6 citations · 8 across the 7 of their papers we have counts for
8 papers · 1 filter
PairIT: Autoregressive Transformers for Low-Data Molecule Optimization
Hannah Lawrence, Bodhi P. Vani, Ji Won Park +5
Generating novel molecules with desired properties is a central challenge in drug discovery. Although foundational work focused on de novo generation, practical use cases require a…
Training Dynamics of Learning 3D-Rotational Equivariance
Max W. Shen, Ewa Nowara, Michael Maser +1
While data augmentation is widely used to train symmetry-agnostic models, it remains unclear how quickly and effectively they learn to respect symmetries. We investigate this by de…
Do we need equivariant models for molecule generation?
Ewa M. Nowara, Joshua Rackers, Patricia Suriana +4
Deep generative models are increasingly used for molecular discovery, with most recent approaches relying on equivariant graph neural networks (GNNs) under the assumption that expl…
NEBULA: Neural Empirical Bayes Under Latent Representations for Efficient and Controllable Design of Molecular Libraries
Ewa M. Nowara, Pedro O. Pinheiro, Sai Pooja Mahajan +4
We present NEBULA, the first latent 3D generative model for scalable generation of large molecular libraries around a seed compound of interest. Such libraries are crucial for scie…
MoleCLUEs: Molecular Conformers Maximally In-Distribution for Predictive Models
Michael Maser, Natasa Tagasovska, Jae Hyeon Lee +1
Structure-based molecular ML (SBML) models can be highly sensitive to input geometries and give predictions with large variance. We present an approach to mitigate the challenge of…
3D molecule generation by denoising voxel grids
Pedro O. Pinheiro, Joshua Rackers, Joseph Kleinhenz +6
We propose a new score-based approach to generate 3D molecules represented as atomic densities on regular grids. First, we train a denoising neural network that learns to map from…
BOtied: Multi-objective Bayesian optimization with tied multivariate ranks
Ji Won Park, Nataša Tagasovska, Michael Maser +2
Many scientific and industrial applications require the joint optimization of multiple, potentially competing objectives. Multi-objective Bayesian optimization (MOBO) is a sample-e…
SupSiam: Non-contrastive Auxiliary Loss for Learning from Molecular Conformers
Michael Maser, Ji Won Park, Joshua Yao-Yu Lin +3
We investigate Siamese networks for learning related embeddings for augmented samples of molecular conformers. We find that a non-contrastive (positive-pair only) auxiliary task ai…