HDAC3i-Finder: A Machine Learning-based Computational Tool to Screen for HDAC3 Inhibitors

Stack-HDAC3i: A high-precision identification of HDAC3 inhibitors by exploiting a stacked ensemble-learning framework

Epigenetics involves reversible modifications in gene expression without altering the genetic code itself. Among these modifications, histone deacetylases (HDACs) play a key role by removing acetyl groups from lysine residues on histones. Overexpression of HDACs is linked to the proliferation and survival of tumor cells. To combat this, HDAC inhibitors (HDACi) are commonly used in cancer treatments. However, pan-HDAC inhibition can lead to numerous side effects. Therefore, isoform-selective HDAC inhibitors, such as HDAC3i, could be advantageous for treating various medical conditions while minimizing off-target effects. To date, computational approaches that use only the SMILES notation without any experimental evidence have become increasingly popular and necessary for the initial discovery of novel potential therapeutic drugs. In this study, we develop an innovative and high-precision stacked-ensemble framework, called Stack-HDAC3i, which can directly identify HDAC3i using only the SMILES notation. Using an up-to-date benchmark dataset, we first employed both molecular descriptors and Mol2Vec embeddings to generate feature representations that cover multi-view information embedded in HDAC3i, such as structural and contextual information. Subsequently, these feature representations were used to train baseline models using nine popular ML algorithms. Finally, the probabilistic features derived from the selected baseline models were fused to construct the final stacked model. Both cross-validation and independent tests showed that Stack-HDAC3i is a high-accuracy prediction model with great generalization ability for identifying HDAC3i. Furthermore, in the independent test, Stack-HDAC3i achieved an accuracy of 0.926 and Matthew's correlation coefficient of 0.850, which are 0.44-6.11% and 0.83-11.90% higher than its constituent baseline models, respectively.

HT_PREDICT: a machine learning-based computational open-source tool for screening HDAC6 inhibitors

Histone deacetylase 6 (HDAC6) is a promising drug target for the treatment of human diseases such as cancer, neurodegenerative diseases (in particular, Alzheimer's disease), and multiple sclerosis. Considerable attention is paid to the development of selective non-toxic HDAC6 inhibitors. To this end, we successfully form a set of 3854 compounds and proposed adequate regression QSAR models for HDAC6 inhibitors. The models have been developed using the PubChem, Klekota-Roth, 2D atom pair fingerprints, and RDkit descriptors and the gradient boosting, support vector machines, neural network, and k-nearest neighbours methods. The models are integrated into the developed HT_PREDICT application, which is freely available at https://htpredict.streamlit.app/. In vitro studies have confirmed the predictive ability of the proposed QSAR models integrated into the HT_PREDICT web application. In addition, the virtual screening performed with the HT_PREDICT web application allowed us to propose two promising inhibitors for further investigations.

Exploring different classification-dependent QSAR modelling strategies for HDAC3 inhibitors in search of meaningful structural contributors

Histone deacetylase 3 (HDAC3), a Zn2+-dependent class I HDACs, contributes to numerous disorders such as neurodegenerative disorders, diabetes, cardiovascular disease, kidney disease and several types of cancers. Therefore, the development of novel and selective HDAC3 inhibitors might be promising to combat such diseases. Here, different classification-based molecular modelling studies such as Bayesian classification, recursive partitioning (RP), SARpy and linear discriminant analysis (LDA) were conducted on a set of HDAC3 inhibitors to pinpoint essential structural requirements contributing to HDAC3 inhibition followed by molecular docking study and molecular dynamics (MD) simulation analyses. The current study revealed the importance of hydroxamate function for Zn2+ chelation as well as hydrogen bonding interaction with Tyr298 residue. The importance of hydroxamate function for higher HDAC3 inhibition was noticed in the case of Bayesian classification, recursive partitioning and SARpy models. Also, the importance of substituted thiazole ring was revealed, whereas the presence of linear alkyl groups with carboxylic acid function, any type of ester function, benzodiazepine moiety and methoxy group in the molecular structure can be detrimental to HDAC3 inhibition. Therefore, this study can aid in the design and discovery of effective novel HDAC3 inhibitors in the future.

HDAC3 inhibitors: a patent review of their broad-spectrum applications as therapeutic agents

INTRODUCTION

Histone deacetylases (HDACs) are a class of zinc-dependent enzymes. They maintain acetylation homeostasis, with numerous biological functions and are associated with many diseases. HDAC3 strictly requires multi-subunit complex formation for activity. It is associated with the progression of numerous non-communicable diseases. Its widespread involvement in diseases makes it an epigenetic drug target. Preexisting HDAC3 inhibitors have many uses, highlighting the need for continued research in the discovery of HDAC3-selective inhibitors.

