태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
This task evaluates the ability of generative models to sample valid and realistic molecular structures.
The training dataset can be:
Following prior work (Hoogeboom et al., 2022), we generally sample 10,000 molecules and compute validity, uniqueness and Posebusters sanity checks (Buttenschoen et al., 2024) for molecules. Data is generally split following prior work (Hoogeboom et al., 2022, Vignac et al., 2023) to ensure fair comparisons.
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
QM9 provides quantum chemical properties (at DFT level) for a relevant, consistent, and comprehensive chemical space of small organic molecules. This database may serve the benchmarking of existing methods, development of new methods, such as hybrid quantum mechanics/machine learning, and systematic identification of structure-property relationships. Source: QM9 Dataset Image Source: https://pubs.acs.org/doi/pdf/10.1021/ci300415d
GEOM-DRUGS is a dataset of 430,000 large organic molecules of up to 180 atoms from Axelrod and Gómez-Bombarelli, Nature Scientific Data, 2022. The dataset used by most machine learning papers is a processed version from: link or link. The original, unprocessed dataset is available: link.
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.