Molecular Property Prediction
128 papers with code • 18 benchmarks • 19 datasets
Molecular property prediction is the task of predicting the properties of a molecule from its structure.
Benchmarks
These leaderboards are used to track progress in Molecular Property Prediction
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Molecular Property Prediction models and implementationsDatasets
MoleculeNet
QM9
Tox21
QM7
SIDER
Subtasks
Most implemented papers
Path-Augmented Graph Transformer Network
benatorc/PA-Graph-Transformer
•
•
Much of the recent work on learning molecular representations has been based on Graph Convolution Networks (GCN).
Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective
In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction.
Optimal Transport Graph Neural Networks
benatorc/OTGNN
•
•
Current graph neural network (GNN) architectures naively average or sum node embeddings into an aggregated graph representation -- potentially losing structural or semantic information.
Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction
biomed-AI/MolRep
•
•
Advances in machine learning have led to graph neural network-based methods for drug discovery, yielding promising results in molecular design, chemical synthesis planning, and molecular property prediction.
ChemBERTa-2: Towards Chemical Foundation Models
seyonechithrananda/bert-loves-chemistry
•
•
Large pretrained models such as GPT-3 have had tremendous impact on modern natural language processing by leveraging self-supervised learning to learn salient representations that can be used to readily finetune on a wide variety of downstream tasks.
MUBen: Benchmarking the Uncertainty of Molecular Representation Models
Yinghao-Li/UncertaintyBenchmark
•
•
While some studies have included UQ to improve molecular pre-trained models, the process of selecting suitable backbone and UQ methods for reliable molecular uncertainty estimation remains underexplored.
Lo-Hi: Practical ML Drug Discovery Benchmark
We analyzed modern benchmarks and showed that they are unrealistic and overoptimistic.
Can Large Language Models Understand Molecules?
Notably, LLaMA-based SMILES embeddings show results comparable to pre-trained models on SMILES in molecular prediction tasks and outperform the pre-trained models for the DDI prediction tasks.
The Role of Model Architecture and Scale in Predicting Molecular Properties: Insights from Fine-Tuning RoBERTa, BART, and LLaMA
BrightBlueCheese/transformers_and_chemistry
•
•
However, we observed that absolute validation loss is not a definitive indicator of model performance - contradicts previous research - at least for fine-tuning tasks: instead, model size plays a crucial role.
N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
chao1224/n_gram_graph
•
•
NeurIPS 2019
This paper introduces the N-gram graph, a simple unsupervised representation for molecules.
