Automated generation of molecular derivatives – DerGen software package. (2022)

• Record Type: Journal Article
• Authors: Kichev, Ilia; Borislavov, Lyuben; Tadjer, Alia
• Is Part Of: Materials today. Volume 61:Part 4(2022)
• Page Start: 1287
• Page End: 1291
• Publication Date: 2022
• Subjects: Machine learning -- Dataset generation -- Dataset expansion -- Depth first search; Materials science -- Congresses -- Periodicals; 620.1
• DOI: 10.1016/j.matpr.2022.04.628
• Languages: English
• ISSNs: 2214-7853

Abstract

Abstract: For the needs of machine-learning aided novel materials discovery, large databases containing various compounds and properties need to be constructed. One possible approach is to extract a large number of chemical structures from an existing database. Another approach relies on the generation of diverse positional isomers of a given parent structure by introducing different functional groups and varying their positions. The present work is focused on building a software for automatic generation of all non-redundant positional isomers of a parent structure to build or expand different datasets. An illustrative example is provided. The software package could be found at the repository https://github.com/carim2020/der-gen .