Predicting Drug-Target Interaction Using a Novel Graph Neural Network with 3D Structure-Embedded Graph Representation

By Jaechang Lim, Seongok Ryu, Kyubyong Park, Yo Joong Choe, Jiyeon Ham, Woo Youn Kim. 2019

366 citations recorded by the source corpus.

We propose a novel deep learning approach for predicting drug-target interaction using a graph neural network. We introduce a distance-aware graph attention algorithm to differentiate various types of intermolecular interactions. Furthermore, we extract the graph feature of intermolecular interactions directly from the 3D structural information on the protein-ligand binding pose. Thus, the model can learn key features for accurate predictions of drug-target interaction rather than just memorize certain patterns of ligand molecules. As a result, our model shows better performance than docking and other deep learning methods for both virtual screening (AUROC of 0.968 for the DUD-E test set) and pose prediction (AUROC of 0.935 for the PDBbind test set). In addition, it can reproduce the natural population distribution of active molecules and inactive molecules.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology, Graph Learning, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Tommi S. Jaakkola
2. Regina Barzilay
3. Octavian-Eugen Ganea
4. Hannes Stärk
5. Fergus Boyles
6. Charlotte M. Deane
7. Lagnajit Pattanaik
8. Dejing Dou

In Materials Chemistry

1. Tommi S. Jaakkola
2. Regina Barzilay
3. Octavian-Eugen Ganea
4. Fergus Boyles
5. Charlotte M. Deane
6. Lagnajit Pattanaik
7. Marc A. Moesser
8. Daisuke Kihara

In Molecular Biology

1. Tommi S. Jaakkola
2. Regina Barzilay
3. Hannes Stärk
4. Fergus Boyles
5. Charlotte M. Deane
6. Lagnajit Pattanaik
7. Dejing Dou
8. Octavian-Eugen Ganea

In Graph Learning

1. Tommi S. Jaakkola
2. Regina Barzilay
3. Charlotte M. Deane
4. Octavian-Eugen Ganea
5. Petar Velickovic
6. Jure Leskovec
7. Matthias Fey

In Computational Chemistry & Drug Discovery

1. Tommi S. Jaakkola
2. Regina Barzilay
3. Hannes Stärk
4. Charlotte M. Deane
5. Octavian-Eugen Ganea
6. Daisuke Kihara
7. Garrett M. Morris

Citations in the corpus

• EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction (2022, methodology): “…as direct binding affinity prediction from the 3D complex (McNutt et al., 2021; Fran-coeur et al., 2020; Ragoza et al., 2017; Wallach et al., 2015; Lim et al., 2019; Morrone et al., 2020; Jiang et al., 2021; Shen et al., 2021; Jastrzebski et al., 2020; Bao et al., 2021; Torng & Altman, 2019a;…”
• Protein Docking Model Evaluation by Graph Neural Networks (2020, methodology): “We used the same features as used in previous works (Lim et al., 2019; Torng and Altman, 2019) as shown in Table 2.”
• Protein-Ligand Interaction Graphs: Learning from Ligand-Shaped 3D Interaction Graphs to Improve Binding Affinity Prediction (2022, background): “New models that try to incorporate structural features into GNNs add protein nodes to the graph ([12, 15]) which changes the shape of the graph and introduces unnecessary complexity of the model.”
• Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity (2021, methodology): “Meanwhile, there are also some efforts to model the 3D-structure of molecule by improving GNNs with spatial information, such as distance [23, 26], angle [17], and 3D coordinate [6].”
• Everything is Connected: Graph Neural Networks (2023, background): “…tasks include predicting links between drugs and diseases—drug repurposing (Morselli Gysi et al., 2021), drugs and targets—binding affinity prediction (Lim et al., 2019; Jiang et al., 2020), or drugs and drugs—predicting adverse side-effects from polypharmacy (Zitnik et al., 2018; Deac et al., 2019).”