Despite their role as oncogenic drivers and predictive biomarkers, alterations in rearrangement during transfection (RET), a receptor tyrosine kinase (RTK), remain significant challenges due to off-target effects and reduced efficacy against emerging mutations, necessitating more selective and innovative drug design. Herein, we report a multi-layered framework encompassing both reinforcement learning (RL) training and post-processing phases, for the efficient de novo design of RET inhibitors striking a balance between structural novelty and predictive reliability. We evaluated two RL strategies: potency-focused optimization (PFO) and polypharmacological multi-parameter optimization (PMPO), with the latter integrating 131 predictive models for off-target selectivity and phenotypic activity. For the 23 kinase targets, pIC50 classification thresholds were defined using Youden's J statistic (mean J = 0.762, range 0.679–0.918). The 108 NSCLC phenotype models showed limited discriminative performance (mean AUC = 0.550). After applicability domain filtering, the increased mean AUC allowed the use of the phenotype models as a confidence-weighted filter in the generative workflow. Post-hoc similarity distribution analysis confirmed that the generated candidates represent structurally novel yet domain-consistent chemotypes, as evidenced by peak densities situated within the Tanimoto similarity range of 0.20–0.40 (generated vs known). Notably, PMPO significantly enhanced multi-parameter consistency (CV: 5.1

Biomarker based oncology therapeutics leverage molecular signatures to identify patient populations most likely to benefit from a specific treatment, thereby increasing clinical success rates. Despite the significant merits of these biomarkers, the high rate of mutations across various therapeutic markers continues to impede innovative drug design. RET is a complex therapeutic biomarker, characterized by high alteration rates that complicate the development of targeted therapies in oncology. Herein, this study provides a systematic evaluation of single-objective (SO) and multi-objective (MO) reinforcement learning strategies aimed at the de novo design of inhibitors targeting complicated RET malignancies. Both approaches employed the identical downstream selection logic comprising hinge-core analysis, scaffold novelty assessment, drug-likeness filtering, and drug-target affinity (DTA) predictions using SMPLIP-Score and ChargeNET models. The SO approach optimized solely for RET-MUT potency, generating compounds with favorable synthesizability profiles (Tanimoto similarity 0.4–0.6). The MO approach incorporated 23 off-target kinase classification models and 108 NSCLC focused phenotype models; 85% of MO candidates simultaneously achieved high RET potency (pIC50 ≥ 7.0), favorable selectivity (off-target probability ≤ 0.3), and predicted phenotypic activity (NSCLC probability ≥ 0.3). Consequently, while SO optimization achieved rapid output with acceptable multi-parameter performance (off-target selectivity: 0.686 ± 0.126; phenotype: 0.945 ± 0.093), MO optimization provided enhanced selectivity consistency (0.555 ± 0.084, 3.2-fold reduced variability) without sacrificing target potency (mean pIC50 7.03 vs 7.6 for SO). The downstream selection and experimental validation further yielded novel amino quinoxaline derivatives to show the high potency against multiple RET alterations (IC 50 : 0.78 nM for RET V804M , 142 nM for RET G810R , 0.53 nM for RET I788N ), representing an unseen scaffold for RET-driven cancers. Scientific Contribution This work provides three key contributions: (1) the first systematic comparison of single-objective versus multi-objective reinforcement learning for kinase inhibitor discovery using identical evaluation workflows; (2) integration of 23 off-target kinase and 108 phenotype classification models into generative molecular design, enabling prospective selectivity optimization; and (3) experimental validation of a novel amino quinoxaline scaffold with sub-nanomolar activity against clinically relevant RET resistance mutations (V804M, G810R, I788N).

