PredMS: a random forest model for predicting metabolic stability of drug candidates in human liver microsomes

Enhancing Multi-species Liver Microsomal Stability Prediction through Artificial Intelligence

Liver microsomal stability, a crucial aspect of metabolic stability, significantly impacts practical drug discovery. However, current models for predicting liver microsomal stability are based on limited molecular information from a single species. To address this limitation, we constructed the largest public database of compounds from three common species: human, rat, and mouse. Subsequently, we developed a series of classification models using both traditional descriptor-based and classic graph-based machine learning (ML) algorithms. Remarkably, the best-performing models for the three species achieved Matthews correlation coefficients (MCCs) of 0.616, 0.603, and 0.574, respectively, on the test set. Furthermore, through the construction of consensus models based on these individual models, we have demonstrated their superior predictive performance in comparison with the existing models of the same type. To explore the similarities and differences in the properties of liver microsomal stability among multispecies molecules, we conducted preliminary interpretative explorations using the Shapley additive explanations (SHAP) and atom heatmap approaches for the models and misclassified molecules. Additionally, we further investigated representative structural modifications and substructures that decrease the liver microsomal stability in different species using the matched molecule pair analysis (MMPA) method and substructure extraction techniques. The established prediction models, along with insightful interpretation information regarding liver microsomal stability, will significantly contribute to enhancing the efficiency of exploring practical drugs for development.

A molecular docking exploration of the large extracellular loop of tetraspanin CD81 with small molecules

Tetraspanin CD81 is a transmembrane protein used as a co-receptor by different viruses and implicated in some cancer and inflammatory diseases. The design of therapeutic small molecules targeting CD81 lags behind monoclonal antibodies and peptides but different synthetic and natural products binding to CD81 have been identified. We have investigated the interaction between synthetic compounds and CD81, considering both the cholesterol-bound full-length receptor and a truncated protein corresponding to the large extracellular loop (LEL) of the tetraspanin. They represent the closed and open conformations of the protein, respectively. Stable complexes were characterized with bi-aryl compounds (notably the quinolinone-benzothiazole 6) and atypical molecules bearing a 1-amino-boraadamantane scaffold well adapted to interact with CD81 (5a-d). In each case, the mode of binding to CD81 was analyzed, the binding sites identified and the molecular contacts determined. The narrow intra-LEL binding site of CD81 can accommodate the elongated bi-aryl 6 but not a series of isosteric compounds with a bis(bicyclic) scaffold. The bora-adamantane derivatives appeared to bind well to CD81, but essentially to the external surface of the protein loop. The binding selectivity of the compounds was assessed comparing binding to the LEL of tetraspanins CD81, CD9 and Tspan15. A net preference for CD81 over CD9 was evidenced, but the LEL of Tspan15 also provided a suitable binding site for the compounds, notably for the bora-adamantane derivatives. This work provides an aid to the identification and design of tetraspanin-binding small molecules, underlining the distinct behavior of the open and closed conformation of the protein for drug binding.

Supplementary Information

The online version contains supplementary material available at 10.1007/s40203-024-00203-6.

Investigation of the General Molecular Mechanisms of Gallic Acid via Analyses of Its Transcriptome Profile

Gallic acid (GA), a phenolic compound naturally found in many plants, exhibits potential preventive and therapeutic roles. However, the underlying molecular mechanisms of its diverse biological activities remain unclear. Here, we investigated possible mechanisms of GA function through a transcriptome-based analysis using LINCS L1000, a publicly available data resource. We compared the changes in the gene expression profiles induced by GA with those induced by FDA-approved drugs in three cancer cell lines (A549, PC3, and MCF7). The top 10 drugs exhibiting high similarity with GA in their expression patterns were identified by calculating the connectivity score in the three cell lines. We specified the known target proteins of these drugs, which could be potential targets of GA, and identified 19 potential targets. Next, we retrieved evidence in the literature that GA likely binds directly to DNA polymerase β and ribonucleoside-diphosphate reductase. Although our results align with previous studies suggesting a direct and/or indirect connection between GA and the target proteins, further experimental investigations are required to fully understand the exact molecular mechanisms of GA. Our study provides insights into the therapeutic mechanisms of GA, introducing a new approach to characterizing therapeutic natural compounds using transcriptome-based analyses.

