Limits...
A novel two-step hierarchical quantitative structure-activity relationship modeling work flow for predicting acute toxicity of chemicals in rodents.

Zhu H, Ye L, Richard A, Golbraikh A, Wright FA, Rusyn I, Tropsha A - Environ. Health Perspect. (2009)

Bottom Line: A wealth of available biological data requires new computational approaches to link chemical structure, in vitro data, and potential adverse health effects.The analysis of these data showed no significant correlation between IC(50) and LD(50).The novelty of this modeling approach is that it uses the relationships between in vivo and in vitro data only to inform the initial construction of the hierarchical two-step QSAR models.

View Article: PubMed Central - PubMed

Affiliation: Laboratory for Molecular Modeling, Division of Medicinal Chemistry and Natural Products, School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599-7360, USA.

ABSTRACT

Background: Accurate prediction of in vivo toxicity from in vitro testing is a challenging problem. Large public-private consortia have been formed with the goal of improving chemical safety assessment by the means of high-throughput screening.

Objective: A wealth of available biological data requires new computational approaches to link chemical structure, in vitro data, and potential adverse health effects.

Methods and results: A database containing experimental cytotoxicity values for in vitro half-maximal inhibitory concentration (IC(50)) and in vivo rodent median lethal dose (LD(50)) for more than 300 chemicals was compiled by Zentralstelle zur Erfassung und Bewertung von Ersatz- und Ergaenzungsmethoden zum Tierversuch (ZEBET; National Center for Documentation and Evaluation of Alternative Methods to Animal Experiments). The application of conventional quantitative structure-activity relationship (QSAR) modeling approaches to predict mouse or rat acute LD(50) values from chemical descriptors of ZEBET compounds yielded no statistically significant models. The analysis of these data showed no significant correlation between IC(50) and LD(50). However, a linear IC(50) versus LD(50) correlation could be established for a fraction of compounds. To capitalize on this observation, we developed a novel two-step modeling approach as follows. First, all chemicals are partitioned into two groups based on the relationship between IC(50) and LD(50) values: One group comprises compounds with linear IC(50) versus LD(50) relationships, and another group comprises the remaining compounds. Second, we built conventional binary classification QSAR models to predict the group affiliation based on chemical descriptors only. Third, we developed k-nearest neighbor continuous QSAR models for each subclass to predict LD(50) values from chemical descriptors. All models were extensively validated using special protocols.

Conclusions: The novelty of this modeling approach is that it uses the relationships between in vivo and in vitro data only to inform the initial construction of the hierarchical two-step QSAR models. Models resulting from this approach employ chemical descriptors only for external prediction of acute rodent toxicity.

Show MeSH

Related in: MedlinePlus

The correlation between experimental and predicted LD50 values for 27 external compounds within the applicability domain (A) using TOPKAT and (B) using the two-step model developed in this study.
© Copyright Policy - public-domain
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2721870&req=5

f3-ehp-117-1257: The correlation between experimental and predicted LD50 values for 27 external compounds within the applicability domain (A) using TOPKAT and (B) using the two-step model developed in this study.

Mentions: We compared the performance of our modeling approach with that of TOPKAT software, version 6.1 (Accelrys 2009; Enslein 1988). Two types of comparison were considered. First, we have analyzed 27 of the 115 ICCVAM compounds that have been used neither for building our model nor in the TOPKAT LD50 training set. Figure 3 shows the correlation between the experimental and predicted LD50 values obtained from our model versus TOPKAT. The R2 and MAE of TOPKAT were 0.16 and 0.78, respectively, for all 27 compounds, which is considerably less than the same statistical parameters for prediction of the same data set using our model, R2 and MAE of 0.64 and 0.38, respectively. For seven compounds that were outside of the applicability domain for our model, the R2 and MAE using TOPKAT were 0.60 and 0.50, respectively, whereas our model produced values of 0.86 and 0.29, respectively (Table 3).


A novel two-step hierarchical quantitative structure-activity relationship modeling work flow for predicting acute toxicity of chemicals in rodents.

Zhu H, Ye L, Richard A, Golbraikh A, Wright FA, Rusyn I, Tropsha A - Environ. Health Perspect. (2009)

The correlation between experimental and predicted LD50 values for 27 external compounds within the applicability domain (A) using TOPKAT and (B) using the two-step model developed in this study.
© Copyright Policy - public-domain
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2721870&req=5

f3-ehp-117-1257: The correlation between experimental and predicted LD50 values for 27 external compounds within the applicability domain (A) using TOPKAT and (B) using the two-step model developed in this study.
Mentions: We compared the performance of our modeling approach with that of TOPKAT software, version 6.1 (Accelrys 2009; Enslein 1988). Two types of comparison were considered. First, we have analyzed 27 of the 115 ICCVAM compounds that have been used neither for building our model nor in the TOPKAT LD50 training set. Figure 3 shows the correlation between the experimental and predicted LD50 values obtained from our model versus TOPKAT. The R2 and MAE of TOPKAT were 0.16 and 0.78, respectively, for all 27 compounds, which is considerably less than the same statistical parameters for prediction of the same data set using our model, R2 and MAE of 0.64 and 0.38, respectively. For seven compounds that were outside of the applicability domain for our model, the R2 and MAE using TOPKAT were 0.60 and 0.50, respectively, whereas our model produced values of 0.86 and 0.29, respectively (Table 3).

Bottom Line: A wealth of available biological data requires new computational approaches to link chemical structure, in vitro data, and potential adverse health effects.The analysis of these data showed no significant correlation between IC(50) and LD(50).The novelty of this modeling approach is that it uses the relationships between in vivo and in vitro data only to inform the initial construction of the hierarchical two-step QSAR models.

View Article: PubMed Central - PubMed

Affiliation: Laboratory for Molecular Modeling, Division of Medicinal Chemistry and Natural Products, School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599-7360, USA.

ABSTRACT

Background: Accurate prediction of in vivo toxicity from in vitro testing is a challenging problem. Large public-private consortia have been formed with the goal of improving chemical safety assessment by the means of high-throughput screening.

Objective: A wealth of available biological data requires new computational approaches to link chemical structure, in vitro data, and potential adverse health effects.

Methods and results: A database containing experimental cytotoxicity values for in vitro half-maximal inhibitory concentration (IC(50)) and in vivo rodent median lethal dose (LD(50)) for more than 300 chemicals was compiled by Zentralstelle zur Erfassung und Bewertung von Ersatz- und Ergaenzungsmethoden zum Tierversuch (ZEBET; National Center for Documentation and Evaluation of Alternative Methods to Animal Experiments). The application of conventional quantitative structure-activity relationship (QSAR) modeling approaches to predict mouse or rat acute LD(50) values from chemical descriptors of ZEBET compounds yielded no statistically significant models. The analysis of these data showed no significant correlation between IC(50) and LD(50). However, a linear IC(50) versus LD(50) correlation could be established for a fraction of compounds. To capitalize on this observation, we developed a novel two-step modeling approach as follows. First, all chemicals are partitioned into two groups based on the relationship between IC(50) and LD(50) values: One group comprises compounds with linear IC(50) versus LD(50) relationships, and another group comprises the remaining compounds. Second, we built conventional binary classification QSAR models to predict the group affiliation based on chemical descriptors only. Third, we developed k-nearest neighbor continuous QSAR models for each subclass to predict LD(50) values from chemical descriptors. All models were extensively validated using special protocols.

Conclusions: The novelty of this modeling approach is that it uses the relationships between in vivo and in vitro data only to inform the initial construction of the hierarchical two-step QSAR models. Models resulting from this approach employ chemical descriptors only for external prediction of acute rodent toxicity.

Show MeSH
Related in: MedlinePlus