Consensus versus Individual QSARs in Classification: Comparison on a Large-Scale Case Study

Synthesis of thiazolidine-2,4-dione tethered 1,2,3-triazoles as α-amylase inhibitors: In vitro approach coupled with QSAR, molecular docking, molecular dynamics and ADMET studies

A new series of thiazolidine-2,4-dione tethered 1,2,3-triazole derivatives were designed, synthesized and screened for their α-amylase inhibitory potential employing in vitro and in silico approaches. The target compounds were synthesized with the help of Cu (I) catalyzed [3 + 2] cycloaddition of terminal alkyne with numerous azides, followed by unambiguously characterizing the structure by employing various spectroscopic approaches. The synthesized derivatives were assessed for their in vitro α-amylase inhibition and it was found that thiazolidine-2,4-dione derivatives 6e, 6j, 6o, 6u and 6x exhibited comparable inhibition with the standard drug acarbose. The compound 6e with a 7-chloroquinolinyl substituent on the triazole ring exhibited significant inhibition potential with IC50 value of 0.040 μmol mL-1 whereas compound 6c (IC50 = 0.099 μmol mL-1) and 6h (IC50 = 0.098 μmol mL-1) were poor inhibitors. QSAR studies revealed the positively correlating descriptors that aid in the design of novel compounds. Molecular docking was performed to investigate the binding interactions with the active site of the biological receptor and the stability of the complex over a period of 100 ns was examined using molecular dynamics studies. The physiochemical properties and drug-likeliness behavior of the potent derivatives were investigated by carrying out the ADMET studies.

Multi-level data fusion strategy based on spectral and image information for identifying varieties of soybean seeds

Rapid identification of soybean seed varieties is crucial for agricultural production and seed quality. Identifying varieties of soybean seed using conventional chemical methods is time-consuming, destructive, and inappropriate for seed quality evaluation. This study utilized hyperspectral imaging technology (HSI) to identify four varieties of soybean seeds. The hyperspectral images of soybean seeds were collected in the spectral range of 400-1000 nm. A multi-level data fusion strategy based on spectral and image information was proposed to improve the accuracy of model. Subsequently, the multi-level data fusion strategy based on partial least squares discriminant analysis (PLS-DA) was used to establish the classification models of soybean seeds. Compared with the models using individual analytical sources, the results demonstrated that the models with multi-level data fusion strategy obtained better prediction performance. The high-level data fusion (HLDF) based on Bayesian consensus provided the optimal results with an accuracy (Acc) and F1-score of 93.13 % and 93.70 % in the prediction phase, respectively. Therefore, the multi-level data fusion strategy can be used as an identification method for soybean seed varieties and an effective approach to enhance the discriminatory capability of models.

Boosting the Accuracy and Chemical Space Coverage of the Detection of Small Colloidal Aggregating Molecules Using the BAD Molecule Filter

The ability to conduct effective high throughput screening (HTS) campaigns in drug discovery is often hampered by the detection of false positives in these assays due to small colloidally aggregating molecules (SCAMs). SCAMs can produce artifactual hits in HTS by nonspecific inhibition of the protein target. In this work, we present a new computational prediction tool for detecting SCAMs based on their 2D chemical structure. The tool, called the boosted aggregation detection (BAD) molecule filter, employs decision tree ensemble methods, namely, the CatBoost classifier and the light gradient-boosting machine, to significantly improve the detection of SCAMs. In developing the filter, we explore models trained on individual data sets, a consensus approach using these models, and, third, a merged data set approach, each tailored for specific drug discovery needs. The individual data set method emerged as most effective, achieving 93% sensitivity and 90% specificity, outperforming existing state-of-the-art models by 20 and 5%, respectively. The consensus models offer broader chemical space coverage, exceeding 90% for all testing sets. This feature is an important aspect particularly for early stage medicinal chemistry projects, and provides information on applicability domain. Meanwhile, the merged data set models demonstrated robust performance, with a notable sensitivity of 79% in the comprehensive 10-fold cross-validation test set. A SHAP analysis of model features indicates the importance of hydrophobicity and molecular complexity as primary factors influencing the aggregation propensity. The BAD molecule filter is readily accessible for the public usage on https://molmodlab-aau.com/Tools.html. This filter provides a new, more robust tool for aggregate prediction in the early stages of drug discovery to optimize hit rates and reduce associated testing and validation overheads.

