ATOM3D: Tasks On Molecules in Three Dimensions

Townshend, Raphael J.L.; Vögele, Martin; Suriana, Patricia; Derry, Alexander; Powers, Alexander K.; Laloudakis, Yianni; Balachandar, Sidhika; Jing, Bowen; Anderson, Brandon; Eismann, Stephan; Kondor, Risi; Altman, Russ B.; Dror, Ron O.

doi:10.48550/arxiv.2012.04035

Cited by 27 publications

(64 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ATOM3D (Townshend et al, 2020) is a collection of eight tasks and datasets for learning on atomic-level 3D molecular structure. These tasks span several classes of molecules (proteins, RNAs, small molecules, and complexes) and problem formulations (regression, classification, and Siamese tasks) encountered in structural biology (Table 1).…”

Section: On 3d Macromolecular Structurementioning

confidence: 99%

“…In PPI, MSP, and RES, we pick out the output embedding of the alpha carbon at the residue of interest (for PPI and RES), or mean pool over all atoms in the resiudue of interest (MSP), rather than mean pool over the entire graph. These conventions are from Townshend et al (2020).…”

Section: On 3d Macromolecular Structurementioning

confidence: 99%

“…Equivariant neural networks (ENNs), operating on point-cloud representations of structures with equivariant (i.e., geometric vector/tensor) features and spherical harmonic convolutions, address these challenges. These networks have shown promising results on small molecule datasets (Thomas et al, 2018;Kondor, 2018;Anderson et al, 2019;Fuchs et al, 2020;Batzner et al, 2021) and recently also in the context of learning from macromolecular structure (Eismann et al, 2020a;Townshend et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

“…Here, we present a GNN with equivariant message passing and demonstrate that it achieves strong results across a wide variety of tasks on macromolecular structures. Our architecture extends GVP-GNNs (Jing et al, 2021) and we evaluate its performance on ATOM3D (Townshend et al, 2020), a comprehensive suite of tasks and datasets from structural biology. We also demonstrate that our architecture can leverage transfer learning-i.e., pre-training on a data-rich task to improve performance on a data-poor task.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Equivariant Graph Neural Networks for 3D Macromolecular Structure

Jing,

Eismann,

Soni

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Representing and reasoning about 3D structures of macromolecules is emerging as a distinct challenge in machine learning. Here, we extend recent work on geometric vector perceptrons and apply equivariant graph neural networks to a wide range of tasks from structural biology. Our method outperforms all reference architectures on 4 out of 8 tasks in the ATOM3D benchmark and broadly improves over rotation-invariant graph neural networks. We also demonstrate that transfer learning can improve performance in learning from macromolecular structure.

show abstract

Section: On 3d Macromolecular Structurementioning

confidence: 99%

Section: On 3d Macromolecular Structurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Equivariant Graph Neural Networks for 3D Macromolecular Structure

Jing,

Eismann,

Soni

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Residue Identification (RES) aims to predict the identity of a particular masked amino acid in the protein 3D structure based on its local surrounding structure context (Torng & Altman, 2017). We download 100,000 substructures from the ATOM3D project (Townshend et al, 2020), which are originally derived from 574 proteins from the PDB (Berman et al, 2000). We split the entire dataset into training, validation, and testing datasets with the ratio of 80%, 10%, 10% and make sure there are no two proteins with similar structures in the test and non-test datasets.…”

Section: Residue Identificationmentioning

confidence: 99%

Directed Weight Neural Networks for Protein Structure Representation Learning

Li¹,

Luo²,

Deng³

et al. 2022

Preprint

View full text Add to dashboard Cite

A protein performs biological functions by folding to a particular 3D structure. To accurately model the protein structures, both the overall geometric topology and local fine-grained relations between amino acids (e.g. side-chain torsion angles and inter-amino-acid orientations) should be carefully considered. In this work, we propose the Directed Weight Neural Network for better capturing geometric relations among different amino acids. Extending a single weight from a scalar to a 3D directed vector, our new framework supports a rich set of geometric operations on both classical and SO(3)-representation features, on top of which we construct a perceptron unit for processing amino-acid information. In addition, we introduce an equivariant message passing paradigm on proteins for plugging the directed weight perceptrons into existing Graph Neural Networks, showing superior versatility in maintaining SO(3)-equivariance at the global scale. Experiments show that our network has remarkably better expressiveness in representing geometric relations in comparison to classical neural networks and the (globally) equivariant networks. It also achieves state-of-the-art performance on various computational biology applications related to protein 3D structures. All codes and models will be published upon acceptance.

show abstract

Pre‐Training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug Binding

Jin

Jiang³

et al. 2022

Advanced Science

View full text Add to dashboard Cite

The latest biological findings observe that the motionless “lock‐and‐key” theory is not generally applicable and that changes in atomic sites and binding pose can provide important information for understanding drug binding. However, the computational expenditure limits the growth of protein trajectory‐related studies, thus hindering the possibility of supervised learning. A spatial‐temporal pre‐training method based on the modified equivariant graph matching networks, dubbed ProtMD which has two specially designed self‐supervised learning tasks: atom‐level prompt‐based denoising generative task and conformation‐level snapshot ordering task to seize the flexibility information inside molecular dynamics (MD) trajectories with very fine temporal resolutions is presented. The ProtMD can grant the encoder network the capacity to capture the time‐dependent geometric mobility of conformations along MD trajectories. Two downstream tasks are chosen to verify the effectiveness of ProtMD through linear detection and task‐specific fine‐tuning. A huge improvement from current state‐of‐the‐art methods, with a decrease of 4.3% in root mean square error for the binding affinity problem and an average increase of 13.8% in the area under receiver operating characteristic curve and the area under the precision‐recall curve for the ligand efficacy problem is observed. The results demonstrate a strong correlation between the magnitude of conformation's motion in the 3D space and the strength with which the ligand binds with its receptor.

show abstract

ATOM3D: Tasks On Molecules in Three Dimensions

Cited by 27 publications

References 43 publications

Equivariant Graph Neural Networks for 3D Macromolecular Structure

Equivariant Graph Neural Networks for 3D Macromolecular Structure

Directed Weight Neural Networks for Protein Structure Representation Learning

Pre‐Training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug Binding

Contact Info

Product

Resources

About