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.

Computational modelling strategies in exploring triazolopyridazine PIM1 kinase inhibitors as anticancer agents.

BACKGROUND: PIM (Proviral Integration site for Moloney Murine Leukemia virus) kinases are members of the class of kinase family serine/ threonine kinases, which play a crucial role in cancer development. As there is no drug in the market against PIM-1, kinase has transpired as a budding and captivating target for discovering new anticancer agents targeting PIM-1 kinase. AIM: The current research pondered the development of new PIM-1 kinase inhibitors by applying a ligand-based and structure-based drug discovery approach involving 3D QSAR, molecular docking, and dynamics simulation. METHOD: In this study, association allying the structural properties and biological activity was undertaken using 3D-QSAR analysis. The 3D-QSAR model was generated with the help of 35 compounds from which the best model manifested an appreciated cross-validation coefficient (q2) of 0.8866 and conventional correlation coefficient (r2) of 0.9298, respectively and predicted correlation coefficient (r2 pred) was obtained as 0.7878. RESULT: The molecular docking analysis demonstrated that the analogs under analysis occupied the active site of PIM-1 kinase receptor and interactions with Lys67 in the catalytic region, Asp186 in the DFG motif, and Glu171 were noticed with numerous compounds. DISCUSSION: Furthermore, the molecular dynamics simulation study stated that the ligand portrayed the strong conformational stability within the active site of PIM-1 kinase protein, forming of two hydrogen bonds until 100 ns, respectively. CONCLUSION: Overall outcomes of the study revealed that applications of the ligand-based drug discovery approach and structure-based drug discovery strategy conceivably applied to discovering new PIM-1 kinase inhibitors as anticancer agents.

Topical advances in PIM kinases and their inhibitors: Medicinal chemistry perspectives.

Cytosolic PIM kinases are the members of serine/ threonine family play a crucial role in the cancer progression and development. Overexpression of PIM kinases is observed in various types of cancers including prostate, hematological, pancreatic, breast carcinoma and likewise. PIM kinases have now been considered as limelight target for the discovery of new molecules as novel anticancer agents as no drug is in the market targeting PIM kinases. In the last two decades, numerous PIM kinase inhibitors have been developed and few of them were in clinical trial phases but could not pass the pipeline of the clinical trials. The present comprehensive review intends to cover biological and the structural aspects of PIM kinases and also medicinal chemistry of PIM inhibitors developed in recent years.

Advanced Computational Methodologies Used in the Discovery of New Natural Anticancer Compounds.

Natural chemical compounds have been widely investigated for their programmed necrosis causing characteristics. One of the conventional methods for screening such compounds is the use of concentrated plant extracts without isolation of active moieties for understanding pharmacological activity. For the last two decades, modern medicine has relied mainly on the isolation and purification of one or two complicated active and isomeric compounds. The idea of multi-target drugs has advanced rapidly and impressively from an innovative model when first proposed in the early 2000s to one of the popular trends for drug development in 2021. Alternatively, fragment-based drug discovery is also explored in identifying target-based drug discovery for potent natural anticancer agents which is based on well-defined fragments opposite to use of naturally occurring mixtures. This review summarizes the current key advancements in natural anticancer compounds; computer-assisted/fragment-based structural elucidation and a multi-target approach for the exploration of natural compounds.