Advances in Activity/Property Prediction from Chemical Structures

Recent technological advancement in AI modeling of molecular property databases has significantly expanded the opportunities for drug design and development. Quantitative structure-activity relationships (QSARs) are shown to provide more accurate predictions with regards to biological activity as well as toxicological assessment. By using a combination of in-silico models or by combining disparate structure-activity databases, researchers have been able to improve accuracy for a variety of drug discovery and analysis methods, generating viable compounds, which in certain cases, can be synthesized and further studied in vitro to find candidates for potential development. Additionally, the development of compounds of determined toxicology can be discontinued earlier, allowing alternative routes to be evaluated, preventing wasted time and resources. Although the progress that has been made is tremendous, expert review is still necessary for most in-silico generated predictions. Regardless, the scientific community continues to move ever closer to completely automated drug discovery and evaluation.

An Ensemble Classifiers for Improved Prediction of Native-Non-Native Protein-Protein Interaction

In this study, we present an innovative approach to improve the prediction of protein-protein interactions (PPIs) through the utilization of an ensemble classifier, specifically focusing on distinguishing between native and non-native interactions. Leveraging the strengths of various base models, including random forest, gradient boosting, extreme gradient boosting, and light gradient boosting, our ensemble classifier integrates these diverse predictions using a logistic regression meta-classifier. Our model was evaluated using a comprehensive dataset generated from molecular dynamics simulations. While the gains in AUC and other metrics might seem modest, they contribute to a model that is more robust, consistent, and adaptable. To assess the effectiveness of various approaches, we compared the performance of logistic regression to four baseline models. Our results indicate that logistic regression consistently underperforms across all evaluated metrics. This suggests that it may not be well-suited to capture the complex relationships within this dataset. Tree-based models, on the other hand, appear to be more effective for problems involving molecular dynamics simulations. Extreme gradient boosting (XGBoost) and light gradient boosting (LightGBM) are optimized for performance and speed, handling datasets effectively and incorporating regularizations to avoid over-fitting. Our findings indicate that the ensemble method enhances the predictive capability of PPIs, offering a promising tool for computational biology and drug discovery by accurately identifying potential interaction sites and facilitating the understanding of complex protein functions within biological systems.

"DompeKeys": a set of novel substructure-based descriptors for efficient chemical space mapping, development and structural interpretation of machine learning models, and indexing of large databases

The conversion of chemical structures into computer-readable descriptors, able to capture key structural aspects, is of pivotal importance in the field of cheminformatics and computer-aided drug design. Molecular fingerprints represent a widely employed class of descriptors; however, their generation process is time-consuming for large databases and is susceptible to bias. Therefore, descriptors able to accurately detect predefined structural fragments and devoid of lengthy generation procedures would be highly desirable. To meet additional needs, such descriptors should also be interpretable by medicinal chemists, and suitable for indexing databases with trillions of compounds. To this end, we developed-as integral part of EXSCALATE, Dompé's end-to-end drug discovery platform-the DompeKeys (DK), a new substructure-based descriptor set, which encodes the chemical features that characterize compounds of pharmaceutical interest. DK represent an exhaustive collection of curated SMARTS strings, defining chemical features at different levels of complexity, from specific functional groups and structural patterns to simpler pharmacophoric points, corresponding to a network of hierarchically interconnected substructures. Because of their extended and hierarchical structure, DK can be used, with good performance, in different kinds of applications. In particular, we demonstrate how they are very well suited for effective mapping of chemical space, as well as substructure search and virtual screening. Notably, the incorporation of DK yields highly performing machine learning models for the prediction of both compounds' activity and metabolic reaction occurrence. The protocol to generate the DK is freely available at https://dompekeys.exscalate.eu and is fully integrated with the Molecular Anatomy protocol for the generation and analysis of hierarchically interconnected molecular scaffolds and frameworks, thus providing a comprehensive and flexible tool for drug design applications.

