was designed to investigate the pharmacological effects of methanol extract of Chukrasia velutina bark (MECVB) through in vitro, in vivo and in silico assays. Analgesic activity was tested using formalin-induced nociception and acetic acid-induced writhing assays while the antipyretic effect was tested using yeast-induced hyperthermia in mice model. The antioxidant effect was tested using the DPPH and reducing power assay and the cytotoxic screening was tested using the brine shrimp lethality bioassay. In addition, in silico studies were conducted using computer aided methods.

RESULTS

In the acetic acid-induced writhing assay, the extract showed 28.36% and 56.16% inhibition of writhing for doses of 200 and 400 mg/kg, respectively. Moreover, a dose-dependent formalin-induced licking response was observed in both early and late phase. In yeast-induced pyrexia, the MECVB exhibited (p < 0.05) antipyretic effect. The extract demonstrated an IC₅₀ value of 78.86 μg/ml compared with ascorbic acid (IC₅₀ 23.53 μg/ml) in the DPPH scavenging assay. The compounds sitosterol, 5,7-dimethoxycoumarin and scopoletin were seen be effective in molecular docking scores against COX-I (2OYE), COX-II (6COX) and human peroxiredoxin 5 (1HD2). In ADME/T analysis, 5,7-dimethoxycoumarin and scopoletin satisfied Lipinski's rule of five and thus are potential drug candidates.

CONCLUSION

The bark of Chukrasia velutina showed significant analgesic and antipyretic properties and is a potential source of natural anti-oxidative agents.

Discovery of the Cryptic Sites of SARS-CoV-2 Papain-like Protease and Analysis of Its Druggability

In late 2019, a new coronavirus (CoV) caused the outbreak of a deadly respiratory disease, resulting in the COVID-19 pandemic. In view of the ongoing pandemic, there is an immediate need to find drugs to treat patients. SARS-CoV-2 papain-like cysteine protease (PLpro) not only plays an important role in the pathogenesis of the virus but is also a target protein for the development of inhibitor drugs. Therefore, to develop targeted inhibitors, it is necessary to analyse and verify PLpro sites and explore whether there are other cryptic binding pockets with better activity. In this study, first, we detected the site of the whole PLpro protein by sitemap of Schrödinger (version 2018), the cavity of LigBuilder V3, and DeepSite, and roughly judged the possible activated binding site area. Then, we used the mixed solvent dynamics simulation (MixMD) of probe molecules to induce conformational changes in the protein to find the possible cryptic active sites. Finally, the TRAPP method was used to predict the druggability of cryptic pockets and analyse the changes in the physicochemical properties of residues around these sites. This work will help promote the research of SARS-CoV-2 PLpro inhibitors.

Identification of Novel Ribonucleotide Reductase Inhibitors for Therapeutic Application in Bile Tract Cancer: An Advanced Pharmacoinformatics Study

Biliary tract cancer (BTC) is constituted by a heterogeneous group of malignant tumors that may develop in the biliary tract, and it is the second most common liver cancer. Human ribonucleotide reductase M1 (hRRM1) has already been proven to be a potential BTC target. In the current study, a de novo design approach was used to generate novel and effective chemical therapeutics for BTC. A set of comprehensive pharmacoinformatics approaches was implemented and, finally, seventeen potential molecules were found to be effective for the modulation of hRRM1 activity. Molecular docking, negative image-based ShaEP scoring, absolute binding free energy, in silico pharmacokinetics, and toxicity assessments corroborated the potentiality of the selected molecules. Almost all molecules showed higher affinity in comparison to gemcitabine and naphthyl salicylic acyl hydrazone (NSAH). On binding interaction analysis, a number of critical amino acids was found to hold the molecules at the active site cavity. The molecular dynamics (MD) simulation study also indicated the stability between protein and ligands. High negative MM-GBSA (molecular mechanics generalized Born and surface area) binding free energy indicated the potentiality of the molecules. Therefore, the proposed molecules might have the potential to be effective therapeutics for the management of BTC.

The discovery of multi-target compounds with anti-inflammation activity from traditional Chinese medicine by TCM-target effects relationship spectrum

ETHNOPHARMACOLOGICAL RELEVANCE

Rhei Radix et Rhizoma, Lonicerae Japonicae Flos and Zingiberis Rhizoma was widely used in the treatment of inflammatory disease. The discovery of new multi-target compounds for new drug from the TCM was a possible direction.

