MAYGEN: an open-source chemical structure generator for constitutional isomers based on the orderly generation principle

The generation of constitutional isomer chemical spaces has been a subject of cheminformatics since the early 1960s, with applications in structure elucidation and elsewhere. In order to perform such a generation efficiently, exhaustively and isomorphism-free, the structure generator needs to ensure the building of canonical graphs already during the generation step and not by subsequent filtering. Here we present MAYGEN, an open-source, pure-Java development of a constitutional isomer molecular generator. The principles of MAYGEN’s architecture and algorithm are outlined and the software is benchmarked in single-threaded mode against the state-of-the-art, but closed-source solution MOLGEN, as well as against the best open-source solution PMG. Based on the benchmarking, MAYGEN is on average 47 times faster than PMG and on average three times slower than MOLGEN in performance.

MAYGEN - an Open-Source Chemical Structure Generator for Constitutional Isomers Based on the Orderly Generation Principle

<p>The generation of constitutional isomer chemical spaces has been a subject of cheminformatics since the early 1960s, with applications in structure elucidation and elsewhere. In order to perform such a generation efficiently, exhaustively and isomorphism-free, the structure generator needs to ensure the building of canonical graphs already during the generation step and not by subsequent filtering.</p><p>Here we present MAYGEN, an open-source, pure-Java development of a constitutional isomer molecular generator. The principles of MAYGEN’s architecture and algorithm are outlined and the software is benchmarked against the state-of-the-art, but closed-source solution MOLGEN, as well as against the best open-source solution OMG. MAYGEN outperforms OMG by an order of magnitude and gets close to and occasionally outperforms MOLGEN in performance.</p>

MAYGEN - an Open-Source Chemical Structure Generator for Constitutional Isomers Based on the Orderly Generation Principle

<p>The generation of constitutional isomer chemical spaces has been a subject of cheminformatics since the early 1960s, with applications in structure elucidation and elsewhere. In order to perform such a generation efficiently, exhaustively and isomorphism-free, the structure generator needs to ensure the building of canonical graphs already during the generation step and not by subsequent filtering.</p><p>Here we present MAYGEN, an open-source, pure-Java development of a constitutional isomer molecular generator. The principles of MAYGEN’s architecture and algorithm are outlined and the software is benchmarked against the state-of-the-art, but closed-source solution MOLGEN, as well as against the best open-source solution OMG. MAYGEN outperforms OMG by an order of magnitude and gets close to and occasionally outperforms MOLGEN in performance.</p>

MAYGEN - an Open-Source Chemical Structure Generator for Constitutional Isomers Based on the Orderly Generation Principle

<p>The generation of constitutional isomer chemical spaces has been a subject of cheminformatics since the early 1960s, with applications in structure elucidation and elsewhere. In order to perform such a generation efficiently, exhaustively and isomorphism-free, the structure generator needs to ensure the building of canonical graphs already during the generation step and not by subsequent filtering.</p><p>Here we present MAYGEN, an open-source, pure-Java development of a constitutional isomer molecular generator. The principles of MAYGEN’s architecture and algorithm are outlined and the software is benchmarked against the state-of-the-art, but closed-source solution MOLGEN, as well as against the best open-source solution OMG. MAYGEN outperforms OMG by an order of magnitude and gets close to and occasionally outperforms MOLGEN in performance.</p>

Structure-Based De Novo Molecular Generator Combined with Artificial Intelligence and Docking Simulations

Recently, molecular generation models based on deep learning have attracted significant attention in drug discovery. However, most existing molecular generation models have a serious limitation in the context of drug design wherein they do not sufficiently consider the effect of the three-dimensional (3D) structure of the target protein in the generation process. In this study, we developed a new deep learning-based molecular generator, SBMolGen, that integrates a recurrent neural network, a Monte Carlo tree search, and docking simulations. The results of an evaluation using four target proteins (two kinases and two G protein-coupled receptors) showed that the generated molecules had a better binding affinity score (docking score) than the known active compounds, and they possessed a broader chemical space distribution. SBMolGen not only generates novel binding active molecules but also presents 3D docking poses with target proteins, which will be useful in subsequent drug design.

Structure-Based De Novo Molecular Generator Combined with Artificial Intelligence and Docking Simulations

Recently, molecular generation models based on deep learning have attracted significant attention in drug discovery. However, most existing molecular generation models have a serious limitation in the context of drug design wherein they do not sufficiently consider the effect of the three-dimensional (3D) structure of the target protein in the generation process. In this study, we developed a new deep learning-based molecular generator, SBMolGen, that integrates a recurrent neural network, a Monte Carlo tree search, and docking simulations. The results of an evaluation using four target proteins (two kinases and two G protein-coupled receptors) showed that the generated molecules had a better binding affinity score (docking score) than the known active compounds, and they possessed a broader chemical space distribution. SBMolGen not only generates novel binding active molecules but also presents 3D docking poses with target proteins, which will be useful in subsequent drug design.