Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets

Integrating Molecular Dynamics and Machine Learning Algorithms to Predict the Functional Profile of Kinase Ligands

The modulation of protein function via designed small molecules is providing new opportunities in chemical biology and medicinal chemistry. While drugs have traditionally been developed to block enzymatic activities through active site occupation, a growing number of strategies now aim to control protein functions in an allosteric fashion, allowing for the tuning of a target's activation or deactivation via the modulation of the populations of conformational ensembles that underlie its function. In the context of the discovery of new active leads, it would be very useful to generate hypotheses for the functional impact of new ligands. Since the discovery and design of allosteric modulators (inhibitors/activators) is still a challenging and often serendipitous target, the development of a rapid and robust approach to predict the functional profile of a new ligand would significantly speed up candidate selection. Herein, we present different machine learning (ML) classifiers to distinguish between potential orthosteric and allosteric binders. Our approach integrates information on the chemical fingerprints of the ligands with descriptors that recapitulate ligand effects on protein functional motions. The latter are derived from molecular dynamics (MD) simulations of the target protein in complex with orthosteric or allosteric ligands. In this framework, we train and test different ML architectures, which are initially probed on the classification of orthosteric versus allosteric ligands for cyclin-dependent kinases (CDKs). The results demonstrate that different ML methods can successfully partition allosteric versus orthosteric effectors (although to different degrees). Next, we further test the models with FDA-approved CDK drugs, not included in the original dataset, as well as ligands that target other kinases, to test the range of applicability of these models outside of the domain on which they were developed. Overall, the results show that enriching the training dataset with chemical physics-based information on the protein-ligand dynamic cross-talk can significantly expand the reach and applicability of approaches for the prediction and classification of the mode of action of small molecules.

Rationale, in silico docking, ADMET profile, design, synthesis and cytotoxicity evaluations of phthalazine derivatives as VEGFR-2 inhibitors and apoptosis inducers

New phthalazine derivatives as vascular endothelial growth factor receptor-2 (VEGFR-2) inhibitors were synthesized joined to different spacers including pyrazole, α,β-unsaturated ketonic fragment, pyrimidinone and/or pyrimidinthione. A docking study was carried out to explore the suggested binding orientations of the novel derivatives inside the active site of VEGFR-2. The obtained biological data were extremely interrelated to that of the docking study. In particular, compounds 4b and 3e showed the highest activities against Michigan Cancer Foundation-7 (MCF-7) and Hepatocellular carcinoma G2 (HepG2) with half maximal inhibitory concentration (IC50) = 0.06, 0.06 μM and 0.08, 0.19 μM respectively. Our derivatives 3a-e, 4a,b and 5a,b were evaluated for their cytotoxicity against normal VERO cells. Our compounds exhibited low toxicity concerning normal VERO cells with IC50 = 3.00-4.75 μM. In addition, our final derivatives 3a-e, 4a, 4b, 5a and 5b were investigated for their VEGFR-2 inhibitory activities. Derivative 4b exhibited the highest VEGFR-2 inhibitory activities at an IC50 value of 0.09 ± 0.02 μM. Derivatives 3e, 4a and 5b demonstrated good activities with IC50 values = 0.12 ± 0.02, 0.15 ± 0.03 and 0.13 ± 0.03 μM respectively. Furthermore, the activities of 4b were assessed against MCF-7 cancer cells for apoptosis induction, cell cycle distribution and growth inhibition. Compound 4b caused cell growth arrest in growth 2-mitosis (G2-M) phase; accumulation of cells at that phase became 6.92% after being 13.2 in control cells. Moreover, our derivatives 3e, 4b and 5b revealed a good in silico considered absorption, distribution, metabolism, excretion, and toxicity (ADMET) profile in comparison to sorafenib.

