Drug discovery is the task of applying machine learning to discover new candidate drugs.
( Image credit: Neural Graph Fingerprints )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Supervised learning on molecules has incredible potential to be useful in chemistry, drug discovery, and materials science.
Ranked #2 on Drug Discovery on QM9
Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases.
Ranked #2 on Graph Classification on IPC-grounded
Generative models are becoming the tools of choice for the discovery of new molecules and materials.
Multi-task learning (MTL) has led to successes in many applications of machine learning, from natural language processing and speech recognition to computer vision and drug discovery.
Finally, since all of the simulation code is written in Python, researchers can have unprecedented flexibility in setting up experiments without having to edit any low-level C++ or CUDA code.
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.
Ranked #2 on Formation Energy on Materials Project
The unique feature of DeepPurpose is that it enables non-computational drug development scientists to identify drug candidates based on five pre-trained DL models with only a few lines of codes.