Validity and validation of expert (Q)SAR systems

At a recent workshop in Setubal (Portugal) principles were drafted to assess the suitability of (quantitative) structure–activity relationships ((Q)SARs) for assessing the hazards and risks of chemicals. In the present study we applied some of the Setubal principles to test the validity of three (Q)SAR expert systems and validate the results. These principles include a mechanistic basis, the availability of a training set and validation. ECOSAR, BIOWIN and DEREK for Windows have a mechanistic or empirical basis. ECOSAR has a training set for each QSAR. For half of the structural fragments the number of chemicals in the training set is >4. Based on structural fragments and log Kow, ECOSAR uses linear regression to predict ecotoxicity. Validating ECOSAR for three ‘valid’ classes results in predictivity of ?≥?64%. BIOWIN uses (non-)linear regressions to predict the probability of biodegradability based on fragments and molecular weight. It has a large training set and predicts non-ready biodegradability well. DEREK for Windows predictions are supported by a mechanistic rationale and literature references. The structural alerts in this program have been developed with a training set of positive and negative toxicity data. However, to support the prediction only a limited number of chemicals in the training set is presented to the user. DEREK for Windows predicts effects by ‘if-then’ reasoning. The program predicts best for mutagenicity and carcinogenicity. Each structural fragment in ECOSAR and DEREK for Windows needs to be evaluated and validated separately.     

An evaluation of selected (Q)SARs/expert systems for predicting skin sensitisation potential

Predictive testing to characterise substances for their skin sensitisation potential has historically been based on animal models such as the Local Lymph Node Assay (LLNA) and the Guinea Pig Maximisation Test (GPMT). In recent years, EU regulations, have provided a strong incentive to develop non-animal alternatives, such as expert systems software. Here we selected three different types of expert systems: VEGA (statistical), Derek Nexus (knowledge-based) and TIMES-SS (hybrid), and evaluated their performance using two large sets of animal data: one set of 1249 substances from eChemportal and a second set of 515 substances from NICEATM. A model was considered successful at predicting skin sensitisation potential if it had at least the same balanced accuracy as the LLNA and the GPMT had in predicting the other outcomes, which ranged from 79% to 86%. We found that the highest balanced accuracy of any of the expert systems evaluated was 65% when making global predictions. For substances within the domain of TIMES-SS, however, balanced accuracies for the two datasets were found to be 79% and 82%. In those cases where a chemical was within the TIMES-SS domain, the TIMES-SS skin sensitisation hazard prediction had the same confidence as the result from LLNA or GPMT.     

An evaluation of selected global (Q)SARs/expert systems for the prediction of skin sensitisation potential

Skin sensitisation potential is an endpoint that needs to be assessed within the framework of existing and forthcoming legislation. At present, skin sensitisation hazard is normally identified using in vivo test methods, the favoured approach being the local lymph node assay (LLNA). This method can also provide a measure of relative skin sensitising potency which is essential for assessing and managing human health risks. One potential alternative approach to skin sensitisation hazard identification is the use of (Quantitative) structure activity relationships ((Q)SARs) coupled with appropriate documentation and performance characteristics. This represents a major challenge. Current thinking is that (Q)SARs might best be employed as part of a battery of approaches that collectively provide information on skin sensitisation hazard. A number of (Q)SARs and expert systems have been developed and are described in the literature. Here we focus on three models (TOPKAT, Derek for Windows and TOPS-MODE), and evaluate their performance against a recently published dataset of 211 chemicals. The current strengths and limitations of one of these models is highlighted, together with modifications that could be made to improve its performance. Of the models/expert systems evaluated, none performed sufficiently well to act as a standalone tool for hazard identification.     

An evaluation of selected global (Q)SARs/expert systems for the prediction of skin sensitisation potential

Skin sensitisation potential is an endpoint that needs to be assessed within the framework of existing and forthcoming legislation. At present, skin sensitisation hazard is normally identified using in vivo test methods, the favoured approach being the local lymph node assay (LLNA). This method can also provide a measure of relative skin sensitising potency which is essential for assessing and managing human health risks. One potential alternative approach to skin sensitisation hazard identification is the use of (Quantitative) structure activity relationships ((Q)SARs) coupled with appropriate documentation and performance characteristics. This represents a major challenge. Current thinking is that (Q)SARs might best be employed as part of a battery of approaches that collectively provide information on skin sensitisation hazard. A number of (Q)SARs and expert systems have been developed and are described in the literature. Here we focus on three models (TOPKAT, Derek for Windows and TOPS-MODE), and evaluate their performance against a recently published dataset of 211 chemicals. The current strengths and limitations of one of these models is highlighted, together with modifications that could be made to improve its performance. Of the models/expert systems evaluated, none performed sufficiently well to act as a standalone tool for hazard identification.     

Comparative PBT screening using (Q)SAR tools within REACH legislation

Small to medium sized enterprises (SMEs) in the EU are facing challenges due to the introduction of new legislation designed to protect consumers and the environment, REACH (Registration, Evaluation, Authorisation and Restriction of CHemicals). There can be high costs associated with implementing REACH because data on mammalian toxicity, environmental toxicity and environmental fate properties is required and if this data is obtained experimentally the cost is significant. These costs can be reduced if reliable quantitative structure–activity relationships ((Q)SAR) models are instead used to obtain the required information. In this paper we investigate how easily freely available (Q)SAR models can be applied for persistent, bioaccumulative and toxic (PBT) screening of 17 chemicals of interest to SMEs. In this study the PBT predictions obtained from the more user-friendly PBT Profiler and the Danish(Q)SAR database for the chemicals were compared with the results taken directly from the EPI Suite software. It was found that these widely used (Q)SAR databases might have some errors and examples are provided. It was concluded that extra care must be taken when considering the use of these databases for PBT screening. In addition, to increase the likelihood of a correct prediction, data estimates from various (Q)SAR models relevant to the PBT endpoints must be compared.     

The role of the European centre for the validation of alternative methods (ECVAM) in the validation of (Q)SARs

Under the current chemicals legislation, the regulatory use of structure-activity relationships (SARs) and quantitative structure-activity relationships (QSARs), collectively referred to as (Q)SARs, for the assessment of chemicals is limited, partly due to concerns about the extent to which (Q)SAR estimates can be relied upon. On 29 October 2003, the European Commission adopted a legislative proposal that foresees the introduction of a new regulatory system for chemicals called REACH (Registration, Evaluation, and Authorisation of Chemicals), which will impose equivalent information requirements on both new and existing chemicals. For reasons of practicality, cost-effectiveness and animal welfare, it is envisaged that (Q)SARs will play an important role in the assessment of some 30,000 existing chemicals for which further information may be required under the REACH system. It will therefore be essential that the (Q)SAR models used will produce reliable estimates. To overcome the barriers in the acceptance of (Q)SARs for regulatory purposes, it is widely acknowledged that there needs to be international agreement on the principles of (Q)SAR validation, and that the process of (Q)SAR validation should be managed by independent organisations, with a view to providing independent advice to the regulators who make decisions on the acceptability of (Q)SARs. The European Centre for the Validation of Alternative Methods (ECVAM), which is part of the European Commission's Joint Research Centre (JRC), has a well-established role in providing independent scientific and technical advice to European policy makers. This paper describes progress made at an international level regarding the principles of validation, and explains the role of ECVAM regarding the practical validation of (Q)SARs.     

Development and implementation of (Q)SAR modeling within the CHARMMing web‐user interface

Recent availability of large publicly accessible databases of chemical compounds and their biological activities (PubChem, ChEMBL) has inspired us to develop a web‐based tool for structure activity relationship and quantitative structure activity relationship modeling to add to the services provided by CHARMMing ( www.charmming.org ). This new module implements some of the most recent advances in modern machine learning algorithms—Random Forest, Support Vector Machine, Stochastic Gradient Descent, Gradient Tree Boosting, so forth. A user can import training data from Pubchem Bioassay data collections directly from our interface or upload his or her own SD files which contain structures and activity information to create new models (either categorical or numerical). A user can then track the model generation process and run models on new data to predict activity. © 2014 Wiley Periodicals, Inc.     