AREA COVERED

This review provides an overview of 24 patents published from 2010 to 2023, focusing on compounds that inhibit the HDAC3 isoenzyme.

EXPERT OPINION

HDAC3-selective inhibitors - pivotal for pharmacological applications, as single or combination therapies - are gaining traction as a strategy to move away from complications laden pan-HDAC inhibitors. Moreover, there is an unmet need for HDAC3 inhibitors with alternative zinc-binding groups (ZBGs) because some preexisting ZBGs have limitations related to toxicity and side effects. Difficulties in achieving HDAC3 selectivity may be due to isoform selectivity. However, advancements in computer-aided drug design and experimental data of HDAC3 3D co-crystallized models could lead to the discovery of novel HDAC3-selective inhibitors, which bear alternative ZBGs with balanced selectivity for HDAC3 and potency.

MLASM: Machine learning based prediction of anticancer small molecules

Cancer, being the second leading cause of death globally. So, the development of effective anticancer treatments is crucial in the field of medicine. Anticancer peptides (ACPs) have shown promising therapeutic potential in cancer treatment compared to traditional methods. However, the process of identifying ACPs through experimental means is often time-intensive and expensive. To overcome this issue, we employed a machine learning-based approach for the first time to develop an anticancer model using small molecules. Anticancer small molecules (ACSMs) are compounds that have been developed to target and inhibit cancer cells. In this study, we used 10,000 compounds to develop the machine learning models using five algorithms such as, Random Forest (RF), Light gradient boosting machine (LightGBM), K-nearest neighbors (KNN), Decision tree (DT) and Extreme Gradient Boosting (XGB). The developed models were evaluated using the test set and top three models were identified (RF, LightGBM and XGB). Furthermore, to validate the predictive performance of our models, we have performed external validation using an FDA approved anticancer compounds/drugs. Following this analysis, we found that our LightGBM model correctly predicted 9 compounds as active. However, RF and XGB exhibited some limitations by predicting 8 and 7 compounds as active out of 10, respectively. These results demonstrate that, when compared to RF and XGB, the LightGBM model showcase robust prediction capabilities, achieving a superior accuracy of 79% with an AUC of 0.88. These findings provide promising insights into the potential of our approach for predicting anticancer small molecules, highlighting the role of machine learning in advancing cancer treatment research.

Deep reinforcement learning enables better bias control in benchmark for virtual screening

Virtual screening (VS) has been incorporated into the paradigm of modern drug discovery. This field is now undergoing a new wave of revolution driven by artificial intelligence and more specifically, machine learning (ML). In terms of those out-of-the-box datasets for model training or benchmarking, their data volume and applicability domain are limited. They are suffering from the biases constantly reported in the ML application. To address these issues, we present a novel benchmark named MUBDsyn. The utilization of synthetic decoys (i.e., presumed inactives) is the main feature of MUBDsyn, where deep reinforcement learning was leveraged for bias control during decoy generation. Then, we carried out extensive validations on this new benchmark. First, we confirmed that MUBDsyn was superior to the classical benchmarks in control of domain bias, artificial enrichment bias and analogue bias. Moreover, we found that the assessment of ML models based on MUBDsyn was less biased as revealed by the analysis of asymmetric validation embedding bias. In addition, MUBDsyn showed better setting of benchmarking challenge for deep learning models compared with NRLiSt-BDB. Overall, we have proven that MUBDsyn is the close-to-ideal benchmark for VS. The computational tool is publicly available for the easy extension of MUBDsyn.

Large-scale comparison of machine learning methods for profiling prediction of kinase inhibitors