The RET proto-oncogene is a critical oncogenic driver in the development of several types of cancer. Despite the existence of clinically approved RET inhibitors, their limited response rates and emergence of resistance due to diverse actionable mutations underscore the need for novel therapeutics. Herein, we report substituted imidazo[1,2-a]pyridine derivatives as new RET inhibitors exhibiting IC50 values as low as 11 nM against three distinct point mutations and three important RET fusions. The binding mode and measured potency were elucidated by induced-fit docking simulations and cardiotoxicity was evaluated.

Pruritus, or itch, is a common complaint in dermatology, adversely affecting patient's well-being and becoming unbearable when severe. Histamine induces itch by binding to the histamine receptor and antihistamines alleviate itch symptoms by blocking this action in many cases. However, the insufficient relief provided by antihistamines in various chronic conditions necessitates the development of anti-pruritic agents beyond the histamine mechanisms. In this study, we screened our in-house compounds with anti-inflammatory properties to assess their therapeutic potential in pruritus. In particular, protein-ligand interaction pattern of MRGPRX2 was investigated for the screening and KMH-45 was identified as a non-peptide inhibitor through molecular simulations of MRGPRX2 rotamer models, followed by calcium flux assay. Molecular mechanism study for pruritus targets revealed anti-pruritic efficacy of KMH-45 along with the regulation of anti-pruritic targets histamine receptor 1 and TRPA1 ion channel as well as MRGPR family. Moreover, KMH-45 dose-dependently inhibited peritoneal mast cell degranulation and demonstrated in vivo efficacy in the scratching behavior test. For further progression and application to clinical studies, the developability of KMH-45 and feature analysis of the MRGPRX2-ligand interaction pattern using GPCR-IPL Score was addressed.

G-protein-coupled receptors (GPCRs) mediate diverse cell signaling cascades after recognizing extracellular ligands. Despite the successful history of known GPCR drugs, a lack of mechanistic insight into GPCR challenges both the deorphanization of some GPCRs and optimization of the structure-activity relationship of their ligands. Notably, replacing a small substituent on a GPCR ligand can significantly alter extracellular GPCR-ligand interaction patterns and motion of transmembrane helices in turn to occur post-binding events of the ligand. In this study, we designed 3D multilevel features to describe the extracellular interaction patterns. Subsequently, these 3D features were utilized to predict the post-binding events that result from conformational dynamics from the extracellular to intracellular areas. To understand the adaptability of GPCR ligands, we collected the conformational information of flexible residues during binding and performed molecular featurization on a broad range of GPCR-ligand complexes. As a result, we developed GPCR-ligand interaction patterns, binding pockets, and ligand features as score (GPCR-IPL score) for predicting the functional selectivity of GPCR ligands (agonism versus antagonism), using the multilevel features of (1) zoomed-out 'residue level' (for flexible transmembrane helices of GPCRs), (2) zoomed-in 'pocket level' (for sophisticated mode of action) and (3) 'atom level' (for the conformational adaptability of GPCR ligands). GPCR-IPL score demonstrated reliable performance, achieving area under the receiver operating characteristic of 0.938 and area under the precision-recall curve of 0.907 (available in gpcr-ipl-score.onrender.com). Furthermore, we used the molecular features to predict the biased activation of downstream signaling (Gi/o, Gq/11, Gs and beta-arrestin) as well as the functional selectivity. The resulting models are interpreted and applied to out-of-set validation with three scenarios including the identification of a new MRGPRX antagonist.

Actionable mutations of RET kinase have been identified as oncogenic drivers of solid tumors, including thyroid cancer, metastatic colorectal cancer, and nonsmall cell lung cancer. Although multikinase inhibitors and RET selective inhibitors are used to treat patients with RET alterations, there is insufficient research addressing certain issues: which actionable mutations arise from these therapies, how to improve the clinical response rate to RET inhibitors, and how to design new inhibitors to overcome drug resistance. Therefore, the development of sophisticated tool compounds is required to investigate the molecular mechanisms of actionable mutations and to develop breakthrough therapeutics for different RET alterations. Herein, we present our investigation into the side chains of imidazopyridazine hinge binders that are capable of inducing protein-ligand interaction patterns from the gatekeeper to the waterfront regions. Extending the substituents at the second and sixth positions enhanced the IC(50 )up to < 0.5 nM for diverse RET alterations.

