Large scale comparison of QSAR and conformal prediction methods and their applications in drug discovery

AlzyFinder: A Machine-Learning-Driven Platform for Ligand-Based Virtual Screening and Network Pharmacology

Alzheimer's disease (AD), a prevalent neurodegenerative disorder, presents significant challenges in drug development due to its multifactorial nature and complex pathophysiology. The AlzyFinder Platform, introduced in this study, addresses these challenges by providing a comprehensive, free web-based tool for parallel ligand-based virtual screening and network pharmacology, specifically targeting over 85 key proteins implicated in AD. This innovative approach is designed to enhance the identification and analysis of potential multitarget ligands, thereby accelerating the development of effective therapeutic strategies against AD. AlzyFinder Platform incorporates machine learning models to facilitate the ligand-based virtual screening process. These models, built with the XGBoost algorithm and optimized through Optuna, were meticulously trained and validated using robust methodologies to ensure high predictive accuracy. Validation included extensive testing with active, inactive, and decoy molecules, demonstrating the platform's efficacy in distinguishing active compounds. The models are evaluated based on balanced accuracy, precision, and F1 score metrics. A unique soft-voting ensemble approach is utilized to refine the classification process, integrating the strengths of individual models. This methodological framework enables a comprehensive analysis of interaction data, which is presented in multiple formats such as tables, heat maps, and interactive Ligand-Protein Interaction networks, thus enhancing the visualization and analysis of drug-protein interactions. AlzyFinder was applied to screen five molecules recently reported (and not used to train or validate the ML models) as active compounds against five key AD targets. The platform demonstrated its efficacy by accurately predicting all five molecules as true positives with a probability greater than 0.70. This result underscores the platform's capability in identifying potential therapeutic compounds with high precision. In conclusion, AlzyFinder's innovative approach extends beyond traditional virtual screening by incorporating network pharmacology analysis, thus providing insights into the systemic actions of drug candidates. This feature allows for the exploration of ligand-protein and protein-protein interactions and their extensions, offering a comprehensive view of potential therapeutic impacts. As the first open-access platform of its kind, AlzyFinder stands as a valuable resource for the AD research community, available at http://www.alzyfinder-platform.udec.cl with supporting data and scripts accessible via GitHub https://github.com/ramirezlab/AlzyFinder.

Quantitative structure-activity relationships of chemical bioactivity toward proteins associated with molecular initiating events of organ-specific toxicity

The adverse outcome pathway (AOP) concept has gained attention as a way to explore the mechanism of chemical toxicity. In this study, quantitative structure-activity relationship (QSAR) models were developed to predict compound activity toward protein targets relevant to molecular initiating events (MIE) upstream of organ-specific toxicities, namely liver steatosis, cholestasis, nephrotoxicity, neural tube closure defects, and cognitive functional defects. Utilizing bioactivity data from the ChEMBL 33 database, various machine learning algorithms, chemical features and methods to assess prediction reliability were compared and applied to develop robust models to predict compound activity. The results demonstrate high predictive performance across multiple targets, with balanced accuracy exceeding 0.80 for the majority of models. Furthermore, stability checks confirmed the consistency of predictive performance across multiple training-test splits. The results obtained by using QSAR predictions to identify known markers of adversities highlighted the utility of the models for risk assessment and for prioritizing compounds for further experimental evaluation.Scientific contributionThe work describes the development of QSAR models as tools for screening chemicals with potential systemic toxicity, thus contributing to resource savings and providing indications for further better-targeted testing. This study provides advances in the field of computational modeling of MIEs and information from AOP which is still relatively young and unexplored. The comprehensive modeling procedure is highly generalizable, and offers a robust framework for predicting a wide range of toxicological endpoints.

Design of Promising Thiazoloindazole-Based Acetylcholinesterase Inhibitors Guided by Molecular Docking and Experimental Insights

Alzheimer's disease is characterized by a progressive deterioration of cognitive function and memory loss, and it is closely associated with the dysregulation of cholinergic neurotransmission. Since acetylcholinesterase (AChE) is a critical enzyme in the nervous system, responsible for breaking down the neurotransmitter acetylcholine, its inhibition holds a significant interest in the treatment of various neurological disorders. Therefore, it is crucial to develop efficient AChE inhibitors capable of increasing acetylcholine levels, ultimately leading to improved cholinergic neurotransmission. The results reported here represent a step forward in the development of novel thiazoloindazole-based compounds that have the potential to serve as effective AChE inhibitors. Molecular docking studies revealed that certain of the evaluated nitroindazole-based compounds outperformed donepezil, a well-known AChE inhibitor used in Alzheimer's disease treatment. Sustained by these findings, two series of compounds were synthesized. One series included a triazole moiety (Tl45a-c), while the other incorporated a carbazole moiety (Tl58a-c). These compounds were isolated in yields ranging from 66 to 87% through nucleophilic substitution and Cu(I)-catalyzed azide-alkyne 1,3-dipolar cycloaddition (CuAAC) reactions. Among the synthesized compounds, the thiazoloindazole-based 6b core derivatives emerged as selective AChE inhibitors, exhibiting remarkable IC50 values of less than 1.0 μM. Notably, derivative Tl45b displays superior performance as an AChE inhibitor, boasting the lowest IC50 (0.071 ± 0.014 μM). Structure-activity relationship (SAR) analysis indicated that derivatives containing the bis(trifluoromethyl)phenyl-triazolyl group demonstrated the most promising activity against AChE, when compared to more rigid substituents such as carbazolyl moiety. The combination of molecular docking and experimental synthesis provides a suitable and promising strategy for the development of new efficient thiazoloindazole-based AChE inhibitors.

Chemical space exploration with Molpher: Generating and assessing a glucocorticoid receptor ligand library

Computational exploration of chemical space is crucial in modern cheminformatics research for accelerating the discovery of new biologically active compounds. In this study, we present a detailed analysis of the chemical library of potential glucocorticoid receptor (GR) ligands generated by the molecular generator, Molpher. To generate the targeted GR library and construct the classification models, structures from the ChEMBL database as well as from the internal IMG library, which was experimentally screened for biological activity in the primary luciferase reporter cell assay, were utilized. The composition of the targeted GR ligand library was compared with a reference library that randomly samples chemical space. A random forest model was used to determine the biological activity of ligands, incorporating its applicability domain using conformal prediction. It was demonstrated that the GR library is significantly enriched with GR ligands compared to the random library. Furthermore, a prospective analysis demonstrated that Molpher successfully designed compounds, which were subsequently experimentally confirmed to be active on the GR. A collection of 34 potential new GR ligands was also identified. Moreover, an important contribution of this study is the establishment of a comprehensive workflow for evaluating computationally generated ligands, particularly those with potential activity against targets that are challenging to dock.

Developing a Semi-Supervised Approach Using a PU-Learning-Based Data Augmentation Strategy for Multitarget Drug Discovery

Multifactorial diseases demand therapeutics that can modulate multiple targets for enhanced safety and efficacy, yet the clinical approval of multitarget drugs remains rare. The integration of machine learning (ML) and deep learning (DL) in drug discovery has revolutionized virtual screening. This study investigates the synergy between ML/DL methodologies, molecular representations, and data augmentation strategies. Notably, we found that SVM can match or even surpass the performance of state-of-the-art DL methods. However, conventional data augmentation often involves a trade-off between the true positive rate and false positive rate. To address this, we introduce Negative-Augmented PU-bagging (NAPU-bagging) SVM, a novel semi-supervised learning framework. By leveraging ensemble SVM classifiers trained on resampled bags containing positive, negative, and unlabeled data, our approach is capable of managing false positive rates while maintaining high recall rates. We applied this method to the identification of multitarget-directed ligands (MTDLs), where high recall rates are critical for compiling a list of interaction candidate compounds. Case studies demonstrate that NAPU-bagging SVM can identify structurally novel MTDL hits for ALK-EGFR with favorable docking scores and binding modes, as well as pan-agonists for dopamine receptors. The NAPU-bagging SVM methodology should serve as a promising avenue to virtual screening, especially for the discovery of MTDLs.

