Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation
Journal articles

Comparisons of Molecular Structure Generation Methods Based on Fragment Assemblies and Genetic Graphs

Abstract : 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.
Complete list of metadata
Contributor : Catherine Belli Connect in order to contact the contributor
Submitted on : Monday, December 20, 2021 - 6:06:08 PM
Last modification on : Wednesday, December 22, 2021 - 3:31:13 AM


 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2022-08-18

Please log in to resquest access to the document





Philippe Gantzer, Benoit Creton, Carlos Nieto-Draghi. Comparisons of Molecular Structure Generation Methods Based on Fragment Assemblies and Genetic Graphs. Journal of Chemical Information and Modeling, American Chemical Society, 2021, 61 (9), pp.4245-4258. ⟨10.1021/acs.jcim.1c00803⟩. ⟨hal-03498045⟩



Record views