In Silico Prediction of Chemical Toxicity for Drug Design Using Machine Learning Methods and Structural Alerts

QSAR Classification Modeling Using Machine Learning with a Consensus-Based Approach for Multivariate Chemical Hazard End Points

This study introduces an innovative computational approach using hybrid machine learning models to predict toxicity across eight critical end points: cardiac toxicity, inhalation toxicity, dermal toxicity, oral toxicity, skin irritation, skin sensitization, eye irritation, and respiratory irritation. Leveraging advanced cheminformatics tools, we extracted relevant features from curated data sets, incorporating a range of descriptors such as Morgan circular fingerprints, MACCS keys, Mordred calculation descriptors, and physicochemical properties. The consensus model was developed by selecting the best-performing classifier-Random Forest (RF), eXtreme Gradient Boosting (XGBoost), or Support Vector Machines (SVM)-for each descriptor, optimizing predictive accuracy and robustness across the end points. The model obtained strong predictive performance, with area under the curve (AUC) scores ranging from 0.78 to 0.90. This framework offers a reliable, ethical, and effective in silico approach to chemical safety assessment, underscoring the potential of advanced computational methods to support both regulatory and research applications in toxicity prediction.

Development of an Antiviral Medicinal Plant and Natural Product Database (avMpNp Database) from Biodiversity

The construction of compound databases (DB) is a strategy for the rational search of bioactive compounds and drugs for new and old diseases. In order to bring greater impact to drug discovery, we propose the development of a DB of bioactive antiviral compounds. Several research groups have presented evidence of the antiviral activity of medicinal plants and compounds isolated from these plants. We believe that compiling these discoveries in a DB would benefit the scientific research community and increase the speed to discover new potential drugs and medicines. Thus, we present the Antiviral Medicinal Plant and Natural Product DB (avMpNp DB) as an important source for acquiring, organizing, and distributing knowledge related to natural products and antiviral drug discovery. The avMpNp DB contains a series of chemically diverse compounds with drug-like profiles. To test the potential of this DB, SARS-CoV-2 Mpro and PLpro enzymatic inhibition assays were performed for available compounds resulting in IC50 values ranging from 6.308±0.296 to 15.795±0.155 μM. As a perspective, artificial intelligence tools will be added to implement computational predictions, as well as other chemical functionalities that allow data validation.

In vitro 3D skin culture and its sustainability in toxicology: a narrative review

In current toxicological research, 2D cell cultures and animal models are well- accepted and commonly employed methods. However, these approaches have many drawbacks and are distant from the actual environment in human. To embrace this, great efforts have been made to provide alternative methods for non-animal skin models in toxicology studies with the need for more mechanistically informative methods. This review focuses on the current state of knowledge regarding the in vitro 3D skin model methods, with different functional states that correspond to the sustainability in the field of toxicology testing. We discuss existing toxicology testing methods using in vitro 3D skin models which provide a better understanding of the testing requirements that are needed. The challenges and future landscape in using the in vitro 3D skin models in toxicology testing are also discussed. We are confident that the in vitro 3D skin models application may become an important tool in toxicology in the context of risk assessment.

AI and ML-based risk assessment of chemicals: predicting carcinogenic risk from chemical-induced genomic instability

Chemical risk assessment plays a pivotal role in safeguarding public health and environmental safety by evaluating the potential hazards and risks associated with chemical exposures. In recent years, the convergence of artificial intelligence (AI), machine learning (ML), and omics technologies has revolutionized the field of chemical risk assessment, offering new insights into toxicity mechanisms, predictive modeling, and risk management strategies. This perspective review explores the synergistic potential of AI/ML and omics in deciphering clastogen-induced genomic instability for carcinogenic risk prediction. We provide an overview of key findings, challenges, and opportunities in integrating AI/ML and omics technologies for chemical risk assessment, highlighting successful applications and case studies across diverse sectors. From predicting genotoxicity and mutagenicity to elucidating molecular pathways underlying carcinogenesis, integrative approaches offer a comprehensive framework for understanding chemical exposures and mitigating associated health risks. Future perspectives for advancing chemical risk assessment and cancer prevention through data integration, advanced machine learning techniques, translational research, and policy implementation are discussed. By implementing the predictive capabilities of AI/ML and omics technologies, researchers and policymakers can enhance public health protection, inform regulatory decisions, and promote sustainable development for a healthier future.

Recent Advances in Omics, Computational Models, and Advanced Screening Methods for Drug Safety and Efficacy

It is imperative to comprehend the mechanisms that underlie drug toxicity in order to enhance the efficacy and safety of novel therapeutic agents. The capacity to identify molecular pathways that contribute to drug-induced toxicity has been significantly enhanced by recent developments in omics technologies, such as transcriptomics, proteomics, and metabolomics. This has enabled the early identification of potential adverse effects. These insights are further enhanced by computational tools, including quantitative structure-activity relationship (QSAR) analyses and machine learning models, which accurately predict toxicity endpoints. Additionally, technologies such as physiologically based pharmacokinetic (PBPK) modeling and micro-physiological systems (MPS) provide more precise preclinical-to-clinical translation, thereby improving drug safety assessments. This review emphasizes the synergy between sophisticated screening technologies, in silico modeling, and omics data, emphasizing their roles in reducing late-stage drug development failures. Challenges persist in the integration of a variety of data types and the interpretation of intricate biological interactions, despite the progress that has been made. The development of standardized methodologies that further enhance predictive toxicology is contingent upon the ongoing collaboration between researchers, clinicians, and regulatory bodies. This collaboration ensures the development of therapeutic pharmaceuticals that are more effective and safer.

Towards a comprehensive assessment of QSP models: what would it take?

Quantitative Systems Pharmacology (QSP) has emerged as a powerful ensemble of approaches aiming at developing integrated mathematical and computational models elucidating the complex interactions between pharmacology, physiology, and disease. As the field grows and matures its applications expand beyond the boundaries of research and development and slowly enter the decision making and regulatory arenas. However, widespread acceptance and eventual adoption of a new modeling approach requires assessment criteria and quantifiable metrics that establish credibility and increase confidence in model predictions. QSP aims to provide an integrated understanding of pathology in the context of therapeutic interventions. Because of its ambitious nature and the fact that QSP emerged in an uncoordinated manner as a result of activities distributed across organizations and academic institutions, high entropy characterizes the tools, methods, and computational methodologies and approaches used. The eventual acceptance of QSP model predictions as supporting material for an application to a regulatory agency will require that two key aspects are considered: (1) increase confidence in the QSP framework, which drives standardization and assessment; and (2) careful articulation of the expectations. Both rely heavily on our ability to rigorously and consistently assess QSP models. In this manuscript, we wish to discuss the meaning and purpose of such an assessment in the context of QSP model development and elaborate on the differentiating features of QSP that render such an endeavor challenging. We argue that QSP establishes a conceptual, integrative framework rather than a specific and well-defined computational methodology. QSP elicits the use of a wide variety of modeling and computational methodologies optimized with respect to specific applications and available data modalities, which exceed the data structures employed by chemometrics and PK/PD models. While the range of options fosters creativity and promises to substantially advance our ability to design pharmaceutical interventions rationally and optimally, our expectations of QSP models need to be clearly articulated and agreed on, with assessment emphasizing the scope of QSP studies rather than the methods used. Nevertheless, QSP should not be considered an independent approach, rather one of many in the broader continuum of computational models.

