Open Drug Discovery Toolkit (ODDT): a new open-source player in the drug discovery field

Epigenetic target identification strategy based on multi-feature learning

The identification of potential epigenetic targets for a known bioactive compound is essential and promising as more and more epigenetic drugs are used in cancer clinical treatment and the availability of chemogenomic data related to epigenetics increases. In this study, we introduce a novel epigenetic target identification strategy (ETI-Strategy) that integrates a multi-task graph convolutional neural network prior model and a protein-ligand interaction classification discriminating model using large-scale bioactivity data for a panel of 55 epigenetic targets. Our approach utilizes machine learning techniques to achieve an AUC value of 0.934 for the prior model and 0.830 for the discriminating model, outperforming inverse docking in predicting protein-ligand interactions. When comparing with other open-source target identification tools, it was found that only our tool was able to accurately predict all the targets corresponding to each compound. This further demonstrates the ability of our strategy to take full advantage of molecular-level information as well as protein-level information in molecular activity prediction. Our work highlights the contribution of machine learning in the identification of potential epigenetic targets and offers a novel approach for epigenetic drug discovery and development.Communicated by Ramaswamy H. Sarma.

Targeting the Plasmodium falciparum UCHL3 ubiquitin hydrolase using chemically constrained peptides

The ubiquitin-proteasome system is essential to all eukaryotes and has been shown to be critical to parasite survival as well, including Plasmodium falciparum, the causative agent of the deadliest form of malarial disease. Despite the central role of the ubiquitin-proteasome pathway to parasite viability across its entire life-cycle, specific inhibitors targeting the individual enzymes mediating ubiquitin attachment and removal do not currently exist. The ability to disrupt P. falciparum growth at multiple developmental stages is particularly attractive as this could potentially prevent both disease pathology, caused by asexually dividing parasites, as well as transmission which is mediated by sexually differentiated parasites. The deubiquitinating enzyme PfUCHL3 is an essential protein, transcribed across both human and mosquito developmental stages. PfUCHL3 is considered hard to drug by conventional methods given the high level of homology of its active site to human UCHL3 as well as to other UCH domain enzymes. Here, we apply the RaPID mRNA display technology and identify constrained peptides capable of binding to PfUCHL3 with nanomolar affinities. The two lead peptides were found to selectively inhibit the deubiquitinase activity of PfUCHL3 versus HsUCHL3. NMR spectroscopy revealed that the peptides do not act by binding to the active site but instead block binding of the ubiquitin substrate. We demonstrate that this approach can be used to target essential protein-protein interactions within the Plasmodium ubiquitin pathway, enabling the application of chemically constrained peptides as a novel class of antimalarial therapeutics.

graphLambda: Fusion Graph Neural Networks for Binding Affinity Prediction

Predicting the binding affinity of protein-ligand complexes is crucial for computer-aided drug discovery (CADD) and the identification of potential drug candidates. The deep learning-based scoring functions have emerged as promising predictors of binding constants. Building on recent advancements in graph neural networks, we present graphLambda for protein-ligand binding affinity prediction, which utilizes graph convolutional, attention, and isomorphism blocks to enhance the predictive capabilities. The graphLambda model exhibits superior performance across CASF16 and CSAR HiQ NRC benchmarks and demonstrates robustness with respect to different types of train-validation set partitions. The development of graphLambda underscores the potential of graph neural networks in advancing binding affinity prediction models, contributing to more effective CADD methodologies.

Structural Investigations on 2-Amidobenzimidazole Derivatives as New Inhibitors of Protein Kinase CK1 Delta

Protein kinase CK1δ (CK1δ) is a serine-threonine/kinase that modulates different physiological processes, including the cell cycle, DNA repair, and apoptosis. CK1δ overexpression, and the consequent hyperphosphorylation of specific proteins, can lead to sleep disorders, cancer, and neurodegenerative diseases. CK1δ inhibitors showed anticancer properties as well as neuroprotective effects in cellular and animal models of Parkinson's and Alzheimer's diseases and amyotrophic lateral sclerosis. To obtain new ATP-competitive CK1δ inhibitors, three sets of benzimidazole-2-amino derivatives were synthesized (1-32), bearing different substituents on the fused benzo ring (R) and diverse pyrazole-containing acyl moieties on the 2-amino group. The best-performing derivatives were those featuring the (1H-pyrazol-3-yl)-acetyl moiety on the benzimidazol-2-amino scaffold (13-32), which showed CK1δ inhibitor activity in the low micromolar range. Among the R substituents, 5-cyano was the most advantageous, leading to a compound endowed with nanomolar potency (23, IC50 = 98.6 nM). Molecular docking and dynamics studies were performed to point out the inhibitor-kinase interactions.

Comprehensive machine learning boosts structure-based virtual screening for PARP1 inhibitors

Poly ADP-ribose polymerase 1 (PARP1) is an attractive therapeutic target for cancer treatment. Machine-learning scoring functions constitute a promising approach to discovering novel PARP1 inhibitors. Cutting-edge PARP1-specific machine-learning scoring functions were investigated using semi-synthetic training data from docking activity-labelled molecules: known PARP1 inhibitors, hard-to-discriminate decoys property-matched to them with generative graph neural networks and confirmed inactives. We further made test sets harder by including only molecules dissimilar to those in the training set. Comprehensive analysis of these datasets using five supervised learning algorithms, and protein-ligand fingerprints extracted from docking poses and ligand only features revealed one highly predictive scoring function. This is the PARP1-specific support vector machine-based regressor, when employing PLEC fingerprints, which achieved a high Normalized Enrichment Factor at the top 1% on the hardest test set (NEF1% = 0.588, median of 10 repetitions), and was more predictive than any other investigated scoring function, especially the classical scoring function employed as baseline.

Molecular Property Diagnostic Suite for COVID-19 (MPDSCOVID-19): an open-source disease-specific drug discovery portal

Molecular Property Diagnostic Suite (MPDS) was conceived and developed as an open-source disease-specific web portal based on Galaxy. MPDSCOVID-19 was developed for COVID-19 as a one-stop solution for drug discovery research. Galaxy platforms enable the creation of customized workflows connecting various modules in the web server. The architecture of MPDSCOVID-19 effectively employs Galaxy v22.04 features, which are ported on CentOS 7.8 and Python 3.7. MPDSCOVID-19 provides significant updates and the addition of several new tools updated after six years. Tools developed by our group in Perl/Python and open-source tools are collated and integrated into MPDSCOVID-19 using XML scripts. Our MPDS suite aims to facilitate transparent and open innovation. This approach significantly helps bring inclusiveness in the community while promoting free access and participation in software development.

Availability & Implementation

The MPDSCOVID-19 portal can be accessed at https://mpds.neist.res.in:8085/.