AIM OF THE STUDY

Multi-target compounds screening based on polypharmacology was an effective method. As an interdisciplinary field, polypharmacology screen multi-target compounds by various methods. So, a flexible screening framework to avoid the disadvantage of single methods is considered to have great significance.

MATERIALS AND METHODS

The research propose a common framework called Traditional Chinese medicine target-effect relationship spectrum (TCM-TERS). TCM-TERS was constructed based on the pharmacophore and molecular docking models, which provided predicted activity by compounds screening. TCM-TERS merge the results of different models and visualize the targeted activity of each compounds. Then the TCM-TERS were analyzed by the analytic hierarchy process and active components were chosen by the contributing factors. The activity of components was verified on the RAW264.7 by RT-PCR.

RESULTS

This article constructed TCM-TERS of Rhei Radix et Rhizoma, Lonicerae Japonicae Flos and Zingiberis Rhizoma with the COX-2, mPGES-1, 5-LOX and SPLA2-IIA. Seven compounds were chosen with multiple targeted activity based on the TCM-TERS, which showed remarkable activity in RT-PCR.

CONCLUSION

The TCM-TERS was an efficient interdisciplinary method for drug discovery of the TCM, which provide a flexible method to the researcher that can screen specific compounds with multiple screening methods.

Design of SARS-CoV-2 Main Protease Inhibitors Using Artificial Intelligence and Molecular Dynamic Simulations

Drug design is a time-consuming and cumbersome process due to the vast search space of drug-like molecules and the difficulty of investigating atomic and electronic interactions. The present paper proposes a computational drug design workflow that combines artificial intelligence (AI) methods, i.e., an evolutionary algorithm and artificial neural network model, and molecular dynamics (MD) simulations to design and evaluate potential drug candidates. For the purpose of illustration, the proposed workflow was applied to design drug candidates against the main protease of severe acute respiratory syndrome coronavirus 2. From the ∼140,000 molecules designed using AI methods, MD analysis identified two molecules as potential drug candidates.

Advances and Challenges in De Novo Drug Design Using Three-Dimensional Deep Generative Models

A persistent goal for de novo drug design is to generate novel chemical compounds with desirable properties in a labor-, time-, and cost-efficient manner. Deep generative models provide alternative routes to this goal. Numerous model architectures and optimization strategies have been explored in recent years, most of which have been developed to generate two-dimensional molecular structures. Some generative models aiming at three-dimensional (3D) molecule generation have also been proposed, gaining attention for their unique advantages and potential to directly design drug-like molecules in a target-conditioning manner. This review highlights current developments in 3D molecular generative models combined with deep learning and discusses future directions for de novo drug design.

Systemic evolutionary chemical space exploration for drug discovery

Chemical space exploration is a major task of the hit-finding process during the pursuit of novel chemical entities. Compared with other screening technologies, computational de novo design has become a popular approach to overcome the limitation of current chemical libraries. Here, we reported a de novo design platform named systemic evolutionary chemical space explorer (SECSE). The platform was conceptually inspired by fragment-based drug design, that miniaturized a “lego-building” process within the pocket of a certain target. The key to virtual hits generation was then turned into a computational search problem. To enhance search and optimization, human intelligence and deep learning were integrated. Application of SECSE against phosphoglycerate dehydrogenase (PHGDH), proved its potential in finding novel and diverse small molecules that are attractive starting points for further validation. This platform is open-sourced and the code is available at http://github.com/KeenThera/SECSE.

Virtual Screening of Drug-Like Compounds as Potential Inhibitors of the Dengue Virus NS5 Protein

Dengue virus (DENV) is the causative agent of dengue fever. Annually, there are about 400 million new cases of dengue worldwide, and so far there is no specific treatment against this disease. The NS5 protein is the largest and most conserved viral protein among flaviviruses and is considered a therapeutic target of great interest. This study aims to search drug-like compounds for possible inhibitors of the NS5 protein in the four serotypes of DENV. Using a virtual screening from a ∼642,759-compound database, we suggest 18 compounds with NS5 binding and highlight the best compound per region, in the methyltransferase and RNA-dependent RNA polymerase domains. These compounds interact mainly with the amino acids of the catalytic sites and/or are involved in processes of protein activity. The identified compounds presented physicochemical and pharmacological properties of interest for their use as possible drugs; furthermore, we found that some of these compounds do not affect cell viability in Huh-7; therefore, we suggest evaluating these compounds in vitro as candidates in future research.