TISBE: A Public Web Platform for the Consensus-Based Explainable Prediction of Developmental Toxicity

Despite being extremely relevant for the protection of prenatal and neonatal health, the developmental toxicity (Dev Tox) is a highly complex endpoint whose molecular rationale is still largely unknown. The lack of availability of high-quality data as well as robust nontesting methods makes its understanding even more difficult. Thus, the application of new explainable alternative methods is of utmost importance, with Dev Tox being one of the most animal-intensive research themes of regulatory toxicology. Descending from TIRESIA (Toxicology Intelligence and Regulatory Evaluations for Scientific and Industry Applications), the present work describes TISBE (TIRESIA Improved on Structure-Based Explainability), a new public web platform implementing four fundamental advancements for in silico analyses: a three times larger dataset, a transparent XAI (explainable artificial intelligence) framework employing a fragment-based fingerprint coding, a novel consensus classifier based on five independent machine learning models, and a new applicability domain (AD) method based on a double top-down approach for better estimating the prediction reliability. The training set (TS) includes as many as 1008 chemicals annotated with experimental toxicity values. Based on a 5-fold cross-validation, a median value of 0.410 for the Matthews correlation coefficient was calculated; TISBE was very effective, with a median value of sensitivity and specificity equal to 0.984 and 0.274, respectively. TISBE was applied on two external pools made of 1484 bioactive compounds and 85 pediatric drugs taken from ChEMBL (Chemical European Molecular Biology Laboratory) and TEDDY (Task-Force in Europe for Drug Development in the Young) repositories, respectively. Notably, TISBE gives users the option to clearly spot the molecular fragments responsible for the toxicity or the safety of a given chemical query and is available for free at https://prometheus.farmacia.uniba.it/tisbe.

Harmonization Risks and Rewards: Nano-QSAR for Agricultural Nanomaterials

This comprehensive review explores the emerging landscape of Nano-QSAR (quantitative structure-activity relationship) for assessing the risk and potency of nanomaterials in agricultural settings. The paper begins with an introduction to Nano-QSAR, providing background and rationale, and explicitly states the hypotheses guiding the review. The study navigates through various dimensions of nanomaterial applications in agriculture, encompassing their diverse properties, types, and associated challenges. Delving into the principles of QSAR in nanotoxicology, this article elucidates its application in evaluating the safety of nanomaterials, while addressing the unique limitations posed by these materials. The narrative then transitions to the progression of Nano-QSAR in the context of agricultural nanomaterials, exemplified by insightful case studies that highlight both the strengths and the limitations inherent in this methodology. Emerging prospects and hurdles tied to Nano-QSAR in agriculture are rigorously examined, casting light on important pathways forward, existing constraints, and avenues for research enhancement. Culminating in a synthesis of key insights, the review underscores the significance of Nano-QSAR in shaping the future of nanoenabled agriculture. It provides strategic guidance to steer forthcoming research endeavors in this dynamic field.

The pursuit of accurate predictive models of the bioactivity of small molecules

Property prediction is a key interest in chemistry. For several decades there has been a continued and incremental development of mathematical models to predict properties. As more data is generated and accumulated, there seems to be more areas of opportunity to develop models with increased accuracy. The same is true if one considers the large developments in machine and deep learning models. However, along with the same areas of opportunity and development, issues and challenges remain and, with more data, new challenges emerge such as the quality and quantity and reliability of the data, and model reproducibility. Herein, we discuss the status of the accuracy of predictive models and present the authors' perspective of the direction of the field, emphasizing on good practices. We focus on predictive models of bioactive properties of small molecules relevant for drug discovery, agrochemical, food chemistry, natural product research, and related fields.