A comprehensive exploration of the druggable conformational space of protein kinases using AI-predicted structures

Protein kinase function and interactions with drugs are controlled in part by the movement of the DFG and ɑC-Helix motifs that are related to the catalytic activity of the kinase. Small molecule ligands elicit therapeutic effects with distinct selectivity profiles and residence times that often depend on the active or inactive kinase conformation(s) they bind. Modern AI-based structural modeling methods have the potential to expand upon the limited availability of experimentally determined kinase structures in inactive states. Here, we first explored the conformational space of kinases in the PDB and models generated by AlphaFold2 (AF2) and ESMFold, two prominent AI-based protein structure prediction methods. Our investigation of AF2's ability to explore the conformational diversity of the kinome at various multiple sequence alignment (MSA) depths showed a bias within the predicted structures of kinases in DFG-in conformations, particularly those controlled by the DFG motif, based on their overabundance in the PDB. We demonstrate that predicting kinase structures using AF2 at lower MSA depths explored these alternative conformations more extensively, including identifying previously unobserved conformations for 398 kinases. Ligand enrichment analyses for 23 kinases showed that, on average, docked models distinguished between active molecules and decoys better than random (average AUC (avgAUC) of 64.58), but select models perform well (e.g., avgAUCs for PTK2 and JAK2 were 79.28 and 80.16, respectively). Further analysis explained the ligand enrichment discrepancy between low- and high-performing kinase models as binding site occlusions that would preclude docking. The overall results of our analyses suggested that, although AF2 explored previously uncharted regions of the kinase conformational space and select models exhibited enrichment scores suitable for rational drug discovery, rigorous refinement of AF2 models is likely still necessary for drug discovery campaigns.

QSAR prediction, synthesis, anticancer evaluation, and mechanistic investigations of novel sophoridine derivatives as topoisomerase I inhibitors

Sophoridine, which is derived from the Leguminous plant Sophora alopecuroides L., has certain pharmacological activity as a new anticancer drug. Herein, a series of novel N-substituted sophoridine derivatives was designed, synthesized and evaluated with anticancer activity. Through QSAR prediction models, it was discovered that the introduction of a benzene ring as a main pharmacophore and reintroduced into a benzene in para position on the phenyl ring in the novel sophoridine derivatives improved the anticancer activity effectively. In vitro, 28 novel compounds were evaluated for anticancer activity against four human tumor cell lines (A549, CNE-2, HepG-2, and HEC-1-B). In particular, Compound 26 exhibited remarkable inhibitory effects, with an IC50 value of 15.6 μM against HepG-2 cells, surpassing cis-Dichlorodiamineplatinum (II). Molecular docking studies verified that the derivatives exhibit stronger binding affinity with DNA topoisomerase I compared to sophoridine. In addition, 26 demonstrated significant inhibition of DNA Topoisomerase I and could arrest cells in G0/G1 phase. This study provides valuable insights into the design and synthesis of N-substituted sophoridine derivatives with anticancer activity.

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.

Pharmacology activity, toxicity, and clinical trials of Erythrina genus plants (Fabaceae): an evidence-based review

The concept of using plants to alleviate diseases is always challenging. In West Java, Indonesia, a local plant, named dadap serep has been traditionally used to reduce blood glucose, fever, and edema, by pounding the leaves and applying them on the inflamed skin, or boiled and consumed as herbal tea. This plant belongs to the Erythrina genus, which covers approximately 120 species. The scope of this review (1943-2023) is related to the Global Development Goals, in particular Goal 3: Good Health and Wellbeing, by focusing on the pharmacology activity, toxicity, and clinical trials of Erythrina genus plants and their metabolites, e.g., pterocarpans, alkaloids, and flavonoids. Articles were searched on PubMed and ScienceDirect databases, using "Erythrina" AND "pharmacology activity" keywords, and only original articles written in English and open access were included. In vitro and in vivo studies reveal promising results, particularly for antibacterial and anticancer activities. The toxicity and clinical studies of Erythrina genus plants are limitedly reported. Considering that extensive caution should be taken when prescribing botanical drugs for patients parallelly taking a narrow therapeutic window drug, it is confirmed that no interactions of the Erythrina genus were recorded, indicating the safety of the studied plants. We, therefore, concluded that Erythrina genus plants are promising to be further explored for their effects in various signaling pathways as future plant-based drug candidates.

Identification and verification of characteristic differentially expressed ferroptosis-related genes in osteosarcoma using bioinformatics analysis

BACKGROUND

This study identified and verified the characteristic differentially expressed ferroptosis-related genes (CDEFRGs) in osteosarcoma (OS).