Development and Evaluation of Conformal Prediction Methods for Quantitative Structure-Activity Relationship

The quantitative structure-activity relationship (QSAR) regression model is a commonly used technique for predicting the biological activities of compounds using their molecular descriptors. Besides accurate activity estimation, obtaining a prediction uncertainty metric like a prediction interval is highly desirable. Quantifying prediction uncertainty is an active research area in statistical and machine learning (ML), but the implementation for QSAR remains challenging. However, most ML algorithms with high predictive performance require add-on companions for estimating the uncertainty of their prediction. Conformal prediction (CP) is a promising approach as its main components are agnostic to the prediction modes, and it produces valid prediction intervals under weak assumptions on the data distribution. We proposed computationally efficient CP algorithms tailored to the most widely used ML models, including random forests, deep neural networks, and gradient boosting. The algorithms use a novel approach to the derivation of nonconformity scores from the estimates of prediction uncertainty generated by the ensembles of point predictions. The validity and efficiency of proposed algorithms are demonstrated on a diverse collection of QSAR data sets as well as simulation studies. The provided software implementing our algorithms can be used as stand-alone or easily incorporated into other ML software packages for QSAR modeling.

Interpreting Neural Network Models for Toxicity Prediction by Extracting Learned Chemical Features

Neural network models have become a popular machine-learning technique for the toxicity prediction of chemicals. However, due to their complex structure, it is difficult to understand predictions made by these models which limits confidence. Current techniques to tackle this problem such as SHAP or integrated gradients provide insights by attributing importance to the input features of individual compounds. While these methods have produced promising results in some cases, they do not shed light on how representations of compounds are transformed in hidden layers, which constitute how neural networks learn. We present a novel technique to interpret neural networks which identifies chemical substructures in training data found to be responsible for the activation of hidden neurons. For individual test compounds, the importance of hidden neurons is determined, and the associated substructures are leveraged to explain the model prediction. Using structural alerts for mutagenicity from the Derek Nexus expert system as ground truth, we demonstrate the validity of the approach and show that model explanations are competitive with and complementary to explanations obtained from an established feature attribution method.

Small molecule drug discovery for glioblastoma treatment based on bioinformatics and cheminformatics approaches

Background: Glioblastoma (GBM) is a common and highly aggressive brain tumor with a poor prognosis for patients. It is urgently needed to identify potential small molecule drugs that specifically target key genes associated with GBM development and prognosis. Methods: Differentially expressed genes (DEGs) between GBM and normal tissues were obtained by data mining the Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) databases. Gene function annotation was performed to investigate the potential functions of the DEGs. A protein-protein interaction (PPI) network was constructed to explore hub genes associated with GBM. Bioinformatics analysis was used to screen the potential therapeutic and prognostic genes. Finally, potential small molecule drugs were predicted using the DGIdb database and verified using chemical informatics methods including absorption, distribution, metabolism, excretion, toxicity (ADMET), and molecular docking studies. Results: A total of 429 DEGs were identified, of which 19 hub genes were obtained through PPI analysis. The hub genes were confirmed as potential therapeutic targets by functional enrichment and mRNA expression. Survival analysis and protein expression confirmed centromere protein A (CENPA) as a prognostic target in GBM. Four small molecule drugs were predicted for the treatment of GBM. Conclusion: Our study suggests some promising potential therapeutic targets and small molecule drugs for the treatment of GBM, providing new ideas for further research and targeted drug development.

Integrating Mechanistic and Toxicokinetic Information in Predictive Models of Cholestasis

Drug development involves the thorough assessment of the candidate's safety and efficacy. In silico toxicology (IST) methods can contribute to the assessment, complementing in vitro and in vivo experimental methods, since they have many advantages in terms of cost and time. Also, they are less demanding concerning the requirements of product and experimental animals. One of these methods, Quantitative Structure-Activity Relationships (QSAR), has been proven successful in predicting simple toxicity end points but has more difficulties in predicting end points involving more complex phenomena. We hypothesize that QSAR models can produce better predictions of these end points by combining multiple QSAR models describing simpler biological phenomena and incorporating pharmacokinetic (PK) information, using quantitative in vitro to in vivo extrapolation (QIVIVE) models. In this study, we applied our methodology to the prediction of cholestasis and compared it with direct QSAR models. Our results show a clear increase in sensitivity. The predictive quality of the models was further assessed to mimic realistic conditions where the query compounds show low similarity with the training series. Again, our methodology shows clear advantages over direct QSAR models in these situations. We conclude that the proposed methodology could improve existing methodologies and could be suitable for being applied to other toxicity end points.

Comparative safety, pharmacokinetics, and off-target assessment of 1,1-bis(3'-indolyl)-1-(p-chlorophenyl) methane in mouse and dog: implications for therapeutic development

The modified phytochemical derivative, 1,1-bis(3'-indolyl)-1-(p-chlorophenyl) methane (C-DIM12), has been identified as a potential therapeutic platform based on its capacity to improve disease outcomes in models of neurodegeneration and cancer. However, comprehensive safety studies investigating pathology and off-target binding have not been conducted. To address this, we administered C-DIM12 orogastrically to outbred male CD-1 mice for 7 days (50 mg/kg/day, 200 mg/kg/day, and 300 mg/kg/day) and investigated changes in hematology, clinical chemistry, and whole-body tissue pathology. We also delivered a single dose of C-DIM12 (1 mg/kg, 5 mg/kg, 25 mg/kg, 100 mg/kg, 300 mg/kg, 1,000 mg/kg) orogastrically to male and female beagle dogs and investigated hematology and clinical chemistry, as well as plasma pharmacokinetics over 48-h. Consecutive in-vitro off-target binding through inhibition was performed with 10 μM C-DIM12 against 68 targets in tandem with predictive off-target structural binding capacity. These data show that the highest dose C-DIM12 administered in each species caused modest liver pathology in mouse and dog, whereas lower doses were unremarkable. Off-target screening and predictive modeling of C-DIM12 show inhibition of serine/threonine kinases, calcium signaling, G-protein coupled receptors, extracellular matrix degradation, and vascular and transcriptional regulation pathways. Collectively, these data demonstrate that low doses of C-DIM12 do not induce pathology and are capable of modulating targets relevant to neurodegeneration and cancer.

Integrating QSAR modelling and deep learning in drug discovery: the emergence of deep QSAR

Quantitative structure-activity relationship (QSAR) modelling, an approach that was introduced 60 years ago, is widely used in computer-aided drug design. In recent years, progress in artificial intelligence techniques, such as deep learning, the rapid growth of databases of molecules for virtual screening and dramatic improvements in computational power have supported the emergence of a new field of QSAR applications that we term 'deep QSAR'. Marking a decade from the pioneering applications of deep QSAR to tasks involved in small-molecule drug discovery, we herein describe key advances in the field, including deep generative and reinforcement learning approaches in molecular design, deep learning models for synthetic planning and the application of deep QSAR models in structure-based virtual screening. We also reflect on the emergence of quantum computing, which promises to further accelerate deep QSAR applications and the need for open-source and democratized resources to support computer-aided drug design.

The ChEMBL Database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods

ChEMBL (https://www.ebi.ac.uk/chembl/) is a manually curated, high-quality, large-scale, open, FAIR and Global Core Biodata Resource of bioactive molecules with drug-like properties, previously described in the 2012, 2014, 2017 and 2019 Nucleic Acids Research Database Issues. Since its introduction in 2009, ChEMBL's content has changed dramatically in size and diversity of data types. Through incorporation of multiple new datasets from depositors since the 2019 update, ChEMBL now contains slightly more bioactivity data from deposited data vs data extracted from literature. In collaboration with the EUbOPEN consortium, chemical probe data is now regularly deposited into ChEMBL. Release 27 made curated data available for compounds screened for potential anti-SARS-CoV-2 activity from several large-scale drug repurposing screens. In addition, new patent bioactivity data have been added to the latest ChEMBL releases, and various new features have been incorporated, including a Natural Product likeness score, updated flags for Natural Products, a new flag for Chemical Probes, and the initial annotation of the action type for ∼270 000 bioactivity measurements.