The Design of Multi-target Drugs to Treat Cardiovascular Diseases: Two (or more) Birds on one Stone

Cardiovascular diseases (CVDs) comprise a group of diseases and disorders of the heart and blood vessels, which together are the number one cause of death worldwide, being associated with multiple genetic and modifiable risk factors, and that may directly arise from different etiologies. For a long time, the search for cardiovascular drugs was based on the old paradigm "one compound - one target", which aims to obtain a highly potent and selective molecule with only one desired molecular target. Although historically successful in the last decades, this approach ignores the multiple causes and the multifactorial nature of CVD's. Thus, over time, treatment strategies for cardiovascular diseases have changed and, currently, pharmacological therapies for CVD are mainly based on the association of two or more drugs to control symptoms and reduce cardiovascular death. In this context, the development of multitarget drugs, i.e, compounds having the ability to act simultaneously at multiple sites, is an attractive and relevant strategy that can be even more advantageous to achieve predictable pharmacokinetic and pharmacodynamics correlations as well as better patient compliance. In this review, we aim to highlight the efforts and rational pharmacological bases for the design of some promising multitargeted compounds to treat important cardiovascular diseases like heart failure, atherosclerosis, acute myocardial infarction, pulmonary arterial hypertension and arrhythmia.

Fragment-to-lead tailored in silico design

Fragment-based drug discovery (FBDD) emerged as a disruptive technology and became established during the last two decades. Its rationality and low entry costs make it appealing, and the numerous examples of approved drugs discovered through FBDD validate the approach. However, FBDD still faces numerous challenges. Perhaps the most important one is the transformation of the initial fragment hits into viable leads. Fragment-to-lead (F2L) optimization is resource-intensive and is therefore limited in the possibilities that can be actively pursued. In silico strategies play an important role in F2L, as they can perform a deeper exploration of chemical space, prioritize molecules with high probabilities of being active and generate non-obvious ideas. Here we provide a critical overview of current in silico strategies in F2L optimization and highlight their remarkable impact. While very effective, most solutions are target- or fragment- specific. We propose that fully integrated in silico strategies, capable of automatically and systematically exploring the fast-growing available chemical space can have a significant impact on accelerating the release of fragment originated drugs.

Novel 2-(Diphenylmethylidene) Malonic Acid Derivatives as Anti-HIV Agents: Molecular Modeling, Synthesis and Biological Evaluation

HIV, the virus that causes AIDS (acquired immunodeficiency syndrome), is one of the world's most severe health and development challenges. In this study, a novel series of 2-(diphenyl methylidene) malonic acid derivatives were designed as triple inhibitors of HIV reverse transcriptase, integrase, and protease. Docking models revealed that the target compounds have appropriate affinities to the active sites of the three HIV key enzymes. The synthesized malonic acid analogs were evaluated for their activities against the HIV virus (NL4-3) in HeLa cells cultures. Among them, compound 3 was the most potent anti-HIV agent with 55.20% inhibition at 10 μM and an EC50 of 8.4 μM. Interestingly, all the synthesized compounds do not show significant cytotoxicity at a concentration of 10 μM. As a result, these compounds may serve as worthy hits for the development of novel anti-HIV-agents.

A Deep-Learning Proteomic-Scale Approach for Drug Design

Computational approaches have accelerated novel therapeutic discovery in recent decades. The Computational Analysis of Novel Drug Opportunities (CANDO) platform for shotgun multitarget therapeutic discovery, repurposing, and design aims to improve their efficacy and safety by employing a holistic approach that computes interaction signatures between every drug/compound and a large library of non-redundant protein structures corresponding to the human proteome fold space. These signatures are compared and analyzed to determine if a given drug/compound is efficacious and safe for a given indication/disease. In this study, we used a deep learning-based autoencoder to first reduce the dimensionality of CANDO-computed drug-proteome interaction signatures. We then employed a reduced conditional variational autoencoder to generate novel drug-like compounds when given a target encoded "objective" signature. Using this approach, we designed compounds to recreate the interaction signatures for twenty approved and experimental drugs and showed that 16/20 designed compounds were predicted to be significantly (p-value ≤ 0.05) more behaviorally similar relative to all corresponding controls, and 20/20 were predicted to be more behaviorally similar relative to a random control. We further observed that redesigns of objectives developed via rational drug design performed significantly better than those derived from natural sources (p-value ≤ 0.05), suggesting that the model learned an abstraction of rational drug design. We also show that the designed compounds are structurally diverse and synthetically feasible when compared to their respective objective drugs despite consistently high predicted behavioral similarity. Finally, we generated new designs that enhanced thirteen drugs/compounds associated with non-small cell lung cancer and anti-aging properties using their predicted proteomic interaction signatures. his study represents a significant step forward in automating holistic therapeutic design with machine learning, enabling the rapid generation of novel, effective, and safe drug leads for any indication.