Synthesis of Acetaminophen-Based Coumarins as Selective COX-2 Inhibitors: An in vitro-in silico Study

Acetaminophen, a centrally-acting old analgesic drug, is a weak inhibitor of cyclooxygenase (COX) isoforms with some selectivity toward COX-2. This compound was used in this work as a precursor to create nine acetaminophen based coumarins (ACFs). To satisfy the aim of this work, which states the synthesis of acetaminophen-based coumarins as selective COX-2 inhibitors, the ACFs were subjected to two types of investigation: in vitro and in silico. Given the former type, the ACFs capacity to block COX-1 and COX-2 was investigated in lab settings. On the other hand, the in silico investigation included docking the chemical structures of ACFs into the active sites of these enzymes, predicting their anticipated toxicities, and determining the ADME characteristics. The results of the in vitro study revealed that the synthesized ACFs demonstrated good-to-excellent inhibitory properties against the enzymes under study. Also, these ACFs exhibited a high level of COX-2 selectivity, which improved as the capacity of the aromatic substitute for withdrawing electrons was enhanced. Results of docking were comparable to the in vitro investigation in case of COX-2. On the other hand, the in silico investigations indicated that the synthesized ACFs are safer than their precursor, acetaminophen, with a high potential to consider oral-administrated candidates.

Application of machine learning in the study of development, behavior, nerve, and genotoxicity of zebrafish

Machine learning (ML) as a novel model-based approach has been used in studying aquatic toxicology in the environmental field. Zebrafish, as an ideal model organism in aquatic toxicology research, has been widely used to study the toxic effects of various pollutants. However, toxicity testing on organisms may cause significant harm, consume considerable time and resources, and raise ethical concerns. Therefore, ML is used in related research to reduce animal experiments and assist researchers in conducting toxicological research. Although ML techniques have matured in various fields, research on ML-based aquatic toxicology is still in its infancy due to the lack of comprehensive large-scale toxicity databases for environmental pollutants and model organisms. Therefore, to better understand the recent research progress of ML in studying the development, behavior, nerve, and genotoxicity of zebrafish, this review mainly focuses on using ML modeling to assess and predict the toxic effects of zebrafish exposure to different toxic chemicals. Meanwhile, the opportunities and challenges faced by ML in the field of toxicology were analyzed. Finally, suggestions and perspectives were proposed for the toxicity studies of ML on zebrafish in future applications.

Identification of Optimal Machine Learning Algorithms and Molecular Fingerprints for Explainable Toxicity Prediction Models Using ToxCast/Tox21 Bioassay Data

Recent studies have primarily focused on introducing novel frameworks to enhance the predictive power of toxicity prediction models by refining molecular representation methods and algorithms. However, these methods are inherently complex and often pose challenges in understanding and explaining, leading to barriers in their regulatory adoption and validation. Therefore, it is necessary to select the optimal model, considering not only model performance but also interpretability. This study aimed to identify the optimal combination of molecular fingerprints (pattern-based versus algorithm-based) and machine learning algorithms (simple versus complex) for developing explainable toxicity prediction models through an comprehensive investigation of the ToxCast/Tox21 bioassay data set. For 1092 ToxCast/Tox21 assays, five molecular fingerprints (MACCS, Morgan, RDKit, Layered, and Patterned) and six algorithms (MLP, GBT, Random Forest, kNN, Logistic Regression, and Naïve Bayes) were used to train the models. Results showed that 35 models revealed acceptable performance (F1 score or accuracy is 0.8 or higher). Among the combinations, either MACCS or Morgan, paired with Random Forest, demonstrated robust performance compared with other molecular fingerprints and algorithms. MACCS and Random Forest are valuable, even when prioritizing interpretability. Consequently, the MACCS-Random Forest combination model based on four assays, targeting G protein-coupled receptor and kinase, were identified and they can be used to discern specific structural features or patterns in chemical compounds, offering explainable insights into toxicity-related chemical structures. This study indicates the importance of not disregarding the utilization of simple models when assessing both predictivity and interpretability within the context of chemical feature-based Tox21 data analysis.

A comprehensive prediction system for silkworm acute toxicity assessment of environmental and in-silico pesticides

The excessive application and loss of pesticides poses a great risk to the ecosystem, and the environmental safety assessment of pesticides is time-consuming and expensive using traditional animal toxicity tests. In this work, a pesticide acute toxicity dataset was created for silkworm integrating extensive experiments and various common pesticide formulations considering the sensitivity of silkworm to adverse environment, its economic value in China, and a gap in machine learning (ML) research on the toxicity prediction of this species, which addressed the previous limitation of only being able to predict toxicity classification without specific toxicity values. A new comprehensive voting model (CVR) was developed based on ML, combined with three regression algorithms, namely, Bayesian Ridge (BR), K Neighbors Regressor (KNN), Random Forest Regressor (RF) to accurately calculate lethal concentration 50 % (LC50). Three conformal models were successfully constructed, marking the first combination of conformal models with confidence intervals to predict silkworm toxicity. Further, the mechanism by analyzing structural alerts was summarized, and identified 25 warning structures, 24 positive compounds and 14 negative compounds. Importantly, a novel comprehensive prediction system was constructed that can provide LC50 and confidence intervals, structural alerts analysis, lipid-water partition coefficient (LogP) and similarity analysis, which can comprehensively evaluate the ecological toxicity risk of substances to make up for the incomplete toxicity data of new pesticides. The validity and generalization of the CVR model were verified by an external validation set. In addition, five new, low-toxic and green pesticide alternatives were designed through 50,000 cycles. Moreover, our software and ST Profiler can provide low-cost information access to accelerate environmental risk assessment, which can predict not only a single chemical, but also batches of chemicals, simply by inputting the SMILES / CAS / (Chinese / English) name of chemicals.

Predicting non-chemotherapy drug-induced agranulocytosis toxicity through ensemble machine learning approaches

Agranulocytosis, induced by non-chemotherapy drugs, is a serious medical condition that presents a formidable challenge in predictive toxicology due to its idiosyncratic nature and complex mechanisms. In this study, we assembled a dataset of 759 compounds and applied a rigorous feature selection process prior to employing ensemble machine learning classifiers to forecast non-chemotherapy drug-induced agranulocytosis (NCDIA) toxicity. The balanced bagging classifier combined with a gradient boosting decision tree (BBC + GBDT), utilizing the combined descriptor set of DS and RDKit comprising 237 features, emerged as the top-performing model, with an external validation AUC of 0.9164, ACC of 83.55%, and MCC of 0.6095. The model's predictive reliability was further substantiated by an applicability domain analysis. Feature importance, assessed through permutation importance within the BBC + GBDT model, highlighted key molecular properties that significantly influence NCDIA toxicity. Additionally, 16 structural alerts identified by SARpy software further revealed potential molecular signatures associated with toxicity, enriching our understanding of the underlying mechanisms. We also applied the constructed models to assess the NCDIA toxicity of novel drugs approved by FDA. This study advances predictive toxicology by providing a framework to assess and mitigate agranulocytosis risks, ensuring the safety of pharmaceutical development and facilitating post-market surveillance of new drugs.

