Molecular generation targeting desired electronic properties via deep generative models

• Published in: Nanoscale 2020-03, Vol.12 (12), p.6744-6758
• Main Authors: Yuan, Qi, Santana-Bonilla, Alejandro, Zwijnenburg, Martijn A, Jelfs, Kim E
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Construction materials; Dipole moments; Functional materials; Halogenation; Methylation; Molecular orbitals; Neural networks; Oligomers; Photovoltaic cells; Properties (attributes); Recurrent neural networks
• ISSN: 2040-3364; 2040-3372
• DOI: 10.1039/c9nr10687a

As we seek to discover new functional materials, we need ways to explore the vast chemical space of precursor building blocks, not only generating large numbers of possible building blocks to investigate, but trying to find non-obvious options, that we might not suggest by chemical experience alone. Artificial intelligence techniques provide a possible avenue to generate large numbers of organic building blocks for functional materials, and can even do so from very small initial libraries of known building blocks. Specifically, we demonstrate the application of deep recurrent neural networks for the exploration of the chemical space of building blocks for a test case of donor-acceptor oligomers with specific electronic properties. The recurrent neural network learned how to produce novel donor-acceptor oligomers by trading off between selected atomic substitutions, such as halogenation or methylation, and molecular features such as the oligomer's size. The electronic and structural properties of the generated oligomers can be tuned by sampling from different subsets of the training database, which enabled us to enrich the library of donor-acceptors towards desired properties. We generated approximately 1700 new donor-acceptor oligomers with a recurrent neural network tuned to target oligomers with a HOMO-LUMO gap