Papers › An adaptive graph learning method for automated molecular interactions and properties...

An adaptive graph learning method for automated molecular interactions and properties predictions

23 Jun 2022Nature Machine Intelligence 2022 6archive 2025-07-28

Yuquan Li, Chang-Yu Hsieh, Ruiqiang Lu, Xiaoqing Gong, Xiaorui Wang, Pengyong Li, Shuo Liu, Yanan Tian, Dejun Jiang, Jiaxian Yan, Qifeng Bai, Huanxiang Liu, Shengyu Zhang, Xiaojun Yao

Improving drug discovery efficiency is a core and long-standing challenge in drug discovery. For this purpose, many graph learning methods have been developed to search potential drug candidates with fast speed and low cost. In fact, the pursuit of high prediction performance on a limited number of datasets has crystallized their architectures and hyperparameters, making them lose advantage in repurposing to new data generated in drug discovery. Here we propose a flexible method that can adapt to any dataset and make accurate predictions. The proposed method employs an adaptive pipeline to learn from a dataset and output a predictor. Without any manual intervention, the method achieves far better prediction performance on all tested datasets than traditional methods, which are based on hand-designed neural architectures and other fixed items. In addition, we found that the proposed method is more robust than traditional methods and can provide meaningful interpretability. Given the above, the proposed method can serve as a reliable method to predict molecular interactions and properties with high adaptability, performance, robustness and interpretability. This work takes a solid step forward to the purpose of aiding researchers to design better drugs with high efficiency.

PaperPDFCode

Code

yvquanli/GLAM officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Drug DiscoveryGraph LearningGraph Representation LearningMolecular Property Prediction

Datasets

Introduced by this paper, per the archive.

ESOL (Estimated SOLubility)LIT-PCBA(ALDH1)LIT-PCBA(ESR1_ant)LIT-PCBA(MAPK1)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Drug Discovery BACE (β-secretase enzyme) GLAM AUC 0.888 #1 of 1 Archive leaderboard report
Drug Discovery BBBP (Blood-Brain Barrier Penetration) GLAM AUC 0.932 #1 of 1 Archive leaderboard report
Drug Discovery BindingDB GLAM AUC 0.954 #2 of 4 Archive leaderboard report
Drug Discovery ESOL (Estimated SOLubility) GLAM RMSE 0.592 #1 of 1 Archive leaderboard report
Drug Discovery FreeSolv (Free Solvation) GLAM RMSE 1.319 #1 of 1 Archive leaderboard report
Drug Discovery LIT-PCBA(ALDH1) GLAM AUC 0.761 #2 of 4 Archive leaderboard report
Drug Discovery LIT-PCBA(ESR1_ant) GLAM AUC 0.666 #1 of 3 Archive leaderboard report
Drug Discovery LIT-PCBA(KAT2A) GLAM AUC 0.709 #2 of 4 Archive leaderboard report
Drug Discovery LIT-PCBA(MAPK1) GLAM AUC 0.730 #2 of 4 Archive leaderboard report
Drug Discovery Lipophilicity (logd74) GLAM RMSE 0.596 #1 of 1 Archive leaderboard report
Drug Discovery ToxCast (Toxicity Forecaster) GLAM AUC 0.744 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: AutoGL

AutoGLSPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections