liveBook · Manning

BasicAutoencoder

As explained in Build AI Drug Discovery Pipelines

BasicAutoencoder is the book's basic autoencoder architecture for encoding and decoding molecular SMILES.

BasicAutoencoder encodes molecular SMILES into a latent space and decodes them back into molecular strings. Its usefulness depends on both reconstruction fidelity and chemical validity. section 10.2.4

Evaluate reconstruction quality at several levels:

  • Token accuracy reaches 0.994, indicating strong learning of SMILES syntax. section 10.2.4
  • Valid reconstruction rate reaches 88.2% when RDKit successfully parses the reconstructed SMILES, leaving over 10% chemically invalid. section 10.2.4
  • Exact match rate reaches 0.847 on canonical MOSES SMILES; canonicalization matters because equivalent molecules can have different valid strings. section 10.2.4
  • Tanimoto similarity compares non-exact reconstructions using Morgan fingerprints with radius 2 and 2048 bits. section 10.2.4

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Descends from token accuracy to chemical validity, exact canonical-string recovery, and fingerprint similarity without detailing model internals.
Examples
Reports 0.994 token accuracy, 88.2% valid reconstructions, and 0.847 exact canonical matches on MOSES data.
What it assumes
Assumes familiarity with molecular SMILES and introduces token accuracy, chemical validity, canonicalization, and fingerprint similarity through evaluation.
What you can do after
Evaluate reconstruction quality using syntax, chemical validity, canonical exact matches, and fingerprint similarity.
How it connects
Connects SMILES, latent spaces, molecular generation, RDKit, canonicalization, Morgan fingerprints, and Tanimoto similarity.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.