Efficient multi-objective molecular optimization in a continuous latent space

By R. Winter, F. Montanari, Andreas Steffen, H. Briem, Frank No'e, Djork-Arné Clevert. 2019

212 citations recorded by the source corpus.

We utilize Particle Swarm Optimization to optimize molecules in a machine-learned continuous chemical representation with respect to multiple objectives such as biological activity, structural constrains or ADMET properties.

Subfields: Biomedical Engineering, Computational Theory and Mathematics, Control and Systems Engineering

How researchers see this paper

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

In Biomedical Engineering

Jimeng Sun

In Computational Theory and Mathematics

In Control and Systems Engineering

Citations in the corpus

Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties (2020, background): “The discovery of novel molecules has been accelerated by advances in computational quantum chemistry and machine learning assisted exploration of chemical space [1, 2, 3].”
MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design (2022, methodology): “[143] None 2D-Graph VAE GB-GA [112] None 2D-Graph GA GA+D [6] None SELFIES GA EDM [144] None SMILES GA JANUS [145] None SELFIES GA MolDQN [103] None 2D-Graph RL RationaleRL [109] None 2D-Graph RL GCPN [108] None 2D-Graph RL+GAN REINVENT [146] None SMILES RL+AR MCMG [147] None SMILES RL+AR GEGL [ [15”
Generating valid Euclidean distance matrices (2019, background): “the search for new molecular graphs, based on string encodings of that graph structure or other representations [21, 22].”
All SMILES Variational Autoencoder (2019, methodology): “To address this difﬁculty, sequence-to-sequence transcoders [63] have been trained to map between different SMILES strings of a single molecule [5, 67, 68].”