Integrated approach to assess the domain of applicability of some commercial (Q)SAR models

An integrated framework of data analysis has been proposed to systematically address the determination of the domain of applicability (DA) of some commercial Quantitative Structure Activity Relationship ((Q)SAR) models based on the structure of test chemicals. This framework forms one of the important steps in dealing with the growing concerns on reliability of model-based predictions on toxicity of chemicals specifically in the regulatory context. The present study uses some of the well-known mutagenicity and carcinogenicity models that are available within the Casetox (MultiCASE Inc.) and TOPKAT (Accelrys Software Inc.) programs. The approach enumerated in this paper employs chemoinformatics tools that facilitate comparisons of key structural features as well as application of cluster analysis techniques. The approach has been illustrated using a set of eleven chemical structures selected from the Canadian Domestic Substances List (DSL) that are not present in the model training sets, and the efficacy of the approach has also been assessed using seven chemicals with known toxicities. The methodologies presented here could help address the issue of DA of complex (Q)SAR models and at the same time, serve as useful tools for regulators to make a preliminary assessment of (Q)SAR based systems thereby helping the process of hazard-based regulatory assessments of chemicals.     

Integrated approach to assess the domain of applicability of some commercial (Q)SAR models1

An integrated framework of data analysis has been proposed to systematically address the determination of the domain of applicability (DA) of some commercial Quantitative Structure Activity Relationship ((Q)SAR) models based on the structure of test chemicals. This framework forms one of the important steps in dealing with the growing concerns on reliability of model-based predictions on toxicity of chemicals specifically in the regulatory context. The present study uses some of the well-known mutagenicity and carcinogenicity models that are available within the Casetox (MultiCASE Inc.) and TOPKAT (Accelrys Software Inc.) programs. The approach enumerated in this paper employs chemoinformatics tools that facilitate comparisons of key structural features as well as application of cluster analysis techniques. The approach has been illustrated using a set of eleven chemical structures selected from the Canadian Domestic Substances List (DSL) that are not present in the model training sets, and the efficacy of the approach has also been assessed using seven chemicals with known toxicities. The methodologies presented here could help address the issue of DA of complex (Q)SAR models and at the same time, serve as useful tools for regulators to make a preliminary assessment of (Q)SAR based systems thereby helping the process of hazard-based regulatory assessments of chemicals.     

Improving (Q)SAR predictions by examining bias in the selection of compounds for experimental testing

ABSTRACT

Existing data on structures and biological activities are limited and distributed unevenly across distinct molecular targets and chemical compounds. The question arises if these data represent an unbiased sample of the general population of chemical-biological interactions. To answer this question, we analyzed ChEMBL data for 87,583 molecules tested against 919 protein targets using supervised and unsupervised approaches. Hierarchical clustering of the Murcko frameworks generated using Chemistry Development Toolkit showed that the available data form a big diffuse cloud without apparent structure. In contrast hereto, PASS-based classifiers allowed prediction whether the compound had been tested against the particular molecular target, despite whether it was active or not. Thus, one may conclude that the selection of chemical compounds for testing against specific targets is biased, probably due to the influence of prior knowledge. We assessed the possibility to improve (Q)SAR predictions using this fact: PASS prediction of the interaction with the particular target for compounds predicted as tested against the target has significantly higher accuracy than for those predicted as untested (average ROC AUC are about 0.87 and 0.75, respectively). Thus, considering the existing bias in the data of the training set may increase the performance of virtual screening.     

The role of the European Chemicals Bureau in promoting the regulatory use of (Q)SAR methods

Under the proposed REACH (Registration, Evaluation and Authorisation of CHemicals) legislation, (Q)SAR models and grouping methods (chemical categories and read across approaches) are expected to play a significant role in prioritising industrial chemicals for further assessment, and for filling information gaps for the purposes of classification and labelling, risk assessment and the assessment of persistent, bioaccumulative and toxic (PBT) chemicals. The European Chemicals Bureau (ECB), which is part of the European Commission's Joint Research Centre (JRC), has a well-established role in providing independent scientific and technical advice to European policy makers. The ECB also promotes consensus and capacity building on scientific and technical matters among stakeholders in the Member State authorities and industry. To promote the availability and use of (Q)SARs and related estimation methods, the ECB is carrying out a range of activities, including applied research in computational toxicology, the assessment of (Q)SAR models and methods, the development of technical guidance documents and computational tools, and the organisation of training courses. This article provides an overview of ECB activities on computational toxicology, which are intended to promote the development, validation, acceptance and use of (Q)SARs and related estimation methods, both at the European and international levels.     

