---
title: 'PIGNet: Physics-Informed Graph Neural Network'
url: https://www.emergentmind.com/topics/pignet
type: topic
---

# PIGNet: Physics-Informed Graph Neural Network

PIGNet is a physics-informed deep learning model that advances the prediction of drug-target interactions (DTIs) by integrating explicit physical modeling of atom-atom interactions within a graph neural network (GNN) architecture. The model directly sums neural-parameterized, physics-based pairwise interactions to predict the binding affinity of protein–ligand complexes, achieving both state-of-the-art accuracy and interpretability. PIGNet was validated on the CASF-2016 benchmark, demonstrating superior docking and screening performance relative to established methods [2008.12249].

## 1. Architecture and Structural Representation

PIGNet operates on static 3D protein–ligand complex structures, typically obtained from the Protein Data Bank (PDB) or molecular docking procedures. The model constructs a graph representation as follows:

- **Nodes:** All heavy-atom centers within the protein pocket (within 5 Å of any ligand atom) and all ligand atoms.
- **Node features:** One-hot encoding for atom type (C, N, O, S, etc.), formal charge, hybridization, and aromaticity.
- **Edges:** Two parallel adjacency matrices are defined:
  - \(A^{\mathrm{cov}}\): Intra-molecular covalent bonds.
  - \(A^{\mathrm{inter}}\): Intermolecular “neighbor” connections between atoms across the protein–ligand interface, restricted to pairs with \(d_{ij} < 8\) Å.
- **Backbone:** The architecture alternates Gated Graph Attention (GAT) layers—propagating information via \(A^{\mathrm{cov}}\)—with Interaction Network layers that incorporate intermolecular context via \(A^{\mathrm{inter}}\). Typically, \(L=3\)–5 such blocks are stacked, yielding final node embeddings \(h_i \in \mathbb{R}^d\) (with \(d \approx 128\)).

Atom-atom energy terms are then computed for every protein-ligand atom pair, with outputs from learned MLPs parameterizing physical interaction equations.

## 2. Physics-Informed Energy Decomposition

PIGNet explicitly models the total predicted binding free energy as:
\[
E^{\mathrm{total}} = \frac{1}{T^{\mathrm{rotor}}} \left[ E^{\mathrm{vdw}} + E^{\mathrm{hbond}} + E^{\mathrm{metal}} + E^{\mathrm{hydrophobic}} \right]
\]
- **Rotational Entropy Loss (Rotor Penalty):** 
  \[
  T^{\mathrm{rotor}} = 1 + C_{\mathrm{rotor}} \times N_{\mathrm{rotor}}
  \]
  where \(N_{\mathrm{rotor}}\) is the number of rotatable ligand bonds and \(C_{\mathrm{rotor}}\) is a learnable parameter.
- **Interaction Potentials:**
  - **Van der Waals:** Parametrized 12–6 Lennard–Jones:
    \[
    E^{\mathrm{vdw}} = \sum_{i \in \mathrm{prot}} \sum_{j \in \mathrm{lig}} c_{ij}^{(\mathrm{vdw})} \left[ \left( \frac{d'_{ij}}{d_{ij}} \right)^{12} - 2 \left( \frac{d'_{ij}}{d_{ij}} \right)^6 \right]
    \]
    with \(d'_{ij} = r_i + r_j + c_{ij}^{(r)}\), using van der Waals radii and an MLP-learned correction \(c_{ij}^{(r)}\).
  - **Hydrogen bond, metal-ligand, and hydrophobic contributions:** Each is evaluated using a learnable “square-well” formulation:
    \[
    e_{ij} =
    \begin{cases}
      w_{ij} & \Delta_{ij} < c_1 \\
      w_{ij} \frac{\Delta_{ij} - c_2}{c_1 - c_2} & c_1 < \Delta_{ij} < c_2 \\
      0 & \Delta_{ij} > c_2
    \end{cases}
    \]
    Parameters (\(w_{ij}\), \(c_1\), \(c_2\)) and term type (hydrogen bond, hydrophobic, metal) are determined via MLPs applied to \((h_i, h_j)\).

All four energy components are summed over all protein–ligand atomic pairs.