METHODS

We extracted ferroptosis-related genes (FRGs), identified differentially expressed FRGs (DEFRGs) in OS, and conducted correlation analysis between DEFRGs. Next, we conducted GO and KEGG analyses to explore the biological functions and pathways of DEFRGs. Furthermore, we used LASSO and SVM-RFE algorithms to screen CDEFRGs, and evaluated its accuracy in diagnosing OS through ROC curves. Then, we demonstrated the molecular function and pathway enrichment of CDEFRGs through GSEA analysis. In addition, we evaluated the differences in immune cell infiltration between OS and NC groups, as well as the correlation between CDEFRGs expressions and immune cell infiltrations. Finally, the expression of CDEFRGs was verified through qRT-PCR, western blotting, and immunohistochemistry experiments.

RESULTS

We identified 51 DEFRGs and the expression relationship between them. GO and KEGG analysis revealed their key functions and important pathways. Based on four CDEFRGs (PEX3, CPEB1, NOX1, and ALOX5), we built the OS diagnostic model, and verified its accuracy. GSEA analysis further revealed the important functions and pathways of CDEFRGs. In addition, there were differences in immune cell infiltration between OS group and NC group, and CDEFRGs showed significant correlation with certain infiltrating immune cells. Finally, we validated the differential expression levels of four CDEFRGs through external experiments.

CONCLUSIONS

This study has shed light on the molecular pathological mechanism of OS and has offered novel perspectives for the early diagnosis and immune-targeted therapy of OS patients.

Zebrafish as model system for the biological characterization of CK1 inhibitors

Introduction: The CK1 family is involved in a variety of physiological processes by regulating different signaling pathways, including the Wnt/β-catenin, the Hedgehog and the p53 signaling pathways. Mutations or dysregulation of kinases in general and of CK1 in particular are known to promote the development of cancer, neurodegenerative diseases and inflammation. There is increasing evidence that CK1 isoform specific small molecule inhibitors, including CK1δ- and CK1ε-specific inhibitors of Wnt production (IWP)-based small molecules with structural similarity to benzimidazole compounds, have promising therapeutic potential. Methods: In this study, we investigated the suitability of the zebrafish model system for the evaluation of such CK1 inhibitors. To this end, the kinetic parameters of human CK1 isoforms were compared with those of zebrafish orthologues. Furthermore, the effects of selective CK1δ inhibition during zebrafish embryonic development were analyzed in vivo. Results: The results revealed that zebrafish CK1δA and CK1δB were inhibited as effectively as human CK1δ by compounds G2-2 with IC50 values of 345 and 270 nM for CK1δA and CK1δB versus 503 nM for human CK1δ and G2-3 exhibiting IC50 values of 514 and 561 nM for zebrafish CK1δA and B, and 562 nM for human CK1δ. Furthermore, the effects of selective CK1δ inhibition on zebrafish embryonic development in vivo revealed phenotypic abnormalities indicative of downregulation of CK1δ. Treatment of zebrafish embryos with selected inhibitors resulted in marked phenotypic changes including blood stasis, heart failure, and tail malformations. Conclusion: The results suggest that the zebrafish is a suitable in vivo assay model system for initial studies of the biological relevance of CK1δ inhibition.

Machine learning facilitated structural activity relationship approach for the discovery of novel inhibitors targeting EGFR

This research manuscript aims to find the most effective epidermal growth factor receptor (EGFR) inhibitors from millions of in house compounds through Machine Learning (ML) techniques. ML-based structure activity relationship (SAR) models were validated to predict biological activity of untested novel molecules. Six ML algorithms, including k nearest neighbour (KNN), decision tree (DT), Logistic Regression, support vector machine (SVM), multilinear regression (MLR), and random forest (RF), were used to build for activity prediction. Among these, RF classifier (accuracy for train and test set is 90% and 81%) and RF regressor (R2 and MSE for trainset is 0.83 and 0.29 and for test set, 0.69 and 0.46) showed good predictive performance. Also, the six most essential features that affect the biological activity parameter and highly contribute to model development were successfully selected by the variable importance technique. RF regression model was used to predict the biological activity expressed as pIC50 of nearly ten million molecules while RF classification model classifies those molecules into active, moderately active, and least active according to their predicted pIC50. Based on two models, thousand molecules from million molecules with higher predicted pIC50 values and classified as active were selected for molecular docking. Based on the docking scores, predicted pIC50, and binding interactions with MET769 residue, compounds, i.e., Zinc257233137, Zinc257232249, and Zinc101379788, were identified as potential EGFR inhibitors with predicted pIC50 7.72, 7.85, and 7.70. Dynamics studies were also performed on Zinc257233137 to illustrate that it has good binding free energy and stable hydrogen bonding interactions with EGFR. These molecules can be used for further research and proved to be the novel drugs for EGFR in cancer treatment.Communicated by Ramaswamy H. Sarma.

