Carcinogenicity - IRIS upper-bound excess lifetime cancer risk

Endpoint Definition

Unit Risk is defined as the upper-bound excess lifetime cancer risk estimated to result from continuous exposure to an agent at a concentration of 1 µg/L in water, or 1 µg/m3 in air. The interpretation of unit risk would be as follows: if unit risk = 2 x 10-6 per micromol/L, 2 excess cancer cases (upper bound estimate) are expected to develop per 1,000,000 people if exposed daily for a lifetime to 1 microg of the chemical in 1 liter of drinking water. Units are micromol/L. For more information, see: http://www.epa.gov/iris/carcino.htm. Refer to the IRIS Summary for more details on a particular chemical assessment. [ Details ] [ Original data ]

Algorithm Definition

lazar obtains predictions from the experimental results of compounds with similar structures ( neighbors ). For differentiated predictions chemical similarities are always determined in respect to the endpoint under investigation . A detailled description and formal definition of the lazar regression algorithm has been published in: You can donwload the source code for lazar ( GNU General Public License ) with git :
git clone git://github.com/helma/lazar-core.git

Applicability Domain Definition

The applicability domain (AD) of the training set is characterized by the confidence index of a prediction (high confidence index: close to the applicability domain of the training set/reliable prediction, low confidence: far from the applicability domain of the trainingset/unreliable prediction). The confidence index considers (i) the similarity and number of neighbors and (ii) contradictory examples within the neighbors. A formal definition can be found in: The reliability of predictions decreases gradually with increasing distance from the applicability domain (i.e. decreasing confidence index). Figure 1 shows this dependency visually.

For simplicity we provide also results for an applicability domain definition with a sharp border at a confidence index of 0.2 . These results are summarized in Table 1 and indicated by the grey area in Figure 1 and by the black triangles in Figure 2 . Misclassifications within the applicability domain are summarized in the table of misclassifications .

The presence of substructures that are unknown to the training set ( unknown fragments ) is another factor that limits the applicability domain. As the training data cannot provide any information about unknown fragments, their relevance has to be evaluated by an expert user (as a rule of thumb large fragments are of less concern, because all shorter subfragments have been evaluated by the system). For this reason the presence/absence of unknown fragments is not considered in the formal applicability domain definition, but their presence is indicated in the table of misclassifications .

Validation Results (leave-one-out crossvalidation)

Definition and experimental comparison with external validation procedures:

Table 1: Predictions within applicability domain

r 2 0.78
RMSE 0.56
Mean error 0.41
Predictions within 1 log unit 18 from 19 ( 94.7 %)

Predictions with a confidence > 0.2 are considered to be within the applicability domain (see Applicability Domain Definition )

Table 2: All predictions

r 2 -0.02
RMSE 1.30
Mean error 0.82
Predictions within 1 log unit 24 from 30 ( 80.0 %)

Poor indication of the overall performance. Depends predominatly on the fraction of compounds beyond the applicability domain, which are by definition poorly predictable (see Applicability Domain Definition )

Figure 1: Predictions within 1 log unit vs. prediction confidence

Cumulative_accuracies

Depicts the dependency of predictive accuracy on the confidence index (i.e. the distance to the applicability domain, see Applicability Domain Definition ). Fluctuations at the left hand side of the figure are statistical artefacts (small sample sizes) and therefore irrelevant.
The table of misclassifications shows all misclassified instances within the applicability domain.

Figure 2: Correlation of predicted vs meaѕured values

Correlation

Predictions within the applicability domain are marked in black.

Mechanistic Interpretation

Neighbors

Neighbors are compounds that are similar in respect to iris upper-bound excess lifetime cancer risk . It is likely that compounds with high similarity act by similar mechanisms as the query compound. You can retrieve additional experimental data and literature citations for the neighbors and the query structure by following the "Search PubChem" links on the prediction page.

Fragments

Activating and deactivating parts of the query compound are highlighted in red and green. Fragments that are unknown (or too infrequent for statistical evaluation are marked in yellow. You can retrieve additional statistical information about the individual fragments by following the "Relevant Fragments" link. Please note that lazar predictions are based on neighbors and not on fragments. Fragments and their statistical significance are used for the calculation of activity specific similarities.
© in silico toxicology 2004-2008
Built with: lazar, OpenBabel, CDK, Ruby on Rails
JME Editor courtesy of Peter Ertl, Novartis