An Architecture of Deep Learning in QSPR Modeling for the Prediction of Critical Properties Using Molecular Signatures


Generally, product design and chemical processes largely depend on the physical properties of the materials. Therefore, understanding the relationship between the physical properties and molecular structures of materials is highly desirable for effective optimization and design of high-performance materials. To this end, several mathematical prediction models which are mostly based on semi-empirical quantitative structure-property relationships (QSPR) have been developed. However, these methods cannot be used to automatically characterize molecular structures with physical properties.

For instance, group contribution methods have been majorly used to predict the physical properties with molecular substructures while the topological indices methods are majorly used to characterize the molecular structures in graph theory. On the other hand, the application of atom signatures together with multiple linear regressions are not preferred owing to the complex encoding and mapping involved.

Interestingly, the present advancement in technology especially in computing and machine learning have attracted interest of researchers. Presently, deep learning of the molecular structures and correlating them with the physical properties have been identified as a promising solution. In particular, artificial neural networks have paved the way for the characterization of the various molecular descriptors with regard to the physical properties. However, numerous challenges such as limited computing abilities, frequent changes in the product design and properties have compromised the quality and feasibility of the modeling approach.

Recently, research has shown the feasibility of deep learning in artificial intelligence for automatically capturing the relevant data from a variety of bigger data. This will enable effective formulation of the models through deep neural networks. However, this will be realized by developing more efficient information carriers like images and graphs for representing the molecular structures during modeling.

To this note, the research group of Dr. Weifeng Shen from Chongqing University in collaboration with Dr. Jingzheng Ren from The Hong Kong Polytechnic University and Dr. Mario Eden from Auburn University develop a deep learning approach to automatically predict the physical properties of the molecular structures. They intended to automatically capture the valuable molecular features of the semi-empirical quantitative structure-property relationships modeling for a wider range of substances. Their research work is currently published in the journal, AIChE Journal.

Briefly, the developed architecture entailed: deep neural network based on the tree-structured long short-term memory network and back-propagation neural network which was also used to depict the molecular structures and correlated properties respectively. Next, data preparations were completed by molecular encoding strategies in conjunction with the embedded algorithms for the generation of vector representations. Lastly, in terms of accuracy, the learned deep neural networks models were compared to the classical group contribution methods.

The authors observed that the developed deep neural network approach was capable of automatically capturing relevant molecular features for the semi-empirical quantitative structure-property relationships modeling from the provided text-type descriptors. For instance, this did not require any form of frequency counts or calculation of the molecular descriptors.

In summary, the research team successfully developed a deep learning architecture for prediction of critical properties based on the molecular signatures. To actualize their study, they build, trained and tested semi-empirical quantitative structure-property relationships models based on the deep neural network approach using critical properties of several compounds. In general, it has been proved the learned deep neural network model is more accurate with the ability to cover a wide range of molecular structures. Altogether, the study will advance the use of deep learning and artificial intelligence for proper understanding of the relationship between the molecular structures and physical properties.

Architecture of Deep Learning in QSPR Modeling for the Prediction of Critical Properties Using Molecular Signatures - Advances in Engineering

About the author

Dr. Weifeng Shen is currently a Professor of Process System Engineering at Chongqing University. He obtained his PhD in 2012 at University of Toulouse, France. He worked as a Research Associate at Clarkson University, USA, from 2012 to 2015. He was selected as the “Young Top-Notch Talents “, the “High Level Talents” in Chongqing Province and the “Hundred Young Talents” of Chongqing University. He has published more than 40 papers in Peer-Reviewed Journals including AIChE Journal.

His research interests include Artificial intelligence based green chemical products and sustainable processes developments; Conceptual design, process intensification, AI based optimization and control of chemical processes.

About the author

Dr. Jingzheng Ren is currently an Assistant Professor of Process System Engineering at The Hong Kong Polytechnic University. Based on his academic performances he was interviewed by the most read newspaper in Denmark, Jyllands-Posten, and was also featured in the Ny Viden (New Science) magazine. For his excellence in energy research, he is recurrently invited to give lectures in many countries, i.e. Japan, Italy, China, Greece, Switzerland, Finland, and Sweden, etc..


About the author

Dr. Mario Eden is the Department Chair and Joe T. & Billie Carole McMillan Professor in the Department of Chemical Engineering at Auburn University. His main areas of expertise include process design, integration and optimization, as well as molecular synthesis and product design.

His group focuses on the development of systematic methodologies for process and product synthesis, design, integration, and optimization. Dr. Eden’s research has generated 3 edited books, 145 refereed papers/book chapters and resulted in more than 400 presentations at national/international meetings, including 68 invited lectures and seminars.

About the author

Yang Su is currently a PhD candidate supervised by Professor Weifeng Shen. He received his M.E. degree at Chongqing University and received his B.S degree from Zhejiang University of Technology. He has worked as the vice director of the R&D department in the supplier of large-scale industrial convertors from 2008 to 2011. He served as a process engineer in a petrochemical engineering company from 2013-2016.

His research interests are focused on computer-aided molecular design, quantitative structure-property relationships, machine learning, and multi-objective optimization.

About the author

Dr. Saimeng Jin currently works as a lecturer at the School of Chemistry and Chemical Engineering, Chongqing University. He received his PhD degree in chemistry from the University of York (United Kingdom, with Professor James Clark) in 2017 and his BSc degree from the Sichuan University (China, with Professor Bi Shi) in 2010. His research interests include computer-aided molecular design of green solvents, dimethyl carbonate chemistry, quantum chemistry, chemical engineering.



Su, Y., Wang, Z., Jin, S., Shen, W., Ren, J., & Eden, M. (2019). An Architecture of Deep Learning in QSPR Modeling for the Prediction of Critical Properties Using Molecular Signatures. AIChE Journal.

Go To AIChE Journal

Check Also

Advancing Discovery and Growth of Crystalline Materials using Continuous-Flow, Well-Mixed Microfluidic Devices - Advances in Engineering

Advancing Discovery and Growth of Crystalline Materials using Continuous-Flow, Well-Mixed Microfluidic Devices