ChemTS: an efficient python library for de novo molecular generation

Abstract

Automatic design of organic materials requires black-box optimization in a vast chemical space. In conventional molecular design algorithms, a molecule is built as a combination of predetermined fragments. Recently, deep neural network models such as variational autoencoders and recurrent neural networks (RNNs) are shown to be effective in de novo design of molecules without any predetermined fragments. This paper presents a novel Python library ChemTS that explores the chemical space by combining Monte Carlo tree search and an RNN. In a benchmarking problem of optimizing the octanol-water partition coefficient and synthesizability, our algorithm showed superior efficiency in finding high-scoring molecules. ChemTS is available at https://github.com/tsudalab/ChemTS.

Population-based De Novo Molecule Generation, Using Grammatical Evolution

“…They formulate the molecule generation problem as a black-box optimization of SMILES strings [2] and solve it with deep neural networks and molecular simulations. Recent approaches include (1) Bayesian optimization, over a continuous space, of variational autoencoders [3,4], (2) optimization of recurrent neural network through fine-tuning or reinforcement learning [5,6,7], (3) sequential Monte Carlo search over a language model of SMILES [8], and (4) Monte Carlo tree search guided by recurrent neural network [9].…”

iQSPR in XenonPy: A Bayesian Molecular Design Algorithm

“…In particular, to broaden the search space, ML methods that use probabilistic language models based on deep neural networks (DNNs) have proliferated intensively since 2017. Promising examples have included various types of varia-tional autoencoders, [12][13][14][15] generative adversarial networks, [16] recurrent neural networks, [17,18] and so on. [11] Models trained to recognize chemically realistic structures are then used to refine chemical strings in the molecular design calculation.…”

“…[11] Models trained to recognize chemically realistic structures are then used to refine chemical strings in the molecular design calculation. Promising examples have included various types of varia-tional autoencoders, [12][13][14][15] generative adversarial networks, [16] recurrent neural networks, [17,18] and so on. These methods have been able to produce diverse chemical structures; however, they often require large training datasets to obtain a DNN-based generator that can produce chemically realistic molecules with grammatically valid SMILES.…”

Hunting for Organic Molecules with Artificial Intelligence: Molecules Optimized for Desired Excitation Energies

“…It has been brought closer to reality by recent advances on machine learning algorithms for de novo molecule design, that do not need handcrafted chemical rules [1][2][3][4][5] . Figure 1 illustrates our AI-assisted chemistry platform to develop new molecules.…”

“…Our platform, consisting of ChemTS (a molecule generator) 1 and a calculator (B3LYP/3-21G*) based on density functional theory (DFT) 15 , was configured to generate molecules whose first excited state is at five different wavelengths. A ten-day run of our machinelearning algorithm on a 12-core server created a variety of molecules whose DFT-based…”