Journal
JOURNAL OF CHEMICAL INFORMATION AND MODELING
Volume 61, Issue 9, Pages 4245-4258Publisher
AMER CHEMICAL SOC
DOI: 10.1021/acs.jcim.1c00803
Keywords
-
Ask authors/readers for more resources
This paper addresses the problem of molecular structure generation by revisiting fragment-based methods and genetic-based methods, defining a set of indices to compare generation methods. These indices provide information on the coverage of data space, the representativeness of data space exploration, and the generation specificity of molecules without the use of a database composed of real chemicals as a reference.
The use of quantitative structure-property relationships (QSPRs) helps in predicting molecular properties for several decades, while the automatic design of new molecular structures is still emerging. The choice of algorithms to generate molecules is not obvious and is related to several factors such as the desired chemical diversity (according to an initial dataset's content) and the level of construction (the use of atoms, fragments, pattern-based methods). In this paper, we address the problem of molecular structure generation by revisiting two approaches: fragment-based methods (FMs) and genetic-based methods (GMs). We define a set of indices to compare generation methods on a specific task. New indices inform about the explored data space (coverage), compare how the data space is explored (representativeness), and quantifies the ratio of molecules satisfying requirements (generation specificity) without the use of a database composed of real chemicals as a reference. These indices were employed to compare generations of molecules fulfilling the desired property criterion, evaluated by QSPR.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available