## 3. Deep Architecture and Learning Workflow

- **Gated Graph Attention (GAT) blocks:** Use self-attention mechanisms over bonded neighbors. Each block incorporates a highway-style gate (small GRU) to control information flow.
- **Interaction Network blocks:** Combine linear embeddings for sender/receiver atoms, aggregate via max-pooling over neighbors, and return messages to nodes through a gating mechanism.
- **Physics MLP Heads:** Each energy term’s coefficient is independently predicted by dedicated MLP heads, typically 2–3 layers, using ReLU activation, and width commensurate with embedding dimensionality.
- **Final prediction:** The total affinity for the complex is computed by summing the physics-informed pairwise terms and adjusting for rotational entropy.

## 4. Training Objectives and Data Augmentation

PIGNet employs a composite loss constructed to encourage both absolute binding affinity accuracy and robust ranking across native, decoy, and random complexes. Three key data augmentation strategies are used, with ~1.65 million complexes in total:
- **Docking augmentation:** For each ≈2,600 experimental PDBbind-refined complex, ~100 decoy structures are generated and used with a pairwise margin loss ensuring \(E(\mathrm{decoy}) > E(\mathrm{native}) + 1.0\,\mathrm{kcal/mol}\).
- **Random–screening augmentation:** ~0.8 million random small molecules from the IBS library are docked per target; constraints enforce that most non-binders have binding free energy \(\Delta G > -6.8\) kcal/mol.
- **Cross-screening augmentation:** Ligands are docked with random proteins to create non-binding pairs and trained with similar loss constraints.

Native complexes are trained by regression to experimental affinities, while decoys/non-binders are enforced to score less favorably via margin and hinge losses.

## 5. Benchmark Performance and Comparative Assessment

PIGNet’s effectiveness was assessed on the CASF-2016 benchmark with two principal tasks:
- **Docking power:** Top-1 accuracy for correctly identifying the native binding pose among ~200 decoys.
- **Screening power:** Enrichment factor (EF) at the top 1% of scored ligands, and hit rate for identifying true binders among ~5,000 decoys.

Key outcomes from Table 1, [2008.12249]:

| Model                      | Docking SR (Top 1) | Screening EF (1%) | Screening SR (1%) |
|----------------------------|--------------------|-------------------|-------------------|
| AutoDock Vina              | 84.6%              | 7.7               | 29.8%             |
| 3D-GNN baseline            | 66.6%              | 10.2              | 28.5%             |
| PIGNet (single model)      | 85.8%              | 18.5              | 50.0%             |
| PIGNet (ensemble, MCDO×30) | 87.0%              | 19.6              | 55.4%             |

PIGNet's ensemble achieves 87.0% top-1 docking success, outperforming Vina, and a screening hit rate (55.4%) and enrichment factor (19.6) that are approximately double previous best methods.

## 6. Interpretability and Insight via Atom-Pair Decomposition

A defining feature of PIGNet is explicit atom-pair attribution. The net energy contribution of any ligand substructure \(M\) is given by:
\[
\Delta G_M = \frac{ \sum_{i \in \mathrm{prot}} \sum_{j \in M} \left[ E^{\mathrm{vdw}}_{ij} + e^{\mathrm{hbond}}_{ij} + e^{\mathrm{metal}}_{ij} + e^{\mathrm{hydrophobic}}_{ij} \right] } { T^{\mathrm{rotor}} }
\]
This permits direct visualization (e.g., heat maps) of which moieties are energetically favorable or unfavorable within the protein context. The model has demonstrated instance-specific interpretability, capturing energetically meaningful responses to substructural modifications, such as an R-group switch between cyclohexyl and tetramethylcyclohexyl in PTPN1 and PAF-AH case studies.

The learned MLPs also adjust van der Waals radii corrections \(c_{ij}^{(r)}\) in a chemically realistic manner, distinguishing between, for example, sp²–sp² and sp³–sp³ C–C pairs.

## 7. Context, Impact, and Relevance

PIGNet establishes a methodological framework bridging graph neural networks and physics-based modeling for drug discovery, combining interpretable additive energy decomposition with high-throughput computational scalability. The model’s explicit pairwise structure links predictive outcomes to underlying chemical interactions, affording detailed rationalization that is amenable to medicinal chemistry optimization. The data-driven parameterization within a physically-motivated framework directly addresses the generalization failures of black-box DNN screening functions, setting a new benchmark for DTI prediction in a highly competitive environment [2008.12249].

Source: https://www.emergentmind.com/topics/pignet