A novel strategy for the study on molecular mechanism of prostate injury induced by 4,4'-sulfonyldiphenol based on network toxicology analysis

The study aimed to investigate the underlying molecular mechanisms of prostate injury induced by 4,4'-sulfonyldiphenol (BPS) exposure and propose a novel research strategy to systematically explore the molecular mechanisms of toxicant-induced adverse health effects. By utilizing the ChEMBL, STITCH, and GeneCards databases, a total of 208 potential targets associated with BPS exposure and prostate injury were identified. Through screening the potential target network in the STRING database and Cytoscape software, we determined 21 core targets including AKT1, EGFR, and MAPK3. Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses conducted through the DAVID database illustrated that the potential targets of BPS in prostatic toxicity were primarily enriched in cancer signaling pathways and calcium signaling pathways. These findings suggest that BPS may actively participate in the occurrence and development of prostate inflammation, prostatic hyperplasia, prostate cancer, and other aspects of prostate injury by regulating prostate cancer cell apoptosis and proliferation, activating inflammatory signaling pathways, and modulating prostate adipocytes and fibroblasts. This research provides a theoretical basis for understanding the molecular mechanism of underlying BPS-induced prostatic toxicity and establishes a foundation for the prevention and treatment of prostatic diseases associated with exposure to plastic products containing BPS and certain BPS-overwhelmed environments.

Calibrated geometric deep learning improves kinase-drug binding predictions

Protein kinases regulate various cellular functions and hold significant pharmacological promise in cancer and other diseases. Although kinase inhibitors are one of the largest groups of approved drugs, much of the human kinome remains unexplored but potentially druggable. Computational approaches, such as machine learning, offer efficient solutions for exploring kinase-compound interactions and uncovering novel binding activities. Despite the increasing availability of three-dimensional (3D) protein and compound structures, existing methods predominantly focus on exploiting local features from one-dimensional protein sequences and two-dimensional molecular graphs to predict binding affinities, overlooking the 3D nature of the binding process. Here we present KDBNet, a deep learning algorithm that incorporates 3D protein and molecule structure data to predict binding affinities. KDBNet uses graph neural networks to learn structure representations of protein binding pockets and drug molecules, capturing the geometric and spatial characteristics of binding activity. In addition, we introduce an algorithm to quantify and calibrate the uncertainties of KDBNet's predictions, enhancing its utility in model-guided discovery in chemical or protein space. Experiments demonstrated that KDBNet outperforms existing deep learning models in predicting kinase-drug binding affinities. The uncertainties estimated by KDBNet are informative and well-calibrated with respect to prediction errors. When integrated with a Bayesian optimization framework, KDBNet enables data-efficient active learning and accelerates the exploration and exploitation of diverse high-binding kinase-drug pairs.

High-Throughput Phenotypic Screening and Machine Learning Methods Enabled the Selection of Broad-Spectrum Low-Toxicity Antitrypanosomatidic Agents

Broad-spectrum anti-infective chemotherapy agents with activity against Trypanosomes, Leishmania, and Mycobacterium tuberculosis species were identified from a high-throughput phenotypic screening program of the 456 compounds belonging to the Ty-Box, an in-house industry database. Compound characterization using machine learning approaches enabled the identification and synthesis of 44 compounds with broad-spectrum antiparasitic activity and minimal toxicity against Trypanosoma brucei, Leishmania Infantum, and Trypanosoma cruzi. In vitro studies confirmed the predictive models identified in compound 40 which emerged as a new lead, featured by an innovative N-(5-pyrimidinyl)benzenesulfonamide scaffold and promising low micromolar activity against two parasites and low toxicity. Given the volume and complexity of data generated by the diverse high-throughput screening assays performed on the compounds of the Ty-Box library, the chemoinformatic and machine learning tools enabled the selection of compounds eligible for further evaluation of their biological and toxicological activities and aided in the decision-making process toward the design and optimization of the identified lead.

Therapeutic potential of Lianhua Qingke in airway mucus hypersecretion of acute exacerbation of chronic obstructive pulmonary disease

BACKGROUND

Lianhua Qingke (LHQK) is an effective traditional Chinese medicine used for treating acute tracheobronchitis. In this study, we evaluated the effectiveness of LHQK in managing airway mucus hypersecretion in the acute exacerbation of chronic obstructive pulmonary disease (AECOPD).

METHODS

The AECOPD model was established by subjecting male Wistar rats to 12 weeks of cigarette smoke (CS) exposure (80 cigarettes/day, 5 days/week for 12 weeks) and intratracheal lipopolysaccharide (LPS) exposure (200 μg, on days 1, 14, and 84). The rats were divided into six groups: control (room air exposure), model (CS + LPS exposure), LHQK (LHQK-L, LHQK-M, and LHQK-H), and a positive control group (Ambroxol). H&E staining, and AB-PAS staining were used to evaluate lung tissue pathology, inflammatory responses, and goblet cell hyperplasia. RT-qPCR, immunohistochemistry, immunofluorescence and ELISA were utilized to analyze the transcription, expression and secretion of proteins related to mucus production in vivo and in the human airway epithelial cell line NCI-H292 in vitro. To predict and screen the active ingredients of LHQK, network pharmacology analysis and NF-κB reporter system analysis were employed.

RESULTS

LHQK treatment could ameliorate AECOPD-triggered pulmonary structure damage, inflammatory cell infiltration, and pro-inflammatory cytokine production. AB-PAS and immunofluorescence staining with CCSP and Muc5ac antibodies showed that LHQK reduced goblet cell hyperplasia, probably by inhibiting the transdifferentiation of Club cells into goblet cells. RT-qPCR and immunohistochemistry of Muc5ac and APQ5 showed that LHQK modulated mucus homeostasis by suppressing Muc5ac transcription and hypersecretion in vivo and in vitro, and maintaining the balance between Muc5ac and AQP5 expression. Network pharmacology analysis and NF-κB luciferase reporter system analysis provided insights into the active ingredients of LHQK that may help control airway mucus hypersecretion and regulate inflammation.

CONCLUSION

LHQK demonstrated therapeutic effects in AECOPD by reducing inflammation, suppressing goblet cell hyperplasia, preventing Club cell transdifferentiation, reducing Muc5ac hypersecretion, and modulating airway mucus homeostasis. These findings support the clinical use of LHQK as a potential treatment for AECOPD.

Qili Qiangxin (QLQX) capsule as a multi-functional traditional Chinese medicine in treating chronic heart failure (CHF): A review of ingredients, molecular, cellular, and pharmacological mechanisms

Chronic heart failure (CHF) is a key part of cardiovascular continuum. Under the guidance of the theory of vessel-collateral doctrine, the present study proposes therapeutic benefits of Qili Qiangxin (QLQX) capsules, an innovative Chinese medicine, on chronic heart failure. The studies show that multiple targets of the drug on CHF, including enhancing myocardial systole, promoting urine excretion, inhibiting excessive activation of the neuroendocrine system, preventing ventricular remodeling by inhibiting inflammatory response, myocardial fibrosis, apoptosis and autophagy, enhancing myocardial energy metabolism, promoting angiogenesis, and improving endothelial function. Investigation on the effects and mechanism of the drug is beneficial to the treatment of chronic heart failure (CHF) through multiple targets and/or signaling pathways. Meanwhile, it provides new insights to further understand other refractory diseases in the cardiovascular continuum, and it also has an important theoretical and practical significance in enhancing prevention and therapeutic effect of traditional Chinese medicine for these diseases.