Conventional machine learning (ML) and deep learning (DL) play a key role in the selectivity prediction of kinase inhibitors. A number of models based on available datasets can be used to predict the kinase profile of compounds, but there is still controversy about the advantages and disadvantages of ML and DL for such tasks. In this study, we constructed a comprehensive benchmark dataset of kinase inhibitors, involving in 141,086 unique compounds and 216,823 well-defined bioassay data points for 354 kinases. We then systematically compared the performance of 12 ML and DL methods on the kinase profiling prediction task. Extensive experimental results reveal that (1) Descriptor-based ML models generally slightly outperform fingerprint-based ML models in terms of predictive performance. RF as an ensemble learning approach displays the overall best predictive performance. (2) Single-task graph-based DL models are generally inferior to conventional descriptor- and fingerprint-based ML models, however, the corresponding multi-task models generally improves the average accuracy of kinase profile prediction. For example, the multi-task FP-GNN model outperforms the conventional descriptor- and fingerprint-based ML models with an average AUC of 0.807. (3) Fusion models based on voting and stacking methods can further improve the performance of the kinase profiling prediction task, specifically, RF::AtomPairs + FP2 + RDKitDes fusion model performs best with the highest average AUC value of 0.825 on the test sets. These findings provide useful information for guiding choices of the ML and DL methods for the kinase profiling prediction tasks. Finally, an online platform called KIPP ( https://kipp.idruglab.cn ) and python software are developed based on the best models to support the kinase profiling prediction, as well as various kinase inhibitor identification tasks including virtual screening, compound repositioning and target fishing.

Predicting GPR40 Agonists with A Deep Learning-Based Ensemble Model

Recent studies have identified G protein-coupled receptor 40 (GPR40) as a promising target for treating type 2 diabetes mellitus, and GPR40 agonists have several superior effects over other hypoglycemic drugs, including cardiovascular protection and suppression of glucagon levels. In this study, we constructed an up-to-date GPR40 ligand dataset for training models and performed a systematic optimization of the ensemble model, resulting in a powerful ensemble model (ROC AUC: 0.9496) for distinguishing GPR40 agonists and non-agonists. The ensemble model is divided into three layers, and the optimization process is carried out in each layer. We believe that these results will prove helpful for both the development of GPR40 agonists and ensemble models. All the data and models are available on GitHub. (https://github.com/Jiamin-Yang/ensemble_model).

Development and validation of machine learning models for the prediction of SH-2 containing protein tyrosine phosphatase 2 inhibitors

Discovery and development of a new drug to the market is a highly challenging and resource consuming process. Although, modern drug discovery technologies have enabled the rapid identification of lead compounds, translation of the lead compounds into successful clinical candidates remains a big challenge. In recent years, the availability of massive structural and biological data of diverse small molecules and macromolecules has helped the researchers to deep mine the multidimensional data with the help of artificial intelligence-based predictive tools to draw useful insights on the structural features of biological or therapeutic significance. The aim of this study was to utilize the available data on small molecule (SH2)-containing protein tyrosine phosphatase 2 (SHP2) inhibitors to build and develop machine learning (ML) models that can predict the SHP2 inhibitory potential of new compounds. The dataset contained 2739 unique small molecule SHP2 inhibitors obtained from the BindingDB, ChEMBL and recent literature. After curation of the data, the predictive models such as XGBoost, K nearest neighbours, neural networks were developed and validated through a tenfold cross-validation testing procedure. Out of the seven models developed, the XGBoost model showed an excellent performance with ROC AUC score of 0.96 and accuracy of 0.97 on the test data. Moreover, the Shapley Additive Explanations method was applied to assess a more in-depth understanding of the influence of variables on the model's predictions. In summary, the XGBoost model developed in this study can be useful in the identification of novel SHP2 inhibitors and therefore, can accelerate the discovery of novel therapeutics for cancer therapy.

A machine learning-integrated stepwise method to discover novel anti-obesity phytochemicals that antagonize the glucocorticoid receptor

As a type of stress hormone, glucocorticoids (GCs) affect numerous physiological pathways by binding to the glucocorticoid receptor (GR) and regulating the transcription of various genes. However, when GCs are dysregulated, the resulting hypercortisolism may contribute to various metabolic disorders, including obesity. Thus, attempts have been made to discover potent GR antagonists that can reverse excess-GC-related metabolic diseases. Phytochemicals are a collection of valuable bioactive compounds that are known for their wide variety of chemotypes. Recently, various computational methods have been developed to obtain active phytochemicals that can modulate desired target proteins. In this study, we developed a workflow comprising two consecutive quantitative structure-activity relationship-based machine learning models to discover novel GR-antagonizing phytochemicals. These two models collectively identified 65 phytochemicals that bind to and antagonize GR. Of these, nine commercially available phytochemicals were validated for GR-antagonist and anti-obesity activities. In particular, we confirmed that demethylzeylasteral, a phytochemical of the Tripterygium wilfordii Radix, exhibits potent anti-obesity activity in vitro through GR antagonism.