CNS Drug discovery has been challenging due to the lack of clarity on CNS diseases' basic biological and pathological mechanisms. Despite the difficulty, some CNS drugs have been developed based on phenotypic effects. Herein, we propose a phenotype-structure relationship model, which predicts an anti-neuroinflammatory potency based on 3D molecular structures of the phenotype-active or inactive compounds without specifying targets. For this chemo-centric study, a predictive model of the nitric oxide (NO) inhibitory potency in hyper-activated microglia is built from the 548 agents, which were collected from 95 research articles (28 substructures consisting of natural products and synthetic scaffolds) and doubly externally validated by the agents of 9 research articles as third set. 3D Structures (multi-conformer ensemble) of every agent were encoded into the E3FP molecular fingerprint of the Keiser group as a 3D molecular representation. The location information of the molecular fingerprints could be learned and validated to classify the inhibitory potency of compounds (IC50 cut-off between the active and inactive: 37.1 µM): (1) multi-layer perceptron (MLP) (AUC-CV: 0.997, AUC-Test: 0.992), (2) recurrent neural network (RNN) (AUC-CV: 0.999, AUC-Test: 0.995), and (3) convolutional neural network (CNN) (AUC-CV: 0.998, AUC-Test: 0.994). The high performance of these models was compared with that of four classical machine classification models (Logistic, Ridge, Lasso, and Naïve Bayes). We named the binary classification models NO-Classifier. Independent test set validation and decision region analysis of the independent test set doubly demonstrated NO-Classifier effectively discerned the anti-inflammatory potency of testing compounds in inflammatory cell phenotype with the webserver in https://no-classifier.onrender.com.

RET receptor tyrosine kinase is crucial for nerve and tissue development but can be an important oncogenic driver. This study focuses on exploring the design principles of potent RET inhibitors through molecular docking and 3D-QSAR modeling of 5,6-fused bicyclic heteroaromatic derivatives. First of all, RET inhibitors of 49 different bicyclic substructures were collected from five different data sources and selected through molecular docking simulations. QSAR models were built from the 3399 conformers of 952 RET inhibitors using the partial least-squares method and statistically evaluated. The optimal QSAR model exhibited high predictive performance, with R 2 (of training data) and Q 2 (of test data) values of 0.801 and 0.794, respectively, effectively predicting known inhibitors. The optimal model was doubly verified by patent-filed RET inhibitors as the out-of-set data to demonstrate acceptable residual analysis results. Moreover, feature importance analysis of the QSAR model outlined the impact of substituent characteristics on the inhibitory activity within the 5,6-fused bicyclic heteroaromatic core structures. Furthermore, the relationship between structure and inhibitory activity was successfully applied to the RET screening of known clinical and nonclinical kinase inhibitors to afford accurate off-target prediction.

Abstract Molecular insights into chemical safety are very important for sustainable development as well as risk assessment. This study considers how to manage future upcoming harmful agents, especially potentially cholinergic chemical warfare agents (CWAs). For this purpose, structures of known cholinergic agents were encoded by molecular descriptors. And then each drug target interaction (DTI) was learned from the encoded structures and their cholinergic activities to build DTI classification models for five cholinergic targets with reliable statistical validation (ensemble-AUC: up to 0.790, MCC: up to 0.991, accuracy: up to 0.995). The collected classifiers were transformed to 2D or 3D array type meta-predictors for multi-tasking: (1) cholinergic prediction and (2) CWA detection. The detection ability of the array classifiers was verified under the imbalanced dataset between CWAs and none CWAs (area under the precision-recall curve: up to 0.997, MCC: up to 0.638, F1-sore of none CWAs: up to 0.991, F1-sore of CWAs: up to 0.585).

