Structural Analysis and Identification of False Positive Hits in Luciferase-Based Assays

Prediction of blood-brain barrier permeability using machine learning approaches based on various molecular representation

The assessment of compound blood-brain barrier (BBB) permeability poses a significant challenge in the discovery of drugs targeting the central nervous system. Conventional experimental approaches to measure BBB permeability are labor-intensive, cost-ineffective, and time-consuming. In this study, we constructed six machine learning classification models by combining various machine learning algorithms and molecular representations. The model based on ExtraTree algorithm and random partitioning strategy obtains the best prediction result, with AUC value of 0.932±0.004 and balanced accuracy (BA) of 0.837±0.010 for the test set. We employed the SHAP method to identify important features associated with BBB permeability. In addition, matched molecular pair (MMP) analysis and representative substructure derivation method were utilized to uncover the transformation rules and distinctive structural features of BBB permeable compounds. The machine learning models proposed in this work can serve as an effective tool for assessing BBB permeability in the drug discovery for central nervous system disease.

ChemFH: an integrated tool for screening frequent false positives in chemical biology and drug discovery

High-throughput screening rapidly tests an extensive array of chemical compounds to identify hit compounds for specific biological targets in drug discovery. However, false-positive results disrupt hit compound screening, leading to wastage of time and resources. To address this, we propose ChemFH, an integrated online platform facilitating rapid virtual evaluation of potential false positives, including colloidal aggregators, spectroscopic interference compounds, firefly luciferase inhibitors, chemical reactive compounds, promiscuous compounds, and other assay interferences. By leveraging a dataset containing 823 391 compounds, we constructed high-quality prediction models using multi-task directed message-passing network (DMPNN) architectures combining uncertainty estimation, yielding an average AUC value of 0.91. Furthermore, ChemFH incorporated 1441 representative alert substructures derived from the collected data and ten commonly used frequent hitter screening rules. ChemFH was validated with an external set of 75 compounds. Subsequently, the virtual screening capability of ChemFH was successfully confirmed through its application to five virtual screening libraries. Furthermore, ChemFH underwent additional validation on two natural products and FDA-approved drugs, yielding reliable and accurate results. ChemFH is a comprehensive, reliable, and computationally efficient screening pipeline that facilitates the identification of true positive results in assays, contributing to enhanced efficiency and success rates in drug discovery. ChemFH is freely available via https://chemfh.scbdd.com/.

ADMETlab 3.0: an updated comprehensive online ADMET prediction platform enhanced with broader coverage, improved performance, API functionality and decision support

ADMETlab 3.0 is the second updated version of the web server that provides a comprehensive and efficient platform for evaluating ADMET-related parameters as well as physicochemical properties and medicinal chemistry characteristics involved in the drug discovery process. This new release addresses the limitations of the previous version and offers broader coverage, improved performance, API functionality, and decision support. For supporting data and endpoints, this version includes 119 features, an increase of 31 compared to the previous version. The updated number of entries is 1.5 times larger than the previous version with over 400 000 entries. ADMETlab 3.0 incorporates a multi-task DMPNN architecture coupled with molecular descriptors, a method that not only guaranteed calculation speed for each endpoint simultaneously, but also achieved a superior performance in terms of accuracy and robustness. In addition, an API has been introduced to meet the growing demand for programmatic access to large amounts of data in ADMETlab 3.0. Moreover, this version includes uncertainty estimates in the prediction results, aiding in the confident selection of candidate compounds for further studies and experiments. ADMETlab 3.0 is publicly for access without the need for registration at: https://admetlab3.scbdd.com.

Tackling assay interference associated with small molecules

Biochemical and cell-based assays are essential to discovering and optimizing efficacious and safe drugs, agrochemicals and cosmetics. However, false assay readouts stemming from colloidal aggregation, chemical reactivity, chelation, light signal attenuation and emission, membrane disruption, and other interference mechanisms remain a considerable challenge in screening synthetic compounds and natural products. To address assay interference, a range of powerful experimental approaches are available and in silico methods are now gaining traction. This Review begins with an overview of the scope and limitations of experimental approaches for tackling assay interference. It then focuses on theoretical methods, discusses strategies for their integration with experimental approaches, and provides recommendations for best practices. The Review closes with a summary of the critical facts and an outlook on potential future developments.

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.

Structural Analysis and Prediction of Hematotoxicity Using Deep Learning Approaches

Hematotoxicity has been becoming a serious but overlooked toxicity in drug discovery. However, only a few in silico models have been reported for the prediction of hematotoxicity. In this study, we constructed a high-quality dataset comprising 759 hematotoxic compounds and 1623 nonhematotoxic compounds and then established a series of classification models based on a combination of seven machine learning (ML) algorithms and nine molecular representations. The results based on two data partitioning strategies and applicability domain (AD) analysis illustrate that the best prediction model based on Attentive FP yielded a balanced accuracy (BA) of 72.6%, an area under the receiver operating characteristic curve (AUC) value of 76.8% for the validation set, and a BA of 69.2%, an AUC of 75.9% for the test set. In addition, compared with existing filtering rules and models, our model achieved the highest BA value of 67.5% for the external validation set. Additionally, the shapley additive explanation (SHAP) and atom heatmap approaches were utilized to discover the important features and structural fragments related to hematotoxicity, which could offer helpful tips to detect undesired positive substances. Furthermore, matched molecular pair analysis (MMPA) and representative substructure derivation technique were employed to further characterize and investigate the transformation principles and distinctive structural features of hematotoxic chemicals. We believe that the novel graph-based deep learning algorithms and insightful interpretation presented in this study can be used as a trustworthy and effective tool to assess hematotoxicity in the development of new drugs.

