Publications by authors named "Runwen Wang"

2 Publications

  • Page 1 of 1

Density Prediction Models for Energetic Compounds Merely Using Molecular Topology.

J Chem Inf Model 2021 Apr 12. Epub 2021 Apr 12.

Institute of Chemical Materials, China Academy of Engineering Physics (CAEP), P.O. Box 919-311, Mianyang 621999, Sichuan, China.

Newly developed high-throughput methods for property predictions make the process of materials design faster and more efficient. Density is an important physical property for energetic compounds to assess detonation velocity and detonation pressure, but the time cost of recent density prediction models is still high owing to the time-consuming processes to calculate molecular descriptors. To improve the screening efficiency of potential energetic compounds, new methods for density prediction with more accuracy and less time cost are urgently needed, and a possible solution is to establish direct mappings between the molecular structure and density. We propose three machine learning (ML) models, support vector machine (SVM), random forest (RF), and Graph neural network (GNN), using molecular topology as the only known input. The widely applied quantitative structure-property relationship based on the density functional theory (DFT-QSPR) is adopted as the benchmark to evaluate the accuracies of the models. All these four models are trained and tested by using the same data set enclosing over 2000 reported nitro compounds searched out from the Cambridge Structural Database. The proportions of compounds with prediction error less than 5% are evaluated by using the independent test set, and the values for the models of SVM, RF, DFT-QSPR, and GNN are 48, 63, 85, and 88%, respectively. The results show that, for the models of SVM and RF, fingerprint bit vectors alone are not facilitated to obtain good QSPRs. Mapping between the molecular structure and density can be well established by using GNN and molecular topology, and its accuracy is slightly better than that of the time-consuming DFT-QSPR method. The GNN-based model has higher accuracy and lower computational resource cost than the widely accepted DFT-QSPR model, so it is more suitable for high-throughput screening of energetic compounds.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1021/acs.jcim.0c01393DOI Listing
April 2021

[Expression of HSP70/HSP27 protein in residual lesion after NPC radiotherapy].

Zhong Nan Da Xue Xue Bao Yi Xue Ban 2009 Nov;34(11):1091-5

Department of Radiology, Xiangya Hospital, Central South University, Changsha 410008, China.

Objective: To analyze HSP70/HSP27 protein expression in the nasopharyngeal carcinoma (NPC) primary tissues and the residual lesion, and to explore its predictive value.

Methods: Immunohistochemical experiment was performed to detect the expression of HSP70 and HSP27 in 58 NPC primary tissues: 28 were in the experimental group with the local residual lesion and 30 in the control group without recurring and metastasis within 5 years by conventional radiotherapy.

Results: The positive expression of HSP70 and HSP27 in the experimental group was 92.9%(26/28) and 53.6%(15/28), while that in the control group was 53.3%(16/30) and 53.3%(16/30),respectively. There was significant difference in the 2 groups. The common positive expression of HSP70 and HSP27 between the 2 groups had significant difference, 50.0% (14/28) in the experimental group and 16.7% (5/30) in the control group, respectively. There was no significant difference in the negative ratio of HSP70 and HSP27 common expression between the 2 groups, 3.6% (1/28) in the experimental group and 10.0% (3/30) in the control group, respectively.

Conclusion: HSP70 may have an important role in the radioresistance of NPC, and may predict the residual lesion after radiotherapy.
View Article and Find Full Text PDF

Download full-text PDF

Source
November 2009