Structural basis for sugar perception by Drosophila gustatory receptors

Insects rely on a family of seven transmembrane proteins called gustatory receptors (GRs) to encode different taste modalities, such as sweet and bitter. We report structures of Drosophila sweet taste receptors GR43a and GR64a in the apo and sugar-bound states. Both GRs form tetrameric sugar-gated cation channels composed of one central pore domain (PD) and four peripheral ligand-binding domains (LBDs). Whereas GR43a is specifically activated by the monosaccharide fructose that binds to a narrow pocket in LBDs, disaccharides sucrose and maltose selectively activate GR64a by binding to a larger and flatter pocket in LBDs. Sugar binding to LBDs induces local conformational changes, which are subsequently transferred to the PD to cause channel opening. Our studies reveal a structural basis for sugar recognition and activation of GRs.

Relationship of Cytotoxic and Antimicrobial Effects of Triphenylphosphonium Conjugates with Various Quinone Derivatives

Quinone derivatives of triphenylphosphonium have proven themselves to be effective geroprotectors and antioxidants that prevent oxidation of cell components with participation of active free radicals - peroxide (RO2·), alkoxy (RO·), and alkyl (R·) radicals, as well as reactive oxygen species (superoxide anion, singlet oxygen). Their most studied representatives are derivatives of plastoquinone (SkQ1) and ubiquinone (MitoQ), which in addition to antioxidant properties also have a strong antibacterial effect. In this study, we investigated antibacterial properties of other quinone derivatives based on decyltriphenylphosphonium (SkQ3, SkQT, and SkQThy). We have shown that they, just like SkQ1, inhibit growth of various Gram-positive bacteria at micromolar concentrations, while being less effective against Gram-negative bacteria, which is associated with recognition of the triphenylphosphonium derivatives by the main multidrug resistance (MDR) pump of Gram-negative bacteria, AcrAB-TolC. Antibacterial action of SkQ1 itself was found to be dependent on the number of bacterial cells. It is important to note that the cytotoxic effect of SkQ1 on mammalian cells was observed at higher concentrations than the antibacterial action, which can be explained by (i) the presence of a large number of membrane organelles, (ii) lower membrane potential, (iii) spatial separation of the processes of energy generation and transport, and (iv) differences in the composition of MDR pumps. Differences in the cytotoxic effects on different types of eukaryotic cells may be associated with the degree of membrane organelle development, energy status of the cell, and level of the MDR pump expression.

Inactive-enriched machine-learning models exploiting patent data improve structure-based virtual screening for PDL1 dimerizers

INTRODUCTION

Small-molecule Programmable Cell Death Protein 1/Programmable Death-Ligand 1 (PD1/PDL1) inhibition via PDL1 dimerization has the potential to lead to inexpensive drugs with better cancer patient outcomes and milder side effects. However, this therapeutic approach has proven challenging, with only one PDL1 dimerizer reaching early clinical trials so far. There is hence a need for fast and accurate methods to develop alternative PDL1 dimerizers.

OBJECTIVES

We aim to show that structure-based virtual screening (SBVS) based on PDL1-specific machine-learning (ML) scoring functions (SFs) is a powerful drug design tool for detecting PD1/PDL1 inhibitors via PDL1 dimerization.

METHODS

By incorporating the latest MLSF advances, we generated and evaluated PDL1-specific MLSFs (classifiers and inactive-enriched regressors) on two demanding test sets.

RESULTS

60 PDL1-specific MLSFs (30 classifiers and 30 regressors) were generated. Our large-scale analysis provides highly predictive PDL1-specific MLSFs that benefitted from training with large volumes of docked inactives and enabling inactive-enriched regression.

CONCLUSION

PDL1-specific MLSFs strongly outperformed generic SFs of various types on this target and are released here without restrictions.

Improving structure-based protein-ligand affinity prediction by graph representation learning and ensemble learning

Predicting protein-ligand binding affinity presents a viable solution for accelerating the discovery of new lead compounds. The recent widespread application of machine learning approaches, especially graph neural networks, has brought new advancements in this field. However, some existing structure-based methods treat protein macromolecules and ligand small molecules in the same way and ignore the data heterogeneity, potentially leading to incomplete exploration of the biochemical information of ligands. In this work, we propose LGN, a graph neural network-based fusion model with extra ligand feature extraction to effectively capture local features and global features within the protein-ligand complex, and make use of interaction fingerprints. By combining the ligand-based features and interaction fingerprints, LGN achieves Pearson correlation coefficients of up to 0.842 on the PDBbind 2016 core set, compared to 0.807 when using the features of complex graphs alone. Finally, we verify the rationalization and generalization of our model through comprehensive experiments. We also compare our model with state-of-the-art baseline methods, which validates the superiority of our model. To reduce the impact of data similarity, we increase the robustness of the model by incorporating ensemble learning.

ChemEM: Flexible Docking of Small Molecules in Cryo-EM Structures

Cryo-electron microscopy (cryo-EM), through resolution advancements, has become pivotal in structure-based drug discovery. However, most cryo-EM structures are solved at 3-4 Å resolution, posing challenges for small-molecule docking and structure-based virtual screening due to issues in the precise positioning of ligands and the surrounding side chains. We present ChemEM, a software package that employs cryo-EM data for the accurate docking of one or multiple ligands in a protein-binding site. Validated against a highly curated benchmark of high- and medium-resolution cryo-EM structures and the corresponding high-resolution controls, ChemEM displayed impressive performance, accurately placing ligands in all but one case, often surpassing cryo-EM PDB-deposited solutions. Even without including the cryo-EM density, the ChemEM scoring function outperformed the well-established AutoDock Vina score. Using ChemEM, we illustrate that valuable information can be extracted from maps at medium resolution and underline the utility of cryo-EM structures for drug discovery.

Fingerprinting Interactions between Proteins and Ligands for Facilitating Machine Learning in Drug Discovery

Molecular recognition is fundamental in biology, underpinning intricate processes through specific protein-ligand interactions. This understanding is pivotal in drug discovery, yet traditional experimental methods face limitations in exploring the vast chemical space. Computational approaches, notably quantitative structure-activity/property relationship analysis, have gained prominence. Molecular fingerprints encode molecular structures and serve as property profiles, which are essential in drug discovery. While two-dimensional (2D) fingerprints are commonly used, three-dimensional (3D) structural interaction fingerprints offer enhanced structural features specific to target proteins. Machine learning models trained on interaction fingerprints enable precise binding prediction. Recent focus has shifted to structure-based predictive modeling, with machine-learning scoring functions excelling due to feature engineering guided by key interactions. Notably, 3D interaction fingerprints are gaining ground due to their robustness. Various structural interaction fingerprints have been developed and used in drug discovery, each with unique capabilities. This review recapitulates the developed structural interaction fingerprints and provides two case studies to illustrate the power of interaction fingerprint-driven machine learning. The first elucidates structure-activity relationships in β2 adrenoceptor ligands, demonstrating the ability to differentiate agonists and antagonists. The second employs a retrosynthesis-based pre-trained molecular representation to predict protein-ligand dissociation rates, offering insights into binding kinetics. Despite remarkable progress, challenges persist in interpreting complex machine learning models built on 3D fingerprints, emphasizing the need for strategies to make predictions interpretable. Binding site plasticity and induced fit effects pose additional complexities. Interaction fingerprints are promising but require continued research to harness their full potential.

