Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks

In de novo drug design, computational strategies are used to generate novel molecules with good affinity to the desired biological target. In this work, we show that recurrent neural networks can be trained as generative models for molecular structures, similar to statistical language models in natural language processing. We demonstrate that the properties of the generated molecules correlate very well with the properties of the molecules used to train the model. In order to enrich libraries with molecules active toward a given biological target, we propose to fine-tune the model with small sets of molecules, which are known to be active against that target. Against Staphylococcus aureus, the model reproduced 14% of 6051 hold-out test molecules that medicinal chemists designed, whereas against Plasmodium falciparum (Malaria), it reproduced 28% of 1240 test molecules. When coupled with a scoring function, our model can perform the complete de novo drug design cycle to generate large sets of novel molecules for drug discovery.

Abstract licence: CC BY

• A review of large language models and autonomous agents in chemistry · 2025

• Corrected

  Discovering highly potent antimicrobial peptides with deep generative model HydrAMP · 2023

• Generative Models as an Emerging Paradigm in the Chemical Sciences · 2023

• Leveraging molecular structure and bioactivity with chemical language models for de novo drug design · 2023

• Artificial Intelligence and Machine Learning Technology Driven Modern Drug Discovery and Development · 2023

• Exposing the Limitations of Molecular Machine Learning with Activity Cliffs · 2022

• MSNovelist: de novo structure generation from mass spectra · 2022

• Generating 3D molecules conditional on receptor binding sites with deep generative models · 2022

• Accelerating antibiotic discovery through artificial intelligence · 2021

• High-confidence structural annotation of metabolites absent from spectral libraries · 2021

• Advances in De Novo Drug Design: From Conventional to Machine Learning Methods · 2021

• DEEPScreen: high performance drug–target interaction prediction with convolutional neural networks using 2-D structural compound representations · 2020

• Artificial intelligence and machine learning‐aided drug discovery in central nervous system diseases: State‐of‐the‐arts and future directions · 2020

• De novo generation of hit-like molecules from gene expression signatures using artificial intelligence · 2020

• SMILES-based deep generative scaffold decorator for de-novo drug design · 2020

• Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models · 2020

• Constrained Bayesian optimization for automatic chemical design using variational autoencoders · 2020

• Mol-CycleGAN: a generative model for molecular optimization · 2020

• The Recent Progress and Applications of Digital Technologies in Healthcare: A Review · 2020

• Transformer-CNN: Swiss knife for QSAR modeling and interpretation · 2020

and 16 more

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.