Automatic generation of functional peptides with desired bioactivity and membrane permeability using Bayesian optimization.

Peptides are potentially useful modalities of drugs; however, cell membrane permeability is an obstacle in peptide drug discovery. The identification of bioactive peptides for a therapeutic target is also challenging because of the huge amino acid sequence patterns of peptides. In this study, we propose a novel computational method, PEptide generation system using Neural network Trained on Amino acid sequence data and Gaussian process-based optimizatiON (PENTAGON), to automatically generate new peptides with desired bioactivity and cell membrane permeability. In the algorithm, we mapped peptide amino acid sequences onto the latent space constructed using a variational autoencoder and searched for peptides with desired bioactivity and cell membrane permeability using Bayesian optimization. We used our proposed method to generate peptides with cell membrane permeability and bioactivity for each of the nine therapeutic targets, such as the estrogen receptor (ER). Our proposed method outperformed a previously developed peptide generator in terms of similarity to known active peptide sequences and the length of generated peptide sequences.

De novo drug design based on patient gene expression profiles via deep learning.

Computational de novo drug design is a challenging issue in medicine, and it is desirable to consider all of the relevant information of the biological systems in a disease state. Here, we propose a novel computational method to generate drug candidate molecular structures from patient gene expression profiles via deep learning, which we call DRAGONET. Our model can generate new molecules that are likely to counteract disease-specific gene expression patterns in patients, which is made possible by exploring the latent space constructed by a transformer-based variational autoencoder and integrating the substructures of disease-correlated molecules. We applied DRAGONET to generate drug candidate molecules for gastric cancer, atopic dermatitis, and Alzheimer's disease, and demonstrated that the newly generated molecules were chemically similar to registered drugs for each disease. This approach is applicable to diseases with unknown therapeutic target proteins and will make a significant contribution to the field of precision medicine.

Scaffold-Retained Structure Generator to Exhaustively Create Molecules in an Arbitrary Chemical Space.

The construction of a virtual library (VL) consisting of novel molecules based on structure-activity relationships is crucial for lead optimization in rational drug design. In this study, we propose a novel scaffold-retained structure generator, EMPIRE (Exhaustive Molecular library Production In a scaffold-REtained manner), to create novel molecules in an arbitrary chemical space. By combining a deep learning model-based generator and a building block-based generator, the proposed method efficiently provides a VL consisting of molecules that retain the input scaffold and contain unique arbitrary substructures. The proposed method enables us to construct rational VLs located in unexplored chemical spaces containing molecules with unique skeletons (e.g., bicyclo[1.1.1]pentane and cubane) or elements (e.g., boron and silicon). We expect EMPIRE to contribute to efficient drug design with unique substructures by virtual screening.

TRIOMPHE: Transcriptome-Based Inference and Generation of Molecules with Desired Phenotypes by Machine Learning.

One of the most challenging tasks in the drug-discovery process is the efficient identification of small molecules with desired phenotypes. In this study, we propose a novel computational method for omics-based de novo drug design, which we call TRIOMPHE (transcriptome-based inference and generation of molecules with desired phenotypes). We investigated the correlation between chemically induced transcriptome profiles (reflecting cellular responses to compound treatment) and genetically perturbed transcriptome profiles (reflecting cellular responses to gene knock-down or gene overexpression of target proteins) in terms of ligand-target interactions. Subsequently, we developed novel machine learning methods to generate the chemical structures of new molecules with desired transcriptome profiles in the framework of a variational autoencoder. The use of desired transcriptome profiles enables the automatic design of molecules that are likely to have bioactivities for target proteins of interest. We showed that our methods can generate chemically valid molecules that are likely to have biological activities on 10 target proteins; moreover, they can outperform previous methods that had the same objective. Our omics-based structure generator is expected to be useful for the de novo design of drugs for a variety of target proteins.

Prediction of the Health Effects of Food Peptides and Elucidation of the Mode-of-action Using Multi-task Graph Convolutional Neural Network.

Food proteins work not only as nutrients but also modulators for the physiological functions of the human body. The physiological functions of food proteins are basically regulated by peptides encrypted in food protein sequences (food peptides). In this study, we propose a novel deep learning-based method to predict the health effects of food peptides and elucidate the mode-of-action. In the algorithm, we estimate potential target proteins of food peptides using a multi-task graph convolutional neural network, and predict its health effects using information about therapeutic targets for diseases. We constructed predictive models based on 21,103 peptide-protein interactions involving 10,950 peptides and 2,533 proteins, and applied the models to food peptides (e. g., lactotripeptide, isoleucyltyrosine and sardine peptide) defined in food for specified health use. The models suggested potential effects such as blood-pressure lowering effects, blood glucose level lowering effects, and anti-cancer effects for several food peptides. The interactions of food peptides with target proteins were confirmed by docking simulations.

Design, Synthesis and Biological Evaluation of Novel Nonsteroidal Progesterone Receptor Antagonists Based on Phenylamino-1,3,5-triazine Scaffold.

We report here the development of phenylamino-1,3,5-triazine derivatives as novel nonsteroidal progesterone receptor (PR) antagonists. PR plays key roles in various physiological systems, including the female reproductive system, and PR antagonists are promising candidates for clinical treatment of multiple diseases. By using the phenylamino-1,3,5-triazine scaffold as a template structure, we designed and synthesized a series of 4-cyanophenylamino-1,3,5-triazine derivatives. The synthesized compounds exhibited PR antagonistic activity, and among them, compound 12n was the most potent (IC50 = 0.30 µM); it also showed significant binding affinity to the PR ligand-binding domain. Docking simulation supported the design rationale of the compounds. Our results suggest that the phenylamino-1,3,5-triazine scaffold is a versatile template for development of nonsteroidal PR antagonists and that the developed compounds are promising lead compounds for further structural development of nonsteroidal PR antagonists.

Novel Electrotopological Atomic Descriptors for the Prediction of Xenobiotic Cytochrome P450 Reactions.

Cytochrome P450 (CYP) is an enzyme family that plays a crucial role in metabolism, mainly metabolizing xenobiotics to produce non-toxic structures, however, some metabolized products can cause hepatotoxicity. Hence, predicting the structures of CYP products is an important task in designing non-hepatotoxic drugs. Here, we have developed novel atomic descriptors to predict the sites of metabolism (SoM) in CYP substrates. We proposed descriptors that describe topological and electrostatic characteristics of CYP substrates using Gasteiger charge. The proposed descriptors were applied to CYP3A4 data analysis as a case study. As a result of the descriptor selection, we obtained a gradient boosting decision tree-based SoM classification model that used 139 existing descriptors and the proposed 45 descriptors, and the model performed well in terms of the Matthews correlation coefficient. We also developed a structure converter to predict CYP products. This converter correctly generated 51 structural formulas of experimentally observed CYP3A4 products according to a manual evaluation.