Generative Recurrent Networks for De Novo Drug Design

By Anvita Gupta, Alex T. Müller, Berend J. H. Huisman, Jens A Fuchs, Petra Schneider, Gisbert Schneider. Molecular Informatics, 2017

453 citations recorded by the source corpus.

Generative artificial intelligence models present a fresh approach to chemogenomics and de novo drug design, as they provide researchers with the ability to narrow down their search of the chemical space and focus on regions of interest. We present a method for molecular de novo design that utilizes generative recurrent neural networks (RNN) containing long short‐term memory (LSTM) cells. This computational model captured the syntax of molecular representation in terms of SMILES strings with close to perfect accuracy. The learned pattern probabilities can be used for de novo SMILES generation. This molecular design concept eliminates the need for virtual compound library enumeration. By employing transfer learning, we fine‐tuned the RNN′s predictions for specific molecular targets. This approach enables virtual compound design without requiring secondary or external activity prediction, which could introduce error or unwanted bias. The results obtained advocate this generative RNN‐LSTM system for high‐impact use cases, such as low‐data drug discovery, fragment based molecular design, and hit‐to‐lead optimization for diverse drug targets.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/517a488f06577401422cf7e03647ac6148ef4e44

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Molecular Biology

Citations in the corpus

In silico generation of novel, drug-like chemical matter using the LSTM neural network (2017, methodology): “[14] presented an application of recurrent networks for de novo drug design and fragmentbased drug discovery.”
Molecular generative model based on conditional variational autoencoder for de novo molecular design (2018, background): “[18] applied transfer learning to molecular design for certain biological activities.”
Combining generative artificial intelligence and on-chip synthesis for de novo drug design (2020, methodology): “LSTM models were used for the design of new molecules represented as simplified molecular input line entry systems (SMILES) (35) strings (20, 21, 36).”
All SMILES Variational Autoencoder (2019, methodology): “Recurrent neural networks have also been trained to model SMILES strings directly, and tuned with transfer learning, without an explicit latent space or encoder [18, 58].”
Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns (2019, methodology): “…have involved a variety of systems including drugs (Griﬀen et al., 2018), polymers (Li et al., 2018a), polypeptides (Grisoni et al., 2018; Müller et al., 2018), energetic materials (Elton et al., 2018), metal organic frameworks (He et al., 2018; Jørgensen et al., 2018a; Shen et al.,…”
Likelihood Ratios for Out-of-Distribution Detection (2019, background): “…one of the popular choices for generating images (Oord et al., 2016; Van den Oord et al., 2016; Salimans et al., 2017) and sequence data such as genomics (Zou et al., 2018; Killoran et al., 2017) and drug molecules (Olive-crona et al., 2017; Gupta et al., 2018), and text (Jozefowicz et al., 2016).”