Alarms about structural alerts

Human ether-à-go-go-related potassium channel: exploring SAR to improve drug design

hERG is best known as a primary anti-target, the inhibition of which is responsible for serious side effects. A renewed interest in hERG as a desired target, especially in oncology, was sparked because of its role in cellular proliferation and apoptosis. In this study, we survey the most recent advances regarding hERG by focusing on SAR in the attempt to elucidate, at a molecular level, off-target and on-target actions of potential hERG binders, which are highly promiscuous and largely varying in structure. Understanding the rationale behind hERG interactions and the molecular determinants of hERG activity is a real challenge and comprehension of this is of the utmost importance to prioritize compounds in early stages of drug discovery and to minimize cardiotoxicity attrition in preclinical and clinical studies.

Integrating in silico models and read-across methods for predicting toxicity of chemicals: A step-wise strategy

In silico methods and models are increasingly used for predicting properties of chemicals for hazard identification and hazard characterisation in the absence of experimental toxicity data. Many in silico models are available and can be used individually or in an integrated fashion. Whilst such models offer major benefits to toxicologists, risk assessors and the global scientific community, the lack of a consistent framework for the integration of in silico results can lead to uncertainty and even contradictions across models and users, even for the same chemicals. In this context, a range of methods for integrating in silico results have been proposed on a statistical or case-specific basis. Read-across constitutes another strategy for deriving reference points or points of departure for hazard characterisation of untested chemicals, from the available experimental data for structurally-similar compounds, mostly using expert judgment. Recently a number of software systems have been developed to support experts in this task providing a formalised and structured procedure. Such a procedure could also facilitate further integration of the results generated from in silico models and read-across. This article discusses a framework on weight of evidence published by EFSA to identify the stepwise approach for systematic integration of results or values obtained from these "non-testing methods". Key criteria and best practices for selecting and evaluating individual in silico models are also described, together with the means to combining the results, taking into account any limitations, and identifying strategies that are likely to provide consistent results.

Descriptor Free QSAR Modeling Using Deep Learning With Long Short-Term Memory Neural Networks

Current practice of building QSAR models usually involves computing a set of descriptors for the training set compounds, applying a descriptor selection algorithm and finally using a statistical fitting method to build the model. In this study, we explored the prospects of building good quality interpretable QSARs for big and diverse datasets, without using any pre-calculated descriptors. We have used different forms of Long Short-Term Memory (LSTM) neural networks to achieve this, trained directly using either traditional SMILES codes or a new linear molecular notation developed as part of this work. Three endpoints were modeled: Ames mutagenicity, inhibition of P. falciparum Dd2 and inhibition of Hepatitis C Virus, with training sets ranging from 7,866 to 31,919 compounds. To boost the interpretability of the prediction results, attention-based machine learning mechanism, jointly with a bidirectional LSTM was used to detect structural alerts for the mutagenicity data set. Traditional fragment descriptor-based models were used for comparison. As per the results of the external and cross-validation experiments, overall prediction accuracies of the LSTM models were close to the fragment-based models. However, LSTM models were superior in predicting test chemicals that are dissimilar to the training set compounds, a coveted quality of QSAR models in real world applications. In summary, it is possible to build QSAR models using LSTMs without using pre-computed traditional descriptors, and models are far from being "black box." We wish that this study will be helpful in bringing large, descriptor-less QSARs to mainstream use.

Leveraging heterogeneous data from GHS toxicity annotations, molecular and protein target descriptors and Tox21 assay readouts to predict and rationalise acute toxicity