The use of machine learning modeling, virtual screening, molecular docking, and molecular dynamics simulations to identify potential VEGFR2 kinase inhibitors

Targeting the signaling pathway of the Vascular endothelial growth factor receptor-2 is a promising approach that has drawn attention in the quest to develop novel anti-cancer drugs and cardiovascular disease treatments. We construct a screening pipeline using machine learning classification integrated with similarity checks of approved drugs to find new inhibitors. The statistical metrics reveal that the random forest approach has slightly better performance. By further similarity screening against several approved drugs, two candidates are selected. Analysis of absorption, distribution, metabolism, excretion, and toxicity, along with molecular docking and dynamics are performed for the two candidates with regorafenib as a reference. The binding energies of molecule1, molecule2, and regorafenib are - 89.1, - 95.3, and - 87.4 (kJ/mol), respectively which suggest candidate compounds have strong binding to the target. Meanwhile, the median lethal dose and maximum tolerated dose for regorafenib, molecule1, and molecule2 are predicted to be 800, 1600, and 393 mg/kg, and 0.257, 0.527, and 0.428 log mg/kg/day, respectively. Also, the inhibitory activity of these compounds is predicted to be 7.23 and 7.31, which is comparable with the activity of pazopanib and sorafenib drugs. In light of these findings, the two compounds could be further investigated as potential candidates for anti-angiogenesis therapy.

KUALA: a machine learning-driven framework for kinase inhibitors repositioning

The family of protein kinases comprises more than 500 genes involved in numerous functions. Hence, their physiological dysfunction has paved the way toward drug discovery for cancer, cardiovascular, and inflammatory diseases. As a matter of fact, Kinase binding sites high similarity has a double role. On the one hand it is a critical issue for selectivity, on the other hand, according to poly-pharmacology, a synergistic controlled effect on more than one target could be of great pharmacological interest. Another important aspect of binding similarity is the possibility of exploit it for repositioning of drugs on targets of the same family. In this study, we propose our approach called Kinase drUgs mAchine Learning frAmework (KUALA) to automatically identify kinase active ligands by using specific sets of molecular descriptors and provide a multi-target priority score and a repurposing threshold to suggest the best repurposable and non-repurposable molecules. The comprehensive list of all kinase-ligand pairs and their scores can be found at https://github.com/molinfrimed/multi-kinases .

Interpretable Machine Learning Models for Molecular Design of Tyrosine Kinase Inhibitors Using Variational Autoencoders and Perturbation-Based Approach of Chemical Space Exploration

In the current study, we introduce an integrative machine learning strategy for the autonomous molecular design of protein kinase inhibitors using variational autoencoders and a novel cluster-based perturbation approach for exploration of the chemical latent space. The proposed strategy combines autoencoder-based embedding of small molecules with a cluster-based perturbation approach for efficient navigation of the latent space and a feature-based kinase inhibition likelihood classifier that guides optimization of the molecular properties and targeted molecular design. In the proposed generative approach, molecules sharing similar structures tend to cluster in the latent space, and interpolating between two molecules in the latent space enables smooth changes in the molecular structures and properties. The results demonstrated that the proposed strategy can efficiently explore the latent space of small molecules and kinase inhibitors along interpretable directions to guide the generation of novel family-specific kinase molecules that display a significant scaffold diversity and optimal biochemical properties. Through assessment of the latent-based and chemical feature-based binary and multiclass classifiers, we developed a robust probabilistic evaluator of kinase inhibition likelihood that is specifically tailored to guide the molecular design of novel SRC kinase molecules. The generated molecules originating from LCK and ABL1 kinase inhibitors yielded ~40% of novel and valid SRC kinase compounds with high kinase inhibition likelihood probability values (p > 0.75) and high similarity (Tanimoto coefficient > 0.6) to the known SRC inhibitors. By combining the molecular perturbation design with the kinase inhibition likelihood analysis and similarity assessments, we showed that the proposed molecular design strategy can produce novel valid molecules and transform known inhibitors of different kinase families into potential chemical probes of the SRC kinase with excellent physicochemical profiles and high similarity to the known SRC kinase drugs. The results of our study suggest that task-specific manipulation of a biased latent space may be an important direction for more effective task-oriented and target-specific autonomous chemical design models.

