147 citations · 746 across the 18 of their papers we have counts for
23 papers
Explicit Word Density Estimation for Language Modelling
Jovan Andonov, Octavian Ganea, Paulina Grnarova +2
Language Modelling has been a central part of Natural Language Processing for a very long time and in the past few years LSTM-based language models have been the go-to method for c…
EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction
Hannes Stärk, Octavian-Eugen Ganea, Lagnajit Pattanaik +2
Predicting how a drug-like molecule binds to a specific protein target is a core problem in drug discovery. An extremely fast computational binding method would enable key applicat…
Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking
Octavian-Eugen Ganea, Xinyuan Huang, Charlotte Bunne +4
Protein complex formation is a central problem in biology, being involved in most of the cell's processes, and essential for applications, e.g. drug design or protein engineering.…
Crystal Diffusion Variational Autoencoder for Periodic Material Generation
Tian Xie, Xiang Fu, Octavian-Eugen Ganea +2
Generating the periodic structure of stable materials is a long-standing challenge for the material design community. This task is difficult because stable materials only exist in…
GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles
Octavian-Eugen Ganea, Lagnajit Pattanaik, Connor W. Coley +4
Prediction of a molecule's 3D conformer ensemble from the molecular graph holds a key role in areas of cheminformatics and drug discovery. Existing generative models have several d…
Message Passing Networks for Molecules with Tetrahedral Chirality
Lagnajit Pattanaik, Octavian-Eugen Ganea, Ian Coley +3
Molecules with identical graph connectivity can exhibit different physical and biological properties if they exhibit stereochemistry-a spatial structural characteristic. However, m…