# Fileset

[[Vol. 45]Artificial Intelligence Learns to Predict Photo-Functional Molecules_ WPI-MANA.pdf](https://mdr.nims.go.jp/filesets/31e2fcdc-2638-44ee-aaab-ff7e7bd9b559/download)

## Creator

International Center for Materials Nanoarchitectonics (WPI-MANA)

## Rights

In Copyright[In Copyright](http://rightsstatements.org/vocab/InC/1.0/)

## Other metadata

[[Research Highlights Vol.45] Artificial Intelligence Learns to Predict Photo-Functional Molecules](https://mdr.nims.go.jp/datasets/425b8a45-2e53-463b-9ef0-075ce62e1cdb)

## Fulltext

2022/04/04 9:59 Artificial Intelligence Learns to Predict Photo-Functional Molecules| MANAhttps://www.nims.go.jp/mana/research/highlights/vol45.html 1/2Previous  Index  NextResearch Highlights[Vol. 45]Artificial Intelligence Learns to Predict Photo-Functional Molecules20 Dec, 2018Artificial intelligence can be used to design new molecules; it is becoming a popular tool because ofits potential for discovering molecules in unexplored chemical spaces, its ability to screen a hugenumber of potential molecules in a short amount of time and its tendency to find unconventionalways of solving problems. However, whether such molecules can be actually synthesized andwhether they display the desired functionalities in the real world is an open question.Ryo Tamura, Shinsuke Ishihara at WPI-MANA and colleagues at different institutions in Japanreport in ACS Central Science a proof-of-concept study in which they use a platform based onartificial intelligence to discover photo-functional organic molecules (which are relevant in greenchemistry and molecular sensing) that can be synthesized and that have specific functionalproperties. The platform combines a molecule generator powered by artificial intelligence and acalculator based on density functional theory that performs quantum chemical calculations. Thegenerator suggests molecules with different structures, the calculator predicts their properties. Asa result, this platform can design new molecules with desired properties.The system was initially configured to propose molecules with first excited states at five differentwavelengths, and it was trained on a database containing 13,000 molecules. After ten days ofoperation, the algorithm suggested 3,200 different molecules, 86 of which had the first excitedlevel close to one of the desired energies. Six of these molecules were selected for real worldsynthesis. The selection was done based on two criteria: the existence of at least one knownsynthetic route to produce them and the transition from the ground state to the first excited statebeing energetically possible. Five of the six molecules displayed in spectroscopic measurements ahttps://www.nims.go.jp/mana/research/highlights/vol44.htmlhttps://www.nims.go.jp/mana/research/highlights/index.htmlhttps://www.nims.go.jp/mana/research/highlights/vol46.html2022/04/04 9:59 Artificial Intelligence Learns to Predict Photo-Functional Molecules| MANAhttps://www.nims.go.jp/mana/research/highlights/vol45.html 2/2first excited state at the desired energy; the other molecule perhaps underwent a decompositionprocess and did thus not work as predicted.Normally, to tweak the absorption properties of a molecule chemists alter the structure to modifytransitions from the π to the π* orbitals, but, surprisingly, the system mostly suggested moleculesin which the relevant transition happens from the non-bonding n orbital to the π* orbital. “Thisillustrates AI-chemistry’s ability to not only accelerate discovery, but also shed light on hiddenpaths of possible research,” comment the authors. Because the system relies on propertyprediction by density functional theory, it inherits the drawbacks of this method, in particular thetendency of underestimating the excitation energy. Thus, there is still work to do, but the potentialis high for a transformative tool in chemistry.Reference"Hunting for Organic Molecules with Artificial Intelligence: Molecules Optimized for DesiredExcitation Energies"Masato Sumita, Xiufeng Yang, Shinsuke Ishihara, Ryo Tamura, and Koji TsudaJournal : ACS Cent. Sci. 4, 1126−1133 (2018).DOI : 10.1021/acscentsci.8b00213AffiliationsInternational Center for Materials Nanoarchitectonics (WPI-MANA), National Institute for MaterialsScience (NIMS), Namiki 1-1, Tsukuba, Ibaraki 305-0044, JapanContact informationInternational Center for Materials Nanoarchitectonics(WPI-MANA)National Institute for Materials Science1-1 Namiki, Tsukuba, Ibaraki 305-0044 JapanPhone: +81-29-860-4710E-mail: mana-pr[AT]ml.nims.go.jphttps://samurai.nims.go.jp/profiles/ishihara_shinsuke?locale=enhttps://samurai.nims.go.jp/profiles/tamura_ryo?locale=enhttps://pubs.acs.org/doi/10.1021/acscentsci.8b00213