ToxMPNN: A deep learning model for small molecule toxicity prediction

Machine learning (ML) has shown a great promise in predicting toxicity of small molecules. However, the availability of data for such predictions is often limited. Because of the unsatisfactory performance of models trained on a single toxicity endpoint, we collected toxic small molecules with multiple toxicity endpoints from previous study. The dataset comprises 27 toxic endpoints categorized into seven toxicity classes, namely, carcinogenicity and mutagenicity, acute oral toxicity, respiratory toxicity, irritation and corrosion, cardiotoxicity, CYP450, and endocrine disruption. In addition, a binary classification Common-Toxicity task was added based on the aforementioned dataset. To improve the performance of the models, we added marketed drugs as negative samples. This study presents a toxicity predictive model, ToxMPNN, based on the message passing neural network (MPNN) architecture, aiming to predict the toxicity of small molecules. The results demonstrate that ToxMPNN outperforms other models in capturing toxic features within the molecular structure, resulting in more precise predictions with the ROC_AUC testing score of 0.886 for the Toxicity_drug dataset. Furthermore, it was observed that adding marketed drugs as negative samples not only improves the predictive performance of the binary classification Common-Toxicity task but also enhances the stability of the model prediction. It shows that the graph-based deep learning (DL) algorithms in this study can be used as a trustworthy and effective tool to assess small molecule toxicity in the development of new drugs.

Integration of machine learning models with microsatellite markers: New avenue in world grapevine germplasm characterization

Development of efficient analytical techniques is required for effective interpretation of biological data to take novel hypotheses and finding the critical predictive patterns. Machine Learning algorithms provide a novel opportunity for development of low-cost and practical solutions in biology. In this study, we proposed a new integrated analytical approach using supervised machine learning algorithms and microsatellites data of worldwide vitis populations. A total of 1378 wild (V. vinifera spp. sylvestris) and cultivated (V. vinifera spp. sativa) accessions of grapevine were investigated using 20 microsatellite markers. Data cleaning, feature selection, and supervised machine learning classification models vis, Naive Bayes, Support Vector Machine (SVM) and Tree Induction methods were implied to find most indicative and diagnostic alleles to represent wild/cultivated and originated geography of each population. Our combined approaches showed microsatellite markers with the highest differentiating capacity and proved efficiency for our pipeline of classification and prediction of vitis accessions. Moreover, our study proposed the best combination of markers for better distinguishing of populations, which can be exploited in future germplasm conservation and breeding programs.

Virtual Screening of Molecules via Neural Fingerprint-based Deep Learning Technique

A machine learning-based drug screening technique has been developed and optimized using convolutional neural network-derived fingerprints. The optimization of weights in the neural network-based fingerprinting technique was compared with fixed Morgan fingerprints in regard to binary classification on drug-target binding affinity. The assessment was carried out using six different target proteins using randomly chosen small molecules from the ZINC15 database for training. This new architecture proved to be more efficient in screening molecules that less favorably bind to specific targets and retaining molecules that favorably bind to it.

Scientific contribution

We have developed a new neural fingerprint-based screening model that has a significant ability to capture hits. Despite using a smaller dataset, this model is capable of mapping chemical space similar to other contemporary algorithms designed for molecular screening. The novelty of the present algorithm lies in the speed with which the models are trained and tuned before testing its predictive capabilities and hence is a significant step forward in the field of machine learning-embedded computational drug discovery.

Piquing artificial intelligence towards drug discovery: Tools, techniques, and applications

The purpose of this study was to discuss how artificial intelligence (AI) methods have affected the field of drug development. It looks at how AI models and data resources are reshaping the drug development process by offering more affordable and expedient options to conventional approaches. The paper opens with an overview of well-known information sources for drug development. The discussion then moves on to molecular representation techniques that make it possible to convert data into representations that computers can understand. The paper also gives a general overview of the algorithms used in the creation of drug discovery models based on AI. In particular, the paper looks at how AI algorithms might be used to forecast drug toxicity, drug bioactivity, and drug physicochemical properties. De novo drug design, binding affinity prediction, and other AI-based models for drug-target interaction were covered in deeper detail. Modern applications of AI in nanomedicine design and pharmacological synergism/antagonism prediction were also covered. The potential advantages of AI in drug development are highlighted as the evaluation comes to a close. It underlines how AI may greatly speed up and improve the efficiency of drug discovery, resulting in the creation of new and better medicines. To fully realize the promise of AI in drug discovery, the review acknowledges the difficulties that come with its uses in this field and advocates for more study and development.

A comprehensive overview of advanced dynamic in vitro intestinal and hepatic cell culture models

Orally administered drugs pass through the gastrointestinal tract before being absorbed in the small intestine and metabolised in the liver. To test the efficacy and toxicity of drugs, animal models are often employed; however, they are not suitable for investigating drug-tissue interactions and making reliable predictions, since the human organism differs drastically from animals in terms of absorption, distribution, metabolism and excretion of substances. Likewise, simple static in vitro cell culture systems currently used in preclinical drug screening often do not resemble the native characteristics of biological barriers. Dynamic models, on the other hand, provide in vivo-like cell phenotypes and functionalities that offer great potential for safety and efficacy prediction. Herein, current microfluidic in vitro intestinal and hepatic models are reviewed, namely single- and multi-tissue micro-bioreactors, which are associated with different methods of cell cultivation, i.e., scaffold-based versus scaffold-free.

Bioactive Molecules from the Innate Immunity of Ascidians and Innovative Methods of Drug Discovery: A Computational Approach Based on Artificial Intelligence

The study of bioactive molecules of marine origin has created an important bridge between biological knowledge and its applications in biotechnology and biomedicine. Current studies in different research fields, such as biomedicine, aim to discover marine molecules characterized by biological activities that can be used to produce potential drugs for human use. In recent decades, increasing attention has been paid to a particular group of marine invertebrates, the Ascidians, as they are a source of bioactive products. We describe omics data and computational methods relevant to identifying the mechanisms and processes of innate immunity underlying the biosynthesis of bioactive molecules, focusing on innovative computational approaches based on Artificial Intelligence. Since there is increasing attention on finding new solutions for a sustainable supply of bioactive compounds, we propose that a possible improvement in the biodiscovery pipeline might also come from the study and utilization of marine invertebrates' innate immunity.

