Molecule
A molecule is a discrete chemical entity consisting of two or more atoms held together by chemical bonds.
Build AI Drug Discovery Pipelines
A molecule is an electrically neutral group of atoms held together by chemical bonds.
- How it is used
- Frames molecules as concrete chemical inputs for machine-learning workflows in drug discovery.
- How deep it goes
- Explains molecular bonding and introduces SMILES and graphs, while stopping short of detailed graph-construction methods.
- Examples
- Uses ethane, carbon dioxide, hydrogen cyanide, triethylamine, acetic acid, cyclohexane, and benzene as SMILES examples.
- What you can do after
- Evaluate/understand molecular structure as SMILES strings or graphs suitable for later machine-learning workflows.
Read how Build AI Drug Discovery Pipelines explains molecule →
Sutskever's List
A molecule is a chemically bonded group of atoms that forms a discrete unit of a substance.
- How it is used
- Uses molecules as graph inputs for supervised prediction of molecular-level properties.
- How deep it goes
- Traces iterative node updates through pooled graph readout and identifies the challenge of propagating distant information.
- Examples
- Uses atom-to-neighbor note sharing as an analogy and names energy, dipole, and gap as prediction targets.
- What you can do after
- Understand how atom-level message passing supports molecular property prediction and why distant information can be difficult to propagate.
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.
Related concepts
- RDKitused by · RDKit is an open-source cheminformatics toolkit for representing, manipulating, analyzing, transforming, and visualizing chemical structures.
- generative modelingproduced by · Generative modeling is a machine-learning approach that learns patterns or a data distribution to generate new samples resembling the data.
- graphuses · A graph is a mathematical structure consisting of vertices and edges that connect pairs of vertices to represent relationships or connections.
- graph autoencoderproduced by · A graph autoencoder is a graph neural network encoder-decoder model that learns latent graph representations and reconstructs graph-related inputs or structure.
- variational autoencoderproduced by · A variational autoencoder is a generative neural network that learns a probabilistic latent representation of data and decodes samples from it to reconstruct or generate data.
Questions about molecule
What is molecule?
A molecule is a discrete chemical entity consisting of two or more atoms held together by chemical bonds.
Which Manning books explain molecule?
Build AI Drug Discovery Pipelines and Sutskever's List.
What should I know before learning molecule?
Manning books that teach molecule usually introduce graph neural network first.
What is molecule part of?
Molecule is part of ZINC. ZINC is a database of chemical compounds with molecular representations and properties used for virtual screening, computational chemistry, and drug-discovery research.
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.