The photodissociation reaction dynamics of CF(3)I at 304 nm ((3)Q(0+), (1)Q(1)<--(3)Q(0+), and (3)Q(1))

The photodissociation of CF(3)I at 304 nm has been studied using long time-delayed core-sampling photofragment translational spectroscopy. Due to its capability of detecting the kinetic energy distribution of iodine fragments with high resolution, it is able to directly assign the vibrational state distribution of CF(3) fragments. The vibrational state distributions of CF(3) fragments in the I(*)((2)P(12)) channel, i.e., (3)Q(0+) state, have a propensity of the nu(2) (') umbrella mode with a maximum distribution at the vibrational ground state. For the I((2)P(32)) channel, i.e., (1)Q(1)<--(3)Q(0+), the excitation of the nu(2) (') umbrella mode accounts for the majority of the vibrational excitation of the CF(3) fragments. The 1 nu(1) (') (symmetric CF stretch) +nnu(2) (') combination modes, which are associated with the major progression of the nu(2) (') umbrella mode, are observed for the photodissociation of CF(3)I at the I channel, i.e., (3)Q(1) state. The bond dissociation energy of the CI bond of CF(3)I is determined to be D(0)(CF(3)-I)相似文献   

ToxML,a data exchange standard with content controlled vocabulary used to build better (Q)SAR models

Development of accurate quantitative structure–activity relationship (QSAR) models requires the availability of high quality validated data. International regulations such as REACH in Europe will now accept (Q)SAR-based evaluations for risk assessment. The number of toxicity datasets available for those wishing to share knowledge, or to use for data mining and modelling, is continually expanding. The challenge is the current use of a multitude of different data formats. The issues of comparing or combining disparate data apply both to public and proprietary sources. The ToxML project addresses the need for a common data exchange standard that allows the representation and communication of these data in a well-structured electronic format. It is an open standard based on Extensible Markup Language (XML). Supporting information for overall toxicity endpoint data can be included within ToxML files. This makes it possible to assess the quality and detail of the data used in a model. The data file model allows the aggregation of experimental data to the compound level in the detail needed to support (Q)SAR work. The standard is published on a website together with tools to view, edit and download it.     

Integration of optimization methodology with expert systems

An expert system for ion-pair liquid chromatography of basic drugs is described. Integration of experimental optimization methodology into the expert system is shown to be feasible. The system consists mainly of four modules: an introductory module, and initial guess module, a formal optimization module and an adaptation module. The formal optimization module, based on a simple 2 × 2 factorial design and an overlapping resolution map, is integrated with the expert system. The expert system was validated on 20 basic drugs and their 60 synthetic mixtures combined by using a random method. The rate of succes was satisfactory.     

Structure and emission properties of Er3Q9 (Q = 8-quinolinolate)

We report the first combined optical and structural investigation of the water free Er-quinolinolate complex, an organo-lanthanide system of interest for 1.5-microm telecom applications. Structural data demonstrate that the complex has a trinuclear structure (Er3Q9) which provides the Er metals with an octa-coordination by the organic ligand and prevents solvent and water molecules from entering the lanthanide coordination sphere. The results of the structural analysis allow us to infer that the strong Er luminescence quenching exhibited by the Er3Q9 complex is due uniquely to resonant energy transfer to the aromatic C-H vibrations of the ligand, providing the correct tools to design more efficient emitters.     

Present and future of expert systems in food analysis

This paper presents an overview of the most relevant contributions in the field of expert system (ES) applications in chemical analysis of foods, along with a critical discussion of future, would-be developments. It illustrates the possibilities offered as well as the fact that quality control laboratories should be aware of the power of artificial intelligence that modern computer technology affords. It is worth noting that the applications described are straightforward with a certain versatility and can, therefore, be implemented for other analytes and/or food samples. Special attention is devoted to the promising distributed knowledge-based systems due to their potential advantages over the existing centralized approaches, as inferred from a recent example of application to the on-line monitoring of some key chemical parameters in the course of a food production process. Short and middle term predictions concerning the potential of ES in food analysis are also made.