abs

학술발표회초록보기

Inquiry on Abstract abstract@kcsnet.or.kr

Inquiry on Payment member@kcsnet.or.kr

현재 가능한 작업은 아래와 같습니다.
  • 03월 02일 17시 이후 : 초록수정 불가능, 일정확인 및 검색만 가능

129th General Meeting of Korean Chemical Society & Exposition Exploring extensive chemical space by fragment-based molecular generative model to design de novo TADF emitter

Submission Date :
2 / 28 / 2022 , 16 : 43 : 03
Abstract Number :
129022828528
Presenting Type:
Poster Presentation
Presenting Area :
Physical Chemistry
Authors :
Jun Hyeong Kim, Woo youn Kim1,*
Department of Chemistry, Korea Advanced Institute of Science and Technology, Korea
1Department of Chemistry, KAIST, Korea
Assigned Code :
PHYS.P-220 Assigend Code Guideline
Presenting Time :
April 14 (THU) 11:00~13:00
Thermally activated delayed fluorescence (TADF) emitter is one of the promising organic light-emitting diodes. Various design approaches have been proposed, but conventional design methods rely on human experience and prior design knowledge, resulting in a few fragments and combinatorial rules. Likewise, high-throughput virtual screening can overcome previous limitations of adopting a large library but still suffers from practical issues such as high computational cost. Here, we propose an efficient data-driven approach to search expanded chemical space for novel TADF emitter discovery using the fragment-based molecular generative model. The generative model-based TADF emitter design approach is unnecessary to predefine constraints such as donors, acceptors, and combinational rules; therefore, it can search extensive chemical space. Also, it is efficient because conditional generation produces molecules with the desired properties, resulting in a more focused set of molecules. We show novel TADF emitter candidates can be generated based on the proposed workflow.