Improving Chemical Autoencoder Latent Space and Molecular De novo Generation Diversity with Heteroencoders

TL;DR

This paper demonstrates that using heteroencoders with SMILES enumeration significantly improves the chemical relevance and molecular similarity in the latent space of autoencoders, enhancing de novo molecule generation.

Contribution

It introduces a sequence-to-sequence heteroencoder approach with SMILES enumeration that outperforms traditional autoencoders in capturing molecular similarity and relevance.

Findings

Heteroencoder latent space correlates better with molecular similarity.

SMILES enumeration improves chemical relevance of latent vectors.

Increased decoding errors with enumeration can be mitigated with complex architectures.

Abstract

Chemical autoencoders are attractive models as they combine chemical space navigation with possibilities for de-novo molecule generation in areas of interest. This enables them to produce focused chemical libraries around a single lead compound for employment early in a drug discovery project. Here it is shown that the choice of chemical representation, such as SMILES strings, has a large influence on the properties of the latent space. It is further explored to what extent translating between different chemical representations influences the latent space similarity to the SMILES strings or circular fingerprints. By employing SMILES enumeration for either the encoder or decoder, it is found that the decoder has the largest influence on the properties of the latent space. Training a sequence to sequence heteroencoder based on recurrent neural networks(RNNs) with long short-term memory cells (LSTM) to predict different enumerated SMILES strings from the same canonical SMILES string gives the largest similarity between latent space distance and molecular similarity measured as circular fingerprints similarity. Using the output from the bottleneck in QSAR modelling of five molecular datasets shows that heteroencoder derived vectors markedly outperforms autoencoder derived vectors as well as models built using ECFP4 fingerprints, underlining the increased chemical relevance of the latent space. However, the use of enumeration during training of the decoder leads to a markedly increase in the rate of decoding to a different molecules than encoded, a tendency that can be counteracted with more complex network architectures.