Structure-based de novo drug design using 3D deep generative models

Deep generative models are attracting much attention in the field of de novo molecule design. Compared to traditional methods, deep generative models can be trained in a fully data-driven way with little requirement for expert knowledge. Although many models have been developed to generate 1D and 2D molecular structures, 3D molecule generation is less explored, and the direct design of drug-like molecules inside target binding sites remains challenging. In this work, we introduce DeepLigBuilder, a novel deep learning-based method for de novo drug design that generates 3D molecular structures in the binding sites of target proteins. We first developed Ligand Neural Network (L-Net), a novel graph generative model for the end-to-end design of chemically and conformationally valid 3D molecules with high drug-likeness. Then, we combined L-Net with Monte Carlo tree search to perform structure-based de novo drug design tasks. In the case study of inhibitor design for the main protease of SARS-CoV-2, DeepLigBuilder suggested a list of drug-like compounds with novel chemical structures, high predicted affinity, and similar binding features to those of known inhibitors. The current version of L-Net was trained on drug-like compounds from ChEMBL, which could be easily extended to other molecular datasets with desired properties based on users' demands and applied in functional molecule generation. Merging deep generative models with atomic-level interaction evaluation, DeepLigBuilder provides a state-of-the-art model for structure-based de novo drug design and lead optimization.

DeepLigBuilder, a novel deep generative model for structure-based de novo drug design, directly generates 3D structures of drug-like compounds in the target binding site.

Advances in the Exploration of the Epigenetic Relevant Chemical Space

Epigenetic drug discovery is a promising avenue to find therapeutic agents for treating several diseases and developing novel chemical probes for research. In order to identify hit and lead compounds, the chemical space has been explored and screened, generating valuable bioactivity information that can be used for multiple purposes such as prediction of the activity of existing chemicals, e.g., small molecules, guiding the design or optimization of compounds, and expanding the epigenetic relevant chemical space. Herein, we review the chemical spaces explored for epigenetic drug discovery and discuss the advances in using structure-activity relationships stored in public chemogenomic databases. We also review current efforts to chart and identify novel regions of the epigenetic relevant chemical space. In particular, we discuss the development and accessibility of two significant types of compound libraries focused on epigenetic targets: commercially available libraries for screening and targeted chemical libraries using de novo design. In this mini-review, we emphasize inhibitors of DNA methyltransferases.

Artificial intelligence to deep learning: machine intelligence approach for drug discovery

Drug designing and development is an important area of research for pharmaceutical companies and chemical scientists. However, low efficacy, off-target delivery, time consumption, and high cost impose a hurdle and challenges that impact drug design and discovery. Further, complex and big data from genomics, proteomics, microarray data, and clinical trials also impose an obstacle in the drug discovery pipeline. Artificial intelligence and machine learning technology play a crucial role in drug discovery and development. In other words, artificial neural networks and deep learning algorithms have modernized the area. Machine learning and deep learning algorithms have been implemented in several drug discovery processes such as peptide synthesis, structure-based virtual screening, ligand-based virtual screening, toxicity prediction, drug monitoring and release, pharmacophore modeling, quantitative structure-activity relationship, drug repositioning, polypharmacology, and physiochemical activity. Evidence from the past strengthens the implementation of artificial intelligence and deep learning in this field. Moreover, novel data mining, curation, and management techniques provided critical support to recently developed modeling algorithms. In summary, artificial intelligence and deep learning advancements provide an excellent opportunity for rational drug design and discovery process, which will eventually impact mankind. The primary concern associated with drug design and development is time consumption and production cost. Further, inefficiency, inaccurate target delivery, and inappropriate dosage are other hurdles that inhibit the process of drug delivery and development. With advancements in technology, computer-aided drug design integrating artificial intelligence algorithms can eliminate the challenges and hurdles of traditional drug design and development. Artificial intelligence is referred to as superset comprising machine learning, whereas machine learning comprises supervised learning, unsupervised learning, and reinforcement learning. Further, deep learning, a subset of machine learning, has been extensively implemented in drug design and development. The artificial neural network, deep neural network, support vector machines, classification and regression, generative adversarial networks, symbolic learning, and meta-learning are examples of the algorithms applied to the drug design and discovery process. Artificial intelligence has been applied to different areas of drug design and development process, such as from peptide synthesis to molecule design, virtual screening to molecular docking, quantitative structure-activity relationship to drug repositioning, protein misfolding to protein-protein interactions, and molecular pathway identification to polypharmacology. Artificial intelligence principles have been applied to the classification of active and inactive, monitoring drug release, pre-clinical and clinical development, primary and secondary drug screening, biomarker development, pharmaceutical manufacturing, bioactivity identification and physiochemical properties, prediction of toxicity, and identification of mode of action.