Molecular insights into chemical safety are very important for sustainable development as well as risk assessment. This study considers how to manage future upcoming harmful agents, especially potentially cholinergic chemical warfare agents (CWAs). For this purpose, the structures of known cholinergic agents were encoded by molecular descriptors. And then each drug target interaction (DTI) was learned from the encoded structures and their cholinergic activities to build DTI classification models for five cholinergic targets with reliable statistical validation (ensemble-AUC: up to 0.790, MCC: up to 0.991, accuracy: up to 0.995). The collected classifiers were transformed into 2D or 3D array type meta-predictors for multi-task: (1) cholinergic prediction and (2) CWA detection. The detection ability of the array classifiers was verified under the imbalanced dataset between CWAs and none CWAs (area under the precision-recall curve: up to 0.997, MCC: up to 0.638, F1-score of none CWAs: up to 0.991, F1-score of CWAs: up to 0.585).

The mechanistic underpinnings of asymmetric catalysis at atomic levels provide shortcuts for developing the potential value of chiral catalysts beyond the current state-of-the-art. In the enantioselective redox transformations, the present intuition-driven studies require a systematic approach to support their intuitive idea. Arguably, the most systematic approach would be based on the reliable quantitative structure-selectivity relationship of diverse and dissimilar chiral scaffolds in an optimal feature space that is universally applied to reactions. Here, we introduce a predictive workflow for the extension of the reaction scope of chiral catalysts across name reactions. For this purpose, whole geometry descriptors were encoded from DFT optimized 3D structures of multiple catalyst scaffolds, 113 catalysts in 9 clusters. The molecular descriptors were verified by the statistical comparison of the enantioselective predictive classification models built from each descriptors of chiral iodoarenes. More notably, capturing the whole molecular geometry through one hot encoding of split three-dimensional molecular fingerprints presented reliable enantioselective predictive regression models for three different name reactions by recycling the data and metadata obtained across reactions. The potential use value of this workflow and the advantages of recyclability, compatibility, and generality proved that the workflow can be applied for name reactions other than the aforementioned name reactions (out of samples). Furthermore, for the consensus prediction of ensemble models, this global descriptor can be compared with sterimol parameters and noncovalent interaction vectors. This study is one case showing how to overcome the sparsity of experimental data in organic reactions, especially asymmetric catalysis.

Biomembranes and lipid systems are rich in unsaturated lipid components and are subject to photo-induced lipid peroxidation. The peroxidized lipid products in cellular systems are known to affect the structural organization and function of the biomembrane. We employed molecular dynamics simulations to study the effects of phospholipid peroxidation on membrane properties and the permeability of different reactive species. The results suggest that when the lipids are peroxidized, the peroxide group moves toward the membrane surface, which causes the membrane system to expand laterally and increase in area. The permeability profile revealed that nitrogen species can easily permeate through the native and peroxidized system in comparison to oxygen species, suggesting its importance in plasma-based treatment. Thus, by breaching the energy barrier with lower energy, they can traverse the cell membrane and induce oxidative stress, which leads to apoptosis.Communicated by Ramaswamy H. Sarma

In drug discovery, rapid and accurate prediction of protein–ligand binding affinities is a pivotal task for lead optimization with acceptable on-target potency as well as pharmacological efficacy. Furthermore, researchers hope for a high correlation between docking score and pose with key interactive residues, although scoring functions as free energy surrogates of protein–ligand complexes have failed to provide collinearity. Recently, various machine learning or deep learning methods have been proposed to overcome the drawbacks of scoring functions. Despite being highly accurate, their featurization process is complex and the meaning of the embedded features cannot directly be interpreted by human recognition without an additional feature analysis. Here, we propose SMPLIP-Score (Substructural Molecular and Protein–Ligand Interaction Pattern Score), a direct interpretable predictor of absolute binding affinity. Our simple featurization embeds the interaction fingerprint pattern on the ligand-binding site environment and molecular fragments of ligands into an input vectorized matrix for learning layers (random forest or deep neural network). Despite their less complex features than other state-of-the-art models, SMPLIP-Score achieved comparable performance, a Pearson’s correlation coefficient up to 0.80, and a root mean square error up to 1.18 in p K units with several benchmark datasets (PDBbind v.2015, Astex Diverse Set, CSAR NRC HiQ, FEP, PDBbind NMR, and CASF-2016). For this model, generality, predictive power, ranking power, and robustness were examined using direct interpretation of feature matrices for specific targets.

