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

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.

References in corpus (3)

• The NumPy array: a structure for efficient numerical computation
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Molecular Generation with Recurrent Neural Networks (RNNs)

Cited by in corpus (16)

• Deep learning for molecular design - a review of the state of the art
• Autonomous discovery in the chemical sciences part II: Outlook
• SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery
• Scaffold-based molecular design using graph generative model
• Molecular representation learning with language models and domain-relevant auxiliary tasks
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• Constrained Bayesian Optimization for Automatic Chemical Design
• Difficulty in chirality recognition for Transformer architectures learning chemical structures from string
• All SMILES Variational Autoencoder
• Graph Machine Learning for Design of High-Octane Fuels
• Faster and more diverse de novo molecular optimization with double-loop reinforcement learning using augmented SMILES
• DeepGG: a Deep Graph Generator
• Graph Polish: A Novel Graph Generation Paradigm for Molecular Optimization
• CRNNTL: convolutional recurrent neural network and transfer learning for QSAR modelling
• Augmenting Molecular Images with Vector Representations as a Featurization Technique for Drug Classification
• Generate Novel Molecules With Target Properties Using Conditional Generative Models