MICER: a pre-trained encoder-decoder architecture for molecular image captioning.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: Automatic recognition of chemical structures from molecular images provides an important avenue for the rediscovery of chemicals. Traditional rule-based approaches that rely on expert knowledge and fail to consider all the stylistic variations of molecular images usually suffer from cumbersome recognition processes and low generalization ability. Deep learning-based methods that integrate different image styles and automatically learn valuable features are flexible, but currently under-researched and have limitations, and are therefore not fully exploited.

Authors

  • Jiacai Yi
    School of Computer Science, National University of Defense Technology, Changsha 410073, China.
  • Chengkun Wu
    School of Computer Science, National University of Defense Technology, Changsha, 410073, China. Chenkun_wu@nudt.edu.cn.
  • Xiaochen Zhang
    School of Computer Science, National University of Defense Technology, Changsha 410073, China.
  • Xinyi Xiao
    School of Computer Science, National University of Defense Technology, Changsha 410073, China.
  • Yanlong Qiu
    School of Computer Science, National University of Defense Technology, Changsha 410073, China.
  • Wentao Zhao
    Shanghai New Tobacco Product Research Institute Limited Company, Shanghai 200082, China.
  • Tingjun Hou
    College of Pharmaceutical Sciences, Zhejiang University , Hangzhou, Zhejiang 310058, China.
  • Dongsheng Cao
    School of Pharmaceutical Sciences, Central South University, Changsha, China. oriental-cds@163.com.