Allosteric Type and Pathways Are Governed by the Forces of Protein-Ligand Binding

Allostery is central to many cellular processes, by up- or down-regulating target function. However, what determines the allosteric type remains elusive and currently it is impossible to predict whether the allosteric compounds would activate or inhibit target function before experimental studies. We demonstrated that the allosteric type and allosteric pathways are governed by the forces imposed by ligand binding to target protein using the anisotropic network model and developed an allosteric type prediction method (AlloType). AlloType correctly predicted 13 of the 16 allosteric systems in the data set with experimentally determined protein and complex structures as well as verified allosteric types, which was also used to identify allosteric pathways. When applied to glutathione peroxidase 4, a protein with no complex structure information, AlloType could still be able to predict the allosteric type of the recently reported allosteric activators, demonstrating its potential application in designing specific allosteric drugs and uncovering allosteric mechanisms.

Multiple Target Drug Design Using LigBuilder 3

Designing drugs that directly interact with multiple targets is a promising approach for treating complicated diseases. In order to successfully bind to multiple targets of different families and achieve the desired ligand efficiency, multi-target-directed ligands (MTDLs) require a higher level of diversity and complexity. De novo design strategies for creating more diverse chemical entities with desired properties may present an improved approach for developing MTDLs. In this chapter, we describe a computational protocol for developing MTDLs using the first reported multi-target de novo program, LigBuilder 3, which combines a binding site prediction module with de novo drug design and optimization modules. As an illustration of each detailed procedure, we design dual-functional compounds of two well-characterized virus enzymes, HIV protease and reverse transcriptase (PR and RT, respectively), using fragments extracted from known inhibitors. LigBuilder 3 is accessible at http://www.pkumdl.cn/ligbuilder3/ .

Merging Ligand-Based and Structure-Based Methods in Drug Discovery: An Overview of Combined Virtual Screening Approaches

Virtual screening (VS) is an outstanding cornerstone in the drug discovery pipeline. A variety of computational approaches, which are generally classified as ligand-based (LB) and structure-based (SB) techniques, exploit key structural and physicochemical properties of ligands and targets to enable the screening of virtual libraries in the search of active compounds. Though LB and SB methods have found widespread application in the discovery of novel drug-like candidates, their complementary natures have stimulated continued efforts toward the development of hybrid strategies that combine LB and SB techniques, integrating them in a holistic computational framework that exploits the available information of both ligand and target to enhance the success of drug discovery projects. In this review, we analyze the main strategies and concepts that have emerged in the last years for defining hybrid LB + SB computational schemes in VS studies. Particularly, attention is focused on the combination of molecular similarity and docking, illustrating them with selected applications taken from the literature.

AutoGrow4: an open-source genetic algorithm for de novo drug design and lead optimization

We here present AutoGrow4, an open-source program for semi-automated computer-aided drug discovery. AutoGrow4 uses a genetic algorithm to evolve predicted ligands on demand and so is not limited to a virtual library of pre-enumerated compounds. It is a useful tool for generating entirely novel drug-like molecules and for optimizing preexisting ligands. By leveraging recent computational and cheminformatics advancements, AutoGrow4 is faster, more stable, and more modular than previous versions. It implements new docking-program compatibility, chemical filters, multithreading options, and selection methods to support a wide range of user needs. To illustrate both de novo design and lead optimization, we here apply AutoGrow4 to the catalytic domain of poly(ADP-ribose) polymerase 1 (PARP-1), a well characterized DNA-damage-recognition protein. AutoGrow4 produces drug-like compounds with better predicted binding affinities than FDA-approved PARP-1 inhibitors (positive controls). The predicted binding modes of the AutoGrow4 compounds mimic those of the known inhibitors, even when AutoGrow4 is seeded with random small molecules. AutoGrow4 is available under the terms of the Apache License, Version 2.0. A copy can be downloaded free of charge from http://durrantlab.com/autogrow4.