Expert system toxicity prediction

A Russian expert system, PASS (prediction of activity spectra for substances) [84], uses substructural descriptors called multilevel neighborhoods of atoms [85] to predict over 900 different pharmacological activities from molecular structure. These activities include a number of toxicity end points such as carcinogenicity, mutagenicity, teratogenicity, and embryotoxicity. The accuracy of prediction has been shown [86] to range from about 85% to over 90%. One-off predictions can be obtained free of charge on the PASS website [84]. 

Dearden JC, Barratt MD, Benigni R, Bristol DW, Combes RD, Cronin MTD et al. The development and validation of expert systems for predicting toxicity. ATE A 1997 25 223-52. 

Smithing MP, Darvas F. Hazardexpert an expert system for predicting chemical toxicity. In Finlay JW, Robinson SF, Armstrong DJ, editors, Food safety assessment. Washington DC American Chemical Society, 1992. p. 191-200. 

Chapter 19 The Use by Governmental Regulatory Agencies of Quantitative Structure-Activity Relationships and Expert Systems to Predict Toxicity Mark T.D. Cronin... 

One of the major limitations of expert systems is the availability of high quality toxicity data for a wide range of endpoints. It is only once this problem has been overcome that the true potential of expert systems for predicting all forms of toxicity will be realized. It is most important that both newly generated and existing data are fed into the process where rules can be written for such... 

Darvas, F., Papp, A., Allardyce, A., Benfenati, E., Gini, G., Tichy, M., Sobb, N., and Citti, A., Overview of different artificial intelligence approaches combined with a deductive logic-based expert system for predicting chemical toxicity, in AAAI Spring Symposium Predictive Toxicology of Chemicals, Stanford, CT, pp. 94-99, 1999. 

Smithing, M.P. and Darvas, F., Hazard expert an expert system for predicting chemical toxicity, in Food Safety Assessment, Finlay, J.W., Robinson, S.F., Armstrong, D.J., Eds., American Chemical Society, Washington, D.C., 1992, pp. 191-200. 

While not a regulatory body, the Organization for Economic Co-operation and Development (OECD) has increasingly become involved in the use of QSARs and expert systems to predict toxicity. In particular, the OECD has organized a freely available database on methods to predict chemical and physical properties of molecules (available from www.oecd.org or webdominol.oecd.org/comnet/env/models.nsf)... 

Cronin MTD. The use by governmental regulatory agencies of quantitative structure-activity relationships and expert systems to predict toxicity. In Cronin MTD, Livingstone DJ, editors, Predicting chemical toxicity and fate. Boca Raton, FL CRC Press, 2004. p. 413-27. 

An Expert System for Prediction of Aquatic Toxicity of Contaminants... 

Human health imphcations of transformation products - Most work to date has focused on the assessment and prediction of the ecotoxicity of transformation products. We need to begin to assess the potential human health imphcations of the presence of transformation products in the environment and develop approaches for identifying transformation products of most concern to human health. Expert systems for predicting mammalian toxicity endpoint may play a role here. 

DfW is a knowledge-based expert system for predicting the toxicity of a chemical from its molecular structure (Judson et al., 2003). This system is composed of structural alerts, example compounds, and rules that may each contribute to the toxicity predictions. However, DfW is designed to aid in chemical carcinogenicity risk assessment, and hepatotoxicity is not the major toxicity prediction from this... 

As computing capabiUty has improved, the need for automated methods of determining connectivity indexes, as well as group compositions and other stmctural parameters, for existing databases of chemical species has increased in importance. New naming techniques, such as SMILES, have been proposed which can be easily translated to these indexes and parameters by computer algorithms. Discussions of the more recent work in this area are available (281,282). SMILES has been used to input Contaminant stmctures into an expert system for aquatic toxicity prediction by generating LSER parameter values (243,258). 

A large variety of techniques are available to develop predictive models for toxicity. These range from relatively simple techniques to relate quantitative levels of potency with one or more descriptors to more multivariate techniques and ultimately the so-called expert systems that lead the user directly from an input of structure to a prediction. These are outlined briefly below. 

The need for rapidly accessible estimation of toxicity has led to the development of software and other algorithms that will generate estimations of toxicity, usually for organic compounds [79] such methodology is termed an expert system, which has been defined [34] as any formalised system, not necessarily computer-based, which enables a user to obtain rational predictions about the toxicity of chemicals. Essentially, expert systems fall into two classes— those relying on statistical approaches and those based on explicit rules derived from human knowledge. 

Greene N, Judson PN, Langowski JJ, Marchant CA. Knowledge-based expert systems for toxicity and metabolism prediction DEREK, StAR and METEOR. SAR QSAR Environ Res 1999 10 299-314. 

There are software that use more approaches for the prediction of toxicity expert systems, QSAR, and read-across (http //www.insilico.eu/use-qsar.html). 

Hewitt M, Ellison CM, Enoch SJ, Madden JC, Cronin MTD (2010) Integrating (Q)SAR models, expert systems and read-across approaches for the prediction of developmental toxicity. Reprod Toxicol 30(1) 147-160... 

DEREK Expert system for the prediction of toxicity (genotoxicity, carcinogenicity, skin sensitization, etc.)... 

A number of approaches are available or under development to predict metabolism, including expert systems such as MetabolExpert (Compudrug), Meteor (Lhasa), MetaFore [42] and the databases Metabolite (MDL) and Metabolism (Synopsys) [43]. Ultimately such programs may be linked to computer-aided toxicity prediction based on quantitative structure-toxicity relationships and expert systems for toxicity evaluation such as DEREK (Lhasa) (see also Chapter 8) [44]. 

---