Earticle

초록

영어

In this study, chemicals with acute toxicity experimental data were selected as research subjects, and compareed the model derived from statistical analysis and QSAR open-source programs. The physical and chemical properties, dynamic behaviors, and toxicological estimates of the chemicals were calculated using Mordred, a molecular descriptor calculation program based on RDKit. LD50 was set as the toxicity comparison target for each chemical, and independent variables or factors with similarity to independent variables were estimated from the molecular descriptors calculated through Mordred. Molecule descriptors composed of independent variables were compared to predictions from QSAR open-source models, A regression model was created with the selected molecule descriptors and compared with predictions from QSAR programs, confirming high accuracy for specific functional groups. The QSAR model created in this study considers the characteristics and experimental values of each chemical, and provides evidence for selecting variables when constructing toxicity data for machine learning applications.

목차

Abstract
1. 서론
2. 연구방법
2.1 연구절차
2.2 유해성 지표 선정
2.3 데이터 세트 설정
2.4 소프트웨어 선정
2.5 분석방법
2.6 회귀모델 성능 검증
3. 연구결과
3.1 변수 간 상관분석 결과
3.2 회귀분석 결과 및 회귀모델 생성
3.3 QSAR 기반 회귀모델 성능 검증
4. 고찰 및 결론
5. References

키워드

저자

• 양유호 [ Yu-Ho Yang | 인하대학교 순환경제환경시스템-환경안전공학전공 ]
• 김홍관 [ Hong-Kwan Kim | 인하대학교 순환경제환경시스템-환경안전공학전공 ]
• 김덕한 [ Duk-Han Kim | 인하대학교 순환경제환경시스템-환경안전공학전공 ]
• 천영우 [ Young-Woo Chon | 인하대학교 순환경제환경시스템-환경안전공학전공 ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  대한안전경영과학회지 [Journal of Korea Safety Management & Science]

• 간기

  계간

• pISSN

  1229-6783

• eISSN

  2288-1484

• 수록기간

  1999~2025

• 십진분류

  KDC 530 DDC 620