Deep generative model of constructing chemical latent space for large molecular structures with 3D complexity
Authors:
- Toshiki OchiaiTOToshiki Ochiai
- Manato AkiyamaMAManato Akiyama
- Kairi FuruiKFKairi Furui
- Masahito OhueMasahito Ohue
- Nobuaki MatsumoriNMNobuaki Matsumori
- Shinsuke InukiSIShinsuke Inuki
- Motonari UesugiMUMotonari Uesugi
- Toshiaki SunazukaTSToshiaki Sunazuka
- Kazuya KikuchiKKKazuya Kikuchi
- Hideaki KakeyaHKHideaki Kakeya
- Yasubumi SakakibaraYSYasubumi Sakakibara
Preprint
- 29 May 2023
- preprint
- Published by American Chemical Society (ACS) in ChemRxiv
Abstract
The structural diversity of chemical libraries, which are systematic collections of compounds that have potential to bind to biomolecules, can be represented by chemical latent space. A chemical latent space is a projection of a compound structure into a mathematical space based on several molecular features, and it can express structural diversity within a compound library in order to explore a broader chemical space and generate novel compound structures for drug candidates. Many of the natural compounds produced by living organisms have complicated structures and are highly biologically active. However, no deep learning models exist that can effectively construct chemical latent spaces to handle large and complex compound structures, such as those found in natural compounds, and furthermore manage chirality, which is an essential factor in the 3D complexity of compounds. In this study, we developed a new deep-learning method, called NP-VAE, based on variational autoencoder for handling natural compounds, and constructed a chemical latent space that projected large and complex compound structures including chirality. NP-VAE was successful in construction of the chemical latent space that showed higher accuracy with respect to reconstruction and generalization than the state-of-the-art deep learning methods. Furthermore, by exploring the acquired latent space, we succeeded in comprehensively analyzing a compound library containing natural compounds and generating novel compound structures with optimized functions.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Beam Search for Automated Design and Scoring of Novel ROR Ligands with Machine Intelligence**Angewandte Chemie International Edition, 2021
- Natural Products as Sources of New Drugs over the Nearly Four Decades from 01/1981 to 09/2019Journal of Natural Products, 2020
- Fréchet ChemNet Distance: A Metric for Generative Models for Molecules in Drug DiscoveryJournal of Chemical Information and Modeling, 2018
- Automatic Chemical Design Using a Data-Driven Continuous Representation of MoleculesACS Central Science, 2018
- Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural NetworksACS Central Science, 2017
- A comprehensive review of the preclinical efficacy profile of the ErbB family blocker afatinib in cancerNaunyn-Schmiedeberg's Archives of Pharmacology, 2014
- Insights into the Aberrant Activity of Mutant EGFR Kinase Domain and Drug RecognitionStructure, 2013
- Design, Synthesis, and Biological Evaluation of Aminoboronic Acids as Growth‐Factor Receptor Inhibitors of EGFR and VEGFR‐1 Tyrosine KinasesChemBioChem, 2004
- The art and practice of structure-based drug design: A molecular modeling perspectiveMedicinal Research Reviews, 1996
- Isolation and structure of yessotoxin, a novel polyether compound implicated in diarrhetic shellfish poisoningTetrahedron Letters, 1987