Fig. 1 Illustration of the pipelines proposed for the derivation of structural alerts using categorical (a) and continuous (b) data.
During the last decades, diverse algorithms have been proposed for the automatic derivation of structural alerts from categorical toxicity data sets.
The derivation of structural alerts from dichotomous bioactivity data follows the work by Ahlberg et al. [13].
An open source implementation of two methodologies for the automatic derivation of structural alerts from bioactivity data sets is presented.
Finally the experimental and computational results allow the derivation of structural and notch Woehler S N curves.
Overall, bioalerts constitutes an open source python library for the derivation of structural alerts from categorical and continuous data sets using two methodologies that have been previously validated.
The derivation of structural alerts, i.e. chemical fragments associated to a toxicological response prior or after being metabolized (bioactivation), is an area of intense development in toxicology.
Ahlberg and coworkers showed that their pipeline leads to comparable results to both manual derivation of structural alerts and a clique-based method, namely PAFI [17].
The module calculate_p_values from the class bioalerts.Alerts.CalculatePvaluesContinuous permits the derivation of structural alerts from data sets reporting continuous compound activity values, e.g. (hbox {pIC}_{50}).
This allows a specific derivation of structural shape as pertaining to one particular register variety; and the register varieties, systematically related to each other, represent a register family.