In silico QSAR modeling to predict the safe use of antibiotics during pregnancy

The use of medicines during pregnancy is a growing public health concern due to the risk of developmental toxicity. Healthcare providers heavily rely on the FDA pregnancy risk categories (A, B, C, D, and X). Antibiotics are among the most prescribed drugs during pregnancy and are often listed under category B or C. However, the risk-benefit assessment may be lacking due to challenges in the clinical toxicology studies on pregnant women, such as ethical concerns. The primary focus of this study is to generate a model that predicts the safe use of antibiotics during pregnancy by using in silico approaches. Thus, a QSAR model was created to assess the FDA pregnancy category (B or C) of antibiotics. The dataset consisted of 97 antibiotics obtained from the FDA. A total of 6420 molecular descriptors were determined via multiple software and various machine learning algorithms were utilized. The performance of the models was measured using internal and external validation. The accuracy (ACC) values of the most successful model were 83.82% for the internal and 94.11% for the external validation. Sensitivity (SE), specificity (SP), MCC, and ROC values were 0.878, 0.778, 0.68, and 0.892 for the internal validation and 0.9, 1, 0.887, and 0.936 for the external validation, respectively. Kappa statistics also indicate that there was a substantial agreement for internal validation with 0.6765 and an almost perfect agreement for external validation with 0.8811. In conclusion, our model can be used as an initial step before pre-clinical and clinical studies to predict the safe use of antibiotics in pregnancy.

Staying Ahead of the Game: How SARS-CoV-2 has Accelerated the Application of Machine Learning in Pandemic Management

In recent years, machine learning (ML) techniques have garnered considerable interest for their potential use in accelerating the rate of drug discovery. With the emergence of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic, the utilization of ML has become even more crucial in the search for effective antiviral medications. The pandemic has presented the scientific community with a unique challenge, and the rapid identification of potential treatments has become an urgent priority. Researchers have been able to accelerate the process of identifying drug candidates, repurposing existing drugs, and designing new compounds with desirable properties using machine learning in drug discovery. To train predictive models, ML techniques in drug discovery rely on the analysis of large datasets, including both experimental and clinical data. These models can be used to predict the biological activities, potential side effects, and interactions with specific target proteins of drug candidates. This strategy has proven to be an effective method for identifying potential coronavirus disease 2019 (COVID-19) and other disease treatments. This paper offers a thorough analysis of the various ML techniques implemented to combat COVID-19, including supervised and unsupervised learning, deep learning, and natural language processing. The paper discusses the impact of these techniques on pandemic drug development, including the identification of potential treatments, the understanding of the disease mechanism, and the creation of effective and safe therapeutics. The lessons learned can be applied to future outbreaks and drug discovery initiatives.

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.

Advancement of Computational Design Drug Delivery System in COVID-19: Current Updates and Future Crosstalk- A Critical update

Positive strides have been achieved in developing vaccines to combat the coronavirus-2019 infection (COVID-19) pandemic. Still, the outline of variations, particularly the most current delta divergent, has posed significant health encounters for people. Therefore, developing strong treatment strategies, such as an anti-COVID-19 medicine plan, may help deal with the pandemic more effectively. During the COVID-19 pandemic, some drug design techniques were effectively used to develop and substantiate relevant critical medications. Extensive research, both experimental and computational, has been dedicated to comprehending and characterizing the devastating COVID-19 disease. The urgency of the situation has led to the publication of over 130,000 COVID-19-related research papers in peer-reviewed journals and preprint servers. A significant focus of these efforts has been the identification of novel drug candidates and the repurposing of existing drugs to combat the virus. Many projects have utilized computational or computer-aided approaches to facilitate their studies. In this overview, we will explore the key computational methods and their applications in the discovery of small-molecule therapeutics for COVID-19, as reported in the research literature. We believe that the true effectiveness of computational tools lies in their ability to provide actionable and experimentally testable hypotheses, which in turn facilitate the discovery of new drugs and combinations thereof. Additionally, we recognize that open science and the rapid sharing of research findings are vital in expediting the development of much-needed therapeutics for COVID-19.

In Vitro and In Silico Analysis of the Anticancer Effects of Eurycomanone and Eurycomalactone from Eurycoma longifolia

Eurycomanone and eurycomalactone are known quassinoids present in the roots and stems of Eurycoma longifolia. These compounds had been reported to have cytotoxic effects, however, their mechanism of action in a few cancer cell lines have yet to be elucidated. This study was aimed at investigating the anticancer effects and mechanisms of action of eurycomanone and eurycomalactone in cervical (HeLa), colorectal (HT29) and ovarian (A2780) cancer cell lines via Sulforhodamine B assay. Their mechanism of cell death was evaluated based on Hoechst 33342 assay and in silico molecular docking toward DHFR and TNF-α as putative protein targets. Eurycomanone and eurycomalactone exhibited in vitro anticancer effects manifesting IC50 values of 4.58 ± 0.090 µM and 1.60 ± 0.12 µM (HeLa), 1.22 ± 0.11 µM and 2.21 ± 0.049 µM (HT-29), and 1.37 ± 0.13 µM and 2.46 ± 0.081 µM (A2780), respectively. They induced apoptotic cancer cell death in dose- and time-dependent manners. Both eurycomanone and eurycomalactone were also predicted to have good inhibitory potential as demonstrated by the docking into TNF-α with binding affinity of -8.83 and -7.51 kcal/mol, respectively, as well as into DHFR with binding affinity results of -8.05 and -8.87 kcal/mol, respectively. These results support the evidence of eurycomanone and eurycomalactone as anticancer agents via apoptotic cell death mechanism that could be associated with TNF-α and DHFR inhibition as among possible protein targets.

Identification of medicinal plant-based phytochemicals as a potential inhibitor for SARS-CoV-2 main protease (Mpro) using molecular docking and deep learning methods

Highly transmissive and rapidly evolving Coronavirus disease-2019 (COVID-19), a viral disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), triggered a global pandemic, which is one of the most researched viruses in the academia. Effective drugs to treat people with COVID-19 have yet to be developed to reduce mortality and transmission. Studies on the SARS-CoV-2 virus identified that its main protease (Mpro) might be a potential therapeutic target for drug development, as this enzyme plays a key role in viral replication. In search of potential inhibitors of Mpro, we developed a phytochemical library consisting of 2431 phytochemicals from 104 Korean medicinal plants that exhibited medicinal and antioxidant properties. The library was screened by molecular docking, followed by revalidation by re-screening with a deep learning method. Recurrent Neural Networks (RNN) computing system was used to develop an inhibitory predictive model using SARS coronavirus Mpro dataset. It was deployed to screen the top 12 compounds based on their docked binding affinity that ranged from -8.0 to -8.9 kcal/mol. The top two lead compounds, Catechin gallate and Quercetin 3-O-malonylglucoside, were selected depending on inhibitory potency against Mpro. Interactions with the target protein active sites, including His41, Met49, Cys145, Met165, and Thr190 were also examined. Molecular dynamics simulation was performed to analyze root mean square deviation (RMSD), root mean square fluctuation (RMSF), radius of gyration (RG), solvent accessible surface area (SASA), and number of hydrogen bonds. Results confirmed the inflexible nature of the docked complexes. Absorption, distribution, metabolism, excretion, and toxicity (ADMET), as well as bioactivity prediction confirmed the pharmaceutical activities of the lead compound. Findings of this research might help scientists to optimize compatible drugs for the treatment of COVID-19 patients.

