A multi-task deep learning neural network for predicting flammability-related properties from molecular structures

Ao Yang, Yang Su, Zihao Wang, Saimeng Jin, Jingzheng Ren, Xiangping Zhang, Weifeng Shen, James Hanley Clark

Research output: Contribution to journalArticlepeer-review


It is significant that hazardous properties of chemicals including replacements for banned or restricted products are assessed at an early stage of product and process design. This work proposes a new strategy of modeling quantitate structure–property relationships based on multi-task deep learning for simultaneously predicting four flammability-related properties including lower and upper flammable limits, auto-ignition point temperature and flash point temperature. A multi-task deep neural network (MDNN) has been developed to extract molecular features automatically and correlate multiple properties integrating a Tree-LSTM neural network with multiple feedforward neural networks. Molecular features are encoded in molecular tree graphs, calculated and extracted without manual actions of the user or preliminary molecular descriptor calculation. Two methods, joint training and alternative training, were both employed to train the proposed MDNN, which could capture the relevant information and commonality among multiple target properties. The outlier detection and determination of applicability domain were also introduced into the evaluation of deep learning models. Since the proposed MDNN utilized data more efficiently, the finally obtained model performs better than the multi-task partial least squares model on predicting the flammability-related properties. The proposed framework of multi-task deep learning provides a promising tool to predict multiple properties without calculating descriptors.
Original languageEnglish
Pages (from-to)4451-4465
Number of pages15
JournalGreen Chemistry
Early online date19 May 2021
Publication statusE-pub ahead of print - 19 May 2021

Bibliographical note

© The Royal Society of Chemistry 2021. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

Cite this