The Maximum Unbiased Validation (MUV) dataset is a benchmark dataset selected from PubChem BioAssay. It was created by applying a refined nearest-neighbor analysis. The MUV dataset is specifically designed for the validation of virtual screening techniques.
Variants: MUV
This dataset is used in 3 benchmarks:
Task | Model | Paper | Date |
---|---|---|---|
Molecular Property Prediction | S-CGIB | Pre-training Graph Neural Networks on … | 2025-02-20 |
Graph Classification | G-Tuning | Fine-tuning Graph Neural Networks by … | 2023-12-21 |
Graph Classification | GTOT-Tuning | Fine-Tuning Graph Neural Networks via … | 2022-03-20 |
Drug Discovery | ContextPred | Strategies for Pre-training Graph Neural … | 2019-05-29 |
Drug Discovery | RNN-DFS | Relational Pooling for Graph Representations | 2019-03-06 |
Drug Discovery | GraphConv + dummy super node | Learning Graph-Level Representation for Drug … | 2017-09-12 |
Molecular Property Prediction | IterRefLSTM | Low Data Drug Discovery with … | 2016-11-10 |
Drug Discovery | GraphConv | Convolutional Networks on Graphs for … | 2015-09-30 |
Recent papers with results on this dataset: