Exact sampling of molecules in chemical space

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Weinreich, Jan, Karandashev, Konstantin, von Rudorff, Guido Falk
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916598992863232
author Weinreich, Jan
Karandashev, Konstantin
von Rudorff, Guido Falk
author_facet Weinreich, Jan
Karandashev, Konstantin
von Rudorff, Guido Falk
contents The concept of molecular similarity appears in many machine-learning algorithms based on the assumption that molecules with similar representations will also share similar properties. In this work, we propose a new way to study similarity measures in molecular graph space using a Monte Carlo approach. We enable direct sampling from the underlying distribution of chemical space without numerical approximations or complete enumeration of molecular graphs, the latter intractable for practically relevant graph sets of interest. The Monte Carlo method allows observation of several interesting fundamental properties of chemical space, such as a linear trend of average property derivatives in chemical space with respect to the property's value at the molecule of interest. The trend was observed for extensive and intensive properties, suggesting that this trend is an inherent property of chemical space.
format Preprint
id arxiv_https___arxiv_org_abs_2309_09194
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Exact sampling of molecules in chemical space
Weinreich, Jan
Karandashev, Konstantin
von Rudorff, Guido Falk
Chemical Physics
The concept of molecular similarity appears in many machine-learning algorithms based on the assumption that molecules with similar representations will also share similar properties. In this work, we propose a new way to study similarity measures in molecular graph space using a Monte Carlo approach. We enable direct sampling from the underlying distribution of chemical space without numerical approximations or complete enumeration of molecular graphs, the latter intractable for practically relevant graph sets of interest. The Monte Carlo method allows observation of several interesting fundamental properties of chemical space, such as a linear trend of average property derivatives in chemical space with respect to the property's value at the molecule of interest. The trend was observed for extensive and intensive properties, suggesting that this trend is an inherent property of chemical space.
title Exact sampling of molecules in chemical space
topic Chemical Physics
url https://arxiv.org/abs/2309.09194