Lianhua Qingke ameliorates lipopolysaccharide-induced lung injury by inhibiting neutrophil extracellular traps formation and pyroptosis

LHQK is a patented Traditional Chinese Medicine (TCM) which is clinically used for acute tracheobronchitis, cough, and other respiratory diseases. Recent studies have proved that LHQK exhibits excellent clinical efficacy in the treatment of acute lung injury (ALI). However, the corresponding mechanisms remain largely unexplored. In this study, we investigated the effects and the underlying mechanisms of LHQK on lipopolysaccharide (LPS)-induced ALI in mice. The pathological examination, inflammatory cytokines assessments, and mucus secretion evaluation indicated that administration of LHQK ameliorated LPS-induced lung injury, and suppressed the secretion of Muc5AC and pro-inflammatory cytokines (IL-6, TNF-α, and IL-1β) in plasma and BALF. Furthermore, the results of cell-free DNA level showed that LHQK significantly inhibited LPS-induced NETs formation. Western blot revealed that LHQK effectively inhibited LPS-triggered pyroptosis in the lung. In addition, RNA-Seq data analysis, relatively bioinformatic analysis, and network pharmacology analysis revealed that LHQK and relative components may play multiple protective functions in LPS-induced ALI/acute respiratory distress syndrome (ARDS) by regulating multiple targets directly or indirectly related to NETs and pyroptosis. In conclusion, LHQK can effectively attenuate lung injury and reduce lung inflammation by inhibiting LPS-induced NETs formation and pyroptosis, which may be regulated directly or indirectly by active compounds of LHQK.

Elucidating disease-associated mechanisms triggered by pollutants via the epigenetic landscape using large-scale ChIP-Seq data

BACKGROUND

Despite well-documented effects on human health, the action modes of environmental pollutants are incompletely understood. Although transcriptome-based approaches are widely used to predict associations between chemicals and disorders, the molecular cues regulating pollutant-derived gene expression changes remain unclear. Therefore, we developed a data-mining approach, termed "DAR-ChIPEA," to identify transcription factors (TFs) playing pivotal roles in the action modes of pollutants.

METHODS

Large-scale public ChIP-Seq data (human, n = 15,155; mouse, n = 13,156) were used to predict TFs that are enriched in the pollutant-induced differentially accessible genomic regions (DARs) obtained from epigenome analyses (ATAC-Seq). The resultant pollutant-TF matrices were then cross-referenced to a repository of TF-disorder associations to account for pollutant modes of action. We subsequently evaluated the performance of the proposed method using a chemical perturbation data set to compare the outputs of the DAR-ChIPEA and our previously developed differentially expressed gene (DEG)-ChIPEA methods using pollutant-induced DEGs as input. We then adopted the proposed method to predict disease-associated mechanisms triggered by pollutants.

RESULTS

The proposed approach outperformed other methods using the area under the receiver operating characteristic curve score. The mean score of the proposed DAR-ChIPEA was significantly higher than that of our previously described DEG-ChIPEA (0.7287 vs. 0.7060; Q = 5.278 × 10-42; two-tailed Wilcoxon rank-sum test). The proposed approach further predicted TF-driven modes of action upon pollutant exposure, indicating that (1) TFs regulating Th1/2 cell homeostasis are integral in the pathophysiology of tributyltin-induced allergic disorders; (2) fine particulates (PM2.5) inhibit the binding of C/EBPs, Rela, and Spi1 to the genome, thereby perturbing normal blood cell differentiation and leading to immune dysfunction; and (3) lead induces fatty liver by disrupting the normal regulation of lipid metabolism by altering hepatic circadian rhythms.

CONCLUSIONS

Highlighting genome-wide chromatin change upon pollutant exposure to elucidate the epigenetic landscape of pollutant responses outperformed our previously described method that focuses on gene-adjacent domains only. Our approach has the potential to reveal pivotal TFs that mediate deleterious effects of pollutants, thereby facilitating the development of strategies to mitigate damage from environmental pollution.

Identifying Differences in the Performance of Machine Learning Models for Off-Targets Trained on Publicly Available and Proprietary Data Sets

Each year, publicly available databases are updated with new compounds from different research institutions. Positive experimental outcomes are more likely to be reported; therefore, they account for a considerable fraction of these entries. Established publicly available databases such as ChEMBL allow researchers to use information without constrictions and create predictive tools for a broad spectrum of applications in the field of toxicology. Therefore, we investigated the distribution of positive and nonpositive entries within ChEMBL for a set of off-targets and its impact on the performance of classification models when applied to pharmaceutical industry data sets. Results indicate that models trained on publicly available data tend to overpredict positives, and models based on industry data sets predict negatives more often than those built using publicly available data sets. This is strengthened even further by the visualization of the prediction space for a set of 10,000 compounds, which makes it possible to identify regions in the chemical space where predictions converge. Finally, we highlight the utilization of these models for consensus modeling for potential adverse events prediction.

Repositioning of clinically approved drug Bazi Bushen capsule for treatment of Aizheimer's disease using network pharmacology approach and in vitro experimental validation

Aims

To explore the new indications and key mechanism of Bazi Bushen capsule (BZBS) by network pharmacology and in vitro experiment.

Methods

The ingredients library of BZBS was constructed by retrieving multiple TCM databases. The potential target profiles of the components were predicted by target prediction algorithms based on different principles, and validated by using known activity data. The target spectrum of BZBS with high reliability was screened by considering the source of the targets and the node degree in compound-target (C-T) network. Subsequently, new indications for BZBS were predicted by disease ontology (DO) enrichment analysis and initially validated by GO and KEGG pathway enrichment analysis. Furthermore, the target sets of BZBS acting on AD signaling pathway were identified by intersection analysis. Based on STRING database, the PPI network of target was constructed and their node degree was calculated. Two Alzheimer's disease (AD) cell models, BV-2 and SH-SY5Y, were used to preliminarily verify the anti-AD efficacy and mechanism of BZBS in vitro.

Results

In total, 1499 non-repeated ingredients were obtained from 16 herbs in BZBS formula, and 1320 BZBS targets with high confidence were predicted. Disease enrichment results strongly suggested that BZBS formula has the potential to be used in the treatment of AD. GO and KEGG enrichment results provide a preliminary verification of this point. Among them, 113 functional targets of BZBS belong to AD pathway. A PPI network containing 113 functional targets and 1051 edges for the treatment of AD was constructed. In vitro experiments showed that BZBS could significantly reduce the release of TNF-α and IL-6 and the expression of COX-2 and PSEN1 in Aβ_25-35-induced BV-2 cells, which may be related to the regulation of ERK_1/2/NF-κB signaling pathway. BZBS reduced the apoptosis rate of Aβ_25-35 induced SH-SY5Y cells, significantly increased mitochondrial membrane potential, reduced the expression of Caspase3 active fragment and PSEN1, and increased the expression of IDE. This may be related to the regulation of GSK-3β/β-catenin signaling pathway.

Conclusions

BZBS formula has a potential use in the treatment of AD, which is achieved through regulation of ERK_1/2, NF-κB signaling pathways, and GSK-3β/β-catenin signaling pathway. Furthermore, the network pharmacology technology is a feasible drug repurposing strategy to reposition new clinical use of approved TCM and explore the mechanism of action. The study lays a foundation for the subsequent in-depth study of BZBS in the treatment of AD and provides a basis for its application in the clinical treatment of AD.