Augmenting a training dataset of the generative diffusion model for molecular docking with artificial binding pockets

This study introduces the PocketCFDM generative diffusion model, aimed at improving the prediction of small molecule poses in the protein binding pockets. The model utilizes a novel data augmentation technique, involving the creation of numerous artificial binding pockets that mimic the statistical patterns of non-bond interactions found in actual protein-ligand complexes. An algorithmic method was developed to assess and replicate these interaction patterns in the artificial binding pockets built around small molecule conformers. It is shown that the integration of artificial binding pockets into the training process significantly enhanced the model's performance. Notably, PocketCFDM surpassed DiffDock in terms of non-bond interaction and steric clash numbers, and the inference speed. Future developments and optimizations of the model are discussed. The inference code and final model weights of PocketCFDM are accessible publicly via the GitHub repository: https://github.com/vtarasv/pocket-cfdm.git.

Exploring Scoring Function Space: Developing Computational Models for Drug Discovery

BACKGROUND

The idea of scoring function space established a systems-level approach to address the development of models to predict the affinity of drug molecules by those interested in drug discovery.

OBJECTIVE

Our goal here is to review the concept of scoring function space and how to explore it to develop machine learning models to address protein-ligand binding affinity.

METHODS

We searched the articles available in PubMed related to the scoring function space. We also utilized crystallographic structures found in the protein data bank (PDB) to represent the protein space.

RESULTS

The application of systems-level approaches to address receptor-drug interactions allows us to have a holistic view of the process of drug discovery. The scoring function space adds flexibility to the process since it makes it possible to see drug discovery as a relationship involving mathematical spaces.

CONCLUSION

The application of the concept of scoring function space has provided us with an integrated view of drug discovery methods. This concept is useful during drug discovery, where we see the process as a computational search of the scoring function space to find an adequate model to predict receptor-drug binding affinity.

Deep learning in bioinformatics

Deep learning is a powerful machine learning technique that can learn from large amounts of data using multiple layers of artificial neural networks. This paper reviews some applications of deep learning in bioinformatics, a field that deals with analyzing and interpreting biological data. We first introduce the basic concepts of deep learning and then survey the recent advances and challenges of applying deep learning to various bioinformatics problems, such as genome sequencing, gene expression analysis, protein structure prediction, drug discovery, and disease diagnosis. We also discuss future directions and opportunities for deep learning in bioinformatics. We aim to provide an overview of deep learning so that bioinformaticians applying deep learning models can consider all critical technical and ethical aspects. Thus, our target audience is biomedical informatics researchers who use deep learning models for inference. This review will inspire more bioinformatics researchers to adopt deep-learning methods for their research questions while considering fairness, potential biases, explainability, and accountability.

Thermal titration molecular dynamics (TTMD): shedding light on the stability of RNA-small molecule complexes

Ribonucleic acids are gradually becoming relevant players among putative drug targets, thanks to the increasing amount of structural data exploitable for the rational design of selective and potent binders that can modulate their activity. Mainly, this information allows employing different computational techniques for predicting how well would a ribonucleic-targeting agent fit within the active site of its target macromolecule. Due to some intrinsic peculiarities of complexes involving nucleic acids, such as structural plasticity, surface charge distribution, and solvent-mediated interactions, the application of routinely adopted methodologies like molecular docking is challenged by scoring inaccuracies, while more physically rigorous methods such as molecular dynamics require long simulation times which hamper their conformational sampling capabilities. In the present work, we present the first application of Thermal Titration Molecular Dynamics (TTMD), a recently developed method for the qualitative estimation of unbinding kinetics, to characterize RNA-ligand complexes. In this article, we explored its applicability as a post-docking refinement tool on RNA in complex with small molecules, highlighting the capability of this method to identify the native binding mode among a set of decoys across various pharmaceutically relevant test cases.

A flexible data-free framework for structure-based de novo drug design with reinforcement learning

Contemporary structure-based molecular generative methods have demonstrated their potential to model the geometric and energetic complementarity between ligands and receptors, thereby facilitating the design of molecules with favorable binding affinity and target specificity. Despite the introduction of deep generative models for molecular generation, the atom-wise generation paradigm that partially contradicts chemical intuition limits the validity and synthetic accessibility of the generated molecules. Additionally, the dependence of deep learning models on large-scale structural data has hindered their adaptability across different targets. To overcome these challenges, we present a novel search-based framework, 3D-MCTS, for structure-based de novo drug design. Distinct from prevailing atom-centric methods, 3D-MCTS employs a fragment-based molecular editing strategy. The fragments decomposed from small-molecule drugs are recombined under predefined retrosynthetic rules, offering improved drug-likeness and synthesizability, overcoming the inherent limitations of atom-based approaches. Leveraging multi-threaded parallel simulations combined with a real-time energy constraint-based pruning strategy, 3D-MCTS achieves remarkable efficiency. At a fixed computational cost, it outperforms other state-of-the-art (SOTA) methods by producing molecules with enhanced binding affinity. Furthermore, its fragment-based approach ensures the generation of more dependable binding conformations, exhibiting a success rate 43.6% higher than that of other SOTAs. This advantage becomes even more pronounced when handling targets that significantly deviate from the training dataset. 3D-MCTS is capable of achieving thirty times more hits with high binding affinity than traditional virtual screening methods, which demonstrates the superior ability of 3D-MCTS to explore chemical space. Moreover, the flexibility of our framework makes it easy to incorporate domain knowledge during the process, thereby enabling the generation of molecules with desirable pharmacophores and enhanced binding affinity. The adaptability of 3D-MCTS is further showcased in metalloprotein applications, highlighting its potential across various drug design scenarios.

Iterative Knowledge-Based Scoring Function for Protein-Ligand Interactions by Considering Binding Affinity Information

Scoring functions for protein-ligand interactions play a critical role in structure-based drug design. Owing to the good balance between general applicability and computational efficiency, knowledge-based scoring functions have obtained significant advancements and achieved many successes. Nevertheless, knowledge-based scoring functions face a challenge in utilizing the experimental affinity data and thus may not perform well in binding affinity prediction. Addressing the challenge, we have proposed an improved version of the iterative knowledge-based scoring function ITScore by considering binding affinity information, which is referred to as ITScoreAff, based on a large training set of 6216 protein-ligand complexes with both structures and affinity data. ITScoreAff was extensively evaluated and compared with ITScore, 33 traditional, and 6 machine learning scoring functions in terms of docking power, ranking power, and screening power on the independent CASF-2016 benchmark. It was shown that ITScoreAff obtained an overall better performance than the other 40 scoring functions and gave an average success rate of 85.3% in docking power, a correlation coefficient of 0.723 in scoring power, and an average rank correlation coefficient of 0.668 in ranking power. In addition, ITScoreAff also achieved the overall best screening power when the top 10% of the ranked database were considered. These results demonstrated the robustness of ITScoreAff and its improvement over existing scoring functions.

