A graph-based genetic algorithm and generative model/Monte Carlo tree search for the exploration of chemical space

By Jan H. Jensen. Chemical Science, 2018

389 citations recorded by the source corpus.

This paper presents a comparison of a graph-based genetic algorithm (GB-GA) and machine learning (ML) results for the optimization of log P values with a constraint for synthetic accessibility and shows that the GA is as good as or better than the ML approaches for this particular property.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Spectroscopy

View Paper: https://www.semanticscholar.org/paper/3744c10a10cb93979fab9e97b2db33db0e839ef1

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 Spectroscopy

Citations in the corpus

Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development (2021, methodology): “2019) (simulated as random sampling), Graph-GA (graph-based genetic algorithm) (Jensen 2019), and ML SOTA methods including stringbased LSTM (Segler et al.”
Machine Learning for Synthetic Data Generation: a Review (2023, neutral): “…molecule distribution, including variational autoencoder (VAE) [21], [76], [77], generative adversarial network (GAN) [78], energy-based model (EBM) [79], [80], diffusion model [81], reinforcement learning (RL) [22], [24], [82], genetic algorithm [83], sampling-based methods [84], [85], etc.”
DOCKSTRING: Easy Molecular Docking Yields Better Benchmarks for Ligand Design (2021, neutral): “With our novel de novo design tasks, we compared two genetic algorithms (GAs), a simple GA based on SELFIES 80 and the graph GA by Jensen, 95 with Gaussian process Bayesian optimization (GP-BO) approaches using the upper confidence bound (UCB) and expected improvement (EI) acquisition functions (for”
MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design (2022, methodology): “GB-GA [112] leverages graph-level genetic algorithm and design mutation and crossover operations with empirical experience to edit the molecule population in each generation (i.e., iteration).”
Differentiable Scaffolding Tree for Molecular Optimization (2021, neutral): “When λ goes to infinity, it is equivalent to selecting C candidates with the highest F score regardless of diversity, same as conventional evolutionary learning in [20, 35].”
GuacaMol: Benchmarking Models for De Novo Molecular Design (2018, methodology): “The MCTS molecule generation procedure follows the implementation by Jensen.”
GFlowNet Foundations (2021, neutral): “Evolutionary Methods Evolutionary methods work similarly to MCMC methods, via an iterative process of stochastic local search, and populations of candidates are found that maximize one or many objectives (Brown et al., 2004; Salimans et al., 2017; Jensen, 2019; Swersky et al., 2020).”
Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns (2019, background): “…frameworks based on a variety of generative models for modeling molecules, which diﬀer in the respective model structure and in the selected input features (Kadurin et al., 2017; Gupta et al., 2018; Jørgensen et al., 2018b; Arús-Pous et al., 2019; Brown et al., 2019; Jensen, 2019; Xu et al., 2019).”
Artificial intelligence in drug discovery: recent advances and future perspectives (2021, background): “genetic algorithms [156]), and provide several metrics for their com-”
Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation (2021, methodology): “…al., 2020; Jin et al., 2020; Luo et al., 2021), MCMC methods (Seff et al., 2019; Xie et al., 2021), RL (Segler et al., 2017; Cao and Kipf, 2018; Popova et al., 2019; Gottipati et al., 2020; Angermueller et al., 2020) and evolutionary methods (Brown et al., 2004; Jensen, 2019; Swersky et al., 2020).”