mlsanityData to 14 Oct 2026

Decoding the Protein-ligand Interactions Using Parallel Graph Neural Networks

arXiv 2111.15144 ↗First posted 30 Nov 2021stat.ML cs.LG q-bio.BMcited by 10

Not on the map. Why?

Abstract (arXiv)

Protein-ligand interactions (PLIs) are fundamental to biochemical research and their identification is crucial for estimating biophysical and biochemical properties for rational therapeutic design. Currently, experimental characterization of these properties is the most accurate method, however, this is very time-consuming and labor-intensive. A number of computational methods have been developed in this context but most of the existing PLI prediction heavily depends on 2D protein sequence data. Here, we present a novel parallel graph neural network (GNN) to integrate knowledge representation and reasoning for PLI prediction to perform deep learning guided by expert knowledge and informed by 3D structural data. We develop two distinct GNN architectures, GNNF is the base implementation that employs distinct featurization to enhance domain-awareness, while GNNP is a novel implementation that can predict with no prior knowledge of the intermolecular interactions. The comprehensive evaluation demonstrated that GNN can successfully capture the binary interactions between ligand and proteins 3D structure with 0.979 test accuracy for GNNF and 0.958 for GNNP for predicting activity of a protein-ligand complex. These models are further adapted for regression tasks to predict experimental binding affinities and pIC50 is crucial for drugs potency and efficacy. We achieve a Pearson correlation coefficient of 0.66 and 0.65 on experimental affinity and 0.50 and 0.51 on pIC50 with GNNF and GNNP, respectively, outperforming similar 2D sequence-based models. Our method can serve as an interpretable and explainable artificial intelligence (AI) tool for predicted activity, potency, and biophysical properties of lead candidates. To this end, we show the utility of GNNP on SARS-Cov-2 protein targets by screening a large compound library and comparing our prediction with the experimentally measured data.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 13 of its 55 references that are in the map. First posted on arXiv 30 Nov 2021.

Builds on

13 of 55 references.

References · 13

  1. 2017Graph Attention Networkscited by 8,923
  2. 2015Gated Graph Sequence Neural Networkscited by 796
  3. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  4. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  5. 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
  6. 2020How Neural Networks Extrapolate: From Feedforward to Graph Neural Networkscited by 222
  7. 2018DeepDTA: Deep Drug-Target Binding Affinity Predictioncited by 173
  8. 2016Protein-Ligand Scoring with Convolutional Neural Networkscited by 57
  9. 2018DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networkscited by 52
  10. 2017Development and evaluation of a deep learning model for protein-ligand binding affinity predictioncited by 51
  11. 2015AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discoverycited by 38
  12. 2020Improved Protein-ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inferencecited by 35
1 more
  1. 2016Learning Deep Architectures for Interaction Prediction in Structure-based Virtual Screeningcited by 6

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 5; 2024: 1.

10 papers.

  1. 2024CACTUS: Chemistry Agent Connecting Tool-Usage to Sciencecited by 33
  2. 2022Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applicationscited by 30
  3. 2022Graph Neural Networks for Moleculescited by 21
  4. 2022De novo design of protein target specific scaffold-based Inhibitors via Reinforcement Learningcited by 4
  5. 2023Improved prediction of ligand-protein binding affinities by meta-modelingcited by 3
  6. 2022Dynamic Molecular Graph-based Implementation for Biophysical Properties Predictioncited by 1
  7. 2023Seven open problems in applied combinatoricscited by 1
  8. 2023Graph Representation Learning for Interactive Biomolecule Systemscited by 1
  9. 2023Building explainable graph neural network by sparse learning for the drug-protein binding predictioncited by 0
  10. 2023The logic of rational graph neural networkscited by 0