Despite the increasing knowledge in both the chemical and biological domains the assimilation and exploration of heterogeneous datasets, encoding information about the chemical, bioactivity and phenotypic properties of compounds, remains a challenge due to requirement for overlap between chemicals assayed across the spaces. Here, we have constructed a novel dataset, larger than we have used in prior work, comprising 579 acute oral toxic compounds and 1427 non-toxic compounds derived from regulatory GHS information, along with their corresponding molecular and protein target descriptors and qHTS in vitro assay readouts from the Tox21 project. We found no clear association between the results of a FAFDrugs4 toxicophore screen and the acute oral toxicity classifications for our compound set; and a screen using a subset of the ToxAlerts toxicophores was also of limited utility, with only slight enrichment toward the toxic set (odds ratio of 1.48). We then investigated to what degree toxic and non-toxic compounds could be separated in each of the spaces, to compare their potential contribution to further analyses. Using an LDA projection, we found the largest degree of separation using chemical descriptors (Cohen’s d of 1.95) and the lowest degree of separation between toxicity classes using qHTS descriptors (Cohen’s d of 0.67). To compare the predictivity of the feature spaces for the toxicity endpoint, we next trained Random Forest (RF) acute oral toxicity classifiers on either molecular, protein target and qHTS descriptors. RFs trained on molecular and protein target descriptors were most predictive, with ROC AUC values of 0.80–0.92 and 0.70–0.85, respectively, across three test sets. RFs trained on both chemical and protein target descriptors combined exhibited similar predictive performance to the single-domain models (ROC AUC of 0.80–0.91). Model interpretability was improved by the inclusion of protein target descriptors, which allow the identification of specific targets (e.g. Retinal dehydrogenase) with literature links to toxic modes of action (e.g. oxidative stress). The dataset compiled in this study has been made available for future application.

Computing similarity between structural environments of mutagenicity alerts

This article describes a method to generate molecular fingerprints from structural environments of mutagenicity alerts and calculate similarity between them. This approach was used to improve classification accuracy of alerts and for searching structurally similar analogues of an alerting chemical. It builds fingerprints using molecular fragments from the vicinity of the alerts and automatically accounts for the activating and deactivating/mitigating features of alerts needed for accurate predictions. This study also demonstrates the usefulness of transfer learning in which a distributed representation of chemical fragments was first trained on millions of unlabelled chemicals and then used for generating fingerprints and similarity search on smaller data sets labelled with Ames test outcomes. The distributed fingerprints gave better prediction performance and increased coverage compared to traditional binary fingerprints. The methodology was applied to four common mutagenic functionalities-primary aromatic amine, aromatic nitro, epoxide and alkyl chloride. Effects of various hyperparameters on prediction accuracy and test coverage for the k-nearest neighbours prediction method are also described, e.g. similarity thresholds, number of neighbours and size of the alert environment.

Transfer learning for predicting human skin sensitizers

Computational prioritization of chemicals for potential skin sensitization risks plays essential roles in the risk assessment of environmental chemicals and drug development. Given the huge number of chemicals for testing, computational methods enable the fast identification of high-risk chemicals for experimental validation and design of safer alternatives. However, the development of robust prediction model requires a large dataset of tested chemicals that is usually not available for most toxicological endpoints, especially for human data. A small training dataset makes the development of effective models difficult with insufficient coverage and accuracy. In this study, an ensemble tree-based multitask learning method was developed incorporating three relevant tasks in the well-defined adverse outcome pathway (AOP) of skin sensitization to transfer shared knowledge to the major task of human sensitizers. The results show both largely improved coverage and accuracy compared with three state-of-the-art methods. A user-friendly prediction server was available at https://cwtung.kmu.edu.tw/skinsensdb/predict . As AOPs for various toxicity endpoints are being actively developed, the proposed method can be applied to develop prediction models for other endpoints.

QSAR investigation of acute toxicity of organic compounds during oral administration to mice

The effect of the structure of organic compounds on the acute toxicity upon oral injection in mice was studied using 2D simplex representation of the molecular structure and Random forest (RF) methods. Satisfactory quantitative structure-activity relationship (QSAR) models were constructed (R2 test = 0,61–0,62). The interpretation of the obtained QSAR models was carried out. The contributions of known toxicophores with established mechanisms of action were calculated in order to confirm the ability of the interpretation approach to correctly rank them relative to other structural fragments. The influence of the molecular surroundings of some toxicophores was analyzed. We analyzed the contributions of other highly ranked fragments from the list of common functional groups and ring systems in order to find new potential toxicophores. The on-line version of the expert system “OCHEM” (https://ochem.eu) and Arithmetic Mean Toxicity (AMT) approach were used for a comparative QSAR study.

