Drug Discovery
377 papers with code • 28 benchmarks • 25 datasets
Drug discovery is the task of applying machine learning to discover new candidate drugs.
( Image credit: A Turing Test for Molecular Generators )
Benchmarks
These leaderboards are used to track progress in Drug Discovery
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Drug Discovery models and implementationsDatasets
QM9
Tox21
BACE (β-secretase enzyme)
SIDER
QED
BindingDB
Most implemented papers
ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity?
mostafachatillon/ChemGAN-challenge
•
•
In this paper, we quantify this internal chemical diversity, and we raise the following challenge: can a nontrivial AI model reproduce natural chemical diversity for desired molecules?
CheMixNet: Mixed DNN Architectures for Predicting Chemical Properties using Multiple Molecular Representations
SMILES is a linear representation of chemical structures which encodes the connection table, and the stereochemistry of a molecule as a line of text with a grammar structure denoting atoms, bonds, rings and chains, and this information can be used to predict chemical properties.
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models
Generative models are becoming a tool of choice for exploring the molecular space.
Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
materialsvirtuallab/megnet
•
•
Chem. Mater. 2018
Similarly, we show that MEGNet models trained on $\sim 60, 000$ crystals in the Materials Project substantially outperform prior ML models in the prediction of the formation energies, band gaps and elastic moduli of crystals, achieving better than DFT accuracy over a much larger data set.
End-to-End Differentiable Molecular Mechanics Force Field Construction
Trained with arbitrary loss functions, it can construct entirely new force fields self-consistently applicable to both biopolymers and small molecules directly from quantum chemical calculations, with superior fidelity than traditional atom or parameter typing schemes.
Recursive Tree Grammar Autoencoders
bpaassen/rtgae
•
•
Machine learning on trees has been mostly focused on trees as input to algorithms.
Learning to Extend Molecular Scaffolds with Structural Motifs
microsoft/molecule-generation
•
•
ICLR 2022
Recent advancements in deep learning-based modeling of molecules promise to accelerate in silico drug discovery.
Molecule Generation by Principal Subgraph Mining and Assembling
thunlp-mt/ps-vae
•
•
Molecule generation is central to a variety of applications.
DebiasedDTA: A Framework for Improving the Generalizability of Drug-Target Affinity Prediction Models
boun-tabi/debiaseddta-reproduce
•
•
Here, we present DebiasedDTA, a novel drug-target affinity (DTA) prediction model training framework that addresses dataset biases to improve the generalizability of affinity prediction models.
Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
lfhase/ciga
•
•
Despite recent success in using the invariance principle for out-of-distribution (OOD) generalization on Euclidean data (e. g., images), studies on graph data are still limited.