DataPype: A Fully Automated Unified Software Platform for Computer-Aided Drug Design

With the advent of computer-aided drug design (CADD), traditional physical testing of thousands of molecules has now been replaced by target-focused drug discovery, where potentially bioactive molecules are predicted by computer software before their physical synthesis. However, despite being a significant breakthrough, CADD still faces various limitations and challenges. The increasing availability of data on small molecules has created a need to streamline the sourcing of data from different databases and automate the processing and cleaning of data into a form that can be used by multiple CADD software applications. Several standalone software packages are available to aid the drug designer, each with its own specific application, requiring specialized knowledge and expertise for optimal use. These applications require their own input and output files, making it a challenge for nonexpert users or multidisciplinary discovery teams. Here, we have developed a new software platform called DataPype, which wraps around these different software packages. It provides a unified automated workflow to search for hit compounds using specialist software. Additionally, multiple virtual screening packages can be used in the one workflow, and if different ways of looking at potential hit compounds all predict the same set of molecules, we have higher confidence that we should make or purchase and test the molecules. Importantly, DataPype can run on computer servers, speeding up the virtual screening for new compounds. Combining access to multiple CADD tools within one interface will enhance the early stage of drug discovery, increase usability, and enable the use of parallel computing.

ML-PLIC: a web platform for characterizing protein-ligand interactions and developing machine learning-based scoring functions

Cracking the entangling code of protein-ligand interaction (PLI) is of great importance to structure-based drug design and discovery. Different physical and biochemical representations can be used to describe PLI such as energy terms and interaction fingerprints, which can be analyzed by machine learning (ML) algorithms to create ML-based scoring functions (MLSFs). Here, we propose the ML-based PLI capturer (ML-PLIC), a web platform that automatically characterizes PLI and generates MLSFs to identify the potential binders of a specific protein target through virtual screening (VS). ML-PLIC comprises five modules, including Docking for ligand docking, Descriptors for PLI generation, Modeling for MLSF training, Screening for VS and Pipeline for the integration of the aforementioned functions. We validated the MLSFs constructed by ML-PLIC in three benchmark datasets (Directory of Useful Decoys-Enhanced, Active as Decoys and TocoDecoy), demonstrating accuracy outperforming traditional docking tools and competitive performance to the deep learning-based SF, and provided a case study of the Serine/threonine-protein kinase WEE1 in which MLSFs were developed by using the ML-based VS pipeline in ML-PLIC. Underpinning the latest version of ML-PLIC is a powerful platform that incorporates physical and biological knowledge about PLI, leveraging PLI characterization and MLSF generation into the design of structure-based VS pipeline. The ML-PLIC web platform is now freely available at http://cadd.zju.edu.cn/plic/.

Exploring the ability of machine learning-based virtual screening models to identify the functional groups responsible for binding

Many recently proposed structure-based virtual screening models appear to be able to accurately distinguish high affinity binders from non-binders. However, several recent studies have shown that they often do so by exploiting ligand-specific biases in the dataset, rather than identifying favourable intermolecular interactions in the input protein-ligand complex. In this work we propose a novel approach for assessing the extent to which machine learning-based virtual screening models are able to identify the functional groups responsible for binding. To sidestep the difficulty in establishing the ground truth importance of each atom of a large scale set of protein-ligand complexes, we propose a protocol for generating synthetic data. Each ligand in the dataset is surrounded by a randomly sampled point cloud of pharmacophores, and the label assigned to the synthetic protein-ligand complex is determined by a 3-dimensional deterministic binding rule. This allows us to precisely quantify the ground truth importance of each atom and compare it to the model generated attributions. Using our generated datasets, we demonstrate that a recently proposed deep learning-based virtual screening model, PointVS, identified the most important functional groups with 39% more efficiency than a fingerprint-based random forest, suggesting that it would generalise more effectively to new examples. In addition, we found that ligand-specific biases, such as those present in widely used virtual screening datasets, substantially impaired the ability of all ML models to identify the most important functional groups. We have made our synthetic data generation framework available to facilitate the benchmarking of new virtual screening models. Code is available at https://github.com/tomhadfield95/synthVS .

Efficient and accurate large library ligand docking with KarmaDock

Ligand docking is one of the core technologies in structure-based virtual screening for drug discovery. However, conventional docking tools and existing deep learning tools may suffer from limited performance in terms of speed, pose quality and binding affinity accuracy. Here we propose KarmaDock, a deep learning approach for ligand docking that integrates the functions of docking acceleration, binding pose generation and correction, and binding strength estimation. The three-stage model consists of the following components: (1) encoders for the protein and ligand to learn the representations of intramolecular interactions; (2) E(n) equivariant graph neural networks with self-attention to update the ligand pose based on both protein-ligand and intramolecular interactions, followed by post-processing to ensure chemically plausible structures; (3) a mixture density network for scoring the binding strength. KarmaDock was validated on four benchmark datasets and tested in a real-world virtual screening project that successfully identified experiment-validated active inhibitors of leukocyte tyrosine kinase (LTK).

AI-based identification of therapeutic agents targeting GPCRs: introducing ligand type classifiers and systems biology

Identifying ligands targeting G protein coupled receptors (GPCRs) with novel chemotypes other than the physiological ligands is a challenge for in silico screening campaigns. Here we present an approach that identifies novel chemotype ligands by combining structural data with a random forest agonist/antagonist classifier and a signal-transduction kinetic model. As a test case, we apply this approach to identify novel antagonists of the human adenosine transmembrane receptor type 2A, an attractive target against Parkinson's disease and cancer. The identified antagonists were tested here in a radio ligand binding assay. Among those, we found a promising ligand whose chemotype differs significantly from all so-far reported antagonists, with a binding affinity of 310 ± 23.4 nM. Thus, our protocol emerges as a powerful approach to identify promising ligand candidates with novel chemotypes while preserving antagonistic potential and affinity in the nanomolar range.

Open-Source Machine Learning in Computational Chemistry

The field of computational chemistry has seen a significant increase in the integration of machine learning concepts and algorithms. In this Perspective, we surveyed 179 open-source software projects, with corresponding peer-reviewed papers published within the last 5 years, to better understand the topics within the field being investigated by machine learning approaches. For each project, we provide a short description, the link to the code, the accompanying license type, and whether the training data and resulting models are made publicly available. Based on those deposited in GitHub repositories, the most popular employed Python libraries are identified. We hope that this survey will serve as a resource to learn about machine learning or specific architectures thereof by identifying accessible codes with accompanying papers on a topic basis. To this end, we also include computational chemistry open-source software for generating training data and fundamental Python libraries for machine learning. Based on our observations and considering the three pillars of collaborative machine learning work, open data, open source (code), and open models, we provide some suggestions to the community.