Development and application of consensus in silico models for advancing high-throughput toxicological predictions

Computational toxicology models have been successfully implemented to prioritize and screen chemicals. There are numerous in silico (quantitative) structure-activity relationship ([Q]SAR) models for the prediction of a range of human-relevant toxicological endpoints, but for a given endpoint and chemical, not all predictions are identical due to differences in their training sets, algorithms, and methodology. This poses an issue for high-throughput screening of a large chemical inventory as it necessitates several models to cover diverse chemistries but will then generate data conflicts. To address this challenge, we developed a consensus modeling strategy to combine predictions obtained from different existing in silico (Q)SAR models into a single predictive value while also expanding chemical space coverage. This study developed consensus models for nine toxicological endpoints relating to estrogen receptor (ER) and androgen receptor (AR) interactions (i.e., binding, agonism, and antagonism) and genotoxicity (i.e., bacterial mutation, in vitro chromosomal aberration, and in vivo micronucleus). Consensus models were created by combining different (Q)SAR models using various weighting schemes. As a multi-objective optimization problem, there is no single best consensus model, and therefore, Pareto fronts were determined for each endpoint to identify the consensus models that optimize the multiple-criterion decisions simultaneously. Accordingly, this work presents sets of solutions for each endpoint that contain the optimal combination, regardless of the trade-off, with the results demonstrating that the consensus models improved both the predictive power and chemical space coverage. These solutions were further analyzed to find trends between the best consensus models and their components. Here, we demonstrate the development of a flexible and adaptable approach for in silico consensus modeling and its application across nine toxicological endpoints related to ER activity, AR activity, and genotoxicity. These consensus models are developed to be integrated into a larger multi-tier NAM-based framework to prioritize chemicals for further investigation and support the transition to a non-animal approach to risk assessment in Canada.

Structural Characterization and Cytotoxic Activity Evaluation of Ulvan Polysaccharides Extracted from the Green Algae Ulva papenfussii

Ulvan, a sulfated heteropolysaccharide with structural and functional properties of interest for various uses, was extracted from the green seaweed Ulva papenfussii. U. papenfussii is an unexplored Ulva species found in the South China Sea along the central coast of Vietnam. Based on dry weight, the ulvan yield was ~15% (w/w) and the ulvan had a sulfate content of 13.4 wt%. The compositional constitution encompassed L-Rhamnose (Rhap), D-Xylose (Xylp), D-Glucuronic acid (GlcAp), L-Iduronic acid (IdoAp), D-Galactose (Galp), and D-Glucose (Glcp) with a molar ratio of 1:0.19:0.35:0.52:0.05:0.11, respectively. The structure of ulvan was determined using High-Performance Liquid Chromatography (HPLC), Fourier Transform Infrared Spectroscopy (FT-IR), and Nuclear Magnetic Resonance spectroscopy (NMR) methods. The results showed that the extracted ulvan comprised a mixture of two different structural forms, namely ("A3s") with the repeating disaccharide [→4)-β-D-GlcAp-(1→4)-α-L-Rhap 3S-(1→]n, and ("B3s") with the repeating disaccharide [→4)-α-L-IdoAp-(1→4)-α-L-Rhap 3S(1→]n. The relative abundance of A3s, and B3s was 1:1.5, respectively. The potential anticarcinogenic attributes of ulvan were evaluated against a trilogy of human cancer cell lineages. Concomitantly, Quantitative Structure-Activity Relationship (QSAR) modeling was also conducted to predict potential adverse reactions stemming from pharmacological interactions. The ulvan showed significant antitumor growth activity against hepatocellular carcinoma (IC50 ≈ 90 µg/mL), human breast cancer cells (IC50 ≈ 85 µg/mL), and cervical cancer cells (IC50 ≈ 67 µg/mL). The QSAR models demonstrated acceptable predictive power, and seven toxicity indications confirmed the safety of ulvan, warranting its candidacy for further in vivo testing and applications as a biologically active pharmaceutical source for human disease treatment.