Critical-Illness: Combined Effects of Colistin and Vasoactive Drugs: A Pilot Study

Colistin is often used as a last resort for treating multidrug-resistant infections, particularly in critically ill patients in intensive care units. Nonetheless, its side effects, including myopathy, require careful monitoring. Vasoconstrictive drugs are also used in intensive care to increase blood pressure and improve blood flow to vital organs, which can be compromised in critically ill patients. The exact mechanism of colistin-induced muscle toxicity is of significant interest due to its potential intensive-care clinical implications. Colistin alone or in combination with vasoconstrictive agents was administrated in non-septic and LPS-induced septic animals for 10 days. Histopathological evaluation of the gastrocnemius muscle and dot-blot protein tissue analysis were performed. Increased intramuscular area, de-organization of the muscle fibers and signs of myopathy were observed in colistin-treated animals. This effect was ameliorated in the presence of vasoconstrictive drugs. Administration of colistin to septic animals resulted in a decrease of AMPK and cyclin-D1 levels, while it had no effect on caspase 3 levels. Vasoconstrictive drugs' administration reversed the effects of colistin on AMPK and cyclin D1 levels. Colistin's effects on muscle depend on septic state and vasoconstriction presence, highlighting the need to consider these factors when administering it in critically ill patients.

Evaluating point-prediction uncertainties in neural networks for protein-ligand binding prediction

Neural Network (NN) models provide potential to speed up the drug discovery process and reduce its failure rates. The success of NN models requires uncertainty quantification (UQ) as drug discovery explores chemical space beyond the training data distribution. Standard NN models do not provide uncertainty information. Some methods require changing the NN architecture or training procedure, limiting the selection of NN models. Moreover, predictive uncertainty can come from different sources. It is important to have the ability to separately model different types of predictive uncertainty, as the model can take assorted actions depending on the source of uncertainty. In this paper, we examine UQ methods that estimate different sources of predictive uncertainty for NN models aiming at protein-ligand binding prediction. We use our prior knowledge on chemical compounds to design the experiments. By utilizing a visualization method we create non-overlapping and chemically diverse partitions from a collection of chemical compounds. These partitions are used as training and test set splits to explore NN model uncertainty. We demonstrate how the uncertainties estimated by the selected methods describe different sources of uncertainty under different partitions and featurization schemes and the relationship to prediction error.

Past, Present, and Future Perspectives on Computer-Aided Drug Design Methodologies

The application of computational approaches in drug discovery has been consolidated in the last decades. These families of techniques are usually grouped under the common name of "computer-aided drug design" (CADD), and they now constitute one of the pillars in the pharmaceutical discovery pipelines in many academic and industrial environments. Their implementation has been demonstrated to tremendously improve the speed of the early discovery steps, allowing for the proficient and rational choice of proper compounds for a desired therapeutic need among the extreme vastness of the drug-like chemical space. Moreover, the application of CADD approaches allows the rationalization of biochemical and interactive processes of pharmaceutical interest at the molecular level. Because of this, computational tools are now extensively used also in the field of rational 3D design and optimization of chemical entities starting from the structural information of the targets, which can be experimentally resolved or can also be obtained with other computer-based techniques. In this work, we revised the state-of-the-art computer-aided drug design methods, focusing on their application in different scenarios of pharmaceutical and biological interest, not only highlighting their great potential and their benefits, but also discussing their actual limitations and eventual weaknesses. This work can be considered a brief overview of computational methods for drug discovery.

SIRT2i_Predictor: A Machine Learning-Based Tool to Facilitate the Discovery of Novel SIRT2 Inhibitors

A growing body of preclinical evidence recognized selective sirtuin 2 (SIRT2) inhibitors as novel therapeutics for treatment of age-related diseases. However, none of the SIRT2 inhibitors have reached clinical trials yet. Transformative potential of machine learning (ML) in early stages of drug discovery has been witnessed by widespread adoption of these techniques in recent years. Despite great potential, there is a lack of robust and large-scale ML models for discovery of novel SIRT2 inhibitors. In order to support virtual screening (VS), lead optimization, or facilitate the selection of SIRT2 inhibitors for experimental evaluation, a machine-learning-based tool titled SIRT2i_Predictor was developed. The tool was built on a panel of high-quality ML regression and classification-based models for prediction of inhibitor potency and SIRT1-3 isoform selectivity. State-of-the-art ML algorithms were used to train the models on a large and diverse dataset containing 1797 compounds. Benchmarking against structure-based VS protocol indicated comparable coverage of chemical space with great gain in speed. The tool was applied to screen the in-house database of compounds, corroborating the utility in the prioritization of compounds for costly in vitro screening campaigns. The easy-to-use web-based interface makes SIRT2i_Predictor a convenient tool for the wider community. The SIRT2i_Predictor's source code is made available online.

EMBL's European Bioinformatics Institute (EMBL-EBI) in 2022

The European Molecular Biology Laboratory's European Bioinformatics Institute (EMBL-EBI) is one of the world's leading sources of public biomolecular data. Based at the Wellcome Genome Campus in Hinxton, UK, EMBL-EBI is one of six sites of the European Molecular Biology Laboratory (EMBL), Europe's only intergovernmental life sciences organisation. This overview summarises the status of services that EMBL-EBI data resources provide to scientific communities globally. The scale, openness, rich metadata and extensive curation of EMBL-EBI added-value databases makes them particularly well-suited as training sets for deep learning, machine learning and artificial intelligence applications, a selection of which are described here. The data resources at EMBL-EBI can catalyse such developments because they offer sustainable, high-quality data, collected in some cases over decades and made openly availability to any researcher, globally. Our aim is for EMBL-EBI data resources to keep providing the foundations for tools and research insights that transform fields across the life sciences.

EFMSDTI: Drug-target interaction prediction based on an efficient fusion of multi-source data

Accurate identification of Drug Target Interactions (DTIs) is of great significance for understanding the mechanism of drug treatment and discovering new drugs for disease treatment. Currently, computational methods of DTIs prediction that combine drug and target multi-source data can effectively reduce the cost and time of drug development. However, in multi-source data processing, the contribution of different source data to DTIs is often not considered. Therefore, how to make full use of the contribution of different source data to predict DTIs for efficient fusion is the key to improving the prediction accuracy of DTIs. In this paper, considering the contribution of different source data to DTIs prediction, a DTIs prediction approach based on an effective fusion of drug and target multi-source data is proposed, named EFMSDTI. EFMSDTI first builds 15 similarity networks based on multi-source information networks classified as topological and semantic graphs of drugs and targets according to their biological characteristics. Then, the multi-networks are fused by selective and entropy weighting based on similarity network fusion (SNF) according to their contribution to DTIs prediction. The deep neural networks model learns the embedding of low-dimensional vectors of drugs and targets. Finally, the LightGBM algorithm based on Gradient Boosting Decision Tree (GBDT) is used to complete DTIs prediction. Experimental results show that EFMSDTI has better performance (AUROC and AUPR are 0.982) than several state-of-the-art algorithms. Also, it has a good effect on analyzing the top 1000 prediction results, while 990 of the first 1000DTIs were confirmed. Code and data are available at https://github.com/meng-jie/EFMSDTI.

Ligand-based prediction of hERG-mediated cardiotoxicity based on the integration of different machine learning techniques

Drug-induced cardiotoxicity is a common side effect of drugs in clinical use or under postmarket surveillance and is commonly due to off-target interactions with the cardiac human-ether-a-go-go-related (hERG) potassium channel. Therefore, prioritizing drug candidates based on their hERG blocking potential is a mandatory step in the early preclinical stage of a drug discovery program. Herein, we trained and properly validated 30 ligand-based classifiers of hERG-related cardiotoxicity based on 7,963 curated compounds extracted by the freely accessible repository ChEMBL (version 25). Different machine learning algorithms were tested, namely, random forest, K-nearest neighbors, gradient boosting, extreme gradient boosting, multilayer perceptron, and support vector machine. The application of 1) the best practices for data curation, 2) the feature selection method VSURF, and 3) the synthetic minority oversampling technique (SMOTE) to properly handle the unbalanced data, allowed for the development of highly predictive models (BAMAX = 0.91, AUCMAX = 0.95). Remarkably, the undertaken temporal validation approach not only supported the predictivity of the herein presented classifiers but also suggested their ability to outperform those models commonly used in the literature. From a more methodological point of view, the study put forward a new computational workflow, freely available in the GitHub repository (https://github.com/PDelre93/hERG-QSAR), as valuable for building highly predictive models of hERG-mediated cardiotoxicity.

