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.
Libraries
Use these libraries to find Molecular Property Prediction models and implementationsDatasets
Subtasks
Most implemented papers
Path-Augmented Graph Transformer Network
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
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
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
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
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
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
This paper introduces the N-gram graph, a simple unsupervised representation for molecules.