MERMAID: An Open Source Automated Hit-to-Lead Method Based on Deep Reinforcement Learning

Abstract

<div>The hit-to-lead process makes the physicochemical properties of the hit compounds that show the desired type of activity obtained in the screening assay more drug-like. Deep learning-based molecular generative models are expected to contribute to the hit-to-lead process.</div><div>The simplified molecular input line entry system (SMILES), which is a string of alphanumeric characters representing the chemical structure of a molecule, is one of the most commonly used representations of molecules, and molecular generative models based on SMILES have achieved significant success. However, in contrast to molecular graphs, during the process of generation, SMILES are not considered as valid SMILES. Further, it is quite difficult to generate molecules starting from a certain molecule, thus making it difficult to apply SMILES to the hit-to-lead process.In this study, we have developed a SMILES-based generative model that can be generated starting from a certain compound. This method generates partial SMILES and inserts it into the original SMILES using Monte Carlo Tree Search and a Recurrent Neural Network.We validated our method using a molecule dataset obtained from the ZINC database and successfully generated molecules that were both well optimized for the objectives of the quantitative estimate of drug-likeness (QED) and penalized octanol-water partition coefficient (PLogP) optimization.</div><div>The source code is available at https: //github.com/sekijima-lab/mermaid.</div>

Molecular Level Atomistic and Structural Insights on Biological Macromolecules, Inhibition, and Dynamics Studies

“…A recurrent neural network (RNN) is a type of neural network that is widely used for natural language processing (NLP) tasks from simple language processing to complex cheminformatics problems. RNNs have been successfully applied for protein structure and function predictions from sequences (Liu, 2017;Zhang et al, 2018), property predictions, fragment-based hit generation (Awale et al, 2019), and hit identification (Segler et al, 2018;Erikawa et al, 2021).…”

“…We fine-tuned the generated structures (SMILES) for specific molecular targets or chemical series by employing transfer learning. The generative LSTM approach has proven helpful in low-data drug discovery, hit expansion, molecular design (fragmentbased), and lead optimization (Gupta et al, 2018;Segler et al, 2018;Erikawa et al, 2021).…”