fragSMILES: a Chemical String Notation for Advanced Fragment and Chirality Representation

23 July 2024, Version 2
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

Generative models have revolutionized de novo drug design, allowing to produce molecules on-demand with desired physicochemical and pharmacological properties. String based molecular representations, such as SMILES (Simplified Molecular Input Line Entry System) strings and SELFIES (Self-Referencing Embedded Strings), have played a pivotal role in the success of generative approaches, thanks to their capacity to encode atom- and bond- information and ease-of-generation. However, such ‘atom-level’ string representations have certain limitations, in terms of capturing information on chirality, and synthetic accessibility of the corresponding designs. In this paper, we present fragSMILES, a novel fragment-based molecular representation in the form of string. fragSMILES encode fragments in a ‘chemically-meaningful’ way via a novel graph-reduction approach, allowing to obtain an efficient, interpretable, and expressive molecular representation, which also avoids fragment redundancy. fragSMILES advances the state-of-the-art of fragment-based representations, by reporting fragments and their ‘breaking’ bonds independently, without fragment redundancy. Moreover, fragSMILES also embeds information of molecular chirality, thereby overcoming known limitations of existing string notations. When compared with SMILES and SELFIES for de novo design, the fragSMILES notation showed its promise in generating molecules with desirable biochemical and scaffolds properties.

Keywords

chirality
chemical language model
fragment-based notation
de novo drug design
generative models

Supplementary materials

Title
Description
Actions
Title
Supplementary Material figures and tables
Description
Figure S1. Counts of the fragment types occurring in the fragSMILES of the ZINC-250K database. Table S1. The values of the hyperparameters set for the models used to evaluate the metrics in the main text. Table S2. Epochs for the models employed to sample representations in the main text.
Actions

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.