Artificial intelligence for drug discovery: Resources, methods, and applications

Conventional wet laboratory testing, validations, and synthetic procedures are costly and time-consuming for drug discovery. Advancements in artificial intelligence (AI) techniques have revolutionized their applications to drug discovery. Combined with accessible data resources, AI techniques are changing the landscape of drug discovery. In the past decades, a series of AI-based models have been developed for various steps of drug discovery. These models have been used as complements of conventional experiments and have accelerated the drug discovery process. In this review, we first introduced the widely used data resources in drug discovery, such as ChEMBL and DrugBank, followed by the molecular representation schemes that convert data into computer-readable formats. Meanwhile, we summarized the algorithms used to develop AI-based models for drug discovery. Subsequently, we discussed the applications of AI techniques in pharmaceutical analysis including predicting drug toxicity, drug bioactivity, and drug physicochemical property. Furthermore, we introduced the AI-based models for de novo drug design, drug-target structure prediction, drug-target interaction, and binding affinity prediction. Moreover, we also highlighted the advanced applications of AI in drug synergism/antagonism prediction and nanomedicine design. Finally, we discussed the challenges and future perspectives on the applications of AI to drug discovery.

Machine-learning analysis of opioid use disorder informed by MOR, DOR, KOR, NOR and ZOR-based interactome networks

Opioid use disorder (OUD) continuously poses major public health challenges and social implications worldwide with dramatic rise of opioid dependence leading to potential abuse. Despite that a few pharmacological agents have been approved for OUD treatment, the efficacy of said agents for OUD requires further improvement in order to provide safer and more effective pharmacological and psychosocial treatments. Proteins including mu, delta, kappa, nociceptin, and zeta opioid receptors are the direct targets of opioids and play critical roles in therapeutic treatments. The protein-protein interaction (PPI) networks of the these receptors increase the complexity in the drug development process for an effective opioid addiction treatment. The report below presents a PPI-network informed machine-learning study of OUD. We have examined more than 500 proteins in the five opioid receptor networks and subsequently collected 74 inhibitor datasets. Machine learning models were constructed by pairing gradient boosting decision tree (GBDT) algorithm with two advanced natural language processing (NLP)-based autoencoder and Transformer fingerprints for molecules. With these models, we systematically carried out evaluations of screening and repurposing potential of more than 120,000 drug candidates for four opioid receptors. In addition, absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties were also considered in the screening of potential drug candidates. Our machine-learning tools determined a few inhibitor compounds with desired potency and ADMET properties for nociceptin opioid receptors. Our approach offers a valuable and promising tool for the pharmacological development of OUD treatments.

Exploration of anticancer potential of Lantadenes from weed Lantana camara: Synthesis, in silico, in vitro and in vivo studies

Naturally occurring pentacyclic triterpenoids and their semisynthetic analogues have engrossed increasing attention for their anticancer potential and exhibiting promising role in discovery of new anticancer agents. Present study include the semi synthetic modifications of Lantadenes from the weed Lantana carama and their structures delineation by FT-IR, ¹H-NMR, ¹³C-NMR & mass spectroscopy. All the compounds were scrutinized for in vitro cytotoxicity, ligand receptor interaction and in vivo anticancer studies. Most of the novel analogues displayed potent antiproliferative activity against A375 & A431 cancer cell lines and found superior to parent Lantadenes. In particular, 3β-(4-Methoxybenzoyloxy)-22β-senecioyloxy-olean-12-en-28-oic acid was found to be most suitable compound, with IC₅₀ value of 3.027 μM aganist A375 cell line having least docking score (-69.40 kcal/mol). Promising anticancer potential of the lead was further indicated by significant reduction in tumor volume and burden in two stage carcinoma model. These findings suggests that the Lantadene derivatives may hold promising potential for the intervention of skin cancers.

Pharmacophore-based virtual screening and in-silico study of natural products as potential DENV-2 RdRp inhibitors

Dengue fever is a significant public health concern throughout the world, causing an estimated 500,000 hospitalizations and 20,000 deaths each year, despite the lack of effective therapies. The DENV-2 RdRp has been identified as a potential target for the development of new and effective dengue therapies. This research's primary objective was to discover an anti-DENV inhibitor using in silico ligand- and structure-based approaches. To begin, a ligand-based pharmacophore model was developed, and 130 distinct natural products (NPs) were screened. Docking of the pharmacophore-matched compounds were performed to the active site of DENV-2 RdRp protease . Eleven compounds were identified as potential DENV-2 RdRp inhibitors based on docking energy and binding interactions. ADMET and drug-likeness were done to predict their pharmacologic, pharmacokinetic, and drug-likeproperties . Compounds ranked highest in terms of pharmacokinetics and drug-like appearances were then subjected to additional toxicity testing to determine the leading compound. Additionally, MD simulation of the lead compound was performed to confirm the docked complex's stability and the binding site determined by docking. As a result, the lead compound (compound-108) demonstrated an excellent match to the pharmacophore, a strong binding contact and affinity for the RdRp enzyme, favourable pharmacokinetics, and drug-like characteristics. In summary, the lead compound identified in this study could be a possible DENV-2 RdRp inhibitor that may be further studied on in vitro and in vivo models to develop as a drug candidate.Communicated by Ramaswamy H. Sarma.

TOXRIC: a comprehensive database of toxicological data and benchmarks

The toxic effects of compounds on environment, humans, and other organisms have been a major focus of many research areas, including drug discovery and ecological research. Identifying the potential toxicity in the early stage of compound/drug discovery is critical. The rapid development of computational methods for evaluating various toxicity categories has increased the need for comprehensive and system-level collection of toxicological data, associated attributes, and benchmarks. To contribute toward this goal, we proposed TOXRIC (https://toxric.bioinforai.tech/), a database with comprehensive toxicological data, standardized attribute data, practical benchmarks, informative visualization of molecular representations, and an intuitive function interface. The data stored in TOXRIC contains 113 372 compounds, 13 toxicity categories, 1474 toxicity endpoints covering in vivo/in vitro endpoints and 39 feature types, covering structural, target, transcriptome, metabolic data, and other descriptors. All the curated datasets of endpoints and features can be retrieved, downloaded and directly used as output or input to Machine Learning (ML)-based prediction models. In addition to serving as a data repository, TOXRIC also provides visualization of benchmarks and molecular representations for all endpoint datasets. Based on these results, researchers can better understand and select optimal feature types, molecular representations, and baseline algorithms for each endpoint prediction task. We believe that the rich information on compound toxicology, ML-ready datasets, benchmarks and molecular representation distribution can greatly facilitate toxicological investigations, interpretation of toxicological mechanisms, compound/drug discovery and the development of computational methods.