Chemistry-Wide Association Studies (CWAS): A Novel Framework for Identifying and Interpreting Structure-Activity Relationships

Quantitative structure-activity relationships (QSAR) models are often seen as a "black box" because they are considered difficult to interpret. Meanwhile, qualitative approaches, e.g., structural alerts (SA) or read-across, provide mechanistic insight, which is preferred for regulatory purposes, but predictive accuracy of such approaches is often low. Herein, we introduce the chemistry-wide association study (CWAS) approach, a novel framework that both addresses such deficiencies and combines advantages of statistical QSAR and alert-based approaches. The CWAS framework consists of the following steps: (i) QSAR model building for an end point of interest, (ii) identification of key chemical features, (iii) determination of communities of such features disproportionately co-occurring more frequently in the active than in the inactive class, and (iv) assembling these communities to form larger (and not necessarily chemically connected) novel structural alerts with high specificity. As a proof-of-concept, we have applied CWAS to model Ames mutagenicity and Stevens-Johnson Syndrome (SJS). For the well-studied Ames mutagenicity data set, we identified 76 important individual fragments and assembled co-occurring fragments into SA both replicative of known as well as representing novel mutagenicity alerts. For the SJS data set, we identified 29 important fragments and assembled co-occurring communities into SA including both known and novel alerts. In summary, we demonstrate that CWAS provides a new framework to interpret predictive QSAR models and derive refined structural alerts for more effective design and safety assessment of drugs and drug candidates.

Discovering Highly Potent Molecules from an Initial Set of Inactives Using Iterative Screening

The versatility of similarity searching and quantitative structure-activity relationships to model the activity of compound sets within given bioactivity ranges (i.e., interpolation) is well established. However, their relative performance in the common scenario in early stage drug discovery where lots of inactive data but no active data points are available (i.e., extrapolation from the low-activity to the high-activity range) has not been thoroughly examined yet. To this aim, we have designed an iterative virtual screening strategy which was evaluated on 25 diverse bioactivity data sets from ChEMBL. We benchmark the efficiency of random forest (RF), multiple linear regression, ridge regression, similarity searching, and random selection of compounds to identify a highly active molecule in the test set among a large number of low-potency compounds. We use the number of iterations required to find this active molecule to evaluate the performance of each experimental setup. We show that linear and ridge regression often outperform RF and similarity searching, reducing the number of iterations to find an active compound by a factor of 2 or more. Even simple regression methods seem better able to extrapolate to high-bioactivity ranges than RF, which only provides output values in the range covered by the training set. In addition, examination of the scaffold diversity in the data sets used shows that in some cases similarity searching and RF require two times as many iterations as random selection depending on the chemical space covered in the initial training data. Lastly, we show using bioactivity data for COX-1 and COX-2 that our framework can be extended to multitarget drug discovery, where compounds are selected by concomitantly considering their activity against multiple targets. Overall, this study provides an approach for iterative screening where only inactive data are present in early stages of drug discovery in order to discover highly potent compounds and the best experimental set up in which to do so.

The use of structural alerts to avoid the toxicity of pharmaceuticals

In order to identify compounds with potential toxicity problems, particular attention is paid to structural alerts, which are high chemical reactivity molecular fragments or fragments that can be transformed via bioactivation by human enzymes into fragments with high chemical reactivity. The concept has been introduced in order to reduce the likelihood that future candidate substances as pharmaceuticals will have undesirable toxic effects. A significant proportion (∼78–86%) of drugs characterized by residual toxicity contain structural alerts; there is also evidence indicating the formation of active metabolites as a causal factor for the toxicity of 62–69% of these molecules. On the other hand, the pharmacological action of certain drugs depends on the formation of reactive metabolites. Detailed assessment of the potential for the formation of active metabolites is recommended to characterize a biologically active compound. Although many prescribed drugs frequently contain structural alerts and form reactive metabolites, the vast majority of these drugs are administered in low daily doses. Avoiding structural alerts has become almost a norm in new drug design. An in-depth review of the biochemical reactivity of these structural alerts for new drug candidates is critical from a safety point of view and is currently being monitored in the discovery of drugs. The chemical strategies applied to structural alerts in molecules to limit the toxicity are:

•

partial replacement or full replacement of the structural alert;

•

reduction of electronic density;

•

introduction of a structural element of metabolic interest (metabolic switching);

•

multiple approaches.