Synthesis, Biological Evaluation, and Binding Mode of a New Class of Oncogenic K-Ras4b Inhibitors

Ras proteins are implicated in some of the most common life-threatening cancers. Despite intense research during the past three decades, progress towards small-molecule inhibitors of mutant Ras proteins still has been limited. Only recently has significant progress been made, in particular with ligands for binding sites located in the switch II and between the switch I and switch II region of K-Ras4B. However, the structural diversity of inhibitors identified for those sites to date is narrow. Herein, we show that hydrazones and oxime ethers of specific bis(het)aryl ketones represent structurally variable chemotypes for new GDP/GTP-exchange inhibitors with significant cellular activity.

Gametocyte-specific and all-blood-stage transmission-blocking chemotypes discovered from high throughput screening on Plasmodium falciparum gametocytes

Blocking Plasmodium falciparum human-to-mosquito transmission is essential for malaria elimination, nonetheless drugs killing the pathogenic asexual stages are generally inactive on the parasite transmissible stages, the gametocytes. Due to technical and biological limitations in high throughput screening of non-proliferative stages, the search for gametocyte-killing molecules so far tested one tenth the number of compounds screened on asexual stages. Here we overcome these limitations and rapidly screened around 120,000 compounds, using not purified, bioluminescent mature gametocytes. Orthogonal gametocyte assays, selectivity assays on human cells and asexual parasites, followed by compound clustering, brought to the identification of 84 hits, half of which are gametocyte selective and half with comparable activity against sexual and asexual parasites. We validated seven chemotypes, three of which are, to the best of our knowledge, novel. These molecules are able to inhibit male gametocyte exflagellation and block parasite transmission through the Anopheles mosquito vector in a standard membrane feeding assay. This work shows that interrogating a wide and diverse chemical space, with a streamlined gametocyte HTS and hit validation funnel, holds promise for the identification of dual stage and gametocyte-selective compounds to be developed into new generation of transmission blocking drugs for malaria elimination.

Machine learning & deep learning in data-driven decision making of drug discovery and challenges in high-quality data acquisition in the pharmaceutical industry

Predicting novel small molecule bioactivities for the target deconvolution, hit-to-lead optimization in drug discovery research, requires molecular representation. Previous reports have demonstrated that machine learning (ML) and deep learning (DL) have substantial implications in virtual screening, peptide synthesis, drug ADMET screening and biomarker discovery. These strategies can increase the positive outcomes in the drug discovery process without false-positive rates and can be achieved in a cost-effective way with a minimum duration of time by high-quality data acquisition. This review substantially discusses the recent updates in AI tools as cheminformatics application in medicinal chemistry for the data-driven decision making of drug discovery and challenges in high-quality data acquisition in the pharmaceutical industry while improving small-molecule bioactivities and properties.

Small Molecule Drugs Targeting Non-Coding RNAs as Treatments for Alzheimer's Disease and Related Dementias

Despite the enormous burden of Alzheimer's disease and related dementias (ADRD) on patients, caregivers, and society, only a few treatments with limited efficacy are currently available. While drug development conventionally focuses on disease-associated proteins, RNA has recently been shown to be druggable for therapeutic purposes as well. Approximately 70% of the human genome is transcribed into non-protein-coding RNAs (ncRNAs) such as microRNAs, long ncRNAs, and circular RNAs, which can adopt diverse structures and cellular functions. Many ncRNAs are specifically enriched in the central nervous system, and their dysregulation is implicated in ADRD pathogenesis, making them attractive therapeutic targets. In this review, we first detail why targeting ncRNAs with small molecules is a promising therapeutic strategy for ADRD. We then outline the process from discovery to validation of small molecules targeting ncRNAs in preclinical studies, with special emphasis on primary high-throughput screens for identifying lead compounds. Screening strategies for specific ncRNAs will also be included as examples. Key challenges-including selecting appropriate ncRNA targets, lack of specificity of small molecules, and general low success rate of neurological drugs and how they may be overcome-will be discussed throughout the review.

An Informatics Approach for Designing Conducting Polymers

Doping conjugated polymers, which are potential candidates for the next generation of organic electronics, is an effective strategy for manipulating their electrical conductivity. However, selecting a suitable polymer-dopant combination is exceptionally challenging because of the vastness of the chemical, configurational, and morphological spaces one needs to search. In this work, high-performance surrogate models, trained on available experimentally measured data, are developed to predict the p-type electrical conductivity and are used to screen a large candidate hypothetical data set of more than 800 000 polymer-dopant combinations. Promising candidates are identified for synthesis and device fabrication. Additionally, new design guidelines are extracted that verify and extend knowledge on important molecular fragments that correlate to high conductivity. Conductivity prediction models are also deployed at www.polymergenome.org for broader open-access community use.