Prediction of the effects of small molecules on the gut microbiome using machine learning method integrating with optimal molecular features

BACKGROUND

The human gut microbiome (HGM), consisting of trillions of microorganisms, is crucial to human health. Adverse drug use is one of the most important causes of HGM disorder. Thus, it is necessary to identify drugs or compounds with anti-commensal effects on HGM in the early drug discovery stage. This study proposes a novel anti-commensal effects classification using a machine learning method and optimal molecular features. To improve the prediction performance, we explored combinations of six fingerprints and three descriptors to filter the best characterization as molecular features.

RESULTS

The final consensus model based on optimal features yielded the F1-score of 0.725 ± 0.014, ACC of 82.9 ± 0.7%, and AUC of 0.791 ± 0.009 for five-fold cross-validation. In addition, this novel model outperformed the prior studies by using the same algorithm. Furthermore, the important chemical descriptors and misclassified anti-commensal compounds are analyzed to better understand and interpret the model. Finally, seven structural alerts responsible for the chemical anti-commensal effect are identified, implying valuable information for drug design.

CONCLUSION

Our study would be a promising tool for screening anti-commensal compounds in the early stage of drug discovery and assessing the potential risks of these drugs in vivo.

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.

Leveraging molecular structure and bioactivity with chemical language models for de novo drug design

Generative chemical language models (CLMs) can be used for de novo molecular structure generation by learning from a textual representation of molecules. Here, we show that hybrid CLMs can additionally leverage the bioactivity information available for the training compounds. To computationally design ligands of phosphoinositide 3-kinase gamma (PI3Kγ), a collection of virtual molecules was created with a generative CLM. This virtual compound library was refined using a CLM-based classifier for bioactivity prediction. This second hybrid CLM was pretrained with patented molecular structures and fine-tuned with known PI3Kγ ligands. Several of the computer-generated molecular designs were commercially available, enabling fast prescreening and preliminary experimental validation. A new PI3Kγ ligand with sub-micromolar activity was identified, highlighting the method's scaffold-hopping potential. Chemical synthesis and biochemical testing of two of the top-ranked de novo designed molecules and their derivatives corroborated the model's ability to generate PI3Kγ ligands with medium to low nanomolar activity for hit-to-lead expansion. The most potent compounds led to pronounced inhibition of PI3K-dependent Akt phosphorylation in a medulloblastoma cell model, demonstrating efficacy of PI3Kγ ligands in PI3K/Akt pathway repression in human tumor cells. The results positively advocate hybrid CLMs for virtual compound screening and activity-focused molecular design.

Hybrid consensus and k-nearest neighbours (kNN) strategies to classify dual BRD4/PLK1 inhibitors

A novel decision-making procedure is proposed here for the first time to identify active/inactive and selective/non-selective dual inhibitors using consensus approaches and pools of k-nearest neighbours (kNN) classifications instead of individual models. Dual BRD4/PLK1 inhibition with adequate selectivity is a potential therapeutic strategy for targeting tumour cells in high-risk patients. We report the unique way to identify both active and selective dual BRD4/PLK1 inhibitors using consensus and kNN strategies together with two sources of receptor-based and ligand-based information which are the ranked binding energies of residues and important molecular features, respectively. The results of consensus approaches were compared with the results of individual kNN models. The chemical space similarity was measured using three different distance functions to increase the reliability. All activity and selectivity classification models were validated using cross-validation and y-randomization tests. The outcomes show that consensus approaches can increase the reliability and accuracy of active/inactive or selective/non-selective detections up to 90%. Consensus approaches also reached more balanced values of sensitivity and specificity compared to the individual kNN models because of the compensation in the integration of diverse sources of information.