Therefore, chemical intervention strategies to eliminate bioactivation are often interactive processes; their success depends largely on a close working relationship between drug chemists, pharmacologists and researchers in metabolic science.

Multi-Descriptor Read Across (MuDRA): A Simple and Transparent Approach for Developing Accurate Quantitative Structure-Activity Relationship Models

Multiple approaches to quantitative structure-activity relationship (QSAR) modeling using various statistical or machine learning techniques and different types of chemical descriptors have been developed over the years. Oftentimes models are used in consensus to make more accurate predictions at the expense of model interpretation. We propose a simple, fast, and reliable method termed Multi-Descriptor Read Across (MuDRA) for developing both accurate and interpretable models. The method is conceptually related to the well-known kNN approach but uses different types of chemical descriptors simultaneously for similarity assessment. To benchmark the new method, we have built MuDRA models for six different end points (Ames mutagenicity, aquatic toxicity, hepatotoxicity, hERG liability, skin sensitization, and endocrine disruption) and compared the results with those generated with conventional consensus QSAR modeling. We find that models built with MuDRA show consistently high external accuracy similar to that of conventional QSAR models. However, MuDRA models excel in terms of transparency, interpretability, and computational efficiency. We posit that due to its methodological simplicity and reliable predictive accuracy, MuDRA provides a powerful alternative to a much more complex consensus QSAR modeling. MuDRA is implemented and freely available at the Chembench web portal ( https://chembench.mml.unc.edu/mudra ).

Predictive ecotoxicity of MoA 1 of organic chemicals using in silico approaches

Persistent organic products are compounds used for various purposes, such as personal care products, surfactants, colorants, industrial additives, food, pesticides and pharmaceuticals. These substances are constantly introduced into the environment and many of these pollutants are difficult to degrade. Toxic compounds classified as MoA 1 (Mode of Action 1) are low toxicity compounds that comprise nonreactive chemicals. In silico methods such as Quantitative Structure-Activity Relationships (QSARs) have been used to develop important models for prediction in several areas of science, as well as aquatic toxicity studies. The aim of the present study was to build a QSAR model-based set of theoretical Volsurf molecular descriptors using the fish acute toxicity values of compounds defined as MoA 1 to identify the molecular properties related to this mechanism. The selected Partial Least Squares (PLS) results based on the values of cross-validation coefficients of determination (Q_cv²) show the following values: Q_cv² = 0.793, coefficient of determination (R²) = 0.823, explained variance in external prediction (Q_ext²) = 0.87. From the selected descriptors, not only the hydrophobicity is related to the toxicity as already mentioned in previously published studies but other physicochemical properties combined contribute to the activity of these compounds. The symmetric distribution of the hydrophobic moieties in the structure of the compounds as well as the shape, as branched chains, are important features that are related to the toxicity. This information from the model can be useful in predicting so as to minimize the toxicity of organic compounds.

In silico toxicology protocols

The present publication surveys several applications of in silico (i.e., computational) toxicology approaches across different industries and institutions. It highlights the need to develop standardized protocols when conducting toxicity-related predictions. This contribution articulates the information needed for protocols to support in silico predictions for major toxicological endpoints of concern (e.g., genetic toxicity, carcinogenicity, acute toxicity, reproductive toxicity, developmental toxicity) across several industries and regulatory bodies. Such novel in silico toxicology (IST) protocols, when fully developed and implemented, will ensure in silico toxicological assessments are performed and evaluated in a consistent, reproducible, and well-documented manner across industries and regulatory bodies to support wider uptake and acceptance of the approaches. The development of IST protocols is an initiative developed through a collaboration among an international consortium to reflect the state-of-the-art in in silico toxicology for hazard identification and characterization. A general outline for describing the development of such protocols is included and it is based on in silico predictions and/or available experimental data for a defined series of relevant toxicological effects or mechanisms. The publication presents a novel approach for determining the reliability of in silico predictions alongside experimental data. In addition, we discuss how to determine the level of confidence in the assessment based on the relevance and reliability of the information.

