Molecular graph
A molecular graph is a graph representation of a molecule in which atoms are nodes and chemical bonds are edges.
Build AI Drug Discovery Pipelines
A molecular graph represents a molecule as a graph whose nodes are atoms and whose edges are chemical bonds.
- How it is used
- Provides structured molecular input for graph neural networks in drug–target affinity prediction.
- How deep it goes
- Explains connectivity, graph storage, features, and SMILES conversion through an implementation with directed edges and self-loops.
- Examples
- Uses water to illustrate nodes and bonds, and aspirin to compare graph representations and reconstruct connectivity from SMILES.
- What you can do after
- Apply it via RDKit to convert SMILES into atom features and an edge representation for a graph neural network.
Read how Build AI Drug Discovery Pipelines explains molecular graph →
Graph Neural Networks in Action
A molecular graph is a graph representation in which atoms are nodes and chemical bonds are edges.
- How it is used
- Uses atom-and-bond graphs to prepare small-molecule data for property prediction and graph-based molecule generation.
- How deep it goes
- Builds graphs from SMILES through node and edge features, then reconstructs adjacency and feature matrices during model training.
- Examples
- Uses ZINC molecules, QED values, atomic-number features, bond-type encodings, and generated small-molecule graphs.
- What you can do after
- Build it from scratch by converting SMILES into graph objects for PyTorch Geometric workflows.
Read how Graph Neural Networks in Action explains molecular graph →
Also covered in
What to know first
- graph neural networkA graph neural network is a neural-network model that learns representations or predictions from graph-structured data by combining information from connected entities.
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- moleculeA molecule is a discrete chemical entity consisting of two or more atoms held together by chemical bonds.
Related concepts
- graph neural networkused by · A graph neural network is a neural-network model that learns representations or predictions from graph-structured data by combining information from connected entities.
- SMILESalternative to · SMILES is a textual notation standard that encodes molecular atoms, bonds, and connectivity using defined symbols and grammar rules.
- graphkind of · A graph is a mathematical structure consisting of vertices and edges that connect pairs of vertices to represent relationships or connections.
- RDKitproduced by · RDKit is an open-source cheminformatics toolkit for representing, manipulating, analyzing, transforming, and visualizing chemical structures.
- language modeluses · A language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
Questions about molecular graph
What is molecular graph?
A molecular graph is a graph representation of a molecule in which atoms are nodes and chemical bonds are edges.
Which Manning books explain molecular graph?
Build AI Drug Discovery Pipelines and Graph Neural Networks in Action.
What should I know before learning molecular graph?
Manning books that teach molecular graph usually introduce graph neural network, language model and molecule first.
What is the difference between molecular graph and SMILES?
A molecular graph is a graph representation of a molecule in which atoms are nodes and chemical bonds are edges. SMILES is a textual notation standard that encodes molecular atoms, bonds, and connectivity using defined symbols and grammar rules.
What is molecular graph a kind of?
Molecular graph is a kind of graph. A graph is a mathematical structure consisting of vertices and edges that connect pairs of vertices to represent relationships or connections.
What are the parts of molecular graph?
Molecular graph includes hydrogen atom.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