Harnessing Protein-Ligand Interaction Fingerprints to Predict New Scaffolds of RIPK1 Inhibitors

Necroptosis has emerged as an exciting target in oncological, inflammatory, neurodegenerative, and autoimmune diseases, in addition to acute ischemic injuries. It is known to play a role in innate immune response, as well as in antiviral cellular response. Here we devised a concerted in silico and experimental framework to identify novel RIPK1 inhibitors, a key necroptosis factor. We propose the first in silico model for the prediction of new RIPK1 inhibitor scaffolds by combining docking and machine learning methodologies. Through the data analysis of patterns in docking results, we derived two rules, where rule #1 consisted of a four-residue signature filter, and rule #2 consisted of a six-residue similarity filter based on docking calculations. These were used in consensus with a machine learning QSAR model from data collated from ChEMBL, the literature, in patents, and from PubChem data. The models allowed for good prediction of actives of >90, 92, and 96.4% precision, respectively. As a proof-of-concept, we selected 50 compounds from the ChemBridge database, using a consensus of both molecular docking and machine learning methods, and tested them in a phenotypic necroptosis assay and a biochemical RIPK1 inhibition assay. A total of 7 of the 47 tested compounds demonstrated around 20−25% inhibition of RIPK1’s kinase activity but, more importantly, these compounds were discovered to occupy new areas of chemical space. Although no strong actives were found, they could be candidates for further optimization, particularly because they have new scaffolds. In conclusion, this screening method may prove valuable for future screening efforts as it allows for the exploration of new areas of the chemical space in a very fast and inexpensive manner, therefore providing efficient starting points amenable to further hit-optimization campaigns.

The Molecular Mechanism of Traditional Chinese Medicine Prescription: Gu-tong Formula in Relieving Osteolytic Bone Destruction

Bone metastasis is a common complication in patients with advanced tumors, causing pain and bone destruction and affecting their quality of life. Typically, complementary and alternative medicine (CAM), with unique theoretical guidance, has played key roles in the treatment of tumor-related diseases. Gu-tong formula (GTF), as a representative prescription of traditional Chinese medicine, has been demonstrated to be an effective clinical medication for the relief of cancer pain. However, the molecular mechanism of GTF in the treatment of osteolytic metastasis is still unclear. Herein, we employ network pharmacology and molecular dynamics methods to uncover the potential treatment mechanism, indicating that GTF can reduce the levels of serum IL6 and TGFB1 and thus limit the scope of bone cortical damage. Among the active compounds, sesamin and deltoin can bind stably with IL6 and TGFB1, respectively, and have the potential to become anti-inflammatory and anticancer drugs. Although the reasons for the therapeutic effect of GTF are complex and comprehensive, this work provides biological plausibility in the treatment of osteolytic metastases, which has a guiding significance for the treatment of cancer pain with CAM.

multi-type neighbors enhanced global topology and pairwise attribute learning for drug-protein interaction prediction

MOTIVATION

Accurate identification of proteins interacted with drugs helps reduce the time and cost of drug development. Most of previous methods focused on integrating multisource data about drugs and proteins for predicting drug-target interactions (DTIs). There are both similarity connection and interaction connection between two drugs, and these connections reflect their relationships from different perspectives. Similarly, two proteins have various connections from multiple perspectives. However, most of previous methods failed to deeply integrate these connections. In addition, multiple drug-protein heterogeneous networks can be constructed based on multiple kinds of connections. The diverse topological structures of these networks are still not exploited completely.

RESULTS

We propose a novel model to extract and integrate multi-type neighbor topology information, diverse similarities and interactions related to drugs and proteins. Firstly, multiple drug-protein heterogeneous networks are constructed according to multiple kinds of connections among drugs and those among proteins. The multi-type neighbor node sequences of a drug node (or a protein node) are formed by random walks on each network and they reflect the hidden neighbor topological structure of the node. Secondly, a module based on graph neural network (GNN) is proposed to learn the multi-type neighbor topologies of each node. We propose attention mechanisms at neighbor node level and at neighbor type level to learn more informative neighbor nodes and neighbor types. A network-level attention is also designed to enhance the context dependency among multiple neighbor topologies of a pair of drug and protein nodes. Finally, the attribute embedding of the drug-protein pair is formulated by a proposed embedding strategy, and the embedding covers the similarities and interactions about the pair. A module based on three-dimensional convolutional neural networks (CNN) is constructed to deeply integrate pairwise attributes. Extensive experiments have been performed and the results indicate GCDTI outperforms several state-of-the-art prediction methods. The recall rate estimation over the top-ranked candidates and case studies on 5 drugs further demonstrate GCDTI's ability in discovering potential drug-protein interactions.

Studying and mitigating the effects of data drifts on ML model performance at the example of chemical toxicity data

Machine learning models are widely applied to predict molecular properties or the biological activity of small molecules on a specific protein. Models can be integrated in a conformal prediction (CP) framework which adds a calibration step to estimate the confidence of the predictions. CP models present the advantage of ensuring a predefined error rate under the assumption that test and calibration set are exchangeable. In cases where the test data have drifted away from the descriptor space of the training data, or where assay setups have changed, this assumption might not be fulfilled and the models are not guaranteed to be valid. In this study, the performance of internally valid CP models when applied to either newer time-split data or to external data was evaluated. In detail, temporal data drifts were analysed based on twelve datasets from the ChEMBL database. In addition, discrepancies between models trained on publicly-available data and applied to proprietary data for the liver toxicity and MNT in vivo endpoints were investigated. In most cases, a drastic decrease in the validity of the models was observed when applied to the time-split or external (holdout) test sets. To overcome the decrease in model validity, a strategy for updating the calibration set with data more similar to the holdout set was investigated. Updating the calibration set generally improved the validity, restoring it completely to its expected value in many cases. The restored validity is the first requisite for applying the CP models with confidence. However, the increased validity comes at the cost of a decrease in model efficiency, as more predictions are identified as inconclusive. This study presents a strategy to recalibrate CP models to mitigate the effects of data drifts. Updating the calibration sets without having to retrain the model has proven to be a useful approach to restore the validity of most models.

Prediction of the Neurotoxic Potential of Chemicals Based on Modelling of Molecular Initiating Events Upstream of the Adverse Outcome Pathways of (Developmental) Neurotoxicity

Developmental and adult/ageing neurotoxicity is an area needing alternative methods for chemical risk assessment. The formulation of a strategy to screen large numbers of chemicals is highly relevant due to potential exposure to compounds that may have long-term adverse health consequences on the nervous system, leading to neurodegeneration. Adverse Outcome Pathways (AOPs) provide information on relevant molecular initiating events (MIEs) and key events (KEs) that could inform the development of computational alternatives for these complex effects. We propose a screening method integrating multiple Quantitative Structure–Activity Relationship (QSAR) models. The MIEs of existing AOP networks of developmental and adult/ageing neurotoxicity were modelled to predict neurotoxicity. Random Forests were used to model each MIE. Predictions returned by single models were integrated and evaluated for their capability to predict neurotoxicity. Specifically, MIE predictions were used within various types of classifiers and compared with other reference standards (chemical descriptors and structural fingerprints) to benchmark their predictive capability. Overall, classifiers based on MIE predictions returned predictive performances comparable to those based on chemical descriptors and structural fingerprints. The integrated computational approach described here will be beneficial for large-scale screening and prioritisation of chemicals as a function of their potential to cause long-term neurotoxic effects.