Combination of experimental and in silico methods for the assessment of the phototransformation products of the antipsychotic drug/metabolite Mesoridazine

The lack of studies on the fate and effects of drug metabolites in the environment is of concern. As their parent compounds, metabolites enter the aquatic environment and are subject to biotic and abiotic process. In this regard, photolysis plays an important role. This study combined experimental and in silico quantitative structure-activity relationship (QSAR) methods to assess the fate and effects of Mesoridazine (MESO), a pharmacologically active human drug and metabolite of the antipsychotic agent Thioridazine, and its transformation products (TPs) formed through a Xenon lamp irradiation. After 256min, the photodegradation of MESO⋅besylate (50mgL^-1) achieved 90.4% and 6.9% of primary elimination and mineralization, respectively. The photon flux emitted by the lamp (200-600nm) was 169.55Jcm^-2. Sixteen TPs were detected by means of liquid chromatography-high resolution mass spectrometry (LC-HRMS), and the structures were proposed based on MSⁿ fragmentation patterns. The main transformation reactions were sulfoxidation, hydroxylation, dehydrogenation, and sulfoxide elimination. A back-transformation of MESO to Thioridazine was evidenced. Aerobic biodegradation tests (OECD 301 D and 301F) were applied to MESO and the mixture of TPs present after 256min of photolysis. Most of TPs were not biodegraded, demonstrating their tendency to persist in aquatic environments. The ecotoxicity towards Vibrio fischeri showed a decrease in toxicity during the photolysis process. The in silico QSAR tools QSARINS and US-EPA PBT profiler were applied for the screening of TPs with character of persistence, bioaccumulation, and toxicity (PBT). They have revealed the carbazole derivatives TP 355 and TP 337 as PBT/vPvB (very persistent and very bioaccumulative) compounds. In silico QSAR predictions for mutagenicity and genotoxicity provided by CASE Ultra and Leadscope® indicated positive alerts for mutagenicity on TP 355 and TP 337. Further studies regarding the carbazole derivative TPs should be considered to confirm their hazardous character.

QSAR: What Else?

QSAR (quantitative structure-activity relationship) is a method for predicting the physical and biological properties of small molecules; it is today in large use in companies and public services. However, as any scientific method, it is nowadays challenged by more and more requests, especially considering its possible role in assessing the safety of new chemicals. Posing the question whether QSAR is a way not only to exploit available knowledge but also to build new knowledge, we shortly review QSAR history, thus searching for a QSAR epistemology. We consider the three pillars on which QSAR stands: biological data, chemical knowledge, and modeling algorithms. Most of the time we assume that biological data is a true picture of the world (as they result from good experimental practice), that chemical knowledge is scientifically true; so if a QSAR is not working, blame modeling. This opens the way to look at the role of modeling in developing scientific theories, and in producing knowledge. QSAR is a mature technology; however, debate is still active in many topics, in particular about the acceptability of the models and how they are explained. After an excursus in inductive reasoning, we relate the QSAR methodology to open debates in the philosophy of science.

Annotation of Peptide Structures Using SMILES and Other Chemical Codes-Practical Solutions

Contemporary peptide science exploits methods and tools of bioinformatics, and cheminformatics. These approaches use different languages to describe peptide structures—amino acid sequences and chemical codes (especially SMILES), respectively. The latter may be applied, e.g., in comparative studies involving structures and properties of peptides and peptidomimetics. Progress in peptide science “in silico” may be achieved via better communication between biologists and chemists, involving the translation of peptide representation from amino acid sequence into SMILES code. Recent recommendations concerning good practice in chemical information include careful verification of data and their annotation. This publication discusses the generation of SMILES representations of peptides using existing software. Construction of peptide structures containing unnatural and modified amino acids (with special attention paid on glycosylated peptides) is also included. Special attention is paid to the detection and correction of typical errors occurring in SMILES representations of peptides and their correction using molecular editors. Brief recommendations for training of staff working on peptide annotations, are discussed as well.

