데이터셋

개인회원 공개

ArkDTA 정식 코드

  • 생성일 2023-06-30
  • DOI 10.1093
  • 분야 Other
  • 요약 Motivation Protein–ligand binding affinity prediction is a central task in drug design and development. Cross-modal attention mechanism has recently become a core component of many deep learning models due to its potential to improve model explainability. Non-covalent interactions (NCIs), one of the most critical domain knowledge in binding affinity prediction task, should be incorporated into protein–ligand attention mechanism for more explainable deep drug–target interaction models. We propose ArkDTA, a novel deep neural architecture for explainable binding affinity prediction guided by NCIs. Results Experimental results show that ArkDTA achieves predictive performance comparable to current state-of-the-art models while significantly improving model explainability. Qualitative investigation into our novel attention mechanism reveals that ArkDTA can identify potential regions for NCIs between candidate drug compounds and target proteins, as well as guiding internal operations of the model in a more interpretable and domain-aware manner.
최준석 김모건 백승흔 박주언 이채은



1. 코드 소개
 Drug-Target Interaction (DTI) 예측력 향상 및 약물 주요 반응 부위 예측을 위해 PDBBind 데이터셋의 non-covalent interaction (NCI) 정보를 이용하는 ARK-MAB 모듈이 핵심.

화합물 subset fingerprint 와 단백질 ESM2 임베딩을 활용하며, attention 을 활용하여 약물 주요 반응 부분을 시각화할 수 있음.

2. 레퍼런스 및 출판된 논문 정보:

https://academic.oup.com/bioinformatics/article/39/Supplement_1/i448/7210465


3. Citation 방법: 

Gim, M., Choe, J., Baek, S., Park, J., Lee, C., Ju, M., ... & Kang, J. (2023). ArkDTA: attention regularization guided by non-covalent interactions for explainable drug–target binding affinity prediction. Bioinformatics, 39(Supplement_1), i448-i457.


4. 추가설명 : 

공식 깃헙 링크: https://github.com/dmis-lab/ArkDTA

 

미리보기
File Name Preview Download
ArkDTA.zip
연관성과※ [NTIS] 성과를 클릭하면 NTIS 홈페이지로 이동합니다.
  • 조회수 267
  • 다운로드 수 0
  • 관심수 1