Semi-automated workflow for molecular pair analysis and QSAR-assisted transformation space expansion

In the process of drug discovery, the optimization of lead compounds has always been a challenge faced by pharmaceutical chemists. Matched molecular pair analysis (MMPA), a promising tool to efficiently extract and summarize the relationship between structural transformation and property change, is suitable for local structural optimization tasks. Especially, the integration of MMPA with QSAR modeling can further strengthen the utility of MMPA in molecular optimization navigation. In this study, a new semi-automated procedure based on KNIME was developed to support MMPA on both large- and small-scale datasets, including molecular preparation, QSAR model construction, applicability domain evaluation, and MMP calculation and application. Two examples covering regression and classification tasks were provided to gain a better understanding of the importance of MMPA, which has also shown the reliability and utility of this MMPA-by-QSAR pipeline.

Development of Machine Learning Models for Accurately Predicting and Ranking the Activity of Lead Molecules to Inhibit PRC2 Dependent Cancer

Disruption of epigenetic processes to eradicate tumor cells is among the most promising interventions for cancer control. EZH2 (Enhancer of zeste homolog 2), a catalytic component of polycomb repressive complex 2 (PRC2), methylates lysine 27 of histone H3 to promote transcriptional silencing and is an important drug target for controlling cancer via epigenetic processes. In the present study, we have developed various predictive models for modeling the inhibitory activity of EZH2. Binary and multiclass models were built using SVM, random forest and XGBoost methods. Rigorous validation approaches including predictiveness curve, Y-randomization and applicability domain (AD) were employed for evaluation of the developed models. Eighteen descriptors selected from Boruta methods have been used for modeling. For binary classification, random forest and XGBoost achieved an accuracy of 0.80 and 0.82, respectively, on external test set. Contrastingly, for multiclass models, random forest and XGBoost achieved an accuracy of 0.73 and 0.75, respectively. 500 Y-randomization runs demonstrate that the models were robust and the correlations were not by chance. Evaluation metrics from predictiveness curve show that the selected eighteen descriptors predict active compounds with total gain (TG) of 0.79 and 0.59 for XGBoost and random forest, respectively. Validated models were further used for virtual screening and molecular docking in search of potential hits. A total of 221 compounds were commonly predicted as active with above the set probability threshold and also under the AD of training set. Molecular docking revealed that three compounds have reasonable binding energy and favorable interactions with critical residues in the active site of EZH2. In conclusion, we highlighted the potential of rigorously validated models for accurately predicting and ranking the activities of lead molecules against cancer epigenetic targets. The models presented in this study represent the platform for development of EZH2 inhibitors.

Evaluation of Firefly and Renilla Luciferase Inhibition in Reporter-Gene Assays: A Case of Isoflavonoids

Firefly luciferase is susceptible to inhibition and stabilization by compounds under investigation for biological activity and toxicity. This can lead to false-positive results in in vitro cell-based assays. However, firefly luciferase remains one of the most commonly used reporter genes. Here, we evaluated isoflavonoids for inhibition of firefly luciferase. These natural compounds are often studied using luciferase reporter-gene assays. We used a quantitative structure–activity relationship (QSAR) model to compare the results of in silico predictions with a newly developed in vitro assay that enables concomitant detection of inhibition of firefly and Renilla luciferases. The QSAR model predicted a moderate to high likelihood of firefly luciferase inhibition for all of the 11 isoflavonoids investigated, and the in vitro assays confirmed this for seven of them: daidzein, genistein, glycitein, prunetin, biochanin A, calycosin, and formononetin. In contrast, none of the 11 isoflavonoids inhibited Renilla luciferase. Molecular docking calculations indicated that isoflavonoids interact favorably with the D-luciferin binding pocket of firefly luciferase. These data demonstrate the importance of reporter-enzyme inhibition when studying the effects of such compounds and suggest that this in vitro assay can be used to exclude false-positives due to firefly or Renilla luciferase inhibition, and to thus define the most appropriate reporter gene.

Benchmarking the mechanisms of frequent hitters: limitation of PAINS alerts

In 2010, the pan-assay interference compounds (PAINS) rule was proposed to identify false-positive compounds, especially frequent hitters (FHs), in biological screening campaigns, and has rapidly become an essential component in drug design. However, the specific mechanisms remain unknown, and the result validation and follow-up processing schemes are still unclear. In this review, a large benchmark collection of >600,000 compounds sourced from databases and the literature, including six common false-positive mechanisms, was used to evaluate the detection ability of PAINS. In addition, 400 million purchasable molecules from the ZINC database were also applied to PAINS screening. The results indicate that the PAINS rule is not suitable for the screening of all types of false-positive results and needs more improvement.