Computational prediction of the chromosome-damaging potential of chemicals.

We report on the generation of computer-based models for the prediction of the chromosome-damaging potential of chemicals as assessed in the in vitro chromosome aberration (CA) test. On the basis of publicly available CA-test results of more than 650 chemical substances, half of which are drug-like compounds, we generated two different computational models. The first model was realized using the (Q)SAR tool MCASE. Results obtained with this model indicate a limited performance (53%) for the assessment of a chromosome-damaging potential (sensitivity), whereas CA-test negative compounds were correctly predicted with a specificity of 75%. The low sensitivity of this model might be explained by the fact that the underlying 2D-structural descriptors only describe part of the molecular mechanism leading to the induction of chromosome aberrations, that is, direct drug-DNA interactions. The second model was constructed with a more sophisticated machine learning approach and generated a classification model based on 14 molecular descriptors, which were obtained after feature selection. The performance of this model was superior to the MCASE model, primarily because of an improved sensitivity, suggesting that the more complex molecular descriptors in combination with statistical learning approaches are better suited to model the complex nature of mechanisms leading to a positive effect in the CA-test. An analysis of misclassified pharmaceuticals by this model showed that a large part of the false-negative predicted compounds were uniquely positive in the CA-test but lacked a genotoxic potential in other mutagenicity tests of the regulatory testing battery, suggesting that biologically nonsignificant mechanisms could be responsible for the observed positive CA-test result. Since such mechanisms are not amenable to modeling approaches it is suggested that a positive prediction made by the model reflects a biologically significant genotoxic potential. An integration of the machine-learning model as a screening tool in early discovery phases of drug development is proposed.

[1]  R. Snyder,et al.  Comparison of the results of a modified miniscreen and the standard bacterial reverse mutation assays , 2000, Environmental and molecular mutagenesis.

[2]  D. Kirkland,et al.  Interpretation of the biological relevance of genotoxicity test results: the importance of thresholds. , 2000, Mutation research.

[3]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[4]  L. Breiman.  Arcing Classifiers , 1998 .

[5]  J W Green,et al.  A review of the genotoxicity of marketed pharmaceuticals. , 2001, Mutation research.

[6]  R. Snyder,et al.  Assessment of the sensitivity of the computational programs DEREK, TOPKAT, and MCASE in the prediction of the genotoxicity of pharmaceutical molecules , 2004, Environmental and molecular mutagenesis.

[7]  David Kirkland,et al.  Evaluation of the ability of a battery of three in vitro genotoxicity tests to discriminate rodent carcinogens and non-carcinogens III. Appropriate follow-up testing in vivo. , 2005, Mutation research.

[8]  A.M. Richard,et al.  AI and SAR approaches for predicting chemical carcinogenicity: Survey and status report , 2002, SAR and QSAR in environmental research.

[9]  H S Rosenkranz,et al.  Development, characterization and application of predictive-toxicology models. , 1999, SAR and QSAR in environmental research.

[10]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[11]  P. Jurs,et al.  Development of binary classification of structural chromosome aberrations for a diverse set of organic compounds from molecular structure. , 2003, Chemical research in toxicology.

[12]  Roberto Todeschini,et al.  Handbook of Molecular Descriptors , 2002 .

[13]  Hook Eb.  International Commission for Protection against Environmental Mutagens and Carcinogens. ICPEMC meeting report no. 3. Is the incidence of Down syndrome increasing? , 1983, Mutation research.

[14]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[15]  E. Parry,et al.  Detection and characterization of mechanisms of action of aneugenic chemicals. , 2002, Mutagenesis.

[16]  Peter C Jurs,et al.  Predicting the genotoxicity of polycyclic aromatic compounds from molecular structure with different classifiers. , 2003, Chemical research in toxicology.

[17]  H. Kubinyi,et al.  A scoring scheme for discriminating between drugs and nondrugs. , 1998, Journal of medicinal chemistry.

[18]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[19]  H. Stopper,et al.  Evaluation of the in vitro micronucleus test as an alternative to the in vitro chromosomal aberration assay: position of the GUM Working Group on the in vitro micronucleus test. Gesellschaft für Umwelt-Mutations-forschung. , 1998, Mutation research.

[20]  F. K. Ennever,et al.  Significant differences in the structural basis of the induction of sister chromatid exchanges and chromosomal aberrations in chinese hamster ovary cells , 1990, Environmental and Molecular Mutagenesis.

[21]  Z R Li,et al.  Prediction of genotoxicity of chemical compounds by statistical learning methods. , 2005, Chemical research in toxicology.

[22]  A. Natarajan,et al.  Chromosomal Aberrations , 1990, Springer Berlin Heidelberg.

[23]  X. Y. Zhang,et al.  Application of support vector machine (SVM) for prediction toxic activity of different data sets. , 2006, Toxicology.

[24]  P. Pfeiffer,et al.  Chromosomal aberrations: formation, identification and distribution. , 2002, Mutation research.

[25]  B. Ames,et al.  Does carcinogenic potency correlate with mutagenic potency in the Ames assay? , 1978, Nature.

[26]  F. Palitti,et al.  Chromosomal aberrations and genomic instability induced by topoisomerase-targeted antitumour drugs. , 2004, Current medicinal chemistry. Anti-cancer agents.

[27]  Maciej Ogorzalek,et al.  Time series prediction with ensemble models applied to the CATS benchmark , 2007, Neurocomputing.

[28]  Herbert S Rosenkranz,et al.  SAR modeling of genotoxic phenomena: the consequence on predictive performance of deviation from a unity ratio of genotoxicants/non-genotoxicants. , 2004, Mutation research.

[29]  Thomas Steger-Hartmann,et al.  Use of computer-assisted prediction of toxic effects of chemical substances. , 2006, Toxicology.

[30]  Alan G. E. Wilson,et al.  A multiple in silico program approach for the prediction of mutagenicity from chemical structure. , 2003, Mutation research.

[31]  Neal F. Cariello,et al.  Comparison of the computer programs DEREK and TOPKAT to predict bacterial mutagenicity. Deductive Estimate of Risk from Existing Knowledge. Toxicity Prediction by Komputer Assisted Technology. , 2002, Mutagenesis.

[32]  Lutz Müller,et al.  Evaluation of the ability of a battery of three in vitro genotoxicity tests to discriminate rodent carcinogens and non-carcinogens I. Sensitivity, specificity and relative predictivity. , 2005, Mutation research.

[33]  H S Rosenkranz,et al.  International Commission for Protection Against Environmental Mutagens and Carcinogens. Approaches to SAR in carcinogenesis and mutagenesis. Prediction of carcinogenicity/mutagenicity using MULTI-CASE. , 1994, Mutation research.

[34]  Nigel Greene,et al.  Computer systems for the prediction of toxicity: an update. , 2002, Advanced drug delivery reviews.