Multitask Deep Neural Networks for Ames Mutagenicity Prediction.

Journal: Journal of chemical information and modeling
PMID:

Abstract

The Ames mutagenicity test constitutes the most frequently used assay to estimate the mutagenic potential of drug candidates. While this test employs experimental results using various strains of , the vast majority of the published in silico models for predicting mutagenicity do not take into account the test results of the individual experiments conducted for each strain. Instead, such QSAR models are generally trained employing overall labels (i.e., and ). Recently, neural-based models combined with multitask learning strategies have yielded interesting results in different domains, given their capabilities to model multitarget functions. In this scenario, we propose a novel neural-based QSAR model to predict mutagenicity that leverages experimental results from different strains involved in the Ames test by means of a multitask learning approach. To the best of our knowledge, the modeling strategy hereby proposed has not been applied to model Ames mutagenicity previously. The results yielded by our model surpass those obtained by single-task modeling strategies, such as models that predict the overall Ames label or ensemble models built from individual strains. For reproducibility and accessibility purposes, all source code and datasets used in our experiments are publicly available.

Authors

  • María Jimena Martínez
    Instituto de Ciencias e Ingeniería de la Computación (UNS-CONICET), Departamento de Ciencias e Ingeniería de la Computación, Universidad Nacional del Sur (UNS), CP 8000, Bahía Blanca, Argentina.
  • María Virginia Sabando
    Institute for Computer Science and Engineering, UNS-CONICET, 8000, Bahía Blanca, Argentina.
  • Axel J Soto
    National Centre for Text Mining, School of Computer Science, University of Manchester, Manchester M1 7DN, UK.
  • Carlos Roca
    Centro de Investigaciones Biológicas, Consejo Superior de Investigaciones Científicas (CSIC), Ramiro de Maeztu 9, 28040, Madrid, Spain.
  • Carlos Requena-Triguero
    Centro de Investigaciones Biológicas, Consejo Superior de Investigaciones Científicas (CSIC), Ramiro de Maeztu 9, 28040, Madrid, Spain.
  • Nuria E Campillo
    Centro de Investigaciones Biológicas Margarita Salas (CIB Margarita Salas-CSIC). C/Ramiro de Maeztu, 9, 28040 Madrid, Spain.
  • Juan A Páez
    Instituto de Química Médica (IQM-CSIC). C/Juan de la Cierva, 3, 28006 Madrid, Spain.
  • Ignacio Ponzoni
    Instituto de Ciencias e Ingeniería de la Computación (ICIC), Universidad Nacional del Sur-CONICET, San Andrés 800 - Campus Palihue, 8000, Bahía Blanca, Argentina. ip@cs.uns.edu.ar.