A Robust Machine Learning Framework Built Upon Molecular Representations Predicts CYP450 Inhibition: Toward Precision in Drug Repurposing

Human cytochrome P450 (CYP450) enzymes play a crucial role in drug metabolism and pharmacokinetics. CYP450 inhibition can lead to toxicity, in particular when drugs are co-administered with other drugs and xenobiotics or in the case of polypharmacy. Predicting CYP450 inhibition is also important for rational drug discovery and development, and precision in drug repurposing. In this overarching context, digital transformation of drug discovery and development, for example, using machine and deep learning approaches, offers prospects for prediction of CYP450 inhibition through computational models. We report here the development of a majority-voting machine learning framework to classify inhibitors and noninhibitors for seven major human liver CYP450 isoforms (CYP1A2, CYP2A6, CYP2B6, CYP2C9, CYP2C19, CYP2D6, and CYP3A4). For the machine learning models reported herein, we employed interaction fingerprints that were derived from molecular docking simulations, thus adding an additional layer of information for protein-ligand interactions. The proposed machine learning framework is based on the structure of the binding site of isoforms to produce predictions beyond previously reported approaches. Also, we carried out a comparative analysis so as to identify which representation of test compounds (molecular descriptors, molecular fingerprints, or protein-ligand interaction fingerprints) affects the predictive performance of the models. This work underlines the ways in which the structure of the enzyme catalytic site influences machine learning predictions and the need for robust frameworks toward better-informed predictions.

Ligand-Based Virtual Screening, Molecular Docking, and Molecular Dynamic Simulations of New β-Estrogen Receptor Activators with Potential for Pharmacological Obesity Treatment

Obesity is a pandemic and a serious health problem in developed and undeveloped countries. Activation of estrogen receptor beta (ERβ) has been shown to promote weight loss without modifying caloric intake, making it an attractive target for developing new drugs against obesity. This work aimed to predict new small molecules as potential ERβ activators. A ligand-based virtual screening of the ZINC15, PubChem, and Molport databases by substructure and similarity was carried out using the three-dimensional organization of known ligands as a reference. A molecular docking screening of FDA-approved drugs was also conducted as a repositioning strategy. Finally, selected compounds were evaluated by molecular dynamic simulations. Compounds 1 (-24.27 ± 0.34 kcal/mol), 2 (-23.33 ± 0.3 kcal/mol), and 6 (-29.55 ± 0.51 kcal/mol) showed the best stability on the active site in complex with ERβ with an RMSD < 3.3 Å. RMSF analysis showed that these compounds do not affect the fluctuation of the Cα of ERβ nor the compactness according to the radius of gyration. Finally, an in silico evaluation of ADMET showed they are safe molecules. These results suggest that new ERβ ligands could be promising molecules for obesity control.

3DProtDTA: a deep learning model for drug-target affinity prediction based on residue-level protein graphs

Accurate prediction of the drug-target affinity (DTA) in silico is of critical importance for modern drug discovery. Computational methods of DTA prediction, applied in the early stages of drug development, are able to speed it up and cut its cost significantly. A wide range of approaches based on machine learning were recently proposed for DTA assessment. The most promising of them are based on deep learning techniques and graph neural networks to encode molecular structures. The recent breakthrough in protein structure prediction made by AlphaFold made an unprecedented amount of proteins without experimentally defined structures accessible for computational DTA prediction. In this work, we propose a new deep learning DTA model 3DProtDTA, which utilises AlphaFold structure predictions in conjunction with the graph representation of proteins. The model is superior to its rivals on common benchmarking datasets and has potential for further improvement.

MetalProGNet: a structure-based deep graph model for metalloprotein-ligand interaction predictions

Metalloproteins play indispensable roles in various biological processes ranging from reaction catalysis to free radical scavenging, and they are also pertinent to numerous pathologies including cancer, HIV infection, neurodegeneration, and inflammation. Discovery of high-affinity ligands for metalloproteins powers the treatment of these pathologies. Extensive efforts have been made to develop in silico approaches, such as molecular docking and machine learning (ML)-based models, for fast identification of ligands binding to heterogeneous proteins, but few of them have exclusively concentrated on metalloproteins. In this study, we first compiled the largest metalloprotein-ligand complex dataset containing 3079 high-quality structures, and systematically evaluated the scoring and docking powers of three competitive docking tools (i.e., PLANTS, AutoDock Vina and Glide SP) for metalloproteins. Then, a structure-based deep graph model called MetalProGNet was developed to predict metalloprotein-ligand interactions. In the model, the coordination interactions between metal ions and protein atoms and the interactions between metal ions and ligand atoms were explicitly modelled through graph convolution. The binding features were then predicted by the informative molecular binding vector learned from a noncovalent atom-atom interaction network. The evaluation on the internal metalloprotein test set, the independent ChEMBL dataset towards 22 different metalloproteins and the virtual screening dataset indicated that MetalProGNet outperformed various baselines. Finally, a noncovalent atom-atom interaction masking technique was employed to interpret MetalProGNet, and the learned knowledge accords with our understanding of physics.

Thermal Titration Molecular Dynamics (TTMD): Not Your Usual Post-Docking Refinement

Molecular docking is one of the most widely used computational approaches in the field of rational drug design, thanks to its favorable balance between the rapidity of execution and the accuracy of provided results. Although very efficient in exploring the conformational degrees of freedom available to the ligand, docking programs can sometimes suffer from inaccurate scoring and ranking of generated poses. To address this issue, several post-docking filters and refinement protocols have been proposed throughout the years, including pharmacophore models and molecular dynamics simulations. In this work, we present the first application of Thermal Titration Molecular Dynamics (TTMD), a recently developed method for the qualitative estimation of protein-ligand unbinding kinetics, to the refinement of docking results. TTMD evaluates the conservation of the native binding mode throughout a series of molecular dynamics simulations performed at progressively increasing temperatures with a scoring function based on protein-ligand interaction fingerprints. The protocol was successfully applied to retrieve the native-like binding pose among a set of decoy poses of drug-like ligands generated on four different pharmaceutically relevant biological targets, including casein kinase 1δ, casein kinase 2, pyruvate dehydrogenase kinase 2, and SARS-CoV-2 main protease.

Artificial Intelligence and Machine Learning Technology Driven Modern Drug Discovery and Development

The discovery and advances of medicines may be considered as the ultimate relevant translational science effort that adds to human invulnerability and happiness. But advancing a fresh medication is a quite convoluted, costly, and protracted operation, normally costing USD ~2.6 billion and consuming a mean time span of 12 years. Methods to cut back expenditure and hasten new drug discovery have prompted an arduous and compelling brainstorming exercise in the pharmaceutical industry. The engagement of Artificial Intelligence (AI), including the deep-learning (DL) component in particular, has been facilitated by the employment of classified big data, in concert with strikingly reinforced computing prowess and cloud storage, across all fields. AI has energized computer-facilitated drug discovery. An unrestricted espousing of machine learning (ML), especially DL, in many scientific specialties, and the technological refinements in computing hardware and software, in concert with various aspects of the problem, sustain this progress. ML algorithms have been extensively engaged for computer-facilitated drug discovery. DL methods, such as artificial neural networks (ANNs) comprising multiple buried processing layers, have of late seen a resurgence due to their capability to power automatic attribute elicitations from the input data, coupled with their ability to obtain nonlinear input-output pertinencies. Such features of DL methods augment classical ML techniques which bank on human-contrived molecular descriptors. A major part of the early reluctance concerning utility of AI in pharmaceutical discovery has begun to melt, thereby advancing medicinal chemistry. AI, along with modern experimental technical knowledge, is anticipated to invigorate the quest for new and improved pharmaceuticals in an expeditious, economical, and increasingly compelling manner. DL-facilitated methods have just initiated kickstarting for some integral issues in drug discovery. Many technological advances, such as "message-passing paradigms", "spatial-symmetry-preserving networks", "hybrid de novo design", and other ingenious ML exemplars, will definitely come to be pervasively widespread and help dissect many of the biggest, and most intriguing inquiries. Open data allocation and model augmentation will exert a decisive hold during the progress of drug discovery employing AI. This review will address the impending utilizations of AI to refine and bolster the drug discovery operation.