Investigation of the mutated antimicrobial peptides to inhibit ACE2, TMPRSS2 and GRP78 receptors of SARS-CoV-2 and angiotensin II type 1 receptor (AT1R) as well as controlling COVID-19 disease

SARS-CoV-2 is a global problem nowadays. Based on studies, some human receptors are involved in binding to SARS-CoV-2. Thus, the inhibition of these receptors can be effective in the treatment of Covid-19. Because of the proven benefits of antimicrobial peptides (AMPs) and the side effects of chemical drugs, they can be known as an alternative to recent medicines. RCSB PDB to obtain PDB id, StraPep and PhytAMP to acquire Bio-AMPs information and 3-D structure, and AlgPred, Toxinpred, TargetAntiAngio, IL-4pred, IL-6pred, ACPred and Hemopred databases were used to find the best score peptide features. HADDOCK 2.2 was used for molecular docking analysis, and UCSF Chimera software version 1.15, SWISS-MODEL and BIOVIA Discovery Studio Visualizer4.5 were used for mutation and structure modeling. Furthermore, MD simulation results were achieved from GROMACS 4.6.5. Based on the obtained results, the Moricin peptide was found to have the best affinity for ACE2. Moreover, Bacteriocin leucocin-A had the highest affinity for GRP78, Cathelicidin-6 had the best affinity for AT1R, and Bacteriocin PlnK had the best binding affinity for TMPRSS2. Additionally, Bacteriocin glycocin F, Bacteriocin lactococcin-G subunit beta and Cathelicidin-6 peptides were the most common compounds among the four receptors. However, these peptides also have some side effects. Consequently, the mutation eliminated the side effects, and MD simulation results indicated that the mutation proved the result of the docking analysis. The effect of AMPs on ACE2, GRP78, TMPRSS2 and AT1R receptors can be a novel treatment for Covid-19.Communicated by Ramaswamy H. Sarma.

Artificial intelligence in small molecule drug discovery from 2018 to 2023: Does it really work?

Utilizing artificial intelligence (AI) in drug design represents an advanced approach for identifying targets and developing new drugs. Integrating AI techniques significantly reduces the workload involved in drug development and enhances the efficiency of early-stage drug discovery. This review aims to present a comprehensive overview of the utilization of AI methods in the field of small drug design, with a specific focus on four key areas: protein structure prediction, molecular virtual screening, molecular design, and absorption, distribution, metabolism, excretion, and toxicity (ADMET) prediction. Additionally, the role and limitations of AI in drug development are explored, and the impact of AI on decision-making processes is studied. It is important to note that while AI can bring numerous benefits to the early stage of drug development, the direction and quality of decision-making should still be emphasized, as AI should be considered as a tool rather than a decisive factor.

Intramolecular cyclization of N-cyano sulfoximines by N-CN bond activation

Metal-free halogenated anhydrides promote the intramolecular cyclization of N-cyano sulfoximines. Trifluoro- or trichloroacetic anhydride (TFAA or TCAA, respectively) activate the N-cyano groups of N-cyano sulfoximines, leading to the intramolecular cyclization of 2-benzamide-N-cyano sulfoximines 1. This method results in excellent yields of thiadiazinone 1-oxides 2. A full intramolecular cyclization pattern was suggested by (i) labeling experiments with 13C, (ii) isolating of N-trifluoroacetyl sulfoximine 1ac, and (iii) confirming the generation of the intermediate 1ad by LC/MS analysis.

CMMS-GCL: cross-modality metabolic stability prediction with graph contrastive learning

MOTIVATION

Metabolic stability plays a crucial role in the early stages of drug discovery and development. Accurately modeling and predicting molecular metabolic stability has great potential for the efficient screening of drug candidates as well as the optimization of lead compounds. Considering wet-lab experiment is time-consuming, laborious, and expensive, in silico prediction of metabolic stability is an alternative choice. However, few computational methods have been developed to address this task. In addition, it remains a significant challenge to explain key functional groups determining metabolic stability.