Multi-Task Neural Networks and Molecular Fingerprints to Enhance Compound Identification from LC-MS/MS Data

Mass spectrometry (MS) is widely used for the identification of chemical compounds by matching the experimentally acquired mass spectrum against a database of reference spectra. However, this approach suffers from a limited coverage of the existing databases causing a failure in the identification of a compound not present in the database. Among the computational approaches for mining metabolite structures based on MS data, one option is to predict molecular fingerprints from the mass spectra by means of chemometric strategies and then use them to screen compound libraries. This can be carried out by calibrating multi-task artificial neural networks from large datasets of mass spectra, used as inputs, and molecular fingerprints as outputs. In this study, we prepared a large LC-MS/MS dataset from an on-line open repository. These data were used to train and evaluate deep-learning-based approaches to predict molecular fingerprints and retrieve the structure of unknown compounds from their LC-MS/MS spectra. Effects of data sparseness and the impact of different strategies of data curing and dimensionality reduction on the output accuracy have been evaluated. Moreover, extensive diagnostics have been carried out to evaluate modelling advantages and drawbacks as a function of the explored chemical space.

Modeling and insights into the structural basis of chemical acute aquatic toxicity

It has become a top global regulatory priority to prevent and control pollution from the release of synthetic chemicals, which continues to affect the aquatic communities. In the past decades, computational tools were largely used to significantly reduce the budget and time cost of chemical acute aquatic toxicity assessment. But the structural basis of toxic compounds was rarely analyzed. In the present study, we collected 1438, 485 and 961 chemicals with acute toxicity data records for three representative aquatic species, including Tetrahymena pyriformis, Daphnia magna, and Fathead minnow, respectively. A series of artificial intelligence models were developed using OCHEM tools. For each aquatic toxicity endpoint, a consensus model was developed based on the top performed individual models. The consensus models provided good performance on external validation sets with total accuracy values 96.88 %, 90.63 %, and 84.90 % for Tetrahymena pyriformis toxicity (TPT), Daphnia magna toxicity (DMT), and Fathead minnow toxicity (FMT), respectively. The models can be freely accessed via https://ochem.eu/article/146910. Moreover, the analysis of physical-chemical properties suggested that several key molecular properties of aquatic toxic compounds were significantly different with those of non-toxic compounds. Thus, these descriptors may be associated to chemical acute aquatic toxicity, and may be useful for the understand of chemical aquatic toxicity. Besides, in this study, the structural alerts for aquatic toxicity were detected using f-score and frequency ratio analysis of predefined substructures. A total of 112, 58 and 33 structural alerts were identified responsible for TPT, DMT, and FMT, respectively. These structural alerts could provide useful information for the mechanisms of chemical aquatic toxicity and visual alerts for environmental assessment. All the structural alerts were integrated in the web-server SApredictor (www.sapredictor.cn).

Multi-Strategy Assessment of Different Uses of QSAR under REACH Analysis of Alternatives to Advance Information Transparency

Under the Registration, Evaluation, Authorization, and Restriction of Chemicals (REACH) analysis of alternatives (AoA) process, quantitative structure–activity relationship (QSAR) models play an important role in expanding information gathering and organizing frameworks. Increasingly recognized as an alternative to testing under registration. QSARs have become a relevant tool in bridging data gaps and supporting weight of evidence (WoE) when assessing alternative substances. Additionally, QSARs are growing in importance in integrated testing strategies (ITS). For example, the REACH ITS framework for specific endpoints directs registrants to consider non-testing results, including QSAR predictions, when deciding if further animal testing is needed. Despite the raised profile of QSARs in these frameworks, a gap exists in the evaluation of QSAR use and QSAR documentation under authorization. An assessment of the different uses (e.g., WoE and ITS) in which QSAR predictions play a role in evidence gathering and organizing remains unaddressed for AoA. This study approached the disparity in information for QSAR predictions by conducting a substantive review of 24 AoA through May 2017, which contained higher-tier endpoints under REACH. Understanding the manner in which applicants manage QSAR prediction information in AoA and assessing their potential within ITS will be valuable in promoting regulatory use of QSARs and building out future platforms in the face of rapidly evolving technology while advancing information transparency.