Computational Approach to Structural Alerts: Furans, Phenols, Nitroaromatics, and Thiophenes

Structural alerts are commonly used in drug discovery to identify molecules likely to form reactive metabolites and thereby become toxic. Unfortunately, as useful as structural alerts are, they do not effectively model if, when, and why metabolism renders safe molecules toxic. Toxicity due to a specific structural alert is highly conditional, depending on the metabolism of the alert, the reactivity of its metabolites, dosage, and competing detoxification pathways. A systems approach, which explicitly models these pathways, could more effectively assess the toxicity risk of drug candidates. In this study, we demonstrated that mathematical models of P450 metabolism can predict the context-specific probability that a structural alert will be bioactivated in a given molecule. This study focuses on the furan, phenol, nitroaromatic, and thiophene alerts. Each of these structural alerts can produce reactive metabolites through certain metabolic pathways but not always. We tested whether our metabolism modeling approach, XenoSite, can predict when a given molecule's alerts will be bioactivated. Specifically, we used models of epoxidation, quinone formation, reduction, and sulfur-oxidation to predict the bioactivation of furan-, phenol-, nitroaromatic-, and thiophene-containing drugs. Our models separated bioactivated and not-bioactivated furan-, phenol-, nitroaromatic-, and thiophene-containing drugs with AUC performances of 100%, 73%, 93%, and 88%, respectively. Metabolism models accurately predict whether alerts are bioactivated and thus serve as a practical approach to improve the interpretability and usefulness of structural alerts. We expect that this same computational approach can be extended to most other structural alerts and later integrated into toxicity risk models. This advance is one necessary step toward our long-term goal of building comprehensive metabolic models of bioactivation and detoxification to guide assessment and design of new therapeutic molecules.

Phantom PAINS: Problems with the Utility of Alerts for Pan-Assay INterference CompoundS

The use of substructural alerts to identify Pan-Assay INterference compoundS (PAINS) has become a common component of the triage process in biological screening campaigns. These alerts, however, were originally derived from a proprietary library tested in just six assays measuring protein-protein interaction (PPI) inhibition using the AlphaScreen detection technology only; moreover, 68% (328 out of the 480 alerts) were derived from four or fewer compounds. In an effort to assess the reliability of these alerts as indicators of pan-assay interference, we performed a large-scale analysis of the impact of PAINS alerts on compound promiscuity in bioassays using publicly available data in PubChem. We found that the majority (97%) of all compounds containing PAINS alerts were actually infrequent hitters in AlphaScreen assays measuring PPI inhibition. We also found that the presence of PAINS alerts, contrary to expectations, did not reflect any heightened assay activity trends across all assays in PubChem including AlphaScreen, luciferase, beta-lactamase, or fluorescence-based assays. In addition, 109 PAINS alerts were present in 3570 extensively assayed, but consistently inactive compounds called Dark Chemical Matter. Finally, we observed that 87 small molecule FDA-approved drugs contained PAINS alerts and profiled their bioassay activity. Based on this detailed analysis of PAINS alerts in nonproprietary compound libraries, we caution against the blind use of PAINS filters to detect and triage compounds with possible PAINS liabilities and recommend that such conclusions should be drawn only by conducting orthogonal experiments.

QSAR models of human data can enrich or replace LLNA testing for human skin sensitization

Skin sensitization is a major environmental and occupational health hazard. Although many chemicals have been evaluated in humans, there have been no efforts to model these data to date. We have compiled, curated, analyzed, and compared the available human and LLNA data. Using these data, we have developed reliable computational models and applied them for virtual screening of chemical libraries to identify putative skin sensitizers. The overall concordance between murine LLNA and human skin sensitization responses for a set of 135 unique chemicals was low (R = 28-43%), although several chemical classes had high concordance. We have succeeded to develop predictive QSAR models of all available human data with the external correct classification rate of 71%. A consensus model integrating concordant QSAR predictions and LLNA results afforded a higher CCR of 82% but at the expense of the reduced external dataset coverage (52%). We used the developed QSAR models for virtual screening of CosIng database and identified 1061 putative skin sensitizers; for seventeen of these compounds, we found published evidence of their skin sensitization effects. Models reported herein provide more accurate alternative to LLNA testing for human skin sensitization assessment across diverse chemical data. In addition, they can also be used to guide the structural optimization of toxic compounds to reduce their skin sensitization potential.