Toxicity of transition metal nanoparticles: A review of different experimental models in the gastrointestinal tract

The development of nanotechnology is becoming a major trend nowadays. Nanoparticles (NPs) have been widely used in fields including food, biomedicine, and cosmetics, endowing NPs more opportunities to enter the human body. It is well-known that the gut microbiome plays a key role in human health, and the exposure of intestines to NPs is unavoidable. Accordingly, the toxicity of NPs has attracted more attention than before. This review mainly highlights recent advances in the evaluation of NPs' toxicity in the gastrointestinal system from the existing cell-based experimental models, such as the original mono-culture models, co-culture models, three-dimensional (3D) culture models, and the models established on microfluidic chips, to those in vivo experiments, such as mice models, Caenorhabditis elegans models, zebrafish models, human volunteers, as well as computer-simulated toxicity models. Owing to these models, especially those more biomimetic models, the outcome of the toxicity of NPs acting in the gastrointestinal tract can get results closer to what happened inside the real human microenvironment.

tLyp-1: A peptide suitable to target NRP-1 receptor

Targeting vascular endothelial growth factor receptor (VEFGR) and its co-receptor neuropilin-1 (NRP-1) is an interesting vascular strategy. tLyp-1 is a tumor-homing and penetrating peptide of 7 amino acids (CGNKRTR). It is a truncated form of Lyp-1 (CGNKRTRGC), which is known to target NRP-1 receptor, with high affinity and specificity. It is mediated by endocytosis via C-end rule (CendR) internalization pathway. The aim of this study is to evaluate the importance of each amino acid in the tLyp-1 sequence through alanine-scanning (Ala-scan) technique, during which each of the amino acid in the sequence was systematically replaced by alanine to produce 7 different analogues. In silico approach through molecular docking and molecular dynamics are employed to understand the interaction between the peptide and its analogues with the NRP-1 receptor, followed by in vitro ligand binding assay study. The C-terminal Arg is crucial in the interaction of tLyp-1 with NRP-1 receptor. Substituting this residue dramatically reduces the affinity of this peptide which is clearly seen in this study. Lys-4 is also important in the interaction, which is confirmed via the in vitro study and the MM-PBSA analysis. The finding in this study supports the CendR, in which the presence of R/K-XX-R/K motif is essential in the binding of a ligand with NRP-1 receptor. This presented work will serve as a guide in the future work pertaining the development of active targeting agent towards NRP-1 receptor.

Development of homology model, docking protocol and Machine-Learning based scoring functions for identification of Equus caballus's butyrylcholinesterase inhibitors

Machine learning (ML), an emerging field in drug design, has the potential to predict in silico toxicity, shape-based analysis of inhibitors, scoring function (SF) etc. In the present study, a homology model, docking protocol, and a dedicated SF have been developed to identify the inhibitors of horse butyrylcholinesterase (BChE) enzyme. Horse BChE enzyme has homology with human BChE and is a substitute for the screening of in vitro inhibitors. The developed homology model was validated and the active site residues were identified from Cavityplus to generate grid box for docking. The validation of docking involved comparison of interactions of ligands co-crystallised with human BChE and the docked poses of the corresponding ligands with horse BChE. A high degree of similarity in the interaction profiles of generated poses validated the docking protocol. Scoring of ligands was further validated by docking with known BChE inhibitors. The binding energies obtained from SF was correlated with IC₅₀ values of inhibitors through classification and regression-based methods, which indicated poor predictivity of native SF. Therefore, protein-ligand binding energy, interaction profile, and ligand descriptors were used to develop and validate the classification and regression-based models. The validated extra tree binary classifier, random forest and extra tree regression-based models were compiled as a protein-ligand SF and were made available to the users through web application and python library. ML models exhibited improved area under the curve for ROC and good correlation between the predicted and observed IC₅₀ values, than the Autodock SF. Communicated by Ramaswamy H. Sarma.

Chemical composition/pharmacophore modelling- based, virtual screening, molecular docking and dynamic simulation studies for the discovery of novel superoxide dismutase (SODs) of bioactive molecules from aerial parts of Inula Montana as antioxydant's agents

The accumulation of free radicals in the body develops chronic and degenerative diseases such as cancer, autoimmune diseases, rheumatoid arthritis, cardiovascular and neurodegenerative diseases. The first aim of this work was to study the chemical composition of Inula Montana essential oil using GC-FID and GC/MS analysis and the antioxidant activities using radical scavenging (DPPH) and the Ferric -Reducing Antioxidant Power (FRAP) tests. The second aim was to describe the assess the antioxidant activity and computational study of Superoxide Dismutase (SODs) and ctDNA inhibition. Sixty-nine compounds were identified in the essential oil of the aerial part of Inula montana. Shyobunol and α-Cadinol were the major compounds in the essential oil. The antioxidant power of the essential oil showed an important antioxidant effect compared to ascorbic acid and the methionine co-crystallized inhibitor. The results of the docking simulation revealed that E, E-Farnesyl acetate has an affinity to interact with binding models and the antioxidant activities of the ctDNA sequence and Superoxide Dismutase target. The penetration through the Blood-Brain Barrier came out to be best for E, E-Farnesyl acetate and E-Nerolidolacetate and was significantly higher than the control molecule and Lref. Finally, the application of ADMET filters gives us positive information on the compound E, E-Farnesyl acetate, which appears as a new inhibitor potentially more active towards ctDNA and SODs target. The active compounds, E,E-Farnesyl acetate can be used as templates for further development of more potent antioxidative agents.Communicated by Ramaswamy H. Sarma.

Machine Learning Toxicity Prediction: Latest Advances by Toxicity End Point

Machine learning (ML) models to predict the toxicity of small molecules have garnered great attention and have become widely used in recent years. Computational toxicity prediction is particularly advantageous in the early stages of drug discovery in order to filter out molecules with high probability of failing in clinical trials. This has been helped by the increase in the number of large toxicology databases available. However, being an area of recent application, a greater understanding of the scope and applicability of ML methods is still necessary. There are various kinds of toxic end points that have been predicted in silico. Acute oral toxicity, hepatotoxicity, cardiotoxicity, mutagenicity, and the 12 Tox21 data end points are among the most commonly investigated. Machine learning methods exhibit different performances on different data sets due to dissimilar complexity, class distributions, or chemical space covered, which makes it hard to compare the performance of algorithms over different toxic end points. The general pipeline to predict toxicity using ML has already been analyzed in various reviews. In this contribution, we focus on the recent progress in the area and the outstanding challenges, making a detailed description of the state-of-the-art models implemented for each toxic end point. The type of molecular representation, the algorithm, and the evaluation metric used in each research work are explained and analyzed. A detailed description of end points that are usually predicted, their clinical relevance, the available databases, and the challenges they bring to the field are also highlighted.