Synthesis and bioactivity evaluation of ferrocene-based hydroxamic acids as selective histone deacetylase 6 inhibitors

Histone deacetylase 6 (HDAC6) is involved in multiple regulatory processes and emerges as a promising target for treating cancer and neurodegenerative diseases. Benefited from the unique sandwich conformation of ferrocene, a series of ferrocene-based hydroxamic acids have been developed as novel HDAC6 inhibitors in this paper, especially the two ansa-ferrocenyl complexes with IC₅₀s at the nanomolar level. [3]-Ferrocenophane hydroxamic acid analog II-5 displays the most potent inhibitory activity on HDAC6 and establishes remarkable selectivity towards other HDAC isoforms. Compound II-5 dose-dependently induces accumulation of acetylated α-tubulin while having a negligible effect on the level of acetylated Histone H3, confirming its isoform selectivity. Further biological evaluation of II-5 on cancer cells corroborates its antiproliferative effect, which mainly contributed to the induction of cellular apoptosis. It is worth noting that compound II-5 demonstrates an optimal profile on human plasma stability. These results strengthen ferrocene's unique role in developing selective protein inhibitors and indicate that compound II-5 may be a suitable lead for further evaluation and development for treating HDAC6-associated disorders and diseases.

Computer-Aided Drug Design: An Update

Computer-aided drug design (CADD) approaches are playing an increasingly important role in understanding the fundamentals of ligand-receptor interactions and helping medicinal chemists design therapeutics. About 5 years ago, we presented a chapter devoted to an overview of CADD methods and covered typical CADD protocols including structure-based drug design (SBDD) and ligand-based drug design (LBDD) approaches that were frequently used in the antibiotic drug design process. Advances in computational hardware and algorithms and emerging CADD methods are enhancing the accuracy and ability of CADD in drug design and development. In this chapter, an update to our previous chapter is provided with a focus on new CADD approaches from our laboratory and other peers that can be employed to facilitate the development of antibiotic therapeutics.

Qualitative Estimation of Protein-Ligand Complex Stability through Thermal Titration Molecular Dynamics Simulations

The prediction of ligand efficacy has long been linked to thermodynamic properties such as the equilibrium dissociation constant, which considers both the association and the dissociation rates of a defined protein-ligand complex. In the last 15 years, there has been a paradigm shift, with an increased interest in the determination of kinetic properties such as the drug-target residence time since they better correlate with ligand efficacy compared to other parameters. In this article, we present thermal titration molecular dynamics (TTMD), an alternative computational method that combines a series of molecular dynamics simulations performed at progressively increasing temperatures with a scoring function based on protein-ligand interaction fingerprints for the qualitative estimation of protein-ligand-binding stability. The protocol has been applied to four different pharmaceutically relevant test cases, including protein kinase CK1δ, protein kinase CK2, pyruvate dehydrogenase kinase 2, and SARS-CoV-2 main protease, on a variety of ligands with different sizes, structures, and experimentally determined affinity values. In all four cases, TTMD was successfully able to distinguish between high-affinity compounds (low nanomolar range) and low-affinity ones (micromolar), proving to be a useful screening tool for the prioritization of compounds in a drug discovery campaign.

Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses

Machine learning scoring functions for protein-ligand binding affinity have been found to consistently outperform classical scoring functions when trained and tested on crystal structures of bound protein-ligand complexes. However, it is less clear how these methods perform when applied to docked poses of complexes. We explore how the use of docked rather than crystallographic poses for both training and testing affects the performance of machine learning scoring functions. Using the PDBbind Core Sets as benchmarks, we show that the performance of a structure-based machine learning scoring function trained and tested on docked poses is lower than that of the same scoring function trained and tested on crystallographic poses. We construct a hybrid scoring function by combining both structure-based and ligand-based features, and show that its ability to predict binding affinity using docked poses is comparable to that of purely structure-based scoring functions trained and tested on crystal poses. We also present a new, freely available validation set─the Updated DUD-E Diverse Subset─for binding affinity prediction using data from DUD-E and ChEMBL. Despite strong performance on docked poses of the PDBbind Core Sets, we find that our hybrid scoring function sometimes generalizes poorly to a protein target not represented in the training set, demonstrating the need for improved scoring functions and additional validation benchmarks.

Assessment of the Generalization Abilities of Machine-Learning Scoring Functions for Structure-Based Virtual Screening

In structure-based virtual screening (SBVS), it is critical that scoring functions capture protein-ligand atomic interactions. By focusing on the local domains of ligand binding pockets, a standardized pocket Pfam-based clustering (Pfam-cluster) approach was developed to assess the cross-target generalization ability of machine-learning scoring functions (MLSFs). Subsequently, 12 typical MLSFs were evaluated using random cross-validation (Random-CV), protein sequence similarity-based cross-validation (Seq-CV), and pocket Pfam-based cross-validation (Pfam-CV) methods. Surprisingly, all of the tested models showed decreased performances from Random-CV to Seq-CV to Pfam-CV experiments, not showing satisfactory generalization capacity. Our interpretable analysis suggested that the predictions on novel targets by MLSFs were dependent on buried solvent-accessible surface area (SASA)-related features of complex structures, with greater predicted binding affinities on complexes owning larger protein-ligand interfaces. By combining buried SASA-related features with target-specific patterns that were only shared among structurally similar compounds in the same cluster, the random forest (RF)-Score attained a good performance in the Random-CV test. Based on these findings, we strongly advise assessing the generalization ability of MLSFs with the Pfam-cluster approach and being cautious with the features learned by MLSFs.

A multi-reference poly-conformational method for in silico design, optimization, and repositioning of pharmaceutical compounds illustrated for selected SARS-CoV-2 ligands

Background

This work presents a novel computational multi-reference poly-conformational algorithm for design, optimization, and repositioning of pharmaceutical compounds.

Methods

The algorithm searches for candidates by comparing similarities between conformers of the same compound and identifies target compounds, whose conformers are collectively close to the conformers of each compound in the reference set. Reference compounds may possess highly variable MoAs, which directly, and simultaneously, shape the properties of target candidate compounds.

