서브메뉴
검색
Density-Enriched Representation of Molecules: QTAIM Graphs for Molecular Property Prediction
Density-Enriched Representation of Molecules: QTAIM Graphs for Molecular Property Prediction
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105645
- ISBN
- 9798270213282
- DDC
- 540
- 서명/저자
- Density-Enriched Representation of Molecules: QTAIM Graphs for Molecular Property Prediction
- 발행사항
- [Sl] : University of California, Los Angeles, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 134 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-06, Section: B.
- 주기사항
- Advisor: Alexandrova, Anastassia N.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Los Angeles, 2025.
- 초록/해제
- 요약Computational chemistry enables the screening of compounds for desirable properties before dedicating resources to synthesize them. Traditionally, these properties have been computed with electronic structure theories such as density functional theory (DFT), yet more recently, machine learning has offered a way to make predictions for new compounds by inferring from identified patterns in chemical data. This chemical information must be specified in some meaningful form in order to achieve effective property prediction. This work presents a graph representation of molecules based upon the Quantum Theory of Atoms in Molecules (QTAIM). Graph neural network regression models employing QTAIM graphs are established to predict various properties for small organic molecules and, more challengingly, transition metal complexes. Enriching QTAIM graphs with details about the molecules' density yields particular improvements in prediction ability for more challenging predictive tasks, reduced training set sizes, and extrapolation beyond training domains.
- 일반주제명
- Chemistry
- 일반주제명
- Physical chemistry
- 일반주제명
- Computational chemistry
- 키워드
- QTAIM graphs
- 기타저자
- University of California, Los Angeles Chemistry 0153
- 기본자료저록
- Dissertations Abstracts International. 87-06B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017360967
■00520260202105645
■006m o d
■007cr#unu||||||||
■020 ▼a9798270213282
■035 ▼a(MiAaPQ)AAI32400152
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a540
■1001 ▼aGee, Winston Charles.
■24510▼aDensity-Enriched Representation of Molecules: QTAIM Graphs for Molecular Property Prediction
■260 ▼a[Sl]▼bUniversity of California, Los Angeles▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a134 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-06, Section: B.
■500 ▼aAdvisor: Alexandrova, Anastassia N.
■5021 ▼aThesis (Ph.D.)--University of California, Los Angeles, 2025.
■520 ▼aComputational chemistry enables the screening of compounds for desirable properties before dedicating resources to synthesize them. Traditionally, these properties have been computed with electronic structure theories such as density functional theory (DFT), yet more recently, machine learning has offered a way to make predictions for new compounds by inferring from identified patterns in chemical data. This chemical information must be specified in some meaningful form in order to achieve effective property prediction. This work presents a graph representation of molecules based upon the Quantum Theory of Atoms in Molecules (QTAIM). Graph neural network regression models employing QTAIM graphs are established to predict various properties for small organic molecules and, more challengingly, transition metal complexes. Enriching QTAIM graphs with details about the molecules' density yields particular improvements in prediction ability for more challenging predictive tasks, reduced training set sizes, and extrapolation beyond training domains.
■590 ▼aSchool code: 0031.
■650 4▼aChemistry
■650 4▼aPhysical chemistry
■650 4▼aComputational chemistry
■653 ▼aDensity functional theory
■653 ▼aGraph representation
■653 ▼aQTAIM graphs
■653 ▼aTransition metal complexes
■690 ▼a0485
■690 ▼a0219
■690 ▼a0494
■71020▼aUniversity of California, Los Angeles▼bChemistry 0153.
■7730 ▼tDissertations Abstracts International▼g87-06B.
■790 ▼a0031
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360967▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