RESULTS

To address these issues, we develop a novel cross-modality graph contrastive learning model named CMMS-GCL for predicting the metabolic stability of drug candidates. In our framework, we design deep learning methods to extract features for molecules from two modality data, i.e. SMILES sequence and molecule graph. In particular, for the sequence data, we design a multihead attention BiGRU-based encoder to preserve the context of symbols to learn sequence representations of molecules. For the graph data, we propose a graph contrastive learning-based encoder to learn structure representations by effectively capturing the consistencies between local and global structures. We further exploit fully connected neural networks to combine the sequence and structure representations for model training. Extensive experimental results on two datasets demonstrate that our CMMS-GCL consistently outperforms seven state-of-the-art methods. Furthermore, a collection of case studies on sequence data and statistical analyses of the graph structure module strengthens the validation of the interpretability of crucial functional groups recognized by CMMS-GCL. Overall, CMMS-GCL can serve as an effective and interpretable tool for predicting metabolic stability, identifying critical functional groups, and thus facilitating the drug discovery process and lead compound optimization.

AVAILABILITY AND IMPLEMENTATION

The code and data underlying this article are freely available at https://github.com/dubingxue/CMMS-GCL.

PredPS: Attention-based graph neural network for predicting stability of compounds in human plasma

Stability of compounds in the human plasma is crucial for maintaining sufficient systemic drug exposure and considered an essential factor in the early stages of drug discovery and development. The rapid degradation of compounds in the plasma can result in poor in vivo efficacy. Currently, there are no open-source software programs for predicting human plasma stability. In this study, we developed an attention-based graph neural network, PredPS to predict the plasma stability of compounds in human plasma using in-house and open-source datasets. The PredPS outperformed the two machine learning and two deep learning algorithms that were used for comparison indicating its stability-predicting efficiency. PredPS achieved an area under the receiver operating characteristic curve of 90.1%, accuracy of 83.5%, sensitivity of 82.3%, and specificity of 84.6% when evaluated using 5-fold cross-validation. In the early stages of drug discovery, PredPS could be a helpful method for predicting the human plasma stability of compounds. Saving time and money can be accomplished by adopting an in silico-based plasma stability prediction model at the high-throughput screening stage. The source code for PredPS is available at https://bitbucket.org/krict-ai/predps and the PredPS web server is available at https://predps.netlify.app.

SAR and lead optimization of (Z)-5-(4-hydroxy-3-methoxybenzylidene)-3-(2-morpholinoacetyl)thiazolidine-2,4-dione as a potential multi-target antidiabetic agent

In case of metabolic disorder like Diabetes mellitus (DM), a number of key enzymes are abnormally expressed and hence they might be excellent targets for antidiabetic drug design. Multi-target design strategy has recently attracted great attention to treat challenging diseases. We have previously reported a vanillin-thiazolidine-2,4-dione hybrid 3 as multitarget inhibitor of α-glucosidase, α-amylase, PTP-1B and DPP-4. The reported compound predominantly exhibited good in-vitro DPP-4 inhibition only. Current research describes the goal to optimize an early lead compound. The efforts were focused on enhancing the capability of manipulating multiple pathways at the same time for the treatment of diabetes. The central 5-benzylidinethiazolidine-2,4-dione for Lead compound (Z)-5-(4-hydroxy-3-methoxybenzylidene)-3-(2-morpholinoacetyl)thiazolidine-2,4-dione (Z-HMMTD) was left unchanged. While East and West moieties were altered by the introduction of different building blocks conceived by using a number of rounds of predictive docking studies performed on X-ray crystal structures of four target enzymes. This systematic SAR led to the syntheses of new potent multi-target antidiabetic compounds 47-49 and 55-57 with many fold increase in the in-vitro potency compared to Z-HMMTD. The potent compounds showed good in-vitro and in-vivo safety profile. Compound 56 emerged excellent as glucose-uptake promotor via hemi diaphragm of the rat. Moreover, the compounds demonstrated antidiabetic activity in STZ-induced diabetic animal model.

CDI Exerts Anti-Tumor Effects by Blocking the FoxM1-DNA Interaction

The Forkhead box protein M1 (FoxM1) is an appealing target for anti-cancer therapeutics as this cell proliferation-associated transcription factor is overexpressed in most human cancers. FoxM1 is involved in tumor invasion, angiogenesis, and metastasis. To discover novel inhibitors that disrupt the FoxM1-DNA interaction, we identified CDI, a small molecule that inhibits the FoxM1–DNA interaction. CDI was identified through an assay based on the time-resolved fluorescence energy transfer response of a labeled consensus oligonucleotide that was bound to a recombinant FoxM1-dsDNA binding domain (FoxM1-DBD) protein and exhibited potent inhibitory activity against FoxM1-DNA interaction. CDI suppressed cell proliferation and induced apoptosis in MDA-MB-231 cells obtained from a breast cancer patient. Furthermore, it decreased not only the mRNA and protein expression of FoxM1 but also that of downstream targets such as CDC25b. Additionally, global transcript profiling of MDA-MB-231 cells by RNA-Seq showed that CDI decreases the expression of FoxM1-regulated genes. The docking and MD simulation results indicated that CDI likely binds to the DNA interaction site of FoxM1-DBD and inhibits the function of FoxM1-DBD. These results of CDI being a possible effective inhibitor of FoxM1-DNA interaction will encourage its usage in pharmaceutical applications.