Unswerving modeling of hepatotoxicity of cadmium containing quantum dots using amalgamation of quasiSMILES, index of ideality of correlation, and consensus modeling

Liver toxicity of quantum dots varies with size, concentration, and other structural as well as experimental parameters. For modeling hepatotoxicity, the eclectic data associated with cadmium containing quantum dots have been used in the creation of quasiSMILES for their representation. The core diameter is normalized for wider applicability and the index of the ideality of correlation is applied to construct the better quantitative features toxicity relationship models. Total eight splits are created and the best model is obtained through split 1 with better prediction criteria of validation set objects. The values of all statistical criteria used in the quality determination of a QSAR model are within the specified range for all the eight toxicity models developed here. Factors like TGA ligand and 0.6-0.7 nm diameter are favorable for liver toxicity while L-cysteine ligand and 0.5-0.6 nm core diameter are helpful in the reduction of toxicity. Further, the intelligent consensus modeling process forms a total of 40 individual and 20 consensus models and the best individual and consensus models are 'Good' in MAE-based criteria. The consensus modeling enhances the prediction ability as well as the accuracy of the developed models and increases the applicability space of the built models for hepatotoxicity prediction of quantum dots.

Incorporating human exposure information in a weight of evidence approach to inform design of repeated dose animal studies

Human health risks from chronic exposures to environmental chemicals are typically estimated from potential human exposure estimates and dose-response data obtained from repeated-dose animal toxicity studies. Various criteria are available for selecting the top (highest) dose used in these animal studies. For example, toxicokinetic (TK) and toxicological data provided by shorter-term or dose range finding studies can be evaluated in a weight of evidence approach to provide insight into the dose range that would provide dose-response data that are relevant to human exposures. However, there are concerns that a top dose resulting from the consideration of TK data may be too low compared to other criteria, such as the limit dose or the maximum tolerated dose. In this paper, we address several concerns related to human exposures by discussing 1) the resources and methods available to predict human exposure levels and the associated uncertainty and variability, and 2) the margin between predicted human exposure levels and the dose levels used in repeated-dose animal studies. A series of case studies, ranging from data-rich to data-poor chemicals, are presented to demonstrate that expected human exposures to environmental chemicals are typically orders of magnitude lower than no-observed-adverse-effect levels/lowest-observed-adverse-effect levels (NOAELs/LOAELs) when available (used as conservative surrogates for top doses). The results of these case studies support that a top dose based, in part, on TK data is typically orders of magnitude higher than expected human exposure levels.

In silico prediction of chemical-induced hematotoxicity with machine learning and deep learning methods

Chemical-induced hematotoxicity is an important concern in the drug discovery, since it can often be fatal when it happens. It is quite useful for us to give special attention to chemicals which can cause hematotoxicity. In the present study, we focused on in silico prediction of chemical-induced hematotoxicity with machine learning (ML) and deep learning (DL) methods. We collected a large data set contained 632 hematotoxic chemicals and 1525 approved drugs without hematotoxicity. Computational models were built using several different machine learning and deep learning algorithms integrated on the Online Chemical Modeling Environment (OCHEM). Based on the three best individual models, a consensus model was developed. It yielded the prediction accuracy of 0.83 and balanced accuracy of 0.77 on external validation. The consensus model and the best individual model developed with random forest regression and classification algorithm (RFR) and QNPR descriptors were made available at https://ochem.eu/article/135149 , respectively. The relevance of 8 commonly used molecular properties and chemical-induced hematotoxicity was also investigated. Several molecular properties have an obvious differentiating effect on chemical-induced hematotoxicity. Besides, 12 structural alerts responsible for chemical hematotoxicity were identified using frequency analysis of substructures from Klekota-Roth fingerprint. These results should provide meaningful knowledge and useful tools for hematotoxicity evaluation in drug discovery and environmental risk assessment.