Molecular Bioactivity Prediction of HDAC1: Based on Deep Neural Nets

Miaomiao Chen, Shan Li (), Yu Ding, Hongwei Jin and Jie Xia
Additional contact information
Miaomiao Chen: Nanjing University of Aeronautics and Astronautics
Shan Li: Nanjing University of Aeronautics and Astronautics
Yu Ding: Nanjing University of Aeronautics and Astronautics
Hongwei Jin: Peking University
Jie Xia: Institute of Materia Medica, Chinese Academy of Medical Sciences and Peking Union Medical College

A chapter in AI and Analytics for Public Health, 2022, pp 229-240 from Springer

Abstract: Abstract With the important impact on the research and treatment of tumors and cardiovascular diseases, histone deacetylases1 (HDAC1) has been a hot target recently. In this work, we extracted three kinds of relevant features (molecular descriptors, MACCS and ESTATE fingerprints) from the simplified molecular input line entry specification (SMILES) of HDAC1 molecules, and then established separate predicting models based on deep neural networks. All of the models performed well in predicting the activity of the test set. But with regard to 7 modeling metrics, we found that, in the overall predictive performance and the ability to identify inactive molecules, the model trained with MACCS fingerprints had obvious advantages (the AUC value is up to 0.9). As for the identification of active molecules, the model trained with molecular descriptors performed best. The results provide a reference for feature selection when constructing quantitative structure-activity relationships (QSAR) of inhibitor drugs like HDAC1 based on DNNs.

Keywords: QSAR; HDAC1; DNNs; Bioactivity prediction; Feature selection introduction (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:prbchp:978-3-030-75166-1_15

Ordering information: This item can be ordered from
http://www.springer.com/9783030751661

DOI: 10.1007/978-3-030-75166-1_15

Access Statistics for this chapter

More chapters in Springer Proceedings in Business and Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().