4D-fingerprint categorical QSAR models for skin sensitization based on the classification of local lymph node assay measures

Two Decades of 4D-QSAR: A Dying Art or Staging a Comeback?

A key question confronting computational chemists concerns the preferable ligand geometry that fits complementarily into the receptor pocket. Typically, the postulated ‘bioactive’ 3D ligand conformation is constructed as a ‘sophisticated guess’ (unnecessarily geometry-optimized) mirroring the pharmacophore hypothesis—sometimes based on an erroneous prerequisite. Hence, 4D-QSAR scheme and its ‘dialects’ have been practically implemented as higher level of model abstraction that allows the examination of the multiple molecular conformation, orientation and protonation representation, respectively. Nearly a quarter of a century has passed since the eminent work of Hopfinger appeared on the stage; therefore the natural question occurs whether 4D-QSAR approach is still appealing to the scientific community? With no intention to be comprehensive, a review of the current state of art in the field of receptor-independent (RI) and receptor-dependent (RD) 4D-QSAR methodology is provided with a brief examination of the ‘mainstream’ algorithms. In fact, a myriad of 4D-QSAR methods have been implemented and applied practically for a diverse range of molecules. It seems that, 4D-QSAR approach has been experiencing a promising renaissance of interests that might be fuelled by the rising power of the graphics processing unit (GPU) clusters applied to full-atom MD-based simulations of the protein-ligand complexes.

Machine learning prediction of nanoparticle in vitro toxicity: A comparative study of classifiers and ensemble-classifiers using the Copeland Index

Nano-Particles (NPs) are well established as important components across a broad range of products from cosmetics to electronics. Their utilization is increasing with their significant economic and societal potential yet to be fully realized. Inroads have been made in our understanding of the risks posed to human health and the environment by NPs but this area will require continuous research and monitoring. In recent years Machine Learning (ML) techniques have exploited large datasets and computation power to create breakthroughs in diverse fields from facial recognition to genomics. More recently, ML techniques have been applied to nanotoxicology with very encouraging results. In this study, categories of ML classifiers (rules, trees, lazy, functions and bayes) were compared using datasets from the Safe and Sustainable Nanotechnology (S2NANO) database to investigate their performance in predicting NPs in vitro toxicity. Physicochemical properties, toxicological and quantum-mechanical attributes and in vitro experimental conditions were used as input variables to predict the toxicity of NPs based on cell viability. Voting, an ensemble meta-classifier, was used to combine base models to optimize the classification prediction of toxicity. To facilitate inter-comparison, a Copeland Index was applied that ranks the classifiers according to their performance and suggested the optimal classifier. Neural Network (NN) and Random forest (RF) showed the best performance in the majority of the datasets used in this study. However, the combination of classifiers demonstrated an improved prediction resulting meta-classifier to have higher indices. This proposed Copeland Index can now be used by researchers to identify and clearly prioritize classifiers in order to achieve more accurate classification predictions for NP toxicity for a given dataset.

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.

SkinSensDB: a curated database for skin sensitization assays

Skin sensitization is an important toxicological endpoint for chemical hazard determination and safety assessment. Prediction of chemical skin sensitizer had traditionally relied on data from rodent models. The development of the adverse outcome pathway (AOP) and associated alternative in vitro assays have reshaped the assessment of skin sensitizers. The integration of multiple assays as key events in the AOP has been shown to have improved prediction performance. Current computational models to predict skin sensitization mainly based on in vivo assays without incorporating alternative in vitro assays. However, there are few freely available databases integrating both the in vivo and the in vitro skin sensitization assays for development of AOP-based skin sensitization prediction models. To facilitate the development of AOP-based prediction models, a skin sensitization database named SkinSensDB has been constructed by curating data from published AOP-related assays. In addition to providing datasets for developing computational models, SkinSensDB is equipped with browsing and search tools which enable the assessment of new compounds for their skin sensitization potentials based on data from structurally similar compounds. SkinSensDB is publicly available at http://cwtung.kmu.edu.tw/skinsensdb.

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.

Development and validation of regression-based QSAR models for quantification of contributions of molecular fragments to skin sensitization potency of diverse organic chemicals

In our present work, we have developed regression-based QSAR models for skin sensitization potential of 51 diverse organic chemicals. The objective behind the present work is to determine the influence of different molecular features on the skin sensitizing potential of chemicals. Among several models developed, the two best ones are discussed to unveil specific information regarding the contribution of different structural and physicochemical features towards the property of skin sensitization. The QSAR models suggested that aromatic compounds are more skin sensitizing than aliphatic ones, but in the case of carbonyl compounds, aliphatic ones are more skin sensitizing than aromatic ones. Other descriptors such as LUMO and <2-Atype_H-47> signify the importance of the electrophilic and hydrophilic character respectively of the molecules for showing skin sensitizing property. Another two descriptors, <Dipole-mag-2.72> and (3)χC also exert significant contributions towards the skin sensitization potential of the chemicals. Further, it is observed that the nitrogen atoms (nN), triple bonds (nTB) and also the fragment Al-C(=X)-Al (Atype_C38) are responsible for skin sensitizing property. All the above information provides additional support for further research involving identification of the skin sensitization potential of new chemicals.

