SOTAVerified

Molecular Property Prediction

Molecular property prediction is the task of predicting the properties of a molecule from its structure.

Papers

Showing 1–10 of 354 papers

TitleStatusHype
Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures—0
Combining Graph Neural Networks and Mixed Integer Linear Programming for Molecular Inference under the Two-Layered Model—0
TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence—0
Descriptor-based Foundation Models for Molecular Property PredictionCode2
Robust Molecular Property Prediction via Densifying Scarce Labeled DataCode0
BioLangFusion: Multimodal Fusion of DNA, mRNA, and Protein Language Models—0
The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine LearningCode0
Graph Neural Networks in Modern AI-aided Drug Discovery—0
Recent Developments in GNNs for Drug Discovery—0
AdaptMol: Adaptive Fusion from Sequence String to Topological Structure for Few-shot Drug Discovery—0
Show:102550
← PrevPage 1 of 36Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DumplingGNNROC-AUC96.4—Unverified
2ChemBFNROC-AUC95.74—Unverified
3MTL-BERTROC-AUC93—Unverified
4XGBoostROC-AUC90.5—Unverified
5SELFormerROC-AUC90.2—Unverified
6STL-BERTROC-AUC89.6—Unverified
7Cano-BERTROC-AUC89.2—Unverified
8AttrMaskingROC-AUC89.2—Unverified
9AttentiveFPROC-AUC85.5—Unverified
10Deep-CBNROC-AUC75.8—Unverified