DockedAC: Empowering Deep Learning Models With 3D Protein-ligand Data For Activity Cliff Analysis

Zijing Liu, Xinni Zhang, Yankai Chen, Bin Feng, Mingjun Yang, Zenglin Xu, Yu Li, Irwin King

Keywords: Activity cliff prediction, Molecular property prediction, AI-aided drug discovery

Abstract: Artificial intelligence has become a crucial tool in drug discovery, excelling in tasks such as molecular property prediction. An activity cliff, which refers to a minor structural modification to a molecule resulting in a large change in its biological activity, poses a challenge in predictive modeling. The activity cliff depends on the interaction between the target and the ligand, which is however largely overlooked by previous ligand-centric studies. In this paper, we introduce DockedAC, a new dataset incorporating the protein target and target-ligand 3D complex structure information for studying the problem of activity cliffs. By matching protein binding information and ligand bioactivity, we employ molecular docking to generate the complex structure for each activity value. The DockedAC dataset contains 82,836 activity data on 52 protein targets with activity cliff annotations, which serves as the first step towards activity cliff research with large-scale 3D complex structures. We benchmark the dataset with traditional machine learning and deep learning approaches.

Primary Area: datasets and benchmarks

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6680