In silico predictions of the human pharmacokinetics/toxicokinetics of 65 chemicals from various classes using conformal prediction methodology

Pharmacokinetic/toxicokinetic (PK/TK) information for chemicals in humans is generally lacking. Here we applied machine learning, conformal prediction and a new physiologically-based PK/TK model for prediction of the human PK/TK of 65 chemicals from different classes, including carcinogens, food constituents and preservatives, vitamins, sweeteners, dyes and colours, pesticides, alternative medicines, flame retardants, psychoactive drugs, dioxins, poisons, UV-absorbents, surfactants, solvents and cosmetics.About 80% of the main human PK/TK (fraction absorbed, oral bioavailability, half-life, unbound fraction in plasma, clearance, volume of distribution, fraction excreted) for the selected chemicals was missing in the literature. This information was now added (from in silico predictions). Median and mean prediction errors for these parameters were 1.3- to 2.7-fold and 1.4- to 4.8-fold, respectively. In total, 59 and 86% of predictions had errors <2- and <5-fold, respectively. Predicted and observed PK/TK for the chemicals was generally within the range for pharmaceutical drugs.The results validated the new integrated system for prediction of the human PK/TK for different chemicals and added important missing information. No general difference in PK/TK-characteristics was found between the selected chemicals and pharmaceutical drugs.

Discovery of Kinase and Carbonic Anhydrase Dual Inhibitors by Machine Learning Classification and Experiments

A multi-target small molecule modulator is advantageous for treating complicated diseases such as cancers. However, the strategy and application for discovering a multi-target modulator have been less reported. This study presents the dual inhibitors for kinase and carbonic anhydrase (CA) predicted by machine learning (ML) classifiers, and validated by biochemical and biophysical experiments. ML trained by CA I and CA II inhibitor molecular fingerprints predicted candidates from the protein-specific bioactive molecules approved or under clinical trials. For experimental tests, three sulfonamide-containing kinase inhibitors, 5932, 5946, and 6046, were chosen. The enzyme assays with CA I, CA II, CA IX, and CA XII have allowed the quantitative comparison in the molecules’ inhibitory activities. While 6046 inhibited weakly, 5932 and 5946 exhibited potent inhibitions with 100 nM to 1 μM inhibitory constants. The ML screening was extended for finding CAs inhibitors of all known kinase inhibitors. It found XMU-MP-1 as another potent CA inhibitor with an approximate 30 nM inhibitory constant for CA I, CA II, and CA IX. Differential scanning fluorimetry confirmed the direct interaction between CAs and small molecules. Cheminformatics studies, including docking simulation, suggest that each molecule possesses two separate functional moieties: one for interaction with kinases and the other with CAs.

Computational analyses of mechanism of action (MoA): data, methods and integration

The elucidation of a compound's Mechanism of Action (MoA) is a challenging task in the drug discovery process, but it is important in order to rationalise phenotypic findings and to anticipate potential side-effects. Bioinformatic approaches, advances in machine learning techniques and the increasing deposition of high-throughput data in public databases have significantly contributed to recent advances in the field, but it is not straightforward to decide which data and methods are most suitable to use in a given case. In this review, we focus on these methods and data and their applications in generating MoA hypotheses for subsequent experimental validation. We discuss compound-specific data such as -omics, cell morphology and bioactivity data, as well as commonly used supplementary prior knowledge such as network and pathway data, and provide information on databases where this data can be accessed. In terms of methodologies, we discuss both well-established methods (connectivity mapping, pathway enrichment) as well as more developing methods (neural networks and multi-omics integration). Finally, we review case studies where the MoA of a compound was successfully suggested from computational analysis by incorporating multiple data modalities and/or methodologies. Our aim for this review is to provide researchers with insights into the benefits and drawbacks of both the data and methods in terms of level of understanding, biases and interpretation - and to highlight future avenues of investigation which we foresee will improve the field of MoA elucidation, including greater public access to -omics data and methodologies which are capable of data integration.

Epigenetic landscape of drug responses revealed through large-scale ChIP-seq data analyses

Background

Elucidating the modes of action (MoAs) of drugs and drug candidate compounds is critical for guiding translation from drug discovery to clinical application. Despite the development of several data-driven approaches for predicting chemical–disease associations, the molecular cues that organize the epigenetic landscape of drug responses remain poorly understood.

Results

With the use of a computational method, we attempted to elucidate the epigenetic landscape of drug responses, in terms of transcription factors (TFs), through large-scale ChIP-seq data analyses. In the algorithm, we systematically identified TFs that regulate the expression of chemically induced genes by integrating transcriptome data from chemical induction experiments and almost all publicly available ChIP-seq data (consisting of 13,558 experiments). By relating the resultant chemical–TF associations to a repository of associated proteins for a wide range of diseases, we made a comprehensive prediction of chemical–TF–disease associations, which could then be used to account for drug MoAs. Using this approach, we predicted that: (1) cisplatin promotes the anti-tumor activity of TP53 family members but suppresses the cancer-inducing function of MYCs; (2) inhibition of RELA and E2F1 is pivotal for leflunomide to exhibit antiproliferative activity; and (3) CHD8 mediates valproic acid-induced autism.

Conclusions

Our proposed approach has the potential to elucidate the MoAs for both approved drugs and candidate compounds from an epigenetic perspective, thereby revealing new therapeutic targets, and to guide the discovery of unexpected therapeutic effects, side effects, and novel targets and actions.

Fragment Hotspot Mapping to Identify Selectivity-Determining Regions between Related Proteins

Selectivity is a crucial property in small molecule development. Binding site comparisons within a protein family are a key piece of information when aiming to modulate the selectivity profile of a compound. Binding site differences can be exploited to confer selectivity for a specific target, while shared areas can provide insights into polypharmacology. As the quantity of structural data grows, automated methods are needed to process, summarize, and present these data to users. We present a computational method that provides quantitative and data-driven summaries of the available binding site information from an ensemble of structures of the same protein. The resulting ensemble maps identify the key interactions important for ligand binding in the ensemble. The comparison of ensemble maps of related proteins enables the identification of selectivity-determining regions within a protein family. We applied the method to three examples from the well-researched human bromodomain and kinase families, demonstrating that the method is able to identify selectivity-determining regions that have been used to introduce selectivity in past drug discovery campaigns. We then illustrate how the resulting maps can be used to automate comparisons across a target protein family.

Deep Neural Networks for QSAR

Quantitative structure-activity relationship (QSAR) models are routinely applied computational tools in the drug discovery process. QSAR models are regression or classification models that predict the biological activities of molecules based on the features derived from their molecular structures. These models are usually used to prioritize a list of candidate molecules for future laboratory experiments and to help chemists gain better insights into how structural changes affect a molecule's biological activities. Developing accurate and interpretable QSAR models is therefore of the utmost importance in the drug discovery process. Deep neural networks, which are powerful supervised learning algorithms, have shown great promise for addressing regression and classification problems in various research fields, including the pharmaceutical industry. In this chapter, we briefly review the applications of deep neural networks in QSAR modeling and describe commonly used techniques to improve model performance.

The effect of noise on the predictive limit of QSAR models

A key challenge in the field of Quantitative Structure Activity Relationships (QSAR) is how to effectively treat experimental error in the training and evaluation of computational models. It is often assumed in the field of QSAR that models cannot produce predictions which are more accurate than their training data. Additionally, it is implicitly assumed, by necessity, that data points in test sets or validation sets do not contain error, and that each data point is a population mean. This work proposes the hypothesis that QSAR models can make predictions which are more accurate than their training data and that the error-free test set assumption leads to a significant misevaluation of model performance. This work used 8 datasets with six different common QSAR endpoints, because different endpoints should have different amounts of experimental error associated with varying complexity of the measurements. Up to 15 levels of simulated Gaussian distributed random error was added to the datasets, and models were built on the error laden datasets using five different algorithms. The models were trained on the error laden data, evaluated on error-laden test sets, and evaluated on error-free test sets. The results show that for each level of added error, the RMSE for evaluation on the error free test sets was always better. The results support the hypothesis that, at least under the conditions of Gaussian distributed random error, QSAR models can make predictions which are more accurate than their training data, and that the evaluation of models on error laden test and validation sets may give a flawed measure of model performance. These results have implications for how QSAR models are evaluated, especially for disciplines where experimental error is very large, such as in computational toxicology.

Simplified, interpretable graph convolutional neural networks for small molecule activity prediction

We here present a streamlined, explainable graph convolutional neural network (gCNN) architecture for small molecule activity prediction. We first conduct a hyperparameter optimization across nearly 800 protein targets that produces a simplified gCNN QSAR architecture, and we observe that such a model can yield performance improvements over both standard gCNN and RF methods on difficult-to-classify test sets. Additionally, we discuss how reductions in convolutional layer dimensions potentially speak to the “anatomical” needs of gCNNs with respect to radial coarse graining of molecular substructure. We augment this simplified architecture with saliency map technology that highlights molecular substructures relevant to activity, and we perform saliency analysis on nearly 100 data-rich protein targets. We show that resultant substructural clusters are useful visualization tools for understanding substructure-activity relationships. We go on to highlight connections between our models’ saliency predictions and observations made in the medicinal chemistry literature, focusing on four case studies of past lead finding and lead optimization campaigns.

Critical Assessment of Conformal Prediction Methods Applied in Binary Classification Settings

In recent years there has been an increase in the number of scientific papers that suggest using conformal predictions in drug discovery. We consider that some versions of conformal predictions applied in binary settings are embroiled in pitfalls, not obvious at first sight, and that it is important to inform the scientific community about them. In the paper we first introduce the general theory of conformal predictions and follow with an explanation of the version currently dominant in drug discovery research today. Finally, we provide cases for their critical assessment in binary classification settings.

The role of machine learning method in the synthesis and biological ınvestigation of heterocyclic compounds

Machine learning (ML) methods have attracted increasing interest in chemistry as in all fields of science in recent years. This method is of great importance for the design of targeted bioactive compounds, especially by avoiding loss of time, money, and chemicals. There are lots of online web-based platforms such as LibSVM and OCHEM for the application of ML methods. In this paper, it has been examined the literature data on the activity predictions of heterocyclic compounds, biological activity results such as antiurease, HIV-1 Integrase, E. Coli DNA Gyrase B, and antifungal, pharmacophore-based studies, synthesis, and finding possible inhibitors using different machine learning methods.

Synergy conformal prediction applied to large-scale bioactivity datasets and in federated learning

Confidence predictors can deliver predictions with the associated confidence required for decision making and can play an important role in drug discovery and toxicity predictions. In this work we investigate a recently introduced version of conformal prediction, synergy conformal prediction, focusing on the predictive performance when applied to bioactivity data. We compare the performance to other variants of conformal predictors for multiple partitioned datasets and demonstrate the utility of synergy conformal predictors for federated learning where data cannot be pooled in one location. Our results show that synergy conformal predictors based on training data randomly sampled with replacement can compete with other conformal setups, while using completely separate training sets often results in worse performance. However, in a federated setup where no method has access to all the data, synergy conformal prediction is shown to give promising results. Based on our study, we conclude that synergy conformal predictors are a valuable addition to the conformal prediction toolbox.

Multiple Conformer Descriptors for QSAR Modeling

The most widely used QSAR approaches are mainly based on 2D molecular representation which ignores stereoconfiguration and conformational flexibility of compounds. 3D QSAR uses a single conformer of each compound which is difficult to choose reasonably. 4D QSAR uses multiple conformers to overcome the issues of 2D and 3D methods. However, many of existing 4D QSAR models suffer from the necessity to pre-align conformers, while alignment-independent approaches often ignore stereoconfiguration of compounds. In this study we propose a QSAR modeling approach based on transforming chirality-aware 3D pharmacophore descriptors of individual conformers into a set of latent variables representing the whole conformer set of a molecule. This is achieved by clustering together all conformers of all training set compounds. The final representation of a compound is a bit string encoding cluster membership of its conformers. In our study we used Random Forest, but this representation can be used in combination with any machine learning method. We compared this approach with conventional 2D and 3D approaches using multiple data sets and investigated the sensitivity of the approach proposed to tuning parameters: number of conformers and clusters.

BonMOLière: Small-Sized Libraries of Readily Purchasable Compounds, Optimized to Produce Genuine Hits in Biological Screens across the Protein Space

Experimental screening of large sets of compounds against macromolecular targets is a key strategy to identify novel bioactivities. However, large-scale screening requires substantial experimental resources and is time-consuming and challenging. Therefore, small to medium-sized compound libraries with a high chance of producing genuine hits on an arbitrary protein of interest would be of great value to fields related to early drug discovery, in particular biochemical and cell research. Here, we present a computational approach that incorporates drug-likeness, predicted bioactivities, biological space coverage, and target novelty, to generate optimized compound libraries with maximized chances of producing genuine hits for a wide range of proteins. The computational approach evaluates drug-likeness with a set of established rules, predicts bioactivities with a validated, similarity-based approach, and optimizes the composition of small sets of compounds towards maximum target coverage and novelty. We found that, in comparison to the random selection of compounds for a library, our approach generates substantially improved compound sets. Quantified as the "fitness" of compound libraries, the calculated improvements ranged from +60% (for a library of 15,000 compounds) to +184% (for a library of 1000 compounds). The best of the optimized compound libraries prepared in this work are available for download as a dataset bundle ("BonMOLière").

Quantum Machine Learning Algorithms for Drug Discovery Applications

The growing quantity of public and private data sets focused on small molecules screened against biological targets or whole organisms provides a wealth of drug discovery relevant data. This is matched by the availability of machine learning algorithms such as Support Vector Machines (SVM) and Deep Neural Networks (DNN) that are computationally expensive to perform on very large data sets with thousands of molecular descriptors. Quantum computer (QC) algorithms have been proposed to offer an approach to accelerate quantum machine learning over classical computer (CC) algorithms, however with significant limitations. In the case of cheminformatics, which is widely used in drug discovery, one of the challenges to overcome is the need for compression of large numbers of molecular descriptors for use on a QC. Here, we show how to achieve compression with data sets using hundreds of molecules (SARS-CoV-2) to hundreds of thousands of molecules (whole cell screening data sets for plague and M. tuberculosis) with SVM and the data reuploading classifier (a DNN equivalent algorithm) on a QC benchmarked against CC and hybrid approaches. This study illustrates the steps needed in order to be "quantum computer ready" in order to apply quantum computing to drug discovery and to provide the foundation on which to build this field.

[Predict of metabolic stability of xenobiotics by the PASS and GUSAR programs]

Metabolic stability refers to the susceptibility of compounds to the biotransformation; it is characterized by such pharmacokinetic parameters as half-life (T1/2) and clearance (CL). Generally, these parameters are estimated by in vitro assays, which are based on cells or subcellular fractions (mainly liver microsomal enzymes) and serve as models of the processes occurring in living organisms. Data obtained from the experiments are used to build QSAR (Quantitative Structure-Activity Relationship) models. More than 8000 compounds with known CL and/or T1/2 values obtained in vitro using human liver microsomes were selected from the freely available ChEMBL v.27 database. GUSAR (General Unrestricted Structure-Activity Relationships) and PASS (Prediction of Activity Spectra for Substances) softwares were used to make quantitative and classification models. The quality of the models was evaluated using 5-fold cross-validation. Compounds were subdivided into "stable" and "unstable" by means of the following threshold parameters: T1/2 = 30 minutes, CL = 20 ml/min/kg. The accuracy of the models ranged from 0.5 (calculated in 5-fold CV on the test set for the half-life prediction quantitative model) to 0.96 (calculated in 5-fold CV on the test set for the clearance prediction classification model).