Inhibition of multiple SARS-CoV-2 proteins by an antiviral biomolecule, seselin from Aegle marmelos deciphered using molecular docking analysis

Our earlier experimental and computational report produced evidence on the antiviral nature of the compound seselin purified from the leaf extracts of Aegle marmelos against Bombyx mori Nuclear Polyhedrosis Virus (BmNPV). In the pandemic situation of COVID-19 caused by the SARS-COV-2 virus, an in silico effort to evaluate the potentiality of the seselin was made to test its efficacy against multiple targets of SARS-COV-2 such as spike protein S2, COVID-19 main protease and free enzyme of the SARS-CoV-2 (2019-nCoV) main protease. The ligand seselin showed the best interaction with receptors, spike protein S2, COVID-19 main protease and free enzyme of the SARS-CoV-2 (2019-nCoV) main protease with a binding energy of -6.3 kcal/mol, -6.9 kcal/mol and -6.7 kcal/mol, respectively. Docking analysis with three different receptors identified that all the computationally predicted lowest energy complexes were stabilized by intermolecular hydrogen bonds and stacking interactions. The amino acid residues involved in interactions were ASP1184, GLU1182, ARG1185 and SER943 for spike protein, SER1003, ALA958 and THR961 for COVID-19 main protease, and for SARS-CoV-2 (2019-nCoV) main protease, it was THR111, GLN110 and THR292. The MD simulation and MM/PBSA analysis showed that the compound seselin could effectively bind with the target receptors. The outcome of pharmacokinetic analysis suggested that the compound had favourable drugability properties. The results suggested that the seselin had inhibitory potential over multiple SARS-COV-2 targets and hold a high potential to work effectively as a novel drug for COVID-19 if evaluated in experimental setups in the foreseeable future. Communicated by Ramaswamy H. Sarma.

Modeling and insights into the structural characteristics of drug-induced autoimmune diseases

The incidence and complexity of drug-induced autoimmune diseases (DIAD) have been on the rise in recent years, which may lead to serious or fatal consequences. Besides, many environmental and industrial chemicals can also cause DIAD. However, there are few effective approaches to estimate the DIAD potential of drugs and other chemicals currently, and the structural characteristics and mechanism of action of DIAD compounds have not been clarified. In this study, we developed the in silico models for chemical DIAD prediction and investigated the structural characteristics of DIAD chemicals based on the reliable drug data on human autoimmune diseases. We collected 148 medications which were reported can cause DIAD clinically and 450 medications that clearly do not cause DIAD. Several different machine learning algorithms and molecular fingerprints were combined to develop the in silico models. The best performed model provided the good overall accuracy on validation set with 76.26%. The model was made freely available on the website http://diad.sapredictor.cn/. To further investigate the differences in structural characteristics between DIAD chemicals and non-DIAD chemicals, several key physicochemical properties were analyzed. The results showed that AlogP, molecular polar surface area (MPSA), and the number of hydrogen bond donors (nHDon) were significantly different between the DIAD and non-DIAD structures. They may be related to the DIAD toxicity of chemicals. In addition, 14 structural alerts (SA) for DIAD toxicity were detected from predefined substructures. The SAs may be helpful to explain the mechanism of action of drug induced autoimmune disease, and can used to identify the chemicals with potential DIAD toxicity. The structural alerts have been integrated in a structural alert-based web server SApredictor (http://www.sapredictor.cn). We hope the results could provide useful information for the recognition of DIAD chemicals and the insights of structural characteristics for chemical DIAD toxicity.

Molecular Docking, Validation, Dynamics Simulations, and Pharmacokinetic Prediction of Phytochemicals Isolated From Croton dichogamus Against the HIV-1 Reverse Transcriptase

The human immunodeficiency virus (HIV) infection and the associated acquired immune deficiency syndrome (AIDS) remain global challenges even after decades of successful treatment, with eastern and southern Africa still bearing the highest burden of disease. Following a thorough computational study, we report top 10 phytochemicals isolated from Croton dichogamus as potent reverse transcriptase inhibitors. The pentacyclic triterpenoid, aleuritolic acid (L12) has displayed best docking pose with binding energy of -8.48 kcal/mol and Ki of 0.61 μM making it superior in binding efficiency when compared to all docked compounds including the FDA-approved drugs. Other phytochemicals such as crotoxide A, crothalimene A, crotodichogamoin B and crotonolide E have also displayed strong binding energies. These compounds could further be investigated as potential antiretroviral medication.

Designing drugs when there is low data availability: one-shot learning and other approaches to face the issues of a long-term concern

INTRODUCTION

Modern drug discovery generally is accessed by useful information from previous large databases or uncovering novel data. The lack of biological and/or chemical data tends to slow the development of scientific research and innovation. Here, approaches that may help provide solutions to generate or obtain enough relevant data or improve/accelerate existing methods within the last five years were reviewed.

AREAS COVERED

One-shot learning (OSL) approaches, structural modeling, molecular docking, scoring function space (SFS), molecular dynamics (MD), and quantum mechanics (QM) may be used to amplify the amount of available data to drug design and discovery campaigns, presenting methods, their perspectives, and discussions to be employed in the near future.

EXPERT OPINION

Recent works have successfully used these techniques to solve a range of issues in the face of data scarcity, including complex problems such as the challenging scenario of drug design aimed at intrinsically disordered proteins and the evaluation of potential adverse effects in a clinical scenario. These examples show that it is possible to improve and kickstart research from scarce available data to design and discover new potential drugs.

Using Jupyter Notebooks for re-training machine learning models

Machine learning (ML) models require an extensive, user-driven selection of molecular descriptors in order to learn from chemical structures to predict actives and inactives with a high reliability. In addition, privacy concerns often restrict the access to sufficient data, leading to models with a narrow chemical space. Therefore, we propose a framework of re-trainable models that can be transferred from one local instance to another, and further allow a less extensive descriptor selection. The models are shared via a Jupyter Notebook, allowing the evaluation and implementation of a broader chemical space by keeping most of the tunable parameters pre-defined. This enables the models to be updated in a decentralized, facile, and fast manner. Herein, the method was evaluated with six transporter datasets (BCRP, BSEP, OATP1B1, OATP1B3, MRP3, P-gp), which revealed the general applicability of this approach.

SApredictor: An Expert System for Screening Chemicals Against Structural Alerts

The rapid and accurate evaluation of chemical toxicity is of great significance for estimation of chemical safety. In the past decades, a great number of excellent computational models have been developed for chemical toxicity prediction. But most machine learning models tend to be “black box”, which bring about poor interpretability. In the present study, we focused on the identification and collection of structural alerts (SAs) responsible for a series of important toxicity endpoints. Then, we carried out effective storage of these structural alerts and developed a web-server named SApredictor (www.sapredictor.cn) for screening chemicals against structural alerts. People can quickly estimate the toxicity of chemicals with SApredictor, and the specific key substructures which cause the chemical toxicity will be intuitively displayed to provide valuable information for the structural optimization by medicinal chemists.

Comparison of Descriptor- and Fingerprint Sets in Machine Learning Models for ADME-Tox Targets

The screening of compounds for ADME-Tox targets plays an important role in drug design. QSPR models can increase the speed of these specific tasks, although the performance of the models highly depends on several factors, such as the applied molecular descriptors. In this study, a detailed comparison of the most popular descriptor groups has been carried out for six main ADME-Tox classification targets: Ames mutagenicity, P-glycoprotein inhibition, hERG inhibition, hepatotoxicity, blood–brain-barrier permeability, and cytochrome P450 2C9 inhibition. The literature-based, medium-sized binary classification datasets (all above 1,000 molecules) were used for the model building by two common algorithms, XGBoost and the RPropMLP neural network. Five molecular representation sets were compared along with their joint applications: Morgan, Atompairs, and MACCS fingerprints, and the traditional 1D and 2D molecular descriptors, as well as 3D molecular descriptors, separately. The statistical evaluation of the model performances was based on 18 different performance parameters. Although all the developed models were close to the usual performance of QSPR models for each specific ADME-Tox target, the results clearly showed the superiority of the traditional 1D, 2D, and 3D descriptors in the case of the XGBoost algorithm. It is worth trying the classical tools in single model building because the use of 2D descriptors can produce even better models for almost every dataset than the combination of all the examined descriptor sets.

