| Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on Chemical Structure | | 96.4 | DumplingGNN | 2024-09-23 |
| A Bayesian Flow Network Framework for Chemistry Tasks | ✓ Link | 95.74 | ChemBFN | 2024-07-28 |
| Pushing the boundaries of molecular property prediction for drug discovery with multitask learning BERT enhanced by SMILES enumeration | ✓ Link | 93.0 | MTL-BERT | 2022-12-15 |
| Accurate ADMET Prediction with XGBoost | ✓ Link | 90.5 | XGBoost | 2022-04-15 |
| SELFormer: Molecular Representation Learning via SELFIES Language Models | ✓ Link | 90.2 | SELFormer | 2023-04-10 |
| Pushing the boundaries of molecular property prediction for drug discovery with multitask learning BERT enhanced by SMILES enumeration | ✓ Link | 89.6 | STL-BERT | 2022-12-15 |
| Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development | ✓ Link | 89.2 | AttrMasking | 2021-02-18 |
| Pushing the boundaries of molecular property prediction for drug discovery with multitask learning BERT enhanced by SMILES enumeration | ✓ Link | 89.2 | Cano-BERT | 2022-12-15 |
| Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck | ✓ Link | 88.75±0.49 | S-CGIB | 2025-02-20 |
| Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development | ✓ Link | 85.5 | AttentiveFP | 2021-02-18 |
| MolXPT: Wrapping Molecules with Text for Generative Pre-training | ✓ Link | 80.5 ± 0.5 | MolXPT | 2023-05-18 |
| Integrating convolutional layers and biformer network with forward-forward and backpropagation training | ✓ Link | 75.8 | Deep-CBN | 2025-02-28 |
| Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning | ✓ Link | 75.0 | SMA | 2024-02-22 |
| Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model | ✓ Link | 73.3 | SPMM | 2022-11-19 |
| Uni-Mol: A Universal 3D Molecular Representation Learning Framework | ✓ Link | 72.9 | Uni-Mol | 2022-09-08 |
| Galactica: A Large Language Model for Science | ✓ Link | 72.9 | Uni-Mol | 2022-11-16 |
| ChemBERTa-2: Towards Chemical Foundation Models | ✓ Link | 72.8 | ChemBERTa-2 (MTR-77M) | 2022-09-05 |
| ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction | | 72.4 | ChemRL-GEM | 2021-06-11 |
| Analyzing Learned Molecular Representations for Property Prediction | ✓ Link | 71.0 | D-MPNN | 2019-04-02 |
| Self-Supervised Graph Transformer on Large-Scale Molecular Data | ✓ Link | 70.0 | GROVER (base) | 2020-06-18 |
| N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules | ✓ Link | 69.7 | N-GramRF | 2018-06-24 |
| Self-Supervised Graph Transformer on Large-Scale Molecular Data | ✓ Link | 69.5 | GROVER (large) | 2020-06-18 |
| N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules | ✓ Link | 69.1 | N-GramXGB | 2018-06-24 |
| Strategies for Pre-training Graph Neural Networks | ✓ Link | 68.7 | PretrainGNN | 2019-05-29 |
| Galactica: A Large Language Model for Science | ✓ Link | 66.1 | GAL 120B | 2022-11-16 |
| Galactica: A Large Language Model for Science | ✓ Link | 60.4 | GAL 1.3B | 2022-11-16 |
| Galactica: A Large Language Model for Science | ✓ Link | 59.6 | GAL 30B | 2022-11-16 |
| Galactica: A Large Language Model for Science | ✓ Link | 53.5 | GAL 6.7B | 2022-11-16 |
| Galactica: A Large Language Model for Science | ✓ Link | 39.3 | GAL 125M | 2022-11-16 |