Poster Presentation SETAC Asia-Pacific Virtual Conference 2022

Multi-Task Neural Network Models for Simultaneous Prediction of Bioaccumulation Parameters 搜索 复制 (#210)

Shuying Zhang 1 2 , Rui Ding 1 , Zhiqiang Fu 1 , Jingwen Chen 1
  1. Dalian University of Technology, Dalian, China
  2. Guangzhou Institute of Geochemistry, Chinese Academy of Sciences, Guangzhou, China

Bioaccumulation parameters of chemicals were necessary data for chemical risk assessment and management.1,2In silico methods, e.g., quantitative structure-activity relationship (QSAR) models can be valid alternatives to costly data measurement.3 In this study, QSAR models for simultaneously predicting bioconcentration factor (BCF) and biomagnification factor (BMF) values of chemicals in fish were constructed by using Dragon descriptors and 12 molecule fingerprints, as well as artificial neural network (ANN) algorithm. Single-task (ST) neural network models based on the backpropagation were established to predict BCF and BMF values, respectively. Appropriate descriptors were screened in the ST models for the development of multi-task (MT) learning with single-input-multiple-output (SIMO-MT) models and multi-input-multiple-output (MIMO-MT) models. Results showed that BCF and BMF values can be simultaneously predicted by MT models. The prediction performance of MT models was generally better than that of ST models, indicating that shared and generalized features can be learned from BCF and BMF, and jointly improve the predictive performance. Compared with SIMO-MT models, better predictive ability was observed in the MIMO-MT model. It can be inferred that the simultaneous input of multiple molecular fingerprints/descriptors can provide more learnable information, which further improves the performance of the MIMO-MT model. The application domain of the MIMO-MT model was characterized based on Tanimoto similarity of molecules, and setting an appropriate application domain range can improve the performance of QSAR models. With MT learning strategies and the case studies, better understanding of practical use of ANN in risk assessment and management of chemicals were provided, and the models developed in the present study can be valuable tools to predict the bioaccumulation parameters.

搜索

复制

  1. Arnot, J. A.; Gobas, F. A. P. C. A review of bioconcentration factor (BCF) and bioaccumulation factor (BAF) assessments for organic chemicals in aquatic organisms. Environmental Reviews 2006, 14, 257-297.
  2. Arnot, J. A.; Quinn, C. L. Development and evaluation of a database of dietary bioaccumulation test data for organic chemicals in fish. Environ. Sci. Technol. 2015, 49, 4783-4396.
  3. Nendza, M.; Kuhne, R.; Lombardo, A.; Strempel, S.; Schuurmann, G. PBT assessment under REACH: Screening for low aquatic bioaccumulation with QSAR classifications based on physicochemical properties to replace BCF in vivo testing on fish. Sci. Total Environ. 2018, 616-617, 97-106.