Chemical sensitization and allergotoxicology

Chemical sensitization remains an important environmental and occupational health issue. A wide range of substances have been shown to possess the ability to induce skin sensitization or respiratory sensitization. As a consequence, there is a need to have appropriate methods to identify sensitizing agents. Although a considerable investment has been made in exploring opportunities to develop methods for hazard identification and characterization, there are, as yet, no validated nonanimal methods available. A state of the art of the different in vitro approaches to identify contact and respiratory capacity of chemicals is covered in this chapter.

Prediction of skin sensitization potential using D-optimal design and GA-kNN classification methods

Modelling of skin sensitization data of 255 diverse compounds and 450 calculated descriptors was performed to develop global predictive classification models that are applicable to whole chemical space. With this aim, we employed two automated procedures, (a) D-optimal design to select optimal members of the training and test sets and (b) k-Nearest Neighbour classification (kNN) method along with Genetic Algorithms (GA-kNN Classification) to select significant and independent descriptors in order to build the models. This methodology helped us to derive multiple models, M1-M5, that are stable and robust. The best among them, model M1 (CCR(train) = 84.3%, CCR(test) = 87.2% and CCR(ext) = 80.4%), is based on six neighbours and nine descriptors and further suggests that: (a) it is stable and robust and performs better than the reported models in literature, and (b) the combination of D-optimal design and GA-kNN classification approach is a very promising approach. Consensus prediction based on the models M1-M5 improved the CCR of training, test and external validation datasets by 3.8%, 4.45% and 3.85%, respectively, over M1. From the analysis of the physical meaning of the selected descriptors, it is inferred that the skin sensitization potential of small organic compounds can be accurately predicted using calculated descriptors that code for the following fundamental properties: (i) lipophilicity, (ii) atomic polarizability, (iii) shape, (iii) electrostatic interactions, and (iv) chemical reactivity.

3D pharmacophore mapping using 4D QSAR analysis for the cytotoxicity of lamellarins against human hormone-dependent T47D breast cancer cells

4D quantitative structure-activity relationship (QSAR) and 3D pharmacophore models were built and investigated for cytotoxicity using a training set of 25 lamellarins against human hormone dependent T47D breast cancer cells. Receptor-independent (RI) 4D QSAR models were first constructed from the exploration of eight possible receptor-binding alignments for the entire training set. Since the training set is small (25 compounds), the generality of the 4D QSAR paradigm was then exploited to devise a strategy to maximize the extraction of binding information from the training set and to also permit virtual screening of diverse lamellarin chemistry. 4D QSAR models were sought for only six of the most potent lamellarins of the training set as well as another subset composed of lamellarins with constrained ranges in molecular weight and lipophilicity. This overall modeling strategy has permitted maximizing 3D pharmacophore information from this small set of structurally complex lamellarins that can be used to drive future analog synthesis and the selection of alternate scaffolds. Overall, it was found that the formation of an intermolecular hydrogen bond and the hydrophobic interactions for substituents on the E ring most modulate the cytotoxicity against T47D breast cancer cells. Hydrophobic substitutions on the F-ring can also enhance cytotoxic potency. A complementary high-throughput virtual screen to the 3D pharmacophore models, a 4D fingerprint QSAR model, was constructed using absolute molecular similarity. This 4D fingerprint virtual high-throughput screen permits a larger range of chemistry diversity to be assayed than with the 4D QSAR models. The optimized 4D QSAR 3D pharmacophore model has a leave-one-out cross-correlation value of xv-r2 = 0.947, while the optimized 4D fingerprint virtual screening model has a value of xv-r2 = 0.719. This work reveals that it is possible to develop significant QSAR, 3D pharmacophore, and virtual screening models for a small set of lamellarins showing cytotoxic behavior in breast cancer screens that can guide future drug development based upon lamellarin chemistry.

Prediction of skin sensitization with a particle swarm optimized support vector machine

Skin sensitization is the most commonly reported occupational illness, causing much suffering to a wide range of people. Identification and labeling of environmental allergens is urgently required to protect people from skin sensitization. The guinea pig maximization test (GPMT) and murine local lymph node assay (LLNA) are the two most important in vivo models for identification of skin sensitizers. In order to reduce the number of animal tests, quantitative structure-activity relationships (QSARs) are strongly encouraged in the assessment of skin sensitization of chemicals. This paper has investigated the skin sensitization potential of 162 compounds with LLNA results and 92 compounds with GPMT results using a support vector machine. A particle swarm optimization algorithm was implemented for feature selection from a large number of molecular descriptors calculated by Dragon. For the LLNA data set, the classification accuracies are 95.37% and 88.89% for the training and the test sets, respectively. For the GPMT data set, the classification accuracies are 91.80% and 90.32% for the training and the test sets, respectively. The classification performances were greatly improved compared to those reported in the literature, indicating that the support vector machine optimized by particle swarm in this paper is competent for the identification of skin sensitizers.

