Evaluation of QSAR models for predicting mutagenicity: outcome of the Second Ames/QSAR international challenge project

A. Furuhama, Atsushi Kitazawa, Jiahao Yao, Carlos Santos, James F. Rathman, Chihae Yang, J.v. Ribeiro, Kevin P. Cross, Glenn J. Myatt, Giuseppa Raitano, Emilio Benfenati, Nina Jeliazkova, Roustem Saiakhov, Suman Chakravarti, Robert S. Foster, Cecilia Bossa, Chiara Laura Battistelli, Romualdo Benigni, Takahisa Sawada, Hiroaki Wasada, Takuya Hashimoto, Menghua Wu, Regina Barzilay, Pankaj Daga, Robert D. Clark, Jordi Mestres, A. Montero, E. Gregori-Puigjané, P. Petkov, H. Ivanova, Ovanes Mekenyan, Slade Matthews, Davy Guan, J. Spicer, Raymond Lui, Yoshihiro Uesawa, Kazuhiro Kurosaki, Yasunari Matsuzaka, S. Sasaki, M Cronin, Samuel J. Belfield, James W. Firman, Nicoleta Sp̂înu, Meikang Qiu, Joseph M. Keca, G. Gini, T. Li, Weida Tong, Huixiao Hong, Zhihong Liu, Yoshinobu Igarashi, Hiroshi Yamada, Kei‐ichi Sugiyama, Masamitsu HonmaFigshare 2023 · DOI · OpenAlex

Abstract

Quantitative structure−activity relationship (QSAR) models are powerful in silico tools for predicting the mutagenicity of unstable compounds, impurities and metabolites that are difficult to examine using the Ames test. Ideally, Ames/QSAR models for regulatory use should demonstrate high sensitivity, low false-negative rate and wide coverage of chemical space. To promote superior model development, the Division of Genetics and Mutagenesis, National Institute of Health Sciences, Japan (DGM/NIHS), conducted the Second Ames/QSAR International Challenge Project (2020–2022) as a successor to the First Project (2014–2017), with 21 teams from 11 countries participating. The DGM/NIHS provided a curated training dataset of approximately 12,000 chemicals and a trial dataset of approximately 1,600 chemicals, and each participating team predicted the Ames mutagenicity of each trial chemical using various Ames/QSAR models. The DGM/NIHS then provided the Ames test results for trial chemicals to assist in model improvement. Although overall model performance on the Second Project was not superior to that on the First, models from the eight teams participating in both projects achieved higher sensitivity than models from teams participating in only the Second Project. Thus, these evaluations have facilitated the development of QSAR models.
BibTeX
@inproceedings{furuhama2023evaluation,
  author = {A. Furuhama and Atsushi Kitazawa and Jiahao Yao and Carlos Santos and James F. Rathman and Chihae Yang and J.V. Ribeiro and Kevin P. Cross and Glenn J. Myatt and Giuseppa Raitano and Emilio Benfenati and Nina Jeliazkova and Roustem Saiakhov and Suman Chakravarti and Robert S. Foster and Cecilia Bossa and Chiara Laura Battistelli and Romualdo Benigni and Takahisa Sawada and Hiroaki Wasada and Takuya Hashimoto and Menghua Wu and Regina Barzilay and Pankaj Daga and Robert D. Clark and Jordi Mestres and A. Montero and E. Gregori-Puigjané and P. Petkov and H. Ivanova and Ovanes Mekenyan and Slade Matthews and Davy Guan and J. Spicer and Raymond Lui and Yoshihiro Uesawa and Kazuhiro Kurosaki and Yasunari Matsuzaka and S. Sasaki and M Cronin and Samuel J. Belfield and James W. Firman and Nicoleta Sp̂înu and Meikang Qiu and Joseph M. Keca and G. Gini and T. Li and Weida Tong and Huixiao Hong and Zhihong Liu and Yoshinobu Igarashi and Hiroshi Yamada and Kei‐ichi Sugiyama and Masamitsu Honma},
  title = {{Evaluation of QSAR models for predicting mutagenicity: outcome of the Second Ames/QSAR international challenge project}},
  booktitle = {Figshare},
  year = {2023},
  doi = {10.6084/m9.figshare.24720632},
}

Loading related content...

Figure