QSAR prediction of rodent carcinogenicity for a set of chemicals currently bioassayed by the US National Toxicology Program

Benigni, Romualdo

doi:10.1093/mutage/6.5.423

Cited by 24 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This system empirically identifies structural alerts that are statistically related to a particular activity. A number of other approaches have been applied based on a variety of sources of information and SAR learning methods (8)(9)(10)(11)(12)(13). The effectiveness of these different SAR methods was evaluated on a test set of compounds for which predictions were made before the trials were completed (round 1 of the NTP's tests for carcinogenesis prediction) (8,14,15) There is currently a second round of tests.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Rodent Carcinogenicity Bioassays from Molecular Structure Using Inductive Logic Programming

King¹,

Srinivasan²

1996

Environmental Health Perspectives

View full text Add to dashboard Cite

The machine learning program Progol was applied to the problem of forming the structure-activity relationship (SAR) for a set of compounds tested for carcinogenicity in rodent bioassays by the U.S. National Toxicology Program (NTP). Progol is the first inductive logic programming (ILP) algorithm to use a fully relational method for describing chemical structure in SARs, based on using atoms and their bond connectivities. Progol is well suited to forming SARs for carcinogenicity as it is designed to produce easily understandable rules (structural alerts) for sets of noncongeneric compounds. The Progol SAR method was tested by prediction of a set of compounds that have been widely predicted by other SAR methods (the compounds used in the NTP's first round of carcinogenesis predictions). For these compounds no method (human or machine) was significantly more accurate than Progol. Progol was the most accurate method that did not use data from biological tests on rodents (however, the difference in accuracy is not significant). The Progol predictions were based solely on chemical structure and the results of tests for Salmonella mutagenicity. Using the full NTP database, the prediction accuracy of Progol was estimated to be 63% (+/- 3%) using 5-fold cross validation. A set of structural alerts for carcinogenesis was automatically generated and the chemical rationale for them investigated- these structural alerts are statistically independent of the Salmonella mutagenicity. Carcinogenicity is predicted for the compounds used in the NTP's second round of carcinogenesis predictions. The results for prediction of carcinogenesis, taken together with the previous successful applications of predicting mutagenicity in nitroaromatic compounds, and inhibition of angiogenesis by suramin analogues, show that Progol has a role to play in understanding the SARs of cancer-related compounds.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Rodent Carcinogenicity Bioassays from Molecular Structure Using Inductive Logic Programming

King¹,

Srinivasan²

1996

Environmental Health Perspectives

View full text Add to dashboard Cite

show abstract

“…[ I ] to 32% for Benigni (-) [7]; specificity ranged from 95% for Weisburger [reviewed in 91 to 38% for COMPACT/Lewis [4]. The FP/FN ratio ranged from 2.33…”

Section: Resultsmentioning

confidence: 99%

“…However, the chemicals were not specified. From Table 1, nine of these are most probably chemicals #44, #43, #42, #41, #40, #39, #31, #30, and #28, all of which do have one or two dissents even with generous scoring for DEREK [3], Benigni [7], and RASH [&I. Of these nine chemicals, #42, #41, and #31 were, in fact, negative in the NTP call.…”

Section: Discussionmentioning

confidence: 99%

Predictions of rodent carcinogenicity testing results: Interpretation in light of the lave‐omenn value‐of‐information model

Omenn

Stuebbe

Lave

1995

Molecular Carcinogenesis

View full text Add to dashboard Cite

The recent National Institute of Environmental Health Sciences/National Toxicology Program Carcinogen Prediction Challenge elicited a valuable array of predictions of the carcinogenicity of chemicals tested in the lifetime rodent bioassay. The data warrant additional analyses of the similarities and differences of the predictive methods. We provide here analyses of the sensitivity, specificity, and false-positive/false-negative tendencies of the different sets of predictions. Our value-of-information model provides guidance to testing agencies and regulatory agencies in determining the social value of additional information and setting up the framework for assessing the social consequences of different test strategies and nontest predictive methods. These considerations deserve attention in the second round of the Carcinogen Prediction Challenge.

show abstract

“…Cluster 3 was composed of very diverse methods, among which were the three AI approaches mentioned above: CASE/MultiCASE [43] and PROGOL [44], which identify the structural alerts in an unbiased way, and the rule-based expert system DEREK [45]. Benigni used the same approach (consideration of structural alerts and estimated electrophilicity) employed in the first comparative exercise [46], the Purdy method employed a combination of human expert rules and QSAR information [47], as did the COMPACT/HAZARDEXPERT approach [48], and the final two methods evaluated the predictive utility of the Salmonella mutagenicity assay result [31] and an estimated measure of electrophilicity, K e [46].…”

Section: Evaluating Prediction Performance Of Modelsmentioning

confidence: 99%

AI and SAR approaches for predicting chemical carcinogenicity: Survey and status report

Benigni

2002

SAR and QSAR in Environmental Research

Self Cite

View full text Add to dashboard Cite

A wide variety of artificial intelligence (AI) and structure-activity relationship (SAR) approaches have been applied to tackling the general problem of predicting rodent chemical carcinogenicity. Given the diversity of chemical structures and mechanisms relative to this endpoint, the shared challenge of these approaches is to accurately delineate classes of active chemicals representing distinct biological and chemical mechanism domains, and within those classes determine the structural features and properties responsible for modulating activity. In the following discussion, we present a survey of AI and SAR approaches that have been applied to the prediction of rodent carcinogenicity, and discuss these in general terms and in the context of the results of two organized prediction exercises (PTE-1 and PTE-2) sponsored by the US National Cancer Institute/National Toxicology Program. Most models participating in these exercises were successful in identifying major structural-alerting classes of active carcinogens, but failed in modeling the more subtle modifiers to activity within those classes. In addition, methods that incorporated mechanism-based reasoning or biological data along with structural information outperformed models limited to structural information exclusively. Finally, a few recent carcinogenicity-modeling efforts are presented illustrating progress in tackling some aspects of the carcinogenicity prediction problem. The first example, a QSAR model for predicting carcinogenic potency of aromatic amines, illustrates that success is possible within well-represented classes of carcinogens. From the second example, a newly developed FDA/OTR MultiCASE model for predicting the carcinogenicity of pharmaceuticals, we conclude that the definitions of biological activity and nature of chemicals in the training set are important determinants of the predictive success and specificity/sensitivity characteristics of a derived model.

show abstract

QSAR prediction of rodent carcinogenicity for a set of chemicals currently bioassayed by the US National Toxicology Program

Cited by 24 publications

References 0 publications

Prediction of Rodent Carcinogenicity Bioassays from Molecular Structure Using Inductive Logic Programming

Prediction of Rodent Carcinogenicity Bioassays from Molecular Structure Using Inductive Logic Programming

Predictions of rodent carcinogenicity testing results: Interpretation in light of the lave‐omenn value‐of‐information model

AI and SAR approaches for predicting chemical carcinogenicity: Survey and status report

Contact Info

Product

Resources

About