Property Prediction
225 papers with code • 0 benchmarks • 0 datasets
Property prediction involves forecasting or estimating a molecule's inherent physical and chemical properties based on information derived from its structural characteristics. It facilitates high-throughput evaluation of an extensive array of molecular properties, enabling the virtual screening of compounds. Additionally, it provides the means to predict the unknown attributes of new molecules, thereby bolstering research efficiency and reducing development times.
Benchmarks
These leaderboards are used to track progress in Property Prediction
Libraries
Use these libraries to find Property Prediction models and implementationsMost implemented papers
Neural Message Passing for Quantum Chemistry
brain-research/mpnn
•
•
ICML 2017
Supervised learning on molecules has incredible potential to be useful in chemistry, drug discovery, and materials science.
Strategies for Pre-training Graph Neural Networks
snap-stanford/pretrain-gnns
•
•
ICLR 2020
Many applications of machine learning require a model to make accurate pre-dictions on test examples that are distributionally different from training ones, while task-specific labels are scarce during training.
Object-Centric Learning with Slot Attention
google-research/google-research
•
•
NeurIPS 2020
Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features.
Molecule Attention Transformer
gmum/MAT
•
•
Designing a single neural network architecture that performs competitively across a range of molecule property prediction tasks remains largely an open challenge, and its solution may unlock a widespread use of deep learning in the drug discovery industry.
InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
fanyun-sun/InfoGraph
•
•
ICLR 2020
There are also some recent methods based on language models (e. g. graph2vec) but they tend to only consider certain substructures (e. g. subtrees) as graph representatives.
Conditional molecular design with deep generative models
nyu-dl/conditional-molecular-design-ssvae
•
•
Although machine learning has been successfully used to propose novel molecules that satisfy desired properties, it is still challenging to explore a large chemical space efficiently.
Analyzing Learned Molecular Representations for Property Prediction
In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets.
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language
bingsu12/momu
•
•
Although artificial intelligence (AI) has made significant progress in understanding molecules in a wide range of fields, existing models generally acquire the single cognitive ability from the single molecular modality.
MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure Prediction
Predicting protein properties such as solvent accessibility and secondary structure from its primary amino acid sequence is an important task in bioinformatics.
DeeperGCN: All You Need to Train Deeper GCNs
dmlc/dgl
•
•
Graph Convolutional Networks (GCNs) have been drawing significant attention with the power of representation learning on graphs.