Hypoxia is an effective preconditioning stimulus and many cellular responses to hypoxia are mediated through a transcription control complex termed the hypoxia‐inducible factor (HIF). The stability and activation of HIF are governed by HIF prolyl‐4‐hydroxylases 2 (PHD2). Hence, the development of a small molecule inhibitor for prolyl hydroxylase has been suggested as a potentially useful therapeutic strategy for the treatment of oxidative/ischemic stress conditions. Thus, to unveil a novel human PHD2 inhibitor, a custom‐based virtual screening was carried out to identify the potential inhibitors against PHD2 based on; (1) the per‐residue energy decomposition (PRED)‐based pharmacophore model, (2) molecular docking, and (3) MD approaches. The PRED analysis was performed to identify the common interaction pattern of HIF fragment (5L9B) and crystallized ligand (4JZR) to develop a relevant accurate allosteric pharmacophore model. The custom pharmacophore model (AAARR) was developed and further used to screen multiple databases. The docking was performed as a secondary strategy for screening the pharmacophore hits. Furthermore, the docked complexes were screened by molecular dynamics (MD) simulation and molecular mechanics/generalized Born surface area (MM–GBSA) based binding free energy calculations to determine the binding energy of the inhibitors and to identify crucial interaction energy fingerprint. One hit has demonstrated good binding free energy and a better binding affinity for PHD2 compared to the other four selected ligands. Thus, the results obtained from pharmacophore, docking, and MD simulations depicted that linker length and metal binding in the scaffold could be effectively used as a potent inhibitor toward human PHD2 in AD therapeutics.

Electroporation processes affect the permeability of cell membranes, which can be utilized for the delivery of plasma species in cancer therapy. By means of computational dynamics, many aspects of membrane electroporation have been unveiled at the atomic level for lipid membranes. Herein, a molecular dynamics simulation study was performed on native and oxidized membrane systems with transversal electric fields. The simulation result shows that the applied electric field mainly affects the membrane properties so that electroporation takes place and these pores are lined by hydrophilic headgroups of the lipid components. The calculated hydrophobic thickness, lateral diffusion and pair correlation revealed the role of 5 alpha-CH in creation of water-pore in an oxidized membrane. Additionally, the permeability of reactive oxygen species was examined through these electroporated systems. The permeability study suggested that water pores in the membrane facilitate the penetration of these species across the membrane to the interior of the cell. These findings may have significance in experimental applications in vivo as once the reactive oxygen species reaches the interior of the cell, they may cause oxidative stress and induce apoptosis. Communicated by Ramaswamy H. Sarma

Aquaporin-3 (AQP3) is one of the aquaglyceroporins, which is expressed in the basolateral layer of the skin membrane. Studies have reported that human skin squamous cell carcinoma overexpresses AQP3 and inhibition of its function may alleviate skin tumorigenesis. In the present study, we have applied a virtual screening method that encompasses filters for physicochemical properties and molecular docking to select potential hit compounds that bind to the Aquaporin-3 protein. Based on molecular docking results, the top 20 hit compounds were analyzed for stability in the binding pocket using unconstrained molecular dynamics simulations and further evaluated for binding free energy. Furthermore, examined the ligand-unbinding pathway of the inhibitor from its bound form to explore possible routes for inhibitor approach to the ligand-binding site. With a good docking score, stability in the binding pocket, and free energy of binding, these hit compounds can be developed as Aquaporin-3 inhibitors in the near future.

