Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

noise annotations

Noise annotations refer to metadata or markers within a dataset that characterize, quantify, or identify the presence, level, or source of error and uncertainty associated with target labels and experimental measurements. In machine learning and scientific data curation, real-world data frequently contain measurement inaccuracies, assay variability, or human labeling discrepancies rather than perfect ground truth. Noise annotations document these imperfections systematically, allowing researchers to gauge data reliability, benchmark algorithm robustness against corrupted or inconsistent targets, and develop learning methods capable of generalizing effectively despite varying degrees of label noise.

1 item

DrugOOD: Out-of-Distribution Dataset Curator and Benchmark for AI-Aided Drug Discovery - a Focus on Affinity Prediction Problems with Noise Annotations

DrugOOD: Out-of-Distribution Dataset Curator and Benchmark for AI-Aided Drug Discovery - a Focus on Affinity Prediction Problems with Noise Annotations

Yuanfeng Ji, Lu Zhang, Jiaxiang Wu, Bingzhe Wu, Lanqing Li, Long-Kai Huang, Tingyang Xu, Yu Rong, Jie Ren, Ding Xue, Houtim Lai, Wei Liu, Junzhou Huang, Shuigeng Zhou, Ping Luo, Peilin Zhao, Yatao Bian

OrganizationsFudan UniversityTencentUniversity of Hong Kong

Why you should read this

Presents DrugOOD, an automated dataset generation pipeline and evaluation suite that enables researchers to build customized drug-target binding affinity benchmarks with realistic label noise and domain shifts to test the out-of-distribution generalization of graph neural networks.

AI-aided drug discovery (AIDD) is gaining popularity due to its potential to make the search for new pharmaceuticals faster, less expensive, and more effective. Despite its extensive use in numerous fields (e.g., ADMET prediction, virtual screening), little research has been conducted on the out-of-distribution (OOD) learning problem with noise. We present DrugOOD, a systematic OOD dataset curator and benchmark for AIDD. Particularly, we focus on the drug-target binding affinity prediction problem, which involves both macromolecule (protein target) and small-molecule (drug compound). DrugOOD offers an automated dataset curator with user-friendly customization scripts, rich domain annotations aligned with biochemistry knowledge, realistic noise level annotations, and rigorous benchmarking of SOTA OOD algorithms, as opposed to only providing fixed datasets. Since the molecular data is often modeled as irregular graphs using graph neural network (GNN) backbones, DrugOOD also serves as a valuable testbed for graph OOD learning problems. Extensive empirical studies have revealed a significant performance gap between in-distribution and out-of-distribution experiments, emphasizing the need for the development of more effective schemes that permit OOD generalization under noise for AIDD.

Added

2026-09-26