<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Melissa Van Bossuyt</style></author><author><style face="normal" font="default" size="100%">Els Van Hoeck</style></author><author><style face="normal" font="default" size="100%">Raitano, Giuseppa</style></author><author><style face="normal" font="default" size="100%">Vanhaecke, Tamara</style></author><author><style face="normal" font="default" size="100%">Benfenati, Emilio</style></author><author><style face="normal" font="default" size="100%">Birgit Mertens</style></author><author><style face="normal" font="default" size="100%">Rogiers, Vera</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Performance of in silico models for mutagenicity prediction of food contact materials</style></title><secondary-title><style face="normal" font="default" size="100%">Toxicological Sciences</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">(Q)SAR</style></keyword><keyword><style  face="normal" font="default" size="100%">food contact materials</style></keyword><keyword><style  face="normal" font="default" size="100%">In silico</style></keyword><keyword><style  face="normal" font="default" size="100%">mutagenicity</style></keyword><keyword><style  face="normal" font="default" size="100%">VALIDATION</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2018</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2018 mar 20</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">163</style></volume><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;In silico methodologies, such as (quantitative) structure-activity relationships ((Q)SARs), are&lt;/p&gt;

&lt;p&gt;available to predict a wide variety of toxicological properties and biological activities for&lt;/p&gt;

&lt;p&gt;structurally diverse substances. To obtain insights in the scientific value of these predictions,&lt;/p&gt;

&lt;p&gt;the capacity of the prediction models to generate (sufficiently) reliable results for a particular&lt;/p&gt;

&lt;p&gt;type of compounds needs to be evaluated. In the current study, performance parameters to&lt;/p&gt;

&lt;p&gt;predict the endpoint ‘bacterial mutagenicity’ were calculated for a battery of common&lt;/p&gt;

&lt;p&gt;(Q)SAR tools, namely Toxtree, Derek Nexus, VEGA Consensus and Sarah Nexus. Printed&lt;/p&gt;

&lt;p&gt;paper and board food contact material (FCM) constituents were chosen as study substances&lt;/p&gt;

&lt;p&gt;since many of these lack experimental data, making them an interesting group for in silico&lt;/p&gt;

&lt;p&gt;screening. Accuracy, sensitivity, specificity, positive predictivity, negative predictivity and&lt;/p&gt;

&lt;p&gt;Matthews correlation coefficient for the individual models and for the combination of VEGA&lt;/p&gt;

&lt;p&gt;Consensus and Sarah Nexus were determined and compared. Our results demonstrate that&lt;/p&gt;

&lt;p&gt;performance varies among the four models, but can be increased by applying a combination&lt;/p&gt;

&lt;p&gt;strategy. Furthermore, the importance of the applicability domain is illustrated. Limited&lt;/p&gt;

&lt;p&gt;performance to predict the mutagenic potential of substances that are new to the model (i.e.&lt;/p&gt;

&lt;p&gt;not included in the training set) is reported. In this context, the generally poor sensitivity for&lt;/p&gt;

&lt;p&gt;these new substances is also addressed.&lt;/p&gt;
</style></abstract><issue><style face="normal" font="default" size="100%">2</style></issue></record></records></xml>