Opportunities and challenges in application of artificial intelligence in pharmacology

Artificial intelligence (AI) is a machine science that can mimic human behaviour like intelligent analysis of data. AI functions with specialized algorithms and integrates with deep and machine learning. Living in the digital world can generate a huge amount of medical data every day. Therefore, we need an automated and reliable evaluation tool that can make decisions more accurately and faster. Machine learning has the potential to learn, understand and analyse the data used in healthcare systems. In the last few years, AI is known to be employed in various fields in pharmaceutical science especially in pharmacological research. It helps in the analysis of preclinical (laboratory animals) and clinical (in human) trial data. AI also plays important role in various processes such as drug discovery/manufacturing, diagnosis of big data for disease identification, personalized treatment, clinical trial research, radiotherapy, surgical robotics, smart electronic health records, and epidemic outbreak prediction. Moreover, AI has been used in the evaluation of biomarkers and diseases. In this review, we explain various models and general processes of machine learning and their role in pharmacological science. Therefore, AI with deep learning and machine learning could be relevant in pharmacological research.

SIRT2i_Predictor: A Machine Learning-Based Tool to Facilitate the Discovery of Novel SIRT2 Inhibitors

A growing body of preclinical evidence recognized selective sirtuin 2 (SIRT2) inhibitors as novel therapeutics for treatment of age-related diseases. However, none of the SIRT2 inhibitors have reached clinical trials yet. Transformative potential of machine learning (ML) in early stages of drug discovery has been witnessed by widespread adoption of these techniques in recent years. Despite great potential, there is a lack of robust and large-scale ML models for discovery of novel SIRT2 inhibitors. In order to support virtual screening (VS), lead optimization, or facilitate the selection of SIRT2 inhibitors for experimental evaluation, a machine-learning-based tool titled SIRT2i_Predictor was developed. The tool was built on a panel of high-quality ML regression and classification-based models for prediction of inhibitor potency and SIRT1-3 isoform selectivity. State-of-the-art ML algorithms were used to train the models on a large and diverse dataset containing 1797 compounds. Benchmarking against structure-based VS protocol indicated comparable coverage of chemical space with great gain in speed. The tool was applied to screen the in-house database of compounds, corroborating the utility in the prioritization of compounds for costly in vitro screening campaigns. The easy-to-use web-based interface makes SIRT2i_Predictor a convenient tool for the wider community. The SIRT2i_Predictor's source code is made available online.

Identification of novel leads as potent inhibitors of HDAC3 using ligand-based pharmacophore modeling and MD simulation

In the landscape of epigenetic regulation, histone deacetylase 3 (HDAC3) has emerged as a prominent therapeutic target for the design and development of candidate drugs against various types of cancers and other human disorders. Herein, we have performed ligand-based pharmacophore modeling, virtual screening, molecular docking, and MD simulations to design potent and selective inhibitors against HDAC3. The predicted best pharmacophore model 'Hypo 1' showed excellent correlation (R2 = 0.994), lowest RMSD (0.373), lowest total cost value (102.519), and highest cost difference (124.08). Hypo 1 consists of four salient pharmacophore features viz. one hydrogen bond acceptor (HBA), one ring aromatic (RA), and two hydrophobic (HYP). Hypo 1 was validated by Fischer's randomization with a 95% of confidence level and the external test set of 60 compounds with a good correlation coefficient (R2 = 0.970). The virtual screening of chemical databases, drug-like properties calculations followed by molecular docking resulted in identifying 22 representative hit compounds. Performed 50 ns of MD simulations on top three hits were retained the salient π-stacking, Zn2+ coordination, hydrogen bonding, and hydrophobic interactions with catalytic residues from the active site pocket of HDAC3. Total binding energy calculated by MM-PBSA showed that the Hit 1 and Hit 2 formed stable complexes with HDAC3 as compared to reference TSA. Further, the PLIP analysis showed a close resemblance between the salient pharmacophore features of Hypo 1 and the presence of molecular interactions in co-crystallized FDA-approved drugs. We conclude that the screened hit compounds may act as potent inhibitors of HDAC3 and further preclinical and clinical studies may pave the way for developing them as effective therapeutic agents for the treatment of different cancers and neurodegenerative disorders.

Machine Learning Enables Accurate and Rapid Prediction of Active Molecules Against Breast Cancer Cells

Breast cancer (BC) has surpassed lung cancer as the most frequently occurring cancer, and it is the leading cause of cancer-related death in women. Therefore, there is an urgent need to discover or design new drug candidates for BC treatment. In this study, we first collected a series of structurally diverse datasets consisting of 33,757 active and 21,152 inactive compounds for 13 breast cancer cell lines and one normal breast cell line commonly used in in vitro antiproliferative assays. Predictive models were then developed using five conventional machine learning algorithms, including naïve Bayesian, support vector machine, k-Nearest Neighbors, random forest, and extreme gradient boosting, as well as five deep learning algorithms, including deep neural networks, graph convolutional networks, graph attention network, message passing neural networks, and Attentive FP. A total of 476 single models and 112 fusion models were constructed based on three types of molecular representations including molecular descriptors, fingerprints, and graphs. The evaluation results demonstrate that the best model for each BC cell subtype can achieve high predictive accuracy for the test sets with AUC values of 0.689–0.993. Moreover, important structural fragments related to BC cell inhibition were identified and interpreted. To facilitate the use of the model, an online webserver called ChemBC (http://chembc.idruglab.cn/) and its local version software (https://github.com/idruglab/ChemBC) were developed to predict whether compounds have potential inhibitory activity against BC cells.

Chemoinformatics and Machine Learning Approaches for Identifying Antiviral Compounds

Current pandemics propelled research efforts in unprecedented fashion, primarily triggering computational efforts towards new vaccine and drug development as well as drug repurposing. There is an urgent need to design novel drugs with targeted biological activity and minimum adverse reactions that may be useful to manage viral outbreaks. Hence an attempt has been made to develop Machine Learning based predictive models that can be used to assess whether a compound has the potency to be antiviral or not. To this end, a set of 2358 antiviral compounds were compiled from the CAS COVID-19 antiviral SAR dataset whose activity was reported based on IC₅₀ value. A total 1157 two-dimensional molecular descriptors were computed among which, the most highly correlated descriptors were selected using Tree-based, Correlation-based and Mutual information-based feature selection methods. Seven Machine Learning algorithms i. e., Random Forest, XGBoost, Support Vector Machine, KNN, Decision Tree, MLP Classifier and Logistic Regression were benchmarked. The best performance was achieved by the models developed using Random Forest and XGBoost algorithms in all the feature selection methods. The maximum predictive accuracy of both these models was 88 % with internal validation. Whereas, with an external dataset, a maximum accuracy of 93.10 % for XGBoost and 100 % for Random Forest based model was achievable. Furthermore, the study demonstrated scaffold analysis of the molecules as a pragmatic approach to explore the importance of structurally diverse compounds in data driven studies.

Recent trends in artificial intelligence-driven identification and development of anti-neurodegenerative therapeutic agents

Neurological disorders affect various aspects of life. Finding drugs for the central nervous system is a very challenging and complex task due to the involvement of the blood-brain barrier, P-glycoprotein, and the drug's high attrition rates. The availability of big data present in online databases and resources has enabled the emergence of artificial intelligence techniques including machine learning to analyze, process the data, and predict the unknown data with high efficiency. The use of these modern techniques has revolutionized the whole drug development paradigm, with an unprecedented acceleration in the central nervous system drug discovery programs. Also, the new deep learning architectures proposed in many recent works have given a better understanding of how artificial intelligence can tackle big complex problems that arose due to central nervous system disorders. Therefore, the present review provides comprehensive and up-to-date information on machine learning/artificial intelligence-triggered effort in the brain care domain. In addition, a brief overview is presented on machine learning algorithms and their uses in structure-based drug design, ligand-based drug design, ADMET prediction, de novo drug design, and drug repurposing. Lastly, we conclude by discussing the major challenges and limitations posed and how they can be tackled in the future by using these modern machine learning/artificial intelligence approaches.

Epigenetic Target Fishing with Accurate Machine Learning Models

Epigenetic targets are of significant importance in drug discovery research, as demonstrated by the eight approved epigenetic drugs for treatment of cancer and the increasing availability of chemogenomic data related to epigenetics. This data represents many structure-activity relationships that have not been exploited thus far to develop predictive models to support medicinal chemistry efforts. Herein, we report the first large-scale study of 26 318 compounds with a quantitative measure of biological activity for 55 protein targets with epigenetic activity. We built predictive models with high accuracy for small molecules' epigenetic target profiling through a systematic comparison of the machine learning models trained on different molecular fingerprints. The models were thoroughly validated, showing mean precisions of up to 0.952 for the epigenetic target prediction task. Our results indicate that the models reported herein have considerable potential to identify small molecules with epigenetic activity. Therefore, our results were implemented as a freely accessible web application.