An Explainable Supervised Machine Learning Model for Predicting Respiratory Toxicity of Chemicals Using Optimal Molecular Descriptors

Respiratory toxicity is a serious public health concern caused by the adverse effects of drugs or chemicals, so the pharmaceutical and chemical industries demand reliable and precise computational tools to assess the respiratory toxicity of compounds. The purpose of this study is to develop quantitative structure-activity relationship models for a large dataset of chemical compounds associated with respiratory system toxicity. First, several feature selection techniques are explored to find the optimal subset of molecular descriptors for efficient modeling. Then, eight different machine learning algorithms are utilized to construct respiratory toxicity prediction models. The support vector machine classifier outperforms all other optimized models in 10-fold cross-validation. Additionally, it outperforms the prior study by 2% in prediction accuracy and 4% in MCC. The best SVM model achieves a prediction accuracy of 86.2% and a MCC of 0.722 on the test set. The proposed SVM model predictions are explained using the SHapley Additive exPlanations approach, which prioritizes the relevance of key modeling descriptors influencing the prediction of respiratory toxicity. Thus, our proposed model would be incredibly beneficial in the early stages of drug development for predicting and understanding potential respiratory toxic compounds.

Efficient Energy Management Based on Convolutional Long Short-Term Memory Network for Smart Power Distribution System

An efficient energy management system is integrated with the power grid to collect information about the energy consumption and provide the appropriate control to optimize the supply–demand pattern. Therefore, there is a need for intelligent decisions for the generation and distribution of energy, which is only possible by making the correct future predictions. In the energy market, future knowledge of the energy consumption pattern helps the end-user to decide when to buy or sell the energy to reduce the energy cost and decrease the peak consumption. The Internet of things (IoT) and energy data analytic techniques have provided the convenience to collect the data from the end devices on a large scale and to manipulate all the recorded data. Forecasting an electric load is fairly challenging due to the high uncertainty and dynamic nature involved due to spatiotemporal pattern consumption. Existing conventional forecasting models lack the ability to deal with the spatio-temporally varying data. To overcome the above-mentioned challenges, this work proposes an encoder–decoder model based on convolutional long short-term memory networks (ConvLSTM) for energy load forecasting. The proposed architecture uses encode consisting of multiple ConvLSTM layers to extract the salient features in the data and to learn the sequential dependency and then passes the output to the decoder, having LSTM layers to make forecasting. The forecasting results produced by the proposed approach are favorably comparable to the existing state-of-the-art and better than the conventional methods with the least error rate. Quantitative analyses show that a mean absolute percentage error (MAPE) of 6.966% for household energy consumption and 16.81% for city-wide energy consumption is obtained for the proposed forecasting model in comparison with existing encoder–decoder-based deep learning models for two real-world datasets.

Prediction of Drug-Induced Liver Toxicity Using SVM and Optimal Descriptor Sets

Drug-induced liver toxicity is one of the significant safety challenges for the patient's health and the pharmaceutical industry. It causes termination of drug candidates in clinical trials and also the retractions of approved drugs from the market. Thus, it is essential to identify hepatotoxic compounds in the initial stages of drug development process. The purpose of this study is to construct quantitative structure activity relationship models using machine learning algorithms and systematical feature selection methods for molecular descriptor sets. The models were built from a large and diverse set of 1253 drug compounds and were validated internally with 10-fold cross-validation. In this study, we applied a variety of feature selection techniques to extract the optimal subset of descriptors as modeling features to improve the prediction performance. Experimental results suggested that the support vector machine-based classifier had achieved a better classification accuracy with reduced molecular descriptors. The final optimal model provides an accuracy of 0.811, a sensitivity of 0.840, a specificity of 0.783 and Mathew's correlation coefficient of 0.623 with an internal validation set. Furthermore, this model outperformed the prior studies while evaluated in both the internal and external test sets. The utilization of distinct optimal molecular descriptors as modeling features produce an in silico model with a superior performance.