Identification of mechanisms of toxic action for skin sensitisation using a SMARTS pattern based approach

Skin sensitisation is a key endpoint under REACH as it is costly and its assessment currently has a high dependency on animal testing. In order to reduce both the cost and the numbers of animals tested, it is likely that (quantitative) structure-activity relationships ((Q)SAR) and read-across methods will be utilised as part of intelligent testing strategies. The majority of skin sensitisers elicit their effect via covalent bond formation with skin proteins. These reactions have been understood in terms of well defined nucleophilic-electrophilic reaction chemistry. Thus, a first step in (Q)SAR analysis is the assignment of a chemical's potential mechanism of action enabling it to be placed in an appropriate reactivity domain. The aim of this study was to design a series of SMARTS patterns capable of defining these reactivity domains. This was carried out using a large database of local lymph node assay (LLNA) results that had had potential mechanisms of action assigned to them using expert knowledge. A simple algorithm was written enabling the SMARTS patterns to be used to screen a database of SMILES strings. The SMARTS patterns were then evaluated using a second, smaller, test set of LLNA results which had also had potential mechanisms of action assigned by experts. The results showed that the SMARTS patterns provided an excellent method of identifying potential electrophilic mechanisms. The findings are supported, in part, by molecular orbital calculations which confirm assignment of reactive mechanism of action. The ability to define a chemical's potential reaction mechanism is likely to be of significant benefit to regulators and risk assessors as it enables category formation and subsequent read-across to be performed.

Allergic contact dermatitis--formation, structural requirements, and reactivity of skin sensitizers

Contact allergy is caused by a wide range of chemicals after skin contact. Its clinical manifestation, allergic contact dermatitis (ACD), is developed upon repeated contact with the allergen. This perspective focuses on two areas that have yielded new useful information during the last 20 years: (i) structure-activity relationship (SAR) studies of contact allergy based on the concept of hapten-protein binding and (ii) mechanistic investigations regarding activation of nonsensitizing compounds to contact allergens by air oxidation or skin metabolism. The second area is more thoroughly reviewed since the full picture has previously not been published. Prediction of the sensitizing capacity of a chemical is important to avoid outbreaks of ACD in the population. Much research has been devoted to the development of in vitro and in silico predictive testing methods. Today, no method exists that is sensitive enough to detect weak allergens and that is robust enough to be used for routine screening. To cause sensitization, a chemical must bind to macromolecules (proteins) in the skin. Expert systems containing information about the relationship between the chemical structure and the ability of chemicals to haptenate proteins are available. However, few designed SAR studies based on mechanistic investigations of prohaptens have been published. Many compounds are not allergenic themselves but are activated in the skin (e.g., metabolically) or before skin contact (e.g., via air oxidation) to form skin sensitizers. Thus, more basic research is needed on the chemical reactions involved in the antigen formation and the immunological mechanisms. The clinical importance of air oxidation to activate nonallergenic compounds has been demonstrated. Oxidized fragrance terpenes, in contrast to the pure terpenes, gave positive patch test reactions in consecutive dermatitis patients as frequently as the most common standard allergens. This shows the importance of using compounds to which people are exposed when screening for ACD in dermatology clinics.

Categorical QSAR Models for Skin Sensitization based upon Local Lymph Node Assay Classification Measures Part 2: 4D-Fingerprint Three-State and Two-2-State Logistic Regression Models

Three and four state categorical quantitative structure-activity relationship (QSAR) models for skin sensitization have been constructed using data from the murine Local Lymph Node Assay studies. These are the same data we previously used to build two-state (sensitizer, nonsensitizer) QSAR models (Li et al., 2007, Chem. Res. Toxicol. 20, 114-128). 4D-fingerprint descriptors derived from the 4D-molecular similarity paradigm are used to generate these models. A training set of 196 and a test set of 22 structurally diverse compounds were used in this study. Logistic regression, and partial least square coupled logistic regression were used to build the models. The three-state QSAR model gives a classification accuracy of 73.4% for the training set and 63.6% for the test set, while the random average value of classification accuracy for any three-state data set is 33.3%. The two-2-state [four categories in total] QSAR model gives a classification accuracy of 83.2% for the training set and 54.6% for the test set, while the random average value of classification accuracy for any two-2-state data set is 25%. An analysis of the skin-sensitization models developed in this study, as well as the two-state QSAR models developed in our previous analysis, suggests that the "moderate" sensitizers may be the main source of limited model accuracy.