Identification of sulfonamide-based butyrylcholinesterase inhibitors using machine learning

Aim: This study reports the designing of BChE inhibitors through machine learning (ML), followed by in silico and in vitro evaluations. Methodology: ML technique was used to predict the virtual hit, and its derivatives were synthesized and characterized. The compounds were evaluated by using various in vitro tests and in silico methods. Results: The gradient boosting classifier predicted N-phenyl-4-(phenylsulfonamido) benzamide as an active BChE inhibitor. The derivatives of the inhibitor, i.e., compounds 34, 37 and 54 were potent BChE inhibitors and displayed blood-brain barrier permeability with no significant AChE inhibition. Conclusion: The ML prediction was effective, and the synthesized compounds showed the BChE inhibitory activity, which was also supported by the in silico studies.

Identification and New Indication of Melanin-Concentrating Hormone Receptor 1 (MCHR1) Antagonist Derived from Machine Learning and Transcriptome-Based Drug Repositioning Approaches

Melanin-concentrating hormone receptor 1 (MCHR1) has been a target for appetite suppressants, which are helpful in treating obesity. However, it is challenging to develop an MCHR1 antagonist because its binding site is similar to that of the human Ether-à-go-go-Related Gene (hERG) channel, whose inhibition may cause cardiotoxicity. Most drugs developed as MCHR1 antagonists have failed in clinical development due to cardiotoxicity caused by hERG inhibition. Machine learning-based prediction models can overcome these difficulties and provide new opportunities for drug discovery. In this study, we identified KRX-104130 with potent MCHR1 antagonistic activity and no cardiotoxicity through virtual screening using two MCHR1 binding affinity prediction models and an hERG-induced cardiotoxicity prediction model. In addition, we explored other possibilities for expanding the new indications for KRX-104130 using a transcriptome-based drug repositioning approach. KRX-104130 increased the expression of low-density lipoprotein receptor (LDLR), which induced cholesterol reduction in the gene expression analysis. This was confirmed by comparison with gene expression in a nonalcoholic steatohepatitis (NASH) patient group. In a NASH mouse model, the administration of KRX-104130 showed a protective effect by reducing hepatic lipid accumulation, liver injury, and histopathological changes, indicating a promising prospect for the therapeutic effect of NASH as a new indication for MCHR1 antagonists.

Modifications of the Triaminoaryl Metabophore of Flupirtine and Retigabine Aimed at Avoiding Quinone Diimine Formation

The potassium channel opening drugs flupirtine and retigabine have been withdrawn from the market due to occasional drug-induced liver injury (DILI) and tissue discoloration, respectively. While the mechanism underlying DILI after prolonged flupirtine use is not entirely understood, evidence indicates that both drugs are metabolized in an initial step to reactive ortho- and/or para-azaquinone diimines or ortho- and/or para-quinone diimines, respectively. Aiming to develop safer alternatives for the treatment of pain and epilepsy, we have attempted to separate activity from toxicity by employing a drug design strategy of avoiding the detrimental oxidation of the central aromatic ring by shifting oxidation toward the formation of benign metabolites. In the present investigation, an alternative retrometabolic design strategy was followed. The nitrogen atom, which could be involved in the formation of both ortho- or para-quinone diimines of the lead structures, was shifted away from the central ring, yielding a substitution pattern with nitrogen substituents in the meta position only. Evaluation of K_V7.2/3 opening activity of the 11 new specially designed derivatives revealed surprisingly steep structure-activity relationship data with inactive compounds and an activity cliff that led to the identification of an apparent "magic methyl" effect in the case of N-(4-fluorobenzyl)-6-[(4-fluorobenzyl)amino]-2-methoxy-4-methylnicotinamide. This flupirtine analogue showed potent K_V7.2/3 opening activity, being six times as active as flupirtine itself, and by design is devoid of the potential for azaquinone diimine formation.