Results

The algorithm functionality has been case study validated in silico, by scoring ChEMBL drugs against FDA-approved reference compounds that either have the highest predicted binding affinity to our chosen SARS-CoV-2 targets or are confirmed to be inhibiting such targets in-vivo. All our top scoring ChEMBL compounds also turned out to be either high-affinity ligands to the chosen targets (as confirmed in separate studies) or show significant efficacy, in-vivo, against those selected targets. In addition to method case study validation, in silico search for new compounds within two virtual libraries from the Enamine database is presented. The library's virtual compounds have been compared to the same set of reference drugs that we used for case study validation: Olaparib, Tadalafil, Ergotamine and Remdesivir. The large reference set of four potential SARS-CoV-2 compounds has been selected, since no drug has been identified to be 100% effective against the virus so far, possibly because each candidate drug was targeting only one, particular MoA. The goal here was to introduce a new methodology for identifying potential candidate(s) that cover multiple MoA-s presented within a set of reference compounds.

Novel Efficient Multistage Lead Optimization Pipeline Experimentally Validated for DYRK1B Selective Inhibitors

In addition to general challenges in drug discovery such as the identification of lead compounds in time- and cost-effective ways, specific challenges also exist. Particularly, it is necessary to develop pharmacological inhibitors that effectively discriminate between closely related molecular targets. DYRK1B kinase is considered a valuable target for cancer-specific mono- or combination chemotherapy; however, the inhibition of its closely related DYRK1A kinase is not beneficial. Existing inhibitors target both kinases with essentially the same efficiency, and the unavailability of the DYRK1B crystal structure makes the discovery of DYRK1B-specific inhibitors even more challenging. Here, we propose a novel multi-stage compound discovery pipeline aimed at in silico identification of both potent and selective small molecules from a large set of initial candidates. The method uses structure-based docking and ligand-based quantitative structure–activity relationship modeling. This approach allowed us to identify lead and runner-up small-molecule compounds targeting DYRK1B with high efficiency and specificity.

Chemical Space Exploration with Active Learning and Alchemical Free Energies

Drug discovery can be thought of as a search for a needle in a haystack: searching through a large chemical space for the most active compounds. Computational techniques can narrow the search space for experimental follow up, but even they become unaffordable when evaluating large numbers of molecules. Therefore, machine learning (ML) strategies are being developed as computationally cheaper complementary techniques for navigating and triaging large chemical libraries. Here, we explore how an active learning protocol can be combined with first-principles based alchemical free energy calculations to identify high affinity phosphodiesterase 2 (PDE2) inhibitors. We first calibrate the procedure using a set of experimentally characterized PDE2 binders. The optimized protocol is then used prospectively on a large chemical library to navigate toward potent inhibitors. In the active learning cycle, at every iteration a small fraction of compounds is probed by alchemical calculations and the obtained affinities are used to train ML models. With successive rounds, high affinity binders are identified by explicitly evaluating only a small subset of compounds in a large chemical library, thus providing an efficient protocol that robustly identifies a large fraction of true positives.

Target-Specific Machine Learning Scoring Function Improved Structure-Based Virtual Screening Performance for SARS-CoV-2 Drugs Development

Leveraging machine learning has been shown to improve the accuracy of structure-based virtual screening. Furthermore, a tremendous amount of empirical data is publicly available, which further enhances the performance of the machine learning approach. In this proof-of-concept study, the 3CL^pro enzyme of SARS-CoV-2 was used. Structure-based virtual screening relies heavily on scoring functions. It is widely accepted that target-specific scoring functions may perform more effectively than universal scoring functions in real-world drug research and development processes. It would be beneficial to drug discovery to develop a method that can effectively build target-specific scoring functions. In the current study, the bindingDB database was used to retrieve experimental data. Smina was utilized to generate protein-ligand complexes for the extraction of InteractionFingerPrint (IFP) and SimpleInteractionFingerPrint SIFP fingerprints via the open drug discovery tool (oddt). The present study found that randomforestClassifier and randomforestRegressor performed well when used with the above fingerprints along the Molecular ACCess System (MACCS), Extended Connectivity Fingerprint (ECFP4), and ECFP6. It was found that the area under the precision-recall curve was 0.80, which is considered a satisfactory level of accuracy. In addition, our enrichment factor analysis indicated that our trained scoring function ranked molecules correctly compared to smina’s generic scoring function. Further molecular dynamics simulations indicated that the top-ranked molecules identified by our developed scoring function were highly stable in the active site, supporting the validity of our developed process. This research may provide a template for developing target-specific scoring functions against specific enzyme targets.

Benchmarking AlphaFold-enabled molecular docking predictions for antibiotic discovery

Efficient identification of drug mechanisms of action remains a challenge. Computational docking approaches have been widely used to predict drug binding targets; yet, such approaches depend on existing protein structures, and accurate structural predictions have only recently become available from AlphaFold2. Here, we combine AlphaFold2 with molecular docking simulations to predict protein‐ligand interactions between 296 proteins spanning Escherichia coli's essential proteome, and 218 active antibacterial compounds and 100 inactive compounds, respectively, pointing to widespread compound and protein promiscuity. We benchmark model performance by measuring enzymatic activity for 12 essential proteins treated with each antibacterial compound. We confirm extensive promiscuity, but find that the average area under the receiver operating characteristic curve (auROC) is 0.48, indicating weak model performance. We demonstrate that rescoring of docking poses using machine learning‐based approaches improves model performance, resulting in average auROCs as large as 0.63, and that ensembles of rescoring functions improve prediction accuracy and the ratio of true‐positive rate to false‐positive rate. This work indicates that advances in modeling protein‐ligand interactions, particularly using machine learning‐based approaches, are needed to better harness AlphaFold2 for drug discovery.

Fragment Libraries Designed to Be Functionally Diverse Recover Protein Binding Information More Efficiently Than Standard Structurally Diverse Libraries

Current fragment-based drug design relies on the efficient exploration of chemical space by using structurally diverse libraries of small fragments. However, structurally dissimilar compounds can exploit the same interactions and thus be functionally similar. Using three-dimensional structures of many fragments bound to multiple targets, we examined if a better strategy for selecting fragments for screening libraries exists. We show that structurally diverse fragments can be described as functionally redundant, often making the same interactions. Ranking fragments by the number of novel interactions they made, we show that functionally diverse selections of fragments substantially increase the amount of information recovered for unseen targets compared to the amounts recovered by other methods of selection. Using these results, we design small functionally efficient libraries that can give significantly more information about new protein targets than similarly sized structurally diverse libraries. By covering more functional space, we can generate more diverse sets of drug leads.

Viral informatics: bioinformatics-based solution for managing viral infections

Several new viral infections have emerged in the human population and establishing as global pandemics. With advancements in translation research, the scientific community has developed potential therapeutics to eradicate or control certain viral infections, such as smallpox and polio, responsible for billions of disabilities and deaths in the past. Unfortunately, some viral infections, such as dengue virus (DENV) and human immunodeficiency virus-1 (HIV-1), are still prevailing due to a lack of specific therapeutics, while new pathogenic viral strains or variants are emerging because of high genetic recombination or cross-species transmission. Consequently, to combat the emerging viral infections, bioinformatics-based potential strategies have been developed for viral characterization and developing new effective therapeutics for their eradication or management. This review attempts to provide a single platform for the available wide range of bioinformatics-based approaches, including bioinformatics methods for the identification and management of emerging or evolved viral strains, genome analysis concerning the pathogenicity and epidemiological analysis, computational methods for designing the viral therapeutics, and consolidated information in the form of databases against the known pathogenic viruses. This enriched review of the generally applicable viral informatics approaches aims to provide an overview of available resources capable of carrying out the desired task and may be utilized to expand additional strategies to improve the quality of translation viral informatics research.