In recent years, pharmacophore modeling and molecular docking approaches have been extensively used to characterize the structural requirements and explore the conformational space of a ligand in the binding pocket of the selected target protein. Herein, we report a pharmacophore modeling and molecular docking of 45 compounds comprising of the indole scaffold as vitamin D receptor (VDR) inhibitors. Based on the selected best hypothesis (DRRRR.61), an atom-based three-dimensional quantitative structure-activity relationships model was developed to rationalize the structural requirement of biological activity modulating components. The developed model predicted the binding affinity for the training set and test set with R2(training)  = 0.8869 and R2(test)  = 0.8139, respectively. Furthermore, molecular docking and dynamics simulation were performed to understand the underpinning of binding interaction and stability of selected VDR inhibitors in the binding pocket. In conclusion, the results presented here, in the form of functional and structural data, agreed well with the proposed pharmacophores and provide further insights into the development of novel VDR inhibitors with better activity.

In drug repurposing approaches, the chemically diverse and potentially safe molecules can be explored as therapeutic potential beyond those originally targeted indications. However, accessible information on a limited number of drug pipelines can lead to competitive over-heating issues, and intellectual property rights also restrict the free investigation in chemical space. As a complementary approach to the drawbacks, ring systems of approved drugs (instead of clinical drugs) can be optimized and used for repurposing purposes. In this study, bi-directional target (T) and ring system (R) dual screening (TR screening) was developed for the repurposing of their rarely used ring systems from FDA approved drugs. The TR screening suggested RAR β and cyproheptadine as the best pair of target and ring system to escape a saddle point. The selected ring system was virtually grown and elaborated with the defined criteria: synthesizability, drug-likeness, and docking pose showing the top scores. The achieved compounds were synthesized and biologically tested with an acceptable ADME/T profile.

Two series of new benzodiazepines were synthesized and the target compounds (E1-10 and G1-10) were evaluated for antianxiety and skeletal muscle relaxant activity as CNS agents in albino mice. The chemical structures of the compounds were confirmed on the basis of their TLC, IR, 1H NMR and 13C NMR analysis. In computational studies, the physicochemical similarity of the target compounds was assessed by calculating from a set of physicochemical properties using software programs and test compounds demonstrated moderate physiochemical similarity with respect to diazepam. Log P values of the target compounds indicates good penetration to CNS. Molecular docking studies revealed that the target compounds correctly dock into the binding pocket of the GABAA receptor, while their bioavailability/drug-likeness was predicted to be acceptable but requires future optimization. The test compounds (E1-10 and G1-10) were screened for antianxiety and skeletal muscle relaxant activity using Elevated plus maze and Rotarod method respectively. Among them, the compounds E10 and G7 showed maximum potency as CNS agents.

Malignant melanoma is considered to be a heterogeneous disease that arises from altered genes and transformed melanocytes. In this study, special softjet cold atmospheric plasma was used to treat three different human melanoma cells using air and N2 gases to check the anti-melanoma activity. The physical effects by plasma revealed an increase in the temperature with the gradual reduction in pH at 60 sec, 180 sec and 300 sec air and N2 plasma treatment. Cellular toxicity revealed a decreased in cell survival (~50% cell survival using air gas and <~60% cell survival using N2 gas at 60 sec plasma treatment in G-361 cells). Gene analysis by q-PCR revealed that 3 min and 5 min air and N2 plasma treatment activated apoptotic pathways by triggering apoptotic genes in all three melanoma cell lines. The apoptosis was confirmed by DAPI staining and its related pathways were further explored according to protein-protein docking, and their probable activation mechanism was revealed. The pathways highlighted that activation of apoptosis which leads to cellular cascades and hence stimulation ASK1 (docking method) revealed that softjet plasma can be an effective modality for human melanoma treatment.