In Silico Prediction of Chemical Aquatic Toxicity by Multiple Machine Learning and Deep Learning Approaches

Fish is one of the model animals used to evaluate the adverse effects of a chemical exposed to the ecosystem. However, its low throughput and relevantly high expense make it impossible to test all new chemicals in manufacture. Hence using in silico models to prioritize compounds to be tested has been widely applied in environmental risk assessment and drug discovery. In this study, we constructed the local predictive models for four fish species, including bluegill sunfish, rainbow trout, fathead minnow, and sheepshead minnow, and the global models with all four fish data. A total of 1874 unique compounds with their labels, i.e. toxic (LC₅₀ < 10 ppm) or nontoxic were collected from ECOTOX and literature. Both conventional machine learning methods and the deep learning architecture, graph convolutional network (GCN), were used to build predictive models. The classification accuracy of the best local model for each fish species was higher than 0.83. For the global models, two strategies including consistency prediction and probability threshold were adopted to improve the predictive capability at the cost of limiting applicability domain. For 63% of compounds in domain, the accuracy was around 0.97. By comparison of the deep learning and machine learning methods, we found that the single-task GCN showed specific advantages in performance and multi-task GCN showed no advantages over the conventional machine learning methods. The data and models are available on GitHub (https://github.com/ChemPredict/ChemicalAquaticToxicity).

Bioactivity assessment of natural compounds using machine learning models trained on target similarity between drugs

Natural compounds constitute a rich resource of potential small molecule therapeutics. While experimental access to this resource is limited due to its vast diversity and difficulties in systematic purification, computational assessment of structural similarity with known therapeutic molecules offers a scalable approach. Here, we assessed functional similarity between natural compounds and approved drugs by combining multiple chemical similarity metrics and physicochemical properties using a machine-learning approach. We computed pairwise similarities between 1410 drugs for training classification models and used the drugs shared protein targets as class labels. The best performing models were random forest which gave an average area under the ROC of 0.9, Matthews correlation coefficient of 0.35, and F1 score of 0.33, suggesting that it captured the structure-activity relation well. The models were then used to predict protein targets of circa 11k natural compounds by comparing them with the drugs. This revealed therapeutic potential of several natural compounds, including those with support from previously published sources as well as those hitherto unexplored. We experimentally validated one of the predicted pair’s activities, viz., Cox-1 inhibition by 5-methoxysalicylic acid, a molecule commonly found in tea, herbs and spices. In contrast, another natural compound, 4-isopropylbenzoic acid, with the highest similarity score when considering most weighted similarity metric but not picked by our models, did not inhibit Cox-1. Our results demonstrate the utility of a machine-learning approach combining multiple chemical features for uncovering protein binding potential of natural compounds.

Knowledge-based BERT: a method to extract molecular features such as computational chemists

Molecular property prediction models based on machine learning algorithms have become important tools to triage unpromising lead molecules in the early stages of drug discovery. Compared with the mainstream descriptor- and graph-based methods for molecular property predictions, SMILES-based methods can directly extract molecular features from SMILES without human expert knowledge, but they require more powerful algorithms for feature extraction and a larger amount of data for training, which makes SMILES-based methods less popular. Here, we show the great potential of pre-training in promoting the predictions of important pharmaceutical properties. By utilizing three pre-training tasks based on atom feature prediction, molecular feature prediction and contrastive learning, a new pre-training method K-BERT, which can extract chemical information from SMILES like chemists, was developed. The calculation results on 15 pharmaceutical datasets show that K-BERT outperforms well-established descriptor-based (XGBoost) and graph-based (Attentive FP and HRGCN+) models. In addition, we found that the contrastive learning pre-training task enables K-BERT to 'understand' SMILES not limited to canonical SMILES. Moreover, the general fingerprints K-BERT-FP generated by K-BERT exhibit comparative predictive power to MACCS on 15 pharmaceutical datasets and can also capture molecular size and chirality information that traditional binary fingerprints cannot capture. Our results illustrate the great potential of K-BERT in the practical applications of molecular property predictions in drug discovery.

Antibreast cancer activities of phytochemicals from Anonna muricata using computer-aided drug design (CADD) approach

Antibreast cancer activities of 131 phytochemicals from Annona muricata (Soursop) were investigated against human placental aromatase (PDB ID: 3S7S), a prominent target receptor in breast cancer therapy using computer aided-drug design approach. An antibreast cancer drug (tamoxifen) was used for comparison. The result of this work flourishes caffeoquinic acid (−8.4 kcal/mol), roseoside (−8.3 kcal/mol), chlorogenic acid (−8.2 kcal/mol), feruloylglycoside (−8.1 kcal/mol), citroside A (−8.0 kcal/mol), and coreximine (−7.8 kcal/mol), as probable inhibitors of human placental aromatase. This is due to their excellent binding affinities (ΔG), coupled with outstanding druglike, absorption, distribution, metabolism, excretion, and toxicity profiles, bioavailability and oral-bioavailability properties, and the interactions of important residues with the active pocket of human placental aromatase. All the results obtained were similar to that of the standards tamoxifen (−8.0 kcal/mol) but could be better when optimized. Thus, lead optimization, molecular dynamics, and in vivo investigations are thereby recommended on the identified potent compounds in the quest of developing new therapeutic agents against breast cancer.

An Explainable Supervised Machine Learning Model for Predicting Respiratory Toxicity of Chemicals Using Optimal Molecular Descriptors

Respiratory toxicity is a serious public health concern caused by the adverse effects of drugs or chemicals, so the pharmaceutical and chemical industries demand reliable and precise computational tools to assess the respiratory toxicity of compounds. The purpose of this study is to develop quantitative structure-activity relationship models for a large dataset of chemical compounds associated with respiratory system toxicity. First, several feature selection techniques are explored to find the optimal subset of molecular descriptors for efficient modeling. Then, eight different machine learning algorithms are utilized to construct respiratory toxicity prediction models. The support vector machine classifier outperforms all other optimized models in 10-fold cross-validation. Additionally, it outperforms the prior study by 2% in prediction accuracy and 4% in MCC. The best SVM model achieves a prediction accuracy of 86.2% and a MCC of 0.722 on the test set. The proposed SVM model predictions are explained using the SHapley Additive exPlanations approach, which prioritizes the relevance of key modeling descriptors influencing the prediction of respiratory toxicity. Thus, our proposed model would be incredibly beneficial in the early stages of drug development for predicting and understanding potential respiratory toxic compounds.