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.

SCORCH: Improving structure-based virtual screening with machine learning classifiers, data augmentation, and uncertainty estimation

INTRODUCTION

The discovery of a new drug is a costly and lengthy endeavour. The computational prediction of which small molecules can bind to a protein target can accelerate this process if the predictions are fast and accurate enough. Recent machine-learning scoring functions re-evaluate the output of molecular docking to achieve more accurate predictions. However, previous scoring functions were trained on crystalised protein-ligand complexes and datasets of decoys. The limited availability of crystal structures and biases in the decoy datasets can lower the performance of scoring functions.

OBJECTIVES

To address key limitations of previous scoring functions and thus improve the predictive performance of structure-based virtual screening.

METHODS

A novel machine-learning scoring function was created, named SCORCH (Scoring COnsensus for RMSD-based Classification of Hits). To develop SCORCH, training data is augmented by considering multiple ligand poses and labelling poses based on their RMSD from the native pose. Decoy bias is addressed by generating property-matched decoys for each ligand and using the same methodology for preparing and docking decoys and ligands. A consensus of 3 different machine learning approaches is also used to improve performance.

RESULTS

We find that multi-pose augmentation in SCORCH improves its docking power and screening power on independent benchmark datasets. SCORCH outperforms an equivalent scoring function trained on single poses, with a 1% enrichment factor (EF) of 13.78 vs. 10.86 on 18 DEKOIS 2.0 targets and a mean native pose rank of 5.9 vs 30.4 on CSAR 2014. Additionally, SCORCH outperforms widely used scoring functions in virtual screening and pose prediction on independent benchmark datasets.

CONCLUSION

By rationally addressing key limitations of previous scoring functions, SCORCH improves the performance of virtual screening. SCORCH also provides an estimate of its uncertainty, which can help reduce the cost and time required for drug discovery.

Artificial intelligence and machine-learning approaches in structure and ligand-based discovery of drugs affecting central nervous system

CNS disorders are indications with a very high unmet medical needs, relatively smaller number of available drugs, and a subpar satisfaction level among patients and caregiver. Discovery of CNS drugs is extremely expensive affair with its own unique challenges leading to extremely high attrition rates and low efficiency. With explosion of data in information age, there is hardly any aspect of life that has not been touched by data driven technologies such as artificial intelligence (AI) and machine learning (ML). Drug discovery is no exception, emergence of big data via genomic, proteomic, biological, and chemical technologies has driven pharmaceutical giants to collaborate with AI oriented companies to revolutionise drug discovery, with the goal of increasing the efficiency of the process. In recent years many examples of innovative applications of AI and ML techniques in CNS drug discovery has been reported. Research on therapeutics for diseases such as schizophrenia, Alzheimer's and Parkinsonism has been provided with a new direction and thrust from these developments. AI and ML has been applied to both ligand-based and structure-based drug discovery and design of CNS therapeutics. In this review, we have summarised the general aspects of AI and ML from the perspective of drug discovery followed by a comprehensive coverage of the recent developments in the applications of AI/ML techniques in CNS drug discovery.

Implementing a Scoring Function Based on Interaction Fingerprint for Autogrow4: Protein Kinase CK1δ as a Case Study

In the last 20 years, fragment-based drug discovery (FBDD) has become a popular and consolidated approach within the drug discovery pipeline, due to its ability to bring several drug candidates to clinical trials, some of them even being approved and introduced to the market. A class of targets that have proven to be particularly suitable for this method is represented by kinases, as demonstrated by the approval of BRAF inhibitor vemurafenib. Within this wide and diverse set of proteins, protein kinase CK1δ is a particularly interesting target for the treatment of several widespread neurodegenerative diseases, such as Alzheimer’s disease, Parkinson’s disease, and amyotrophic lateral sclerosis. Computational methodologies, such as molecular docking, are already routinely and successfully applied in FBDD campaigns alongside experimental techniques, both in the hit-discovery and in the hit-optimization stage. Concerning this, the open-source software Autogrow, developed by the Durrant lab, is a semi-automated computational protocol that exploits a combination between a genetic algorithm and a molecular docking software for de novo drug design and lead optimization. In the current work, we present and discuss a modified version of the Autogrow code that implements a custom scoring function based on the similarity between the interaction fingerprint of investigated compounds and a crystal reference. To validate its performance, we performed both a de novo and a lead-optimization run (as described in the original publication), evaluating the ability of our fingerprint-based protocol to generate compounds similar to known CK1δ inhibitors based on both the predicted binding mode and the electrostatic and shape similarity in comparison with the standard Autogrow protocol.

Scoring Functions for Protein-Ligand Binding Affinity Prediction using Structure-Based Deep Learning: A Review

The rapid and accurate in silico prediction of protein-ligand binding free energies or binding affinities has the potential to transform drug discovery. In recent years, there has been a rapid growth of interest in deep learning methods for the prediction of protein-ligand binding affinities based on the structural information of protein-ligand complexes. These structure-based scoring functions often obtain better results than classical scoring functions when applied within their applicability domain. Here we review structure-based scoring functions for binding affinity prediction based on deep learning, focussing on different types of architectures, featurization strategies, data sets, methods for training and evaluation, and the role of explainable artificial intelligence in building useful models for real drug-discovery applications.

Pose Classification Using Three-Dimensional Atomic Structure-Based Neural Networks Applied to Ion Channel-Ligand Docking

The identification of promising lead compounds showing pharmacological activities toward a biological target is essential in early stage drug discovery. With the recent increase in available small-molecule databases, virtual high-throughput screening using physics-based molecular docking has emerged as an essential tool in assisting fast and cost-efficient lead discovery and optimization. However, the best scored docking poses are often suboptimal, resulting in incorrect screening and chemical property calculation. We address the pose classification problem by leveraging data-driven machine learning approaches to identify correct docking poses from AutoDock Vina and Glide screens. To enable effective classification of docking poses, we present two convolutional neural network approaches: a three-dimensional convolutional neural network (3D-CNN) and an attention-based point cloud network (PCN) trained on the PDBbind refined set. We demonstrate the effectiveness of our proposed classifiers on multiple evaluation data sets including the standard PDBbind CASF-2016 benchmark data set and various compound libraries with structurally different protein targets including an ion channel data set extracted from Protein Data Bank (PDB) and an in-house KCa3.1 inhibitor data set. Our experiments show that excluding false positive docking poses using the proposed classifiers improves virtual high-throughput screening to identify novel